Industrial cigarette distribution path planning system and method based on big data algorithm

Abstract

The invention discloses an industrial cigarette distribution path planning system and method based on a big data algorithm, and relates to the technical field of cigarette distribution, and the system comprises a data obtaining and processing module which is used for collecting and covering commercial companies, cigarette order data and related data of distribution vehicles, carrying out the cleaning and integration, and then building a unified data storage structure; the region division and clustering module is used for dividing the whole distribution range into a plurality of sub-regions, and clustering the commercial companies into a plurality of clustering groups by using a clustering algorithm; the driving route planning module is used for carrying out vehicle demand calculation, initial route planning and route optimization adjustment according to the clustering result to obtain optimized driving route information; and the distribution scheme generation and implementation module is used for integrating the optimized driving route information and the cigarette order information of the commercial company, distributing the information to corresponding vehicles and drivers, and generating a distribution scheme. The method is used for cigarette distribution path planning, and the cigarette distribution efficiency can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of cigarette distribution, and specifically to an industrial cigarette distribution route planning system and method based on big data algorithms. Background Art

[0002] In the field of tobacco logistics, with the rapid development of information technology, big data analysis technology has been widely used. Many enterprises actively collect and deeply analyze multi-source data such as order data, road conditions information, and customer distribution, so as to realize the real-time monitoring of the distribution progress and the visualization of the entire logistics process.

[0003] For example, the Beijing Tobacco Commercial Company uses big data analysis technology to mine and analyze a large amount of customer data, so as to accurately identify customer needs and provide strong support for optimizing logistics distribution strategies. Tai'an Tobacco makes full use of the big data platform to carry out optimization work on the driving routes. According to the principle of factor balance, they comprehensively consider factors such as vehicle loading capacity and labor intensity of personnel, and innovatively implement the "off-peak line combination" dynamic distribution mode of T+0 and T+1, which greatly improves the per capita distribution efficiency and promotes the efficient development of tobacco logistics distribution to a certain extent.

[0004] However, although big data analysis technology has achieved certain results in tobacco logistics, many defects are still exposed in the actual application process. The most prominent problem is that the existing route planning methods cannot comprehensively consider all relevant factors, resulting in the planned distribution routes being difficult to reach the optimal state. In many cases, the distribution mileage is too long, which not only means a significant increase in fuel consumption during vehicle driving, increased vehicle wear, and rising maintenance costs, but also significantly prolongs the distribution time. The overly long distribution time not only reduces the distribution efficiency, but also may cause the goods to not be delivered to customers on time, seriously affecting customer satisfaction, and greatly increasing the overall transportation cost.

[0005] Delving into the reasons for these problems, they mainly focus on two aspects.

[0006] Firstly, the algorithms have limitations. Some algorithms applied to the route planning of tobacco logistics distribution are not advanced enough to handle complex multi-factor optimization problems. In the actual distribution process, numerous factors need to be considered, including the location of commercial companies, distance, traffic conditions, order urgency, vehicle capacity, etc. These factors are intertwined and interact with each other, and some traditional algorithms cannot comprehensively and accurately analyze and process these complex factors, resulting in unsatisfactory route planning results.

[0007] Second, insufficient data collection and processing capabilities also have a negative impact on the accuracy of path planning. In actual logistics operations, it is impossible to obtain key data such as accurate vehicle location information and customer order change information in real time. For example, when a vehicle encounters unexpected traffic conditions during transportation, such as a traffic accident causing road congestion, due to the lack of real-time and accurate vehicle location information, it is difficult for logistics dispatchers to understand the situation in a timely manner and make timely and effective path adjustments; when a customer order changes, such as a temporary increase or decrease in the quantity of goods requested, if this information cannot be obtained in a timely manner, the distribution path planning cannot be optimized accordingly, thus affecting the distribution efficiency and cost control.

[0008] At the same time, in the current industrial cigarette logistics distribution, the allocation of distribution vehicles still heavily relies on manual experience. Staff rely on their accumulated experience to complete the allocation of distribution vehicles by judging the vehicle's transportation capacity and relevant situations of the cigarette factory. However, in the actual implementation process, this method relying on manual experience also exposes many problems. Due to the extremely wide distribution of commercial companies, and the vastly different goods demand of each commercial company, factors such as the quantity of goods requested and the required arrival time of different commercial companies are not the same, which greatly increases the complexity of distribution path planning. When facing such complex and changeable goods demand, manual experience often fails to comprehensively and accurately consider various factors, resulting in non-optimal distribution paths. The excessive driving mileage of distribution vehicles not only increases transportation costs but also consumes a large amount of time, seriously reducing the distribution efficiency and making it difficult to meet the market demand for fast and efficient distribution.

[0009] In summary, whether it is the path planning relying on big data analysis technology or the allocation of distribution vehicles relying on manual experience, there are problems such as relying on manual experience, being unable to adapt to complex goods demand and real-time traffic changes in the industrial cigarette logistics distribution path planning. Therefore, there is an urgent need to provide a brand-new industrial cigarette logistics distribution path optimization method and system, which comprehensively considers various relevant factors through innovative technical means and scientific algorithm models to optimize the distribution path, thereby effectively improving the distribution efficiency, reducing the distribution cost, and promoting the high-quality development of the industrial cigarette logistics distribution industry. Summary of the Invention

[0010] In view of the requirements and deficiencies of the current technological development, the present invention provides an industrial cigarette distribution path planning system and method based on big data algorithms to solve the problems existing in the existing industrial cigarette distribution path planning, such as relying on manual experience, being unable to adapt to complex goods demand and real-time traffic changes, etc., to optimize the distribution path, improve the distribution efficiency, and reduce the distribution cost.

