Intelligent logistics path optimization algorithm and application system thereof

Abstract

The invention discloses an intelligent logistics path optimization algorithm and an application system thereof, and relates to the technical field of transfer control, and the intelligent logistics path optimization algorithm comprises a decision generation end, an influence prediction end and a path optimization end. The decision generation end is used for acquiring multiple parameters of a cold-chain logistics path in real time, automatically generating a cold-chain logistics path decision scheme, and judging whether the cold-chain logistics path decision scheme at the current moment is abnormal or not in real time in combination with the multiple parameters in the cold-chain logistics path; the influence prediction end is used for collecting dynamic changes generated in a cold-chain logistics process in real time; and the path optimization end is used for carrying out multi-target path collaborative optimization according to the prediction result of the cold-chain logistics path decision scheme. According to the intelligent logistics path optimization algorithm and the application system thereof, the execution accuracy of a cold-chain logistics path decision scheme is ensured, whether the cold-chain logistics path decision scheme is affected or not is predicted in advance, and the cold-chain logistics path can be optimized more accurately in combination with multi-target path collaborative optimization.

Description

Technical Field

[0001] The present invention relates to the field of transport control technology, and in particular to an intelligent logistics path optimization algorithm and an application system thereof. Background Art

[0002] Cold chain logistics is a special supply chain management method that aims to ensure that perishable goods are always kept in a specified low-temperature environment throughout the entire process of production, storage, transportation, sales and consumption by controlling temperature, so as to ensure product quality and reduce losses. The importance of cold chain logistics is reflected in its guarantee of food safety and quality. By strictly controlling the temperature during transportation and storage, cold chain logistics can effectively inhibit the growth and reproduction of microorganisms and slow down the respiration of food, thereby extending the shelf life of food and maintaining the freshness and nutritional value of food. Cold chain logistics can ensure its quality and safety during transportation.

[0003] Application No. CN202311415290.1 ​​discloses a cold chain logistics distribution path optimization method based on an improved ant colony algorithm. First, the cold chain logistics distribution historical data is obtained in advance; secondly, the vehicle transportation cost, the penalty cost for violating the time window constraint, the refrigeration cost calculation, the cargo damage cost and the carbon emission cost are calculated; then, the cold chain logistics distribution path optimization model of the improved ant colony algorithm is constructed with the transportation cost, refrigeration cost, cargo damage cost, carbon emission and time window comprehensive optimization as the goal; finally, the cold chain logistics distribution path optimization model is solved by using the improved ant colony algorithm to find the optimal path for cold chain logistics distribution. The present invention constructs a cold chain logistics distribution path optimization method with the transportation cost, refrigeration cost, cargo damage cost, carbon emission and time window comprehensive optimization as the goal, and the improved ant colony algorithm has a faster initial search speed and good optimization performance, which can quickly find the optimal path and achieve emission reduction.

[0004] After searching the above patents, it was found that the cold chain logistics path optimization algorithm still has some shortcomings: 1. When optimizing the cold chain logistics path, it is impossible to combine the multiple parameters of cold chain logistics in real time to consider whether the path optimization decision is feasible, resulting in lag and uncertainty in the intelligent logistics path optimization; 2. At the same time, there are many dynamic changing factors in the cold chain logistics process, especially traffic emergencies in the logistics process. Traditional algorithms are difficult to predict path optimization decision plans in time when dealing with these dynamic changes, affecting the normal execution of cold chain logistics path decision plans; 3. Cold chain logistics path optimization usually requires considering multiple goals at the same time. These goals cannot be optimized for multiple goals based on the logistics conflicts at the current moment, resulting in limitations in intelligent logistics path optimization.

[0005] Therefore, an intelligent logistics path optimization algorithm and its application system are proposed to solve the above problems. Summary of the invention

[0006] The main purpose of the present invention is to provide an intelligent logistics path optimization algorithm and its application system to solve the problems raised in the above background.

[0007] To achieve the above-mentioned purpose, the technical solution adopted by the present invention is: an intelligent logistics path optimization algorithm and its application system, including a decision-making end, an impact prediction end and a path optimization end; The decision generating end is used to collect multiple parameters of the cold chain logistics path in real time, and automatically generate a cold chain logistics path decision plan, and judge in real time whether the cold chain logistics path decision plan at the current moment is abnormal in combination with the multiple parameters in the cold chain logistics path. If abnormal, the cold chain logistics path decision plan is adjusted in time according to the actual data; The impact prediction end is used to collect dynamic changes occurring in the cold chain logistics process in real time, and timely predict whether the dynamic changes will affect the normal execution of the cold chain logistics path decision plan according to the current traffic emergency situation at the intersection, and if not, continue to predict the execution of the cold chain logistics path decision plan; The path optimization end is used to perform multi-objective path collaborative optimization according to the prediction results of the cold chain logistics path decision plan when it is predicted that the sudden traffic situation at the intersection at the current moment affects the normal execution of the cold chain logistics path decision plan.

