Intelligent and precise distribution method and system for gas cylinders

Abstract

The present application relates to a method and system for intelligent and precise distribution of gas cylinders, which obtains distribution data of gas cylinders, including distribution points and the distribution quantity corresponding to the distribution points; generates an initialization population according to the distribution data, and the initialization population includes multiple initial paths; obtains the first influencing object corresponding to the initial path, including multiple object targets, and the object targets are all matched with an objective function, and the second influencing object at least includes a weight target, and the weight target is matched with a weight function; determines the fitness value of the initial path based on the influence value of the first influencing object and the influence value of the second influencing object; and determines the distribution path of the gas cylinder from the initial path according to the fitness values ​​of the multiple initial paths. The method can ensure that the selected distribution path maximizes efficiency and safety while meeting various distribution needs by considering multiple factors such as distribution efficiency, cost, and safety.

Description

Technical Field

[0001] The present invention relates to the field of gas cylinders, and in particular to a method for optimizing the diameter of an intelligent and precise distribution method for gas cylinders. Background Art

[0002] With the growing demand for gas cylinders in cities, ensuring the safety of the distribution process has become a core issue that gas companies need to solve urgently. In this context, ensuring safe and efficient distribution is the key to improving gas distribution management. At present, gas companies face many challenges in the distribution management process, including the complexity of the process and the lack of response to real-time distribution needs. Traditional path optimization methods focus solely on optimizing delivery time or path length, and fail to fully consider the multi-dimensional needs of delivery cost, safety and service quality. When dealing with distribution path optimization, the existing distribution system lacks the comprehensive management and scheduling capabilities of various distribution scenarios, making it difficult to ensure safety while improving distribution efficiency. Summary of the invention

[0003] Based on this, it is necessary to provide an optimization method for the path of intelligent and precise distribution of gas cylinders to address the above-mentioned technical problems. This method can maximize safety and reduce safety risks during the distribution process.

[0004] In a first aspect, the present application provides a method for optimizing the path of an intelligent and precise gas cylinder distribution method, the method comprising:

[0005] Obtaining the distribution data of the gas cylinders, wherein the distribution data at least includes the distribution point and the distribution quantity;

[0006] Generate an initial path set according to the delivery data, the initial path set including multiple initial paths;

[0007] For any initial path, obtain the first influencing object and the second influencing object corresponding to the initial path, wherein the first influencing object includes multiple object targets, each of which is matched with an objective function, and the second influencing object includes at least a weight target, and the weight target is matched with a weight function;

[0008] For any initial path, the fitness value of the initial path is determined based on the influence value of the first influencing object and the influence value of the second influencing object; wherein the influence value of the first influencing object is determined based on multiple objective functions matched by multiple object targets, and the influence value of the second influencing object is determined based on at least a weight function, and the higher the current gas cylinder load, the greater the influence value of the second influencing object;

[0009] According to the fitness values ​​of multiple initial paths, the distribution path of the gas cylinders is determined.

[0010] In one embodiment, determining the fitness value of the initial path based on the influence value of the first influencing object and the influence value of the second influencing object includes:

[0011] Subtract the influence value of the second influencing object from the influence value of the first influencing object to obtain an influence difference;

[0012] The fitness value of the initial path is determined based on the influence difference; wherein at least one of the multiple object targets can represent the delivery efficiency of the initial path and at least one of the object targets can represent the delivery cost of the initial path.

[0013] In one embodiment, the weight function includes a weight factor, and the weight factor is proportional to the current gas cylinder load;

[0014] The influence of the influence value of the second influencing object on the fitness value when the weight factor is less than the first threshold is less than the influence of the influence value of the second influencing object on the fitness value when the weight factor is equal to or greater than 1, wherein the first threshold is less than 0.5.

[0015] In one embodiment, the weight factor is determined based on the ratio of the current gas cylinder load to the safety threshold load, and if the current gas cylinder load is equal to or exceeds the safety threshold, the weight factor is equal to or greater than 1;

[0016] The weight function also includes a safety factor, which is used to at least indicate the stability of the path. When the load of the gas cylinder is the same, the greater the safety factor, the greater the impact value of the second influencing object.

[0017] In one embodiment, the second influencing object also includes a security inspection rate target, the security inspection rate target is matched with a security inspection rate function, the influence value of the second influencing object is determined based on the weight function and the security inspection rate function, and the higher the security inspection rate, the greater the influence value of the second influencing object.