[0011] In the first aspect, the present invention provides an industrial cigarette distribution path planning system based on big data algorithms. The technical solutions adopted to solve the above technical problems are as follows:

[0012] An industrial cigarette distribution route planning system based on big data algorithms, which includes:

[0013] A data acquisition and processing module, which is used to collect data covering commercial company information, cigarette order data, and distribution vehicle-related information, clean the collected data to remove duplicate, incorrect, or incomplete data records, integrate the cleaned data, and establish a unified data storage structure for subsequent analysis and use;

[0014] A regional division and clustering module, which is used to divide the entire distribution scope into multiple sub-regions according to geographical regions, administrative divisions, and traffic network factors. For commercial companies within each sub-region, using clustering algorithms, according to the order frequency and expected delivery time of commercial companies, cluster commercial companies into multiple clustering groups;

[0015] A driving route planning module, which is used to calculate vehicle requirements, plan initial routes, and optimize route adjustments based on the clustering results, comprehensively considering the quantity of goods included in cigarette orders, vehicle capacity, and commercial company's expected delivery time, to obtain optimized driving route information;

[0016] A distribution plan generation and implementation module, which is used to integrate the optimized driving route information with commercial company cigarette order information, allocate it to corresponding vehicles and drivers, generate a distribution plan including detailed driving routes, and at the same time use GPS positioning to monitor the entire driving route, process driving route feedback in a timely manner, record and analyze distribution data, and provide support for continuously optimizing the driving route.

[0017] Optionally, the involved driving route planning module specifically includes:

[0018] A vehicle requirement calculation unit, which is used to count the quantity of goods included in cigarette orders of the clustering groups to be delivered, compare it with the vehicle capacity of delivery trucks, calculate the required number of delivery trucks or trips, and at the same time, by matching the cigarette order quantities of different commercial companies, make the cigarette loading capacity of each vehicle as close as possible to the vehicle capacity;

[0019] An initial route planning unit, which is used to plan the initial driving routes from the distribution center to each commercial company within the clustering group in units of clustering groups, using neural network algorithms while considering vehicle operating conditions and commercial company's expected delivery time;

[0020] A route optimization and adjustment unit, which is used to optimize the driving route in combination with the load situation and delivery time of each delivery truck.

[0021] Further optionally, before optimizing the driving route by combining the load conditions and delivery times of each delivery truck, the involved route optimization and adjustment unit analyzes the delivery efficiency and costs of different routes in advance with the help of historical delivery data, sets the pheromone weight value, and then selects routes or road sections based on the pheromone weight value to complete the optimization of the driving route;

[0022] During the process of optimizing the driving route by combining the load conditions and delivery times of each delivery truck, the route optimization and adjustment unit uses real-time vehicle information monitoring. Once it is found that the passing time of a certain road section increases due to traffic problems, it immediately searches for feasible roads in the vicinity based on historical delivery data and uses the A* algorithm to re-plan the route to balance the load and delivery time of each vehicle.

[0023] Further optionally, the involved route optimization and adjustment unit optimizes the driving route considering the following constraints:

[0024] (1) Decision variable X ijk , which represents the quantity of goods transported from the shipping point i to the arrival location j using vehicle k. Here, i represents different shipping points, j represents different arrival locations, and k represents different vehicles. Through the decision variable X ijk , the quantity of goods transported from different shipping points to different arrival locations using different vehicles can be clearly represented;

[0025] (2) The objective function for minimizing the total transportation cost is expressed as follows:

[0026] Minimize∑ i ∑ j ∑ k C ijk X ijk ,

[0027] where C ijk represents the unit transportation cost from the shipping point i to the arrival location j using vehicle k, and X ijk is the quantity of goods transported from the shipping point i to the arrival location j using vehicle k. Summing over all shipping points i, arrival locations j, and vehicles k gives the total transportation cost. By minimizing this sum, the transportation plan can be optimized;

[0028] (3) Constraints, specifically including:

[0029] (3.1) Contract quantity constraint, expressed as follows:

[0030]

[0031] where, It means that for all i; for each shipping point i, the total quantity of goods transported from this shipping point to all arrival destinations j using all vehicles k must be greater than or equal to the demand quantity d of contract i i , to meet the goods demand stipulated in the contract;

[0032] (3.2) Vehicle capacity constraint, which is expressed as follows:

[0033] X ijk ≤Q k ,

[0034] where X ijk represents the quantity of goods transported from shipping point i to arrival destination j using vehicle k, and it cannot exceed the capacity Q of vehicle k k , to ensure that the vehicle will not be overloaded during transportation;

[0035] (3.3) Arrival time constraint, which is expressed as follows:

[0036] t ij ≤T ij ,

[0037] where t ij represents the actual transportation time from shipping point i to arrival destination j, and it must be less than or equal to the expected delivery time T required by the commercial company in the contract ij , to ensure that the goods can be delivered on time;

[0038] (3.4) Vehicle availability constraint, which is expressed as follows:

[0039]

[0040] where it means that for all k; for each available vehicle k, the total quantity of goods transported from all shipping points i to all arrival destinations j using this vehicle must be greater than or equal to the number of available vehicles V k , to ensure that the vehicles are fully utilized.

[0041] Furthermore, optionally, the involved distribution plan generation and implementation module specifically includes:

[0042] Distribution plan generation unit, which is used to deeply integrate the driving route information optimized by the driving route planning module with the specific information of the commercial company's cigarette orders, determine the precise driving routes of each delivery truck, plan the order of stopping at the commercial company, calculate the expected arrival time at each commercial company in combination with the vehicle driving speed and road conditions, and then allocate vehicles and drivers to each driving route, generate a distribution plan and send it to the handheld terminal device of the distribution personnel, providing clear and accurate guidance for the distribution work;

[0043] A real-time monitoring and feedback unit, which is used to continuously and real-timely monitor the distribution vehicle during the distribution process by using GPS positioning technology, accurately grasp the driving position, driving speed and real-time status of the vehicle;

[0044] A data recording and analysis unit, which is used to automatically record the actual execution situation of each distribution plan, covering multi-dimensional data such as distribution time, driving mileage, vehicle fuel consumption and feedback from commercial companies, and use data analysis tools and methods to deeply analyze the recorded data and tap the potential value therein.