[0008] The decision-making generation end includes a logistics path module, a multi-source factor module and a real-time judgment module; The logistics path module includes a basic parameter unit and a multi-parameter sorting unit; The basic parameter unit is used to collect multiple parameters and historical data of cold chain logistics path decision through a data acquisition instrument, and the multiple parameters include the economic cost and time cost of the cold chain logistics path decision plan, wherein the calculation formula of the economic cost of the cold chain logistics path decision plan is as follows: The economic cost of the cold chain logistics path decision plan = transportation cost + inventory holding cost + logistics administrative management cost; Transportation costs include vehicle costs and operating overhead costs. Vehicle costs include fuel costs, tire costs, and repair costs. Operating overhead costs include logistics wages and employee welfare costs. Inventory holding costs include capital occupation costs, warehousing costs, insurance costs, and loss costs. Logistics administrative costs include order processing costs, information system maintenance costs, and logistics staff wages. The multi-parameter sorting unit is used to arrange the basic parameters of the cold chain logistics path decision plan in ascending order according to different paths using Arabic numerals.

[0009] The multi-source factor module includes a path link unit and a risk occurrence unit; The path link unit is used to obtain multiple routes of the cold chain logistics distribution path through GPS positioning and navigation technology, and combine the remaining mileage of the vehicle corresponding to the cold chain logistics with the multiple routes through the intelligent vehicle system, and determine the path according to the current path and vehicle endurance. If the vehicle endurance is less than 30 kilometers, the path close to the gas station is preferred. If the vehicle endurance is greater than or equal to 30 kilometers, the path with a short distance is preferred. The risk occurrence unit is used to calculate the risk rate of the logistics path in real time, and the calculation formula is as follows: ; in, Indicates the risk rate of the corresponding path selected by cold chain logistics, represents the risk coefficient of the corresponding path, It indicates the risk probability of the corresponding path execution. If the risk rate is a positive value, it means that the cold chain logistics path decision plan is abnormal. If the risk rate is a negative value, it means that the cold chain logistics path decision plan is normal.

[0010] The real-time judgment module includes a path decision model, a solution judgment unit and an abnormal warning unit; The path decision model is used to set the cold chain logistics path decision standard model, and the cold chain logistics path decision standard model is provided with optimal standard parameters, and the optimal standard parameters include the cold chain logistics path transportation time, the refrigeration time, the optimal traffic quantity of the logistics path and the logistics selectable path; The solution judgment unit is used to receive the basic parameters at the current moment in real time through the data receiver, and perform difference calculation between the basic parameters and the optimal standard parameters. If the difference between the basic parameters and the optimal standard parameters is equal to 0, it means that the corresponding basic parameters are normal, that is, the cold chain logistics path decision solution is normal. If the difference between the basic parameters and the optimal standard parameters is not equal to 0, it means that the corresponding basic parameters are abnormal, that is, the cold chain logistics path decision solution is abnormal. The abnormal warning unit is used to adjust the corresponding cold chain logistics path decision plan according to the difference when the basic parameters are abnormal. Specifically, if the difference between the basic parameters and the optimal standard parameters is greater than 0, the value of the corresponding basic parameters is reduced; if the difference between the basic parameters and the optimal standard parameters is less than 0, the value of the corresponding basic parameters is increased, and the reporting system is notified to issue a voice alarm reminder.

[0011] The impact prediction end includes a dynamic collection module, a dynamic interaction module and an impact prediction module; The dynamic acquisition module includes a dynamic acquisition unit; The dynamic collection unit is used to collect the dynamic parameters of the cold chain logistics distribution path at the current time and historical time in real time through a data acquisition instrument. The dynamic parameters include the traffic volume in the corresponding area at the corresponding time on the corresponding path, the location parameters of the traffic accident, the estimated processing time of the traffic accident, and the customer demand change data during the cold chain logistics path.

[0012] The dynamic interaction module includes a traffic feedback unit and a demand update unit; The traffic feedback unit is used to receive traffic feedback information of the corresponding route in real time through the data positioning navigation device; The demand updating unit is used to receive system feedback in real time through a data receiver and update customer demand in real time.

[0013] The impact prediction module includes an impact prediction unit; The impact prediction unit is used to predict whether the current traffic changes will affect the normal execution of the cold chain logistics path decision plan according to the dynamic changes received in real time. The prediction method is as follows: Step 1: Receive in real time the basic parameters of the cold chain logistics distribution path, the traffic volume at the corresponding time on the corresponding path, the location parameters of the traffic accident, and the customer demand change data during the cold chain logistics path. The traffic volume in the area corresponding to the location parameters of the traffic accident is collected in real time through a data acquisition instrument, and the transportation time of the logistics path is automatically increased or decreased in combination with the estimated processing time of the traffic accident to obtain the predicted data of the transportation time. Step 2: Calculate the difference between the traffic volume at the corresponding time on the corresponding path corresponding to the predicted data of the transportation time and the traffic volume in the area corresponding to the location parameters of the historical traffic accidents. If the difference is less than or equal to 2, it means that the current traffic changes do not affect the normal execution of the cold chain logistics path decision plan. If the difference is greater than 2, it means that the current traffic changes affect the normal execution of the cold chain logistics path decision plan.

[0014] The path optimization end includes a prediction receiving module, a target risk module, an optimization model module and an optimization tracking module; The prediction receiving module is used to receive the prediction result in real time through a data receiver; The target risk module is used to calculate the multi-objective function of the cold chain logistics path decision plan according to the prediction results. Assuming that the cold chain logistics is provided with X logistics paths, each logistics path includes Y logistics accessories, and each logistics accessory corresponds to M delivery addresses, a multi-objective function is given, which includes the transportation cost utilization rate, the actual logistics path site function, the actual cost function and the multi-objective balance rate of the cold chain logistics path. The calculation formula is as follows: Calculate the transportation cost utilization rate, the formula is as follows: ; in, For the Logistics accessories for logistics routes In the The delivery quantity for each delivery address, For the Logistics accessories for logistics routes In the Delivery time for each delivery address, is the actual logistics path site function; Calculate the actual logistics path site function, the formula is as follows: ; in, Indicates the delivery time of each logistics accessory; Calculate the actual cost function, the formula is as follows: ; in, For the Logistics accessories for logistics routes In the Delivery cost to each delivery address; Calculate the multi-objective balance rate of the cold chain logistics path, the formula is as follows: .

[0015] The optimization model module is used to calculate the multi-objective collaborative optimization parameters of the cold chain logistics path collaborative balance according to the multi-objective function , The calculation formula is as follows: ; The constraint condition includes at least one of constraint 1, constraint 2, constraint 3 and constraint 4; The calculation formula for constraint one is as follows: ,in, Indicates Logistics accessories for logistics routes In the Delivery time for each delivery address, Indicates the actual logistics path station Logistics accessories for logistics routes In the The delivery time required for each delivery address to deliver the quantity; The calculation formula for constraint 2 is as follows: ,in, Indicates Logistics path stations for logistics paths; The calculation formula for constraint three is as follows: ; is a positive integer greater than or equal to 1; in, Indicates Logistics accessories for logistics routes In the The actual delivery logistics path stations for the delivery addresses, Indicates The delivery logistics path stations for each delivery address; The calculation formula of constraint four is as follows: , Indicates Logistics accessories for logistics routes In the The logistics distribution cost constraint value of the delivery address; Among them, constraint one represents the delivery time constraint, constraint two represents the delivery quantity constraint, constraint three represents the delivery logistics path site constraint, and constraint four represents the logistics delivery cost constraint; Then follow these steps: Step I: Set the initial cold chain logistics path as q, and use a multi-population genetic algorithm to calculate the multi-objective collaborative optimization parameters; Step II: Select N target individuals from the multi-objective function, randomly pair the N target individuals, use single-point crossover to produce a pair of offspring for each pair, perform site mutation on each offspring with probability to obtain a new offspring, calculate the fitness value of each offspring, and obtain the multi-objective collaborative optimization parameter of q+1; if the algorithm meets the termination condition, terminate the algorithm; if the algorithm does not meet the termination condition, repeat step II; Step III: Analyze the key influencing factors that affect the cold chain logistics path decision-making plan based on the multi-objective collaborative optimization parameters, and then further adjust the multi-objective collaborative optimization parameters. The key influencing factors include the transportation cost utilization rate or the multi-objective balance rate of the cold chain logistics path; The optimization tracking module is used to track the multi-objective collaborative optimization parameters of the cold chain logistics path decision plan in real time through a data tracker, and adjust the cold chain logistics path decision plan in real time according to the multi-objective collaborative optimization parameters.

[0016] A method for using an intelligent logistics path optimization algorithm application system comprises the following steps: Step 1: Configure the IP address information of the cold chain logistics remote control area server; Step 2: Enter the decision-making end, collect multiple parameters of the cold chain logistics path in real time, automatically generate a cold chain logistics path decision plan, and combine multiple parameters to determine in real time whether the cold chain logistics path decision plan at the current moment is abnormal. If abnormal, adjust the cold chain logistics path decision plan in real time according to actual data; Step 3: If normal, enter the impact prediction end, collect the dynamic changes in the cold chain logistics process in real time, and timely predict whether the dynamic changes will affect the normal execution of the cold chain logistics path decision plan according to the current traffic emergency situation at the intersection. If not, continue to predict the execution of the cold chain logistics path decision plan; Step 4: If yes, enter the path optimization end, perform multi-objective path collaborative optimization according to the prediction results of the cold chain logistics path decision standard model, and obtain the multi-objective collaborative optimization parameters.

[0017] The present invention has the following beneficial effects: 1. In the present invention, by setting a decision-making generation end, when performing intelligent logistics path optimization, the cold chain logistics path decision plan generated according to the basic parameters is used to perform real-time difference calculation with the optimal standard parameters of the cold chain logistics path decision standard model. In the process of the cold chain logistics path, it is possible to analyze in real time whether the generated cold chain logistics path decision plan is abnormal, further ensure the accuracy of the execution of the cold chain logistics path decision plan, and reduce the lag and uncertainty existing in the intelligent logistics path optimization.

[0018] 2. In the present invention, by setting an impact prediction terminal, when performing intelligent logistics path optimization, by receiving sudden traffic conditions at intersections and changes in customer demand during the cold chain logistics path process, it is possible to timely predict whether dynamic changes will affect the normal execution of cold chain logistics path decisions, ensure the feasibility of the execution of the cold chain logistics path decision plan, and predict in advance whether the cold chain logistics path decision plan will be affected, thereby further increasing the stability of cold chain logistics distribution.