[0045] In a second aspect, the present invention provides an industrial cigarette distribution route planning method based on a big data algorithm. The technical solution adopted to solve the above technical problems is as follows:

[0046] An industrial cigarette distribution route planning method based on a big data algorithm, which includes the following steps:

[0047] S1. Collect data covering commercial company information, cigarette order data and distribution vehicle-related information, clean the collected data to remove duplicate, incorrect or incomplete data records, integrate the cleaned data, and establish a unified data storage structure for subsequent analysis and use;

[0048] S2. According to geographical regions, administrative divisions and traffic network factors, divide the entire distribution scope into multiple sub-regions. For commercial companies within each sub-region, use the clustering algorithm to cluster commercial companies into multiple clustering groups according to the order frequency and expected distribution time of commercial companies;

[0049] S3. According to the clustering results, comprehensively consider the quantity of goods included in the cigarette order, vehicle capacity and commercial company's distribution expected time, perform vehicle demand calculation, initial route planning and route optimization adjustment to obtain optimized driving route information;

[0050] S4. Integrate the optimized driving route information with the commercial company's cigarette order information, allocate it to the corresponding vehicle and driver, generate a distribution plan including a detailed driving route, and at the same time realize the whole-process monitoring of the driving route by means of GPS positioning, timely process the feedback of the driving route, and record and analyze the distribution data to provide support for continuously optimizing the driving route.

[0051] Optionally, the specific steps of step S3 include:

[0052] S3.1. Statistically calculate the quantity of goods included in the cigarette orders of the clustering groups to be distributed, compare it with the vehicle capacity of the delivery truck, calculate the required number of delivery trucks or trips, and at the same time, by matching the cigarette order quantities of different commercial companies, make the cigarette loading capacity of each vehicle as close as possible to the vehicle capacity;

[0053] S3.2. Based on the clustering groups, use the neural network algorithm to plan the initial driving routes from the distribution center to each commercial company within the clustering groups, taking into account the vehicle operating conditions and the expected delivery time of the commercial company.

[0054] S3.3. Optimize the driving routes in combination with the load conditions and delivery times of each delivery truck.

[0055] Further optionally, when performing step S3.3 to optimize the driving routes in combination with the load conditions and delivery times of each delivery truck, first analyze the delivery efficiency and costs of different routes by means of historical delivery data, set the pheromone weight values, and then select the routes or road segments based on the pheromone weight values to complete the optimization of the driving routes.

[0056] During the process of optimizing the driving routes in combination with the load conditions and delivery times of each delivery truck, use real-time vehicle information monitoring. Once it is found that the passing time of a certain road segment increases due to traffic problems, immediately search for feasible roads in the vicinity according to historical delivery data, and use the A* algorithm to re-plan the routes to make the loads and delivery times of each vehicle tend to be balanced.

[0057] Further optionally, when performing step S3, optimize the driving routes considering the following constraints:

[0058] (1) Decision variable X ijk , which represents the quantity of goods transported from the shipping point i to the arrival location j using vehicle k. Here, i represents different shipping points, j represents different arrival locations, and k represents different vehicles. Through the decision variable X ijk , the quantity of goods transported from different shipping points to different arrival locations using different vehicles can be clearly represented.

[0059] (2) The objective function of minimizing the total transportation cost is expressed as follows:

[0060] Minimize∑ i ∑ j ∑ k C ijk X ijk ,

[0061] where C ijk represents the unit transportation cost from the shipping point i to the arrival location j using vehicle k, and X ijk is the quantity of goods transported from the shipping point i to the arrival location j using vehicle k. Summing over all shipping points i, arrival locations j, and vehicles k, the total transportation cost is obtained. By minimizing this sum, the transportation plan can be optimized.

[0062] (3) Constraints, specifically including:

[0063] (3.1) Contract quantity constraint, expressed as follows:

[0064]

[0065] Among them, It means that for all i; for each shipping point i, the total quantity of goods transported from this shipping point to all arrival locations j using all vehicles k must be greater than or equal to the demand quantity d of contract i i , to meet the goods demand stipulated in the contract;

[0066] (3.2) Vehicle capacity constraint, expressed as follows:

[0067] X ijk ≤Q k ,

[0068] Among them, X ijk represents the quantity of goods transported from shipping point i to arrival location j using vehicle k, which cannot exceed the capacity Q of vehicle k k , to ensure that the vehicle will not be overloaded during transportation;

[0069] (3.3) Arrival time constraint, expressed as follows:

[0070] t ij ≤T ij ,

[0071] Among them, t ij represents the actual transportation time from shipping point i to arrival location j, which must be less than or equal to the expected delivery time T required by the commercial company in the contract ij , to ensure that the goods can be delivered on time;

[0072] (3.4) Vehicle availability constraint, expressed as follows:

[0073]

[0074] Among them, It means that for all k; for each available vehicle k, the total quantity of goods transported from all shipping points i to all arrival locations j using this vehicle must be greater than or equal to the available vehicle quantity V k , to ensure that the vehicles are fully utilized.

[0075] Further optionally, the specific steps involved in step S4 include:

[0076] S4.1. Integrate the optimized driving route information with the specific information of the commercial companies' cigarette orders, determine the precise driving route of each delivery vehicle, plan the order of stopping at the commercial companies, and calculate the estimated time of arrival at each commercial company based on the vehicle's driving speed and road conditions. Then, assign vehicles and drivers to each driving route, generate a delivery plan and send it to the delivery personnel's handheld terminal device, providing clear and accurate guidance for delivery work;

[0077] S4.2. During the delivery process, the delivery vehicles are continuously monitored in real time using GPS positioning technology to accurately grasp the driving position, driving speed and real-time status of the vehicles;

[0078] S4.3. Automatically record the actual implementation status of each delivery plan, including multi-dimensional data such as delivery time, mileage, vehicle fuel consumption and feedback from commercial companies. Use data analysis tools and methods to conduct in-depth analysis of the recorded data to explore its potential value.