[0019] 3. In the present invention, by setting a path optimization end, when performing intelligent logistics path optimization, when it is predicted that the sudden traffic situation at the intersection at the current moment affects the normal execution of the cold chain logistics path decision plan, the multi-objective function of the cold chain logistics path decision plan is calculated according to the prediction result of the cold chain logistics path decision plan, and then the multi-objective collaborative optimization parameters of the collaborative balance of the cold chain logistics path are calculated according to the multi-objective function, so that the cold chain logistics path optimization algorithm can perform multi-objective path collaborative optimization, thereby being able to more accurately optimize the cold chain logistics path and ensure the safety and reliability of the cold chain logistics path. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A schematic diagram of the system architecture of an intelligent logistics path optimization algorithm and its application system of the present invention; Figure 2This is a schematic diagram of the architecture of a decision-making generation end of an intelligent logistics path optimization algorithm and its application system of the present invention; Figure 3 It is a schematic diagram of the architecture of an intelligent logistics path optimization algorithm and an impact prediction end of its application system according to the present invention; Figure 4 This is a schematic diagram of the architecture of the path optimization end of an intelligent logistics path optimization algorithm and its application system of the present invention. DETAILED DESCRIPTION

[0021] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods.

[0022] Embodiment 1 Please refer to Figure 1 to Figure 2 As shown: an intelligent logistics path optimization algorithm and its application system, including a decision-making end, an impact prediction end and a path optimization end; The decision-making end is used to collect multiple parameters of the cold chain logistics path in real time and automatically generate a cold chain logistics path decision plan. It combines the multiple parameters in the cold chain logistics path to determine in real time whether the cold chain logistics path decision plan at the current moment is abnormal. If abnormal, the cold chain logistics path decision plan is adjusted in time according to the actual data; The impact prediction end is used to collect dynamic changes in the cold chain logistics process in real time, and timely predict whether the dynamic changes will affect the normal execution of the cold chain logistics path decision plan according to the current traffic emergency situation at the intersection. If not, it will continue to predict the execution of the cold chain logistics path decision plan; The path optimization end is used to perform multi-objective path collaborative optimization based on the prediction results of the cold chain logistics path decision plan when it is predicted that the sudden traffic situation at the intersection at the current moment will affect the normal execution of the cold chain logistics path decision plan.

[0023] The decision-making end includes a logistics path module, a multi-source factor module, and a real-time judgment module; The logistics path module includes a basic parameter unit and a multi-parameter sorting unit; The basic parameter unit is used to collect multi-parameters and historical data of cold chain logistics path decision through a data acquisition instrument. The multi-parameters include the economic cost and time cost of the cold chain logistics path decision plan. The calculation formula of the economic cost of the cold chain logistics path decision plan is as follows: The economic cost of the cold chain logistics path decision plan = transportation cost + inventory holding cost + logistics administrative management cost; Transportation costs include vehicle costs and operating overhead costs. Vehicle costs include fuel costs, tire costs, and repair costs. Operating overhead costs include logistics wages and employee welfare costs. Inventory holding costs include capital occupation costs, warehousing costs, insurance costs, and loss costs. Logistics administrative costs include order processing costs, information system maintenance costs, and logistics staff wages. The multi-parameter sorting unit is used to arrange the basic parameters of the cold chain logistics path decision plan in ascending order according to different paths using Arabic numerals.

[0024] The multi-source factor module includes path link unit and risk occurrence unit; The path link unit is used to obtain multiple routes of cold chain logistics distribution routes through GPS positioning and navigation technology, and combine the remaining mileage of the corresponding cold chain logistics vehicle with multiple routes through the intelligent vehicle system, and determine the path according to the current path and vehicle endurance. If the vehicle endurance is less than 30 kilometers, the path close to the gas station is given priority. If the vehicle endurance is greater than or equal to 30 kilometers, the path with a short distance is given priority. The risk occurrence unit is used to calculate the risk rate of the logistics path in real time. The calculation formula is as follows: ; in, Indicates the risk rate of the corresponding path selected by cold chain logistics, represents the risk coefficient of the corresponding path, It represents the risk probability of the corresponding path execution. If the risk rate is a positive value, it means that the cold chain logistics path decision plan is abnormal. If the risk rate is a negative value, it means that the cold chain logistics path decision plan is normal. By calculating the difference between the cold chain logistics path decision plan generated according to the basic parameters and the optimal standard parameters of the cold chain logistics path decision standard model in real time, it is possible to analyze in real time whether the generated cold chain logistics path decision plan is abnormal during the cold chain logistics path process.

[0025] The real-time judgment module includes a path decision model, a solution judgment unit, and an abnormal warning unit; The path decision model is used to set the cold chain logistics path decision standard model. The cold chain logistics path decision standard model has optimal standard parameters. The optimal standard parameters include the cold chain logistics path transportation time, refrigeration time, the optimal number of logistics path traffic and the logistics selectable path; The solution judgment unit is used to receive the basic parameters at the current moment in real time through the data receiver, and calculate the difference between the basic parameters and the optimal standard parameters. If the difference between the basic parameters and the optimal standard parameters is equal to 0, it means that the corresponding basic parameters are normal, that is, the cold chain logistics path decision plan is normal. If the difference between the basic parameters and the optimal standard parameters is not equal to 0, it means that the corresponding basic parameters are abnormal, that is, the cold chain logistics path decision plan is abnormal; The abnormal warning unit is used to adjust the corresponding cold chain logistics path decision plan according to the difference when the basic parameters are abnormal. Specifically: if the difference between the basic parameters and the optimal standard parameters is greater than 0, the value of the corresponding basic parameters is reduced; if the difference between the basic parameters and the optimal standard parameters is less than 0, the value of the corresponding basic parameters is increased, and the reporting system is sent out to issue a voice alarm to ensure the accuracy of the execution of the cold chain logistics path decision plan and reduce the lag and uncertainty of intelligent logistics path optimization.

[0026] Embodiment 2 Please refer to Figure 3 As shown: Based on the first embodiment, the impact prediction end includes a dynamic collection module, a dynamic interaction module and an impact prediction module; The dynamic acquisition module includes a dynamic acquisition unit; The dynamic collection unit is used to collect the dynamic parameters of the cold chain logistics distribution path at the current time and historical time in real time through the data collection instrument. The dynamic parameters include the traffic volume in the corresponding area at the corresponding time on the corresponding path, the location parameters of the traffic accident, the estimated processing time of the traffic accident, and the customer demand change data during the cold chain logistics path.

[0027] The dynamic interaction module includes a traffic feedback unit and a demand update unit; The traffic feedback unit is used to receive the traffic feedback information of the corresponding route in real time through the data positioning navigation device; The demand update unit is used to receive system feedback in real time through the data receiver, and to update customer demand in real time. By receiving sudden traffic conditions at intersections and changes in customer demand during the cold chain logistics route, it can timely predict whether dynamic changes will affect the normal execution of cold chain logistics route decisions.

[0028] The impact prediction module includes an impact prediction unit; The impact prediction unit is used to predict whether the current traffic changes will affect the normal execution of the cold chain logistics path decision plan based on the dynamic changes received in real time. The prediction method is as follows: Step 1: Receive in real time the basic parameters of the cold chain logistics distribution path, the traffic volume at the corresponding time on the corresponding path, the location parameters of the traffic accident, and the customer demand change data during the cold chain logistics path. The traffic volume in the area corresponding to the location parameters of the traffic accident is collected in real time through a data acquisition instrument, and the transportation time of the logistics path is automatically increased or decreased in combination with the estimated processing time of the traffic accident to obtain the predicted data of the transportation time. Step 2: Calculate the difference between the traffic volume at the corresponding time on the corresponding path corresponding to the predicted data of the transportation time and the traffic volume in the area corresponding to the location parameters of the historical traffic accidents. If the difference is less than or equal to 2, it means that the current traffic changes do not affect the normal execution of the cold chain logistics path decision plan. If the difference is greater than 2, it means that the current traffic changes affect the normal execution of the cold chain logistics path decision plan, thereby ensuring the feasibility of the execution of the cold chain logistics path decision plan, predicting in advance whether the cold chain logistics path decision plan is affected, and further increasing the stability of cold chain logistics distribution.

[0029] Embodiment 3 Please refer to Figure 4 As shown: Based on the first embodiment, the path optimization end includes a prediction receiving module, a target risk module, an optimization model module and an optimization tracking module; The prediction receiving module is used to receive the prediction result in real time through the data receiver; The target risk module is used to calculate the multi-objective function of the cold chain logistics path decision plan based on the prediction results. Assuming that the cold chain logistics has X logistics paths, each logistics path includes Y logistics accessories, and each logistics accessory corresponds to M delivery addresses, a multi-objective function is given. The multi-objective function includes transportation cost utilization, actual logistics path site function, actual cost function and cold chain logistics path multi-objective balance rate. The calculation formula is as follows: Calculate the transportation cost utilization rate, the formula is as follows: ; in, For the Logistics accessories for logistics routes In the The delivery quantity for each delivery address, For the Logistics accessories for logistics routes In the Delivery time for each delivery address, is the actual logistics path site function; Calculate the actual logistics path site function, the formula is as follows: ; in, Indicates the delivery time of each logistics accessory; Calculate the actual cost function, the formula is as follows: ; in, For the Logistics accessories for logistics routes In the Delivery cost to each delivery address; Calculate the multi-objective balance rate of the cold chain logistics path, the formula is as follows: .