[0079] The industrial cigarette distribution path planning system and method based on big data algorithm of the present invention has the following beneficial effects compared with the prior art:

[0080] 1. Through data collection and preprocessing, the present invention can fully grasp the information of commercial companies, cigarette order data and delivery vehicle information, etc., to provide a basis for accurate planning of delivery routes; by using distribution area division and customer clustering, commercial companies are reasonably grouped, the time in transit and empty mileage of vehicles are reduced, and the delivery efficiency is improved;

[0081] 2. The present invention can reasonably arrange vehicles according to the volume of cigarette orders, avoid empty or overloaded vehicles, improve vehicle utilization, and reduce transportation costs. At the same time, the optimized delivery route reduces unnecessary mileage, reduces fuel consumption and vehicle wear, and further saves costs;

[0082] 3. The present invention can reduce operating costs and improve service quality by optimizing the distribution path, thereby gaining an advantage in market competition. Efficient distribution services can also enhance the brand image of the enterprise and lay the foundation for the long-term development of the enterprise.

[0083] 4. The present invention helps enterprises to more reasonably allocate distribution resources such as vehicles and manpower, avoid waste and excessive use of resources, improve resource utilization efficiency, achieve optimal integration of resources, and enable enterprises to maximize benefits with limited resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] Attached Figure 1 is a module connection block diagram of the first embodiment of the present invention;

[0085] Attached Figure 2It is the flowchart of the method in the second embodiment of the present invention. Specific Embodiments

[0086] To make the technical solutions, technical problems to be solved, and technical effects of the present invention clearer and more understandable, the following combines specific embodiments to clearly and completely describe the technical solutions of the present invention.

[0087] Embodiment 1:

[0088] Combined with the attached Figure 1 , this embodiment proposes an industrial cigarette distribution route planning system based on big data algorithms, which includes:

[0089] A data acquisition and processing module, which is used to collect data covering commercial company information, cigarette order data, and distribution vehicle-related information, clean the collected data to remove duplicate, incorrect, or incomplete data records, integrate the cleaned data, and establish a unified data storage structure for subsequent analysis and use;

[0090] A region division and clustering module, which is used to divide the entire distribution range into multiple sub-regions according to geographical regions, administrative divisions, and traffic network factors, and for each commercial company within each sub-region, use clustering algorithms to cluster commercial companies into multiple clustering groups according to the order frequency and expected delivery time of commercial companies;

[0091] A driving route planning module, which is used to calculate vehicle requirements, plan initial routes, and optimize and adjust routes based on the clustering results, comprehensively considering the quantity of goods included in cigarette orders, vehicle capacity, and the expected delivery time of commercial companies, to obtain optimized driving route information;

[0092] A distribution plan generation and implementation module, which is used to integrate the optimized driving route information with commercial company cigarette order information, allocate it to corresponding vehicles and drivers, generate a distribution plan including detailed driving routes, and at the same time use GPS positioning to monitor the entire driving route in real time, process driving route feedback in a timely manner, record and analyze distribution data, and provide support for continuously optimizing driving routes.

[0093] In this embodiment, the driving route planning module specifically includes:

[0094] A vehicle requirement calculation unit, which is used to count the quantity of goods included in cigarette orders of the clustering groups to be delivered, compare it with the vehicle capacity of delivery trucks, calculate the number of delivery trucks or trips required, and at the same time, by matching the cigarette order quantities of different commercial companies, make the cigarette loading capacity of each vehicle as close as possible to the vehicle capacity;

[0095] An initial route planning unit, which is used to plan the initial driving routes from the distribution center to each commercial company within the clustering group in units of clustering groups, by using a neural network algorithm and considering the vehicle operation conditions and the expected delivery time of the commercial company;

[0096] A route optimization and adjustment unit, which is used to optimize the driving routes in combination with the load conditions and delivery times of each delivery truck.

[0097] Before the route optimization and adjustment unit involved optimizes the driving routes in combination with the load conditions and delivery times of each delivery truck, it pre-uses historical delivery data to analyze the delivery efficiency and costs of different routes, sets the pheromone weight values, and then selects routes or road sections based on the pheromone weight values to complete the optimization of the driving routes. During the process of the route optimization and adjustment unit optimizing the driving routes in combination with the load conditions and delivery times of each delivery truck, it uses real-time vehicle information monitoring. Once it is found that the passing time of a certain road section increases due to traffic problems, it immediately searches for feasible roads in the vicinity based on historical delivery data and uses the A* algorithm to re-plan the routes to make the loads and delivery times of each vehicle tend to be balanced.

[0098] In this embodiment, the route optimization and adjustment unit involved optimizes the driving routes considering the following constraint conditions:

[0099] (1) Decision variable X ijk , which represents the quantity of goods transported from the shipping point i to the arrival location j using vehicle k. Among them, i represents different shipping points, j represents different arrival locations, and k represents different vehicles. Through the decision variable X ijk , the quantity of goods transported from different shipping points to different arrival locations using different vehicles can be clearly represented;

[0100] (2) The objective function of minimizing the total transportation cost is expressed as follows:

[0101] Minimize∑ i ∑ j ∑ k C ijk X ijk ,

[0102] Among them, C ijk represents the unit transportation cost from the shipping point i to the arrival location j using vehicle k, and X ijk is the quantity of goods transported from the shipping point i to the arrival location j using vehicle k. Summing over all shipping points i, arrival locations j, and vehicles k, the total transportation cost can be obtained. By minimizing this sum, the transportation plan can be optimized;

[0103] (3) Constraint conditions, specifically including:

[0104] (3.1) The contract quantity constraint is expressed as follows:

[0105]

[0106] Among them, It means that for all i; for each shipping point i, the total quantity of goods transported from this shipping point to all arrival locations j using all vehicles k must be greater than or equal to the demand quantity d of contract i i , to meet the goods demand stipulated in the contract;

[0107] (3.2) The vehicle capacity constraint is expressed as follows:

[0108] X ijk ≤Q k ,

[0109] Among them, X ijk It means the quantity of goods transported from shipping point i to arrival location j using vehicle k, which cannot exceed the capacity Q of vehicle k k , to ensure that the vehicle will not be overloaded during transportation;

[0110] (3.3) The arrival time constraint is expressed as follows:

[0111] t ij ≤T ij ,

[0112] Among them, t ij It means the actual transportation time from shipping point i to arrival location j, which must be less than or equal to the expected delivery time T required by the commercial company in the contract ij , to ensure that the goods can be delivered on time;

[0113] (3.4) The vehicle availability constraint is expressed as follows:

[0114]

[0115] Among them, It means that for all k; for each available vehicle k, the total quantity of goods transported from all shipping points i to all arrival locations j using this vehicle must be greater than or equal to the number of available vehicles V k , to ensure that the vehicles are fully utilized.

[0116] In this embodiment, the specific components of the distribution plan generation and implementation module include:

[0117] The delivery plan generation unit is used to deeply integrate the driving route information optimized by the driving route planning module with the specific information of the commercial company's cigarette order, determine the precise driving route of each delivery vehicle, plan the order of stopping at the commercial companies, and calculate the estimated time of arrival at each commercial company based on the vehicle's driving speed and road conditions. Then, vehicles and drivers are assigned to each driving route, and a delivery plan is generated and sent to the delivery personnel's handheld terminal device to provide clear and accurate guidance for delivery work;

[0118] Real-time monitoring and feedback unit, used to continuously monitor the delivery vehicles in real time during the delivery process using GPS positioning technology, and accurately grasp the vehicle's driving position, driving speed and real-time status;

[0119] The data recording and analysis unit is used to automatically record the actual implementation status of each delivery plan, covering multi-dimensional data such as delivery time, mileage, vehicle fuel consumption and feedback from commercial companies. It uses data analysis tools and methods to conduct in-depth analysis of the recorded data and explore its potential value.

[0120] Embodiment 2:

[0121] Combined with Figure 2 This embodiment proposes a method for industrial cigarette distribution path planning based on big data algorithm, which includes the following steps:

[0122] S1. Collect data covering commercial company information, cigarette order data, and delivery vehicle related information, clean the collected data to remove duplicate, erroneous, or incomplete data records, integrate the cleaned data, and establish a unified data storage structure for subsequent analysis and use.

[0123] The collected commercial company information and cigarette order data include the location of the commercial company (latitude and longitude coordinates), the number of cigarette orders, the frequency of cigarette orders, the expected delivery time, etc. For example, the address of a commercial company A is collected as "No. XX, XX Road, XX District, XX City", and its longitude and latitude coordinates are obtained after geocoding conversion as (X1, Y1), and the location is marked on the electronic map. At the same time, the number of orders for commercial company A in the past year is 1,000 boxes, the order frequency is 3 times a month, and the expected delivery time is every Tuesday.

[0124] Collect information related to distribution vehicles, including road congestion, accident information, restricted sections, etc., and also include the vehicle's historical location data for analyzing the driving patterns of vehicles at different times and on different sections. For example, through the API interface, it is obtained that the speed of a certain section during the morning rush hour (7:00 - 9:00) on weekdays is 40 km / h, and there have been 2 order deliveries on this section in the past month, with an average driving impact duration of 2 hours each time. Combine these real-time and historical traffic data with the location information of commercial companies to provide comprehensive data support for subsequent distribution route planning.

[0125] Randomly, collect data covering commercial company information, cigarette order data, and information related to distribution vehicles, clean the collected data to remove duplicate, incorrect, or incomplete data. Convert the number of cigarette orders into physical quantities such as weight or volume that are convenient for calculation, and classify commercial companies according to the cigarette order frequency and expected delivery time. For example, high-frequency stable customers (order frequency ≥ 3 times per week, relatively fixed expected delivery time), medium-frequency fluctuating customers (order frequency 2 - 3 times per month, certain flexibility in expected delivery time), and low-frequency flexible customers (order frequency < 2 times per month, relatively loose requirements for delivery time).

[0126] S2. According to geographical regions, administrative divisions, and traffic network factors, divide the entire distribution area into multiple sub-regions. For commercial companies within each sub-region, use clustering algorithms (such as the K-Means clustering algorithm) to cluster commercial companies into multiple clustering groups according to the order frequency and expected delivery time of commercial companies, so that commercial companies within the same clustering group have certain similarities in terms of these two factors of order frequency and expected delivery time, facilitating the reasonable arrangement of the delivery sequence.

[0127] S3. According to the clustering results, comprehensively consider the quantity of goods included in the cigarette order (which can be the total weight or volume of cigarettes), vehicle capacity, and the expected delivery time of commercial companies to calculate vehicle requirements, conduct initial route planning, and optimize and adjust the route to obtain the optimized driving route information.

[0128] This step specifically includes:

[0129] S3.1. Statistically count the quantity of goods (which can be the total weight or volume of cigarettes) included in the cigarette orders of the clustering groups to be delivered, compare it with the vehicle capacity of the delivery trucks, calculate the number of required delivery trucks or trips. At the same time, by matching the cigarette order volumes of different commercial companies, make the cigarette loading capacity of each vehicle as close as possible to the vehicle capacity. For example, if the total order volume of a clustering group is 25 million cigarettes and the maximum loading capacity of each delivery truck is 5 million cigarettes, then 5 trips need to be arranged for delivery. At the same time, considering the full load rate of the vehicles, try to make the loading capacity of each vehicle close to the maximum loading capacity. For example, by reasonably matching customers with different order volumes, make the actual loading capacity of each vehicle reach 4 - 4.5 million cigarettes, and keep the full load rate between 80% - 90%, so as to improve the vehicle use efficiency and reduce the transportation cost.