[0030] The optimization model module is used to calculate the multi-objective collaborative optimization parameters of the cold chain logistics path collaborative balance based on the multi-objective function , The calculation formula is as follows: ; The constraint condition includes at least one of constraint 1, constraint 2, constraint 3 and constraint 4; The calculation formula for constraint one is as follows: ,in, Indicates Logistics accessories for logistics routes In the Delivery time for each delivery address, Indicates the actual logistics path station Logistics accessories for logistics routes In the The delivery time required for each delivery address to deliver the quantity; The calculation formula for constraint 2 is as follows: ,in, Indicates Logistics path stations for logistics paths; The calculation formula for constraint three is as follows: ; is a positive integer greater than or equal to 1; in, Indicates Logistics accessories for logistics routes In the The actual delivery logistics path stations for the delivery addresses, Indicates The delivery logistics path stations for each delivery address; The calculation formula of constraint four is as follows: , Indicates Logistics accessories for logistics routes In the The logistics distribution cost constraint value of the delivery address; Among them, constraint one represents the delivery time constraint, constraint two represents the delivery quantity constraint, constraint three represents the delivery logistics path site constraint, and constraint four represents the logistics delivery cost constraint. When it is predicted that the sudden traffic situation at the intersection at the current moment affects the normal execution of the cold chain logistics path decision plan, the multi-objective function of the cold chain logistics path decision plan is calculated based on the prediction results of the cold chain logistics path decision plan in combination with the cold chain logistics constraint factors, and then the multi-objective collaborative optimization parameters of the cold chain logistics path collaborative balance are calculated based on the multi-objective function, so that the cold chain logistics path optimization algorithm can perform multi-objective path collaborative optimization; Then follow these steps: Step I: Set the initial cold chain logistics path as q, and use a multi-population genetic algorithm to calculate the multi-objective collaborative optimization parameters; Step II: Select N target individuals from the multi-objective function, randomly pair the N target individuals, use single-point crossover to produce a pair of offspring for each pair, perform site mutation on each offspring with probability to obtain a new offspring, calculate the fitness value of each offspring, and obtain the multi-objective collaborative optimization parameter of q+1; if the algorithm meets the termination condition, terminate the algorithm; if the algorithm does not meet the termination condition, repeat step II; Step III: Analyze the key influencing factors that affect the cold chain logistics path decision-making plan based on the multi-objective collaborative optimization parameters, and then further adjust the multi-objective collaborative optimization parameters. The key influencing factors include the transportation cost utilization rate or the multi-objective balance rate of the cold chain logistics path; The optimization tracking module is used to track the multi-objective collaborative optimization parameters of the cold chain logistics path decision plan in real time through a data tracker, and adjust the cold chain logistics path decision plan in real time according to the multi-objective collaborative optimization parameters, so that the cold chain logistics path optimization algorithm can perform multi-objective path collaborative optimization, thereby more accurately optimizing the cold chain logistics path and ensuring the safety and reliability of the cold chain logistics path.

[0031] In the present invention, an intelligent logistics path optimization algorithm and its application system are provided. When the system is in operation, the IP address information of the cold chain logistics remote control area server is first configured; the decision generation end is entered, and the cold chain logistics path decision plan is automatically generated by real-time collection of multiple parameters of the cold chain logistics path, and the cold chain logistics path decision plan at the current moment is judged in real time by combining the multiple parameters. If it is abnormal, the cold chain logistics path decision plan is adjusted in real time according to the actual data. When optimizing the intelligent logistics path, the cold chain logistics path decision plan generated according to the basic parameters is calculated in real time with the optimal standard parameters of the cold chain logistics path decision standard model. In the process of cold chain logistics path, it is possible to analyze in real time whether the generated cold chain logistics path decision plan is abnormal, further ensure the accuracy of the execution of the cold chain logistics path decision plan, and reduce the lag and uncertainty of intelligent logistics path optimization; if it is normal, the impact prediction end is entered, and the dynamic changes occurring in the cold chain logistics process are collected in real time. According to the sudden traffic conditions at the intersection at the current moment, it is predicted in time whether the dynamic changes affect the normal execution of the cold chain logistics path decision plan. Otherwise Continuously predict the execution of the cold chain logistics path decision plan. When performing intelligent logistics path optimization, by receiving the sudden traffic conditions at the intersection and the changes in customer demand during the cold chain logistics path process, timely predict whether the dynamic changes will affect the normal execution of the cold chain logistics path decision, ensure the feasibility of the execution of the cold chain logistics path decision plan, and predict in advance whether the cold chain logistics path decision plan will be affected, further increase the stability of cold chain logistics distribution; if so, enter the path optimization end, and perform multi-objective path collaborative optimization according to the prediction results of the cold chain logistics path decision standard model to obtain multi-objective collaborative optimization parameters. When performing intelligent logistics path optimization, when it is predicted that the sudden traffic conditions at the intersection at the current moment will affect the normal execution of the cold chain logistics path decision plan, calculate the multi-objective function of the cold chain logistics path decision plan according to the prediction results of the cold chain logistics path decision plan, and then calculate the multi-objective collaborative optimization parameters of the cold chain logistics path collaborative balance according to the multi-objective function, so that the cold chain logistics path optimization algorithm can perform multi-objective path collaborative optimization, thereby more accurately optimizing the cold chain logistics path and ensuring the safety and reliability of the cold chain logistics path.

[0032] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. An intelligent logistics path optimization algorithm application system, characterized in that: The intelligent logistics path optimization algorithm application system includes a decision generation end, an impact prediction end and a path optimization end; The decision generating end is used to collect multiple parameters of the cold chain logistics path in real time, and automatically generate a cold chain logistics path decision plan, and judge in real time whether the cold chain logistics path decision plan at the current moment is abnormal in combination with the multiple parameters in the cold chain logistics path. If abnormal, the cold chain logistics path decision plan is adjusted in time according to the actual data; The impact prediction end is used to collect dynamic changes occurring in the cold chain logistics process in real time, and timely predict whether the dynamic changes will affect the normal execution of the cold chain logistics path decision plan according to the current traffic emergency situation at the intersection, and if not, continue to predict the execution of the cold chain logistics path decision plan; The path optimization end is used to perform multi-objective path collaborative optimization according to the prediction results of the cold chain logistics path decision plan to obtain multi-objective collaborative optimization parameters when it is predicted that the sudden traffic situation at the intersection at the current moment affects the normal execution of the cold chain logistics path decision plan.

2. The application system according to claim 1, characterized in that: The decision-making generation end includes a logistics path module, a multi-source factor module and a real-time judgment module; The logistics path module includes a basic parameter unit and a multi-parameter sorting unit; The basic parameter unit is used to collect multiple parameters and historical data of cold chain logistics path decision through a data acquisition instrument, and the multiple parameters include the economic cost and time cost of the cold chain logistics path decision plan, wherein the calculation formula of the economic cost of the cold chain logistics path decision plan is as follows: The economic cost of the cold chain logistics path decision plan = transportation cost + inventory holding cost + logistics administrative management cost; Transportation costs include vehicle costs and operating overhead costs. Vehicle costs include fuel costs, tire costs, and repair costs. Operating overhead costs include logistics wages and employee welfare costs. Inventory holding costs include capital occupation costs, warehousing costs, insurance costs, and loss costs. Logistics administrative costs include order processing costs, information system maintenance costs, and logistics staff wages. The multi-parameter sorting unit is used to arrange the basic parameters of the cold chain logistics path decision plan in ascending order according to different paths using Arabic numerals.

3. The application system according to claim 2, characterized in that: The multi-source factor module includes a path link unit and a risk occurrence unit; The path link unit is used to obtain multiple routes of the cold chain logistics distribution path through GPS positioning and navigation technology, and combine the remaining mileage of the vehicle corresponding to the cold chain logistics with the multiple routes through the intelligent vehicle system, and determine the path according to the current path and vehicle endurance. If the vehicle endurance is less than 30 kilometers, the path close to the gas station is preferred. If the vehicle endurance is greater than or equal to 30 kilometers, the path with a short distance is preferred. The risk occurrence unit is used to calculate the risk rate of the logistics path in real time, and the calculation formula is as follows: ； in, Indicates the risk rate of the corresponding path selected by cold chain logistics, represents the risk coefficient of the corresponding path, It indicates the risk probability of the corresponding path execution. If the risk rate is a positive value, it means that the cold chain logistics path decision plan is abnormal. If the risk rate is a negative value, it means that the cold chain logistics path decision plan is normal.

4. The application system according to claim 3, characterized in that: The real-time judgment module includes a path decision model, a solution judgment unit and an abnormal warning unit; The path decision model is used to set the cold chain logistics path decision standard model, and the cold chain logistics path decision standard model is provided with optimal standard parameters, and the optimal standard parameters include the cold chain logistics path transportation time, the refrigeration time, the optimal traffic quantity of the logistics path and the logistics selectable path; The solution judgment unit is used to receive the basic parameters at the current moment in real time through the data receiver, and perform difference calculation between the basic parameters and the optimal standard parameters. If the difference between the basic parameters and the optimal standard parameters is equal to 0, it means that the corresponding basic parameters are normal, that is, the cold chain logistics path decision solution is normal. If the difference between the basic parameters and the optimal standard parameters is not equal to 0, it means that the corresponding basic parameters are abnormal, that is, the cold chain logistics path decision solution is abnormal. The abnormal warning unit is used to adjust the corresponding cold chain logistics path decision plan according to the difference when the basic parameters are abnormal. Specifically, if the difference between the basic parameters and the optimal standard parameters is greater than 0, the value of the corresponding basic parameters is reduced; if the difference between the basic parameters and the optimal standard parameters is less than 0, the value of the corresponding basic parameters is increased, and the reporting system is notified to issue a voice alarm reminder.

5. The application system according to claim 1, characterized in that: The impact prediction end includes a dynamic collection module, a dynamic interaction module and an impact prediction module; The dynamic acquisition module includes a dynamic acquisition unit; The dynamic collection unit is used to collect the dynamic parameters of the cold chain logistics distribution path at the current time and historical time in real time through a data acquisition instrument. The dynamic parameters include the traffic volume in the corresponding area at the corresponding time on the corresponding path, the location parameters of the traffic accident, the estimated processing time of the traffic accident, and the customer demand change data during the cold chain logistics path.

6. The application system according to claim 5, characterized in that: The dynamic interaction module includes a traffic feedback unit and a demand update unit; The traffic feedback unit is used to receive traffic feedback information of the corresponding route in real time through the data positioning navigation device; The demand updating unit is used to receive system feedback in real time through a data receiver and update customer demand in real time.