[0130] S3.2. Taking the clustering group as a unit, using neural network algorithms (such as Dijkstra algorithm or A* algorithm), based on considering the vehicle operation conditions and the expected delivery time of commercial companies, plan the initial driving routes from the distribution center to each commercial company within the clustering group, and preferentially select the routes with good vehicle operation and can be delivered within the expected time. For example, if a high-frequency and stable customer expects the delivery time to be Tuesday morning every week, then when planning the route, ensure that the vehicle can reach the customer within this time window; through the calculation of the Dijkstra algorithm, find the optimal path starting from the distribution center, passing through each customer within the small combination in turn and meeting the time window constraints and considering the traffic conditions, as the initial delivery route.

[0131] S3.3. Optimize the driving routes in combination with the load conditions and delivery times of each delivery truck.

[0132] When performing step S3.3 to optimize the driving routes in combination with the load conditions and delivery times of each delivery truck, first, with the help of historical delivery data, analyze the delivery efficiency and costs of different routes, set the pheromone weight values, and then select routes or road segments based on the pheromone weight values to complete the optimization of the driving routes. During the process of optimizing the driving routes in combination with the load conditions and delivery times of each delivery truck, use real-time vehicle information monitoring. Once it is found that the passing time of a certain road segment increases due to traffic problems, immediately search for feasible roads in the vicinity based on historical delivery data, and use the A* algorithm to re-plan the routes to make the loads and delivery times of each vehicle tend to be balanced.

[0133] When performing step S3, optimize the driving routes considering the following constraint conditions:

[0134] (1) Decision variable X ijk , which represents the quantity of goods transported from the shipping point i to the arrival place j using vehicle k. Among them, i represents different shipping points, j represents different arrival places, and k represents different vehicles. Through the decision variable X ijkIt can clearly show the quantity of goods transported by different vehicles from different shipping points to different arrival locations;

[0135] (2) The objective function to minimize the total transportation cost is expressed as follows:

[0136] Minimize∑ i ∑ j ∑ k C ijk X ijk ,

[0137] where C ijk represents the unit transportation cost of using vehicle k from shipping point i to arrival location j, and X ijk is the quantity of goods transported from shipping point i to arrival location j using vehicle k. Summing over all shipping points i, arrival locations j, and vehicles k gives the total transportation cost, and the transportation plan can be optimized by minimizing this sum;

[0138] (3) Constraints, specifically including:

[0139] (3.1) Contract quantity constraint, expressed as follows:

[0140]

[0141] where represents for all i; for each shipping point i, the total quantity of goods transported from this shipping point to all arrival locations j and using all vehicles k must be greater than or equal to the demand quantity d i of contract i to meet the goods demand specified in the contract;

[0142] (3.2) Vehicle capacity constraint, expressed as follows:

[0143] X ijk ≤Q k ,

[0144] where X ijk represents the quantity of goods transported from shipping point i to arrival location j using vehicle k, and it cannot exceed the capacity Q k of vehicle k to ensure that the vehicle will not be overloaded during transportation;

[0145] (3.3) Arrival time constraint, expressed as follows:

[0146] t ij ≤T ij ,

[0147] where t ij represents the actual transportation time from shipping point i to arrival location j, and it must be less than or equal to the expected delivery time T required by the commercial company in the contractij , to ensure that the goods can be delivered on time;

[0148] (3.4) Vehicle availability constraint, expressed as follows:

[0149]

[0150] Among them, It means that for all k; for each available vehicle k, the total quantity of goods transported from all shipping points i to all arrival locations j using this vehicle must be greater than or equal to the available number of vehicles V k , to ensure full utilization of the vehicles.

[0151] S4. Integrate the optimized driving route information with the cigarette order information of commercial companies, allocate it to the corresponding vehicles and drivers, and generate a delivery plan including detailed driving routes (including the driving routes of each delivery truck, the order of stopping at commercial companies, the estimated arrival time, etc.). At the same time, use GPS positioning to achieve full-process monitoring of the driving route, promptly handle the feedback of the driving route, and record and analyze the delivery data to provide support for continuously optimizing the driving route.

[0152] This step specifically includes:

[0153] S4.1. Deeply integrate the optimized driving route information with the specific information of the cigarette orders of commercial companies, determine the precise driving routes of each delivery truck, plan the order of stopping at commercial companies, and calculate the estimated arrival time at each commercial company in combination with the vehicle driving speed and road conditions. Subsequently, allocate vehicles and drivers to each driving route, generate a delivery plan (including the driving routes of each delivery truck, the order of stopping at commercial companies, the estimated arrival time, etc.) and send it to the handheld terminal devices of the delivery personnel to provide clear and accurate guidance for the delivery work.

[0154] S4.2. During the delivery process, use GPS positioning technology to continuously monitor the delivery vehicles in real time, accurately grasp the driving position, driving speed, and real-time status of the vehicles.

[0155] S4.3. Automatically record the actual execution situation of each delivery plan, covering multi-dimensional data such as delivery time, driving mileage, vehicle fuel consumption, and feedback from commercial companies. Use data analysis tools and methods to deeply analyze the recorded data, explore the potential value therein, provide a reference basis for subsequent optimization of the delivery route, and continuously improve the quality and efficiency of the delivery service.

[0156] In summary, by adopting the industrial cigarette delivery route planning system and method based on big data algorithm of the present invention, the cigarette delivery efficiency can be improved, the cigarette delivery cost can be reduced, and the resource allocation can be optimized.

[0157] The above specific application examples have elaborated in detail the principles and implementation manners of the present invention. These examples are only used to help understand the core technical content of the present invention. Based on the above specific embodiments of the present invention, any improvements and modifications made by those skilled in the art of this technical field without departing from the principles of the present invention shall fall within the scope of patent protection of the present invention.

Claims

1. An industrial cigarette distribution route planning system based on big data algorithms, characterized in that, It includes: A data acquisition and processing module, which is used to collect data covering commercial company information, cigarette order data, and distribution vehicle-related information, clean the collected data to remove duplicate, incorrect, or incomplete data records, integrate the cleaned data, and establish a unified data storage structure for subsequent analysis and use; A regional division and clustering module, which is used to divide the entire distribution scope into multiple sub-regions according to geographical regions, administrative divisions, and transportation network factors. For commercial companies within each sub-region, a clustering algorithm is used to cluster commercial companies into multiple clustering groups according to the order frequency and expected delivery time of commercial companies; A driving route planning module, which is used to calculate vehicle requirements, plan an initial route, and optimize and adjust the route based on the clustering results, comprehensively considering the quantity of goods in the cigarette order, vehicle capacity, and the expected delivery time of commercial companies, to obtain optimized driving route information; A distribution plan generation and implementation module, which is used to integrate the optimized driving route information with the commercial company's cigarette order information, allocate it to the corresponding vehicles and drivers, generate a distribution plan including detailed driving routes, and at the same time use GPS positioning to monitor the entire driving route in real time, process the feedback of the driving route in a timely manner, record and analyze distribution data, and provide support for continuously optimizing the driving route.

2. The industrial cigarette distribution route planning system based on big data algorithm according to claim 1, characterized in that, The driving route planning module specifically includes: A vehicle requirement calculation unit, which is used to count the quantity of goods in the cigarette orders of the clustering groups to be delivered, compare it with the vehicle capacity of the delivery truck, calculate the required number of delivery trucks or trips, and at the same time, by matching the cigarette order volumes of different commercial companies, make the cigarette loading volume of each vehicle as close as possible to the vehicle capacity; An initial route planning unit, which is used to plan the initial driving route from the distribution center to each commercial company within the clustering group in units of clustering groups, using a neural network algorithm and considering the vehicle operating conditions and the expected delivery time of commercial companies; A route optimization and adjustment unit, which is used to optimize the driving route in combination with the load situation and delivery time of each delivery truck.

3. The industrial cigarette distribution route planning system based on big data algorithm according to claim 2, characterized in that, Before the route optimization and adjustment unit optimizes the driving route in combination with the load situation and delivery time of each delivery truck, it analyzes the distribution efficiency and cost of different routes in advance by means of historical distribution data, sets the pheromone weight value, and then selects routes or road sections based on the pheromone weight value to complete the optimization of the driving route; During the process of the route optimization and adjustment unit optimizing the driving route in combination with the load situation and delivery time of each delivery truck, it uses real-time vehicle information monitoring. Once it is found that the passing time of a certain road section increases due to traffic problems, it immediately searches for feasible roads in the vicinity based on historical distribution data and uses the A* algorithm to re-plan the route to make the load and delivery time of each vehicle tend to be balanced.

4. The industrial cigarette distribution route planning system based on big data algorithm according to claim 2, characterized in that The route optimization and adjustment unit optimizes the driving route considering the following constraints: (1) Decision variable X ijk , which represents the quantity of goods transported from shipping point i to destination j using vehicle k. Here, i represents different shipping points, j represents different destinations, and k represents different vehicles. Through the decision variable X ijk , the quantity of goods transported from different shipping points to different destinations using different vehicles can be clearly represented; (2) The objective function of minimizing the total transportation cost, which is expressed as follows: Minimize∑ i ∑ j ∑ k C ijk X ijk , Among them, C ijk represents the unit transportation cost of using vehicle k from the shipping point i to the arrival location j, and X ijk is the quantity of goods shipped from the shipping point i to the arrival location j using vehicle k. Summing over all shipping points i, arrival locations j, and vehicles k, the total transportation cost is obtained. The transportation plan can be optimized by minimizing this sum; (3) Constraints, specifically including: (3.1) Contract quantity constraint, which is expressed as follows: Among them, represents that for all i; for each shipping point i, the total quantity of goods shipped from this shipping point to all arrival locations j and transported using all vehicles k must be greater than or equal to the demand quantity d of contract i i , to meet the goods demand stipulated in the contract; (3.2) Vehicle capacity constraint, which is expressed as follows: X ijk ≤Q k , Among them, X ijk represents the quantity of goods transported from the shipping point i to the arrival point j using vehicle k, and it cannot exceed the capacity Q of vehicle k k , to ensure that the vehicle will not be overloaded during transportation; (3.3) Arrival time constraint, which is expressed as follows: t ij ≤T ij , Among them, t ij represents the actual transportation time from the shipping point i to the arrival location j, which must be less than or equal to the delivery expectation time T required in the contract for the commercial company ij to ensure that the goods can be delivered on time; (3.4) Vehicle availability constraint, expressed as follows: Among them, represents that for all k; for each available vehicle k, the total quantity of goods transported from all shipping points i to all destinations j using that vehicle must be greater than or equal to the number of available vehicles V k , to ensure that the vehicles are fully utilized.

5. The industrial cigarette distribution route planning system based on big data algorithm according to claim 2, characterized in that, The distribution plan generation and implementation module specifically includes: The delivery plan generation unit is used to deeply integrate the driving route information optimized by the driving route planning module with the specific information of the commercial company's cigarette order, determine the precise driving route of each delivery vehicle, plan the order of stopping at the commercial companies, and calculate the estimated time of arrival at each commercial company based on the vehicle's driving speed and road conditions. Then, vehicles and drivers are allocated for each driving route, and a delivery plan is generated and sent to the delivery personnel's handheld terminal device to provide clear and accurate guidance for delivery work; Real-time monitoring and feedback unit, used to continuously monitor the delivery vehicles in real time during the delivery process using GPS positioning technology, and accurately grasp the vehicle's driving position, driving speed and real-time status; The data recording and analysis unit is used to automatically record the actual implementation status of each delivery plan, covering multi-dimensional data such as delivery time, mileage, vehicle fuel consumption and feedback from commercial companies. It uses data analysis tools and methods to conduct in-depth analysis of the recorded data and explore its potential value.