7. The application system according to claim 6, characterized in that: The impact prediction module includes an impact prediction unit; The impact prediction unit is used to predict whether the current traffic changes will affect the normal execution of the cold chain logistics path decision plan according to the dynamic changes received in real time. The prediction method is as follows: Step 1: Receive in real time the basic parameters of the cold chain logistics distribution path, the traffic volume at the corresponding time on the corresponding path, the location parameters of the traffic accident, and the customer demand change data during the cold chain logistics path. The traffic volume in the area corresponding to the location parameters of the traffic accident is collected in real time through a data acquisition instrument, and the transportation time of the logistics path is automatically increased or decreased in combination with the estimated processing time of the traffic accident to obtain the predicted data of the transportation time. Step 2: Calculate the difference between the traffic volume at the corresponding time on the corresponding path corresponding to the predicted data of the transportation time and the traffic volume in the area corresponding to the location parameters of the historical traffic accidents. If the difference is less than or equal to 2, it means that the current traffic changes do not affect the normal execution of the cold chain logistics path decision plan. If the difference is greater than 2, it means that the current traffic changes affect the normal execution of the cold chain logistics path decision plan.

8. The application system according to claim 1, characterized in that: The path optimization end includes a prediction receiving module, a target risk module, an optimization model module and an optimization tracking module; The prediction receiving module is used to receive the prediction result in real time through a data receiver; The target risk module is used to calculate the multi-objective function of the cold chain logistics path decision plan according to the prediction results. Assuming that the cold chain logistics is provided with X logistics paths, each logistics path includes Y logistics accessories, and each logistics accessory corresponds to M delivery addresses, a multi-objective function is given, which includes the transportation cost utilization rate, the actual logistics path site function, the actual cost function and the multi-objective balance rate of the cold chain logistics path. The calculation formula is as follows: Calculate the transportation cost utilization rate, the formula is as follows: ； in, For the Logistics accessories for logistics routes In the The delivery quantity for each delivery address, For the Logistics accessories for logistics routes In the Delivery time for each delivery address, is the actual logistics path site function; Calculate the actual logistics path site function, the formula is as follows: ； in, Indicates the delivery time of each logistics accessory; Calculate the actual cost function, the formula is as follows: ； in, For the Logistics accessories for logistics routes In the Delivery cost to each delivery address; Calculate the multi-objective balance rate of the cold chain logistics path, the formula is as follows: 。 9. The application system according to claim 8, characterized in that: The optimization model module is used to calculate the multi-objective collaborative optimization parameters of the cold chain logistics path collaborative balance according to the multi-objective function , The calculation formula is as follows: ； The constraint condition includes at least one of constraint 1, constraint 2, constraint 3 and constraint 4; The calculation formula for constraint one is as follows: ,in, Indicates Logistics accessories for logistics routes In the Delivery time for each delivery address, Indicates the actual logistics path station Logistics accessories for logistics routes In the The delivery time required for each delivery address to deliver the quantity; The calculation formula for constraint 2 is as follows: ,in, Indicates Logistics path stations for logistics paths; The calculation formula for constraint three is as follows: ； is a positive integer greater than or equal to 1; in, Indicates Logistics accessories for logistics routes In the The actual delivery logistics path stations for the delivery addresses, Indicates The delivery logistics path stations for each delivery address; The calculation formula of constraint four is as follows: , Indicates Logistics accessories for logistics routes In the The logistics distribution cost constraint value of the delivery address; Among them, constraint one represents the delivery time constraint, constraint two represents the delivery quantity constraint, constraint three represents the delivery logistics path site constraint, and constraint four represents the logistics delivery cost constraint; Then follow these steps: Step I: Set the initial cold chain logistics path as q, and use a multi-population genetic algorithm to calculate the multi-objective collaborative optimization parameters; Step II: Select N target individuals from the multi-objective function, randomly pair the N target individuals, use single-point crossover to produce a pair of offspring for each pair, perform site mutation on each offspring with probability to obtain a new offspring, calculate the fitness value of each offspring, and obtain the multi-objective collaborative optimization parameter of q+1; if the algorithm meets the termination condition, terminate the algorithm; if the algorithm does not meet the termination condition, repeat step II; Step III: Analyze the key influencing factors that affect the cold chain logistics path decision-making plan based on the multi-objective collaborative optimization parameters, and then further adjust the multi-objective collaborative optimization parameters. The key influencing factors include the transportation cost utilization rate or the multi-objective balance rate of the cold chain logistics path; The optimization tracking module is used to track the multi-objective collaborative optimization parameters of the cold chain logistics path decision plan in real time through a data tracker, and adjust the cold chain logistics path decision plan in real time according to the multi-objective collaborative optimization parameters.

10. An intelligent logistics path optimization algorithm, referring to an intelligent logistics path optimization algorithm application system according to any one of claims 1 to 9, characterized in that: The following steps are involved: Step 1: Configure the IP address information of the cold chain logistics remote control area server; Step 2: Enter the decision-making end, collect multiple parameters of the cold chain logistics path in real time, automatically generate a cold chain logistics path decision plan, and combine multiple parameters to determine in real time whether the cold chain logistics path decision plan at the current moment is abnormal. If abnormal, adjust the cold chain logistics path decision plan in real time according to actual data; Step 3: If normal, enter the impact prediction end, collect the dynamic changes in the cold chain logistics process in real time, and timely predict whether the dynamic changes will affect the normal execution of the cold chain logistics path decision plan according to the current traffic emergency situation at the intersection. If not, continue to predict the execution of the cold chain logistics path decision plan; Step 4: If yes, enter the path optimization end, perform multi-objective path collaborative optimization according to the prediction results of the cold chain logistics path decision standard model, and obtain the multi-objective collaborative optimization parameters.

Images