6. An industrial cigarette distribution route planning method based on big data algorithms, characterized in that, The steps include: S1. Collect data covering commercial company information, cigarette order data, and delivery vehicle related information, clean the collected data to remove duplicate, erroneous, or incomplete data records, integrate the cleaned data, and establish a unified data storage structure for subsequent analysis and use; S2. Divide the entire distribution area into multiple sub-areas based on geographical regions, administrative divisions, and transportation network factors. For the commercial companies in each sub-area, use a clustering algorithm to cluster the commercial companies into multiple cluster groups based on the order frequency and expected delivery time of the commercial companies. S3. Based on the clustering results, the quantity of goods included in the cigarette order, the vehicle capacity and the expected delivery time of the commercial company are comprehensively considered to calculate the vehicle demand, plan the initial route and optimize the route to obtain the optimized driving route information; S4. Integrate the optimized driving route information with the commercial company's cigarette order information, assign it to the corresponding vehicles and drivers, and generate a delivery plan including a detailed driving route. At the same time, use GPS positioning to achieve full monitoring of the driving route, handle driving route feedback in a timely manner, and record and analyze delivery data to provide support for continuous optimization of driving routes.

7. The industrial cigarette distribution route planning method based on big data algorithm according to claim 6, characterized in that The step S3 specifically includes: S3.

1. Count the number of goods contained in the cigarette orders of the cluster group to be delivered, compare it with the capacity of the delivery truck, calculate the number of delivery trucks or trips required, and at the same time, make the cigarette loading amount of each vehicle as close to the vehicle capacity as possible by matching the cigarette order quantities of different commercial companies; S3.

2. Taking the cluster group as a unit, using the neural network algorithm, and considering the vehicle operation status and the expected delivery time of the commercial company, plan the initial driving route from the distribution center to each commercial company in the cluster group; S3.

3. Optimize the driving route based on the load conditions and delivery time of each delivery truck.

8. The industrial cigarette distribution path planning method based on big data algorithm according to claim 7, characterized in that Execute step S3.3, before optimizing the driving route, analyze the delivery efficiency and cost of different routes with the help of historical delivery data in advance, set pheromone weight values, and then select routes or road sections based on the pheromone weight values ​​to complete the optimization of the driving route; In the process of optimizing the driving route, the vehicle information is used for real-time monitoring based on the load situation and delivery time of each delivery truck. Once it is found that the travel time of a certain section of road has increased due to traffic problems, a feasible road is immediately searched in the surrounding area based on historical delivery data, and the A* algorithm is used to re-plan the route to balance the load and delivery time of each vehicle.

9. The industrial cigarette distribution route planning method based on big data algorithm according to claim 7, characterized in that, Execute step S3 to optimize the driving route by considering the following constraints: (1) Decision variable X ijk , which represents the quantity of goods transported from shipping point i to destination j using vehicle k. Here, i represents different shipping points, j represents different destinations, and k represents different vehicles. Through the decision variable X ijk , the quantity of goods transported from different shipping points to different destinations using different vehicles can be clearly represented; (2) The objective function of minimizing the total transportation cost is expressed as follows: Minimize∑ i ∑ j ∑ k C ijk X ijk , Among them, C ijk represents the unit transportation cost of using vehicle k from the shipping point i to the arrival location j, and X ijk is the quantity of goods shipped from the shipping point i to the arrival location j using vehicle k. Summing over all shipping points i, arrival locations j, and vehicles k gives the total transportation cost, and the transportation plan can be optimized by minimizing this sum; (3) Constraints, including: (3.1) Contract quantity constraints are expressed as follows: Among them, represents for all i; for each shipping point i, the total quantity of goods shipped from this shipping point to all arrival locations j and transported using all vehicles k must be greater than or equal to the demand quantity d of contract i i , to meet the goods demand stipulated in the contract; (3.2) Vehicle capacity constraint, expressed as follows: X ijk ≤Q k , Among them, X ijk represents the quantity of goods transported from the shipping point i to the destination j using vehicle k, and it cannot exceed the capacity Q of vehicle k k to ensure that the vehicle will not be overloaded during transportation; (3.3) The arrival time constraint is expressed as follows: t ij ≤T ij , where t ij represents the actual transportation time from the shipping point i to the arrival location j, which must be less than or equal to the distribution expected time T required in the contract ij to ensure that the goods can be delivered on time; (3.4) Vehicle availability constraint, expressed as follows: Among them, represents for all k; for each available vehicle k, the total quantity of goods transported from all shipping points i to all destinations j using that vehicle must be greater than or equal to the number of available vehicles V k , to ensure that the vehicles are fully utilized.

10. The industrial cigarette distribution route planning method based on big data algorithm according to claim 7, characterized in that, The step S4 specifically includes: S4.

1. Integrate the optimized driving route information with the specific information of the commercial companies' cigarette orders, determine the precise driving route of each delivery vehicle, plan the order of stopping at the commercial companies, and calculate the estimated time of arrival at each commercial company based on the vehicle's driving speed and road conditions. Then, assign vehicles and drivers to each driving route, generate a delivery plan and send it to the delivery personnel's handheld terminal device, providing clear and accurate guidance for delivery work; S4.

2. During the delivery process, the delivery vehicles are continuously monitored in real time using GPS positioning technology to accurately grasp the driving position, driving speed and real-time status of the vehicles; S4.

3. Automatically record the actual implementation status of each delivery plan, including multi-dimensional data such as delivery time, mileage, vehicle fuel consumption and feedback from commercial companies. Use data analysis tools and methods to conduct in-depth analysis of the recorded data to explore its potential value.

Images