[0018] In one embodiment, for any initial path, determining the influence value of the second influencing object based on the weight function and the security inspection rate function includes:

[0019] For any initial path, obtain the current gas cylinder load, the safety factor corresponding to the initial path, and the safety inspection rate corresponding to the initial path;

[0020] Determine a weight factor based on the ratio of the current gas cylinder load to the safety threshold load, substitute the weight factor and the safety factor of the initial path into the weight function, and obtain a first target value of the second influencing object;

[0021] Substituting the security inspection rate and the security inspection rate weight coefficient corresponding to the initial path into the security inspection rate function to obtain the second target value of the second influencing object;

[0022] An influence value of the second influencing object is determined based on the sum of the first target value of the second influencing object and the second target value of the second influencing object.

[0023] In one embodiment, for any initial path, determining the influence value of the first influencing object based on multiple objective functions matched by multiple object targets includes:

[0024] For any initial path, based on the delivery points on the initial path, a first objective function is calculated to obtain a first objective value of a first influencing object; wherein the first objective function is an objective function matched with an object target representing the delivery efficiency of the initial path;

[0025] For any initial path, multiple cost coefficients of the initial path are obtained, and a second objective function is calculated based on the multiple cost coefficients to obtain a second objective value of the first influencing object; wherein the second objective function is an objective function matched by the object target representing the initial path delivery cost;

[0026] An influence value of the first influence object is determined based on the first target value of the first influence object and the second target value of the first influence object.

[0027] In one embodiment, according to the fitness values ​​of the multiple initial paths, determining the distribution path of the gas cylinder from the initial paths includes:

[0028] According to the fitness values ​​of the multiple initial paths, the initial paths are selected according to the selection strategy of the tournament to form a target population; wherein the target population includes multiple initial paths;

[0029] Perform crossover operation on the initial paths in the target population to generate transition paths; the calculation formula for generating transition paths is: , For the transition path, is a control parameter, at least used to adjust the cross-operation strength, p i and p j are any two initial paths in the target population;

[0030] The paths in the benchmark population are mutated to generate the first generation of offspring population; the paths in the benchmark population include the transition path and the initial path in the target population; the calculation formula for the mutation operation is: , is the path obtained after the mutation operation, δ is the mutation intensity parameter, and p max and p min are the paths with the largest and smallest fitness values ​​in the benchmark population;

[0031] Merge the first generation offspring population with the initialization population to generate a merged population, and optimize the merged population using a hill climbing algorithm based on the paths in the merged population;

[0032] The optimized merged population is subjected to selection, crossover and mutation operations to generate the second generation offspring population, which is iteratively executed. When the maximum number of generations is reached or the fitness converges, the optimized path is output; the optimized path serves as the distribution path of the gas cylinders.

[0033] In one embodiment, the method further includes: performing path adjustment in response to a trigger condition, the path adjustment including:

[0034] For the paths in the merged population, exchange, insert, delete or add distribution points to generate field paths;

[0035] Calculate the fitness value of the domain path. If the fitness value of the domain path is better than the fitness value of the path in the merged population, update the domain path to the merged population.

[0036] When the preset number of iterations is reached or there is no better path in the field path, the updated merged population is determined.

[0037] In one embodiment, the trigger condition includes at least one of the following:

[0038] A new delivery point is detected and needs to be added to the delivery route;

[0039] Changes to existing delivery points are detected;

[0040] A delivery vehicle is detected to have experienced a breakdown;

[0041] It was detected that the number of gas cylinders in the delivery vehicle was insufficient to complete the delivery requirements.

[0042] In a second aspect, the present application also provides a gas cylinder intelligent and precise delivery system, including an electronic device and a delivery vehicle; wherein the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the gas cylinder intelligent and precise delivery method of the first aspect when executing the computer program; the delivery vehicle is configured to execute the delivery of gas cylinders according to the delivery path sent by the electronic device.

[0043] The above-mentioned precise intelligent distribution method for gas cylinders obtains distribution data including distribution points and distribution quantities, and generates an initialization population containing multiple initial paths based on these data. For each initial path, a first influencing object and a second influencing object are obtained. The fitness value of each initial path is determined according to the influence values ​​of the first influencing object and the second influencing object, wherein the influence value of the first influencing object is determined by multiple objective functions, and the influence value of the second influencing object is determined by a weight function, and the higher the load, the greater its influence value. The distribution path of the gas cylinder is determined from the initial path according to the fitness value. This method can ensure that the selected distribution path maximizes efficiency and safety while meeting various distribution needs by considering multiple factors such as distribution efficiency, cost, and safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is an application scenario diagram of a method for intelligent and precise distribution of gas cylinders in an embodiment;

[0045] Figure 2 A flowchart of a method for intelligent and precise distribution of gas cylinders in one embodiment;

[0046] Figure 3 A flowchart of determining an initial path fitness value based on the influence values ​​of the first and second influencing objects in one embodiment;

[0047] Figure 4 A flowchart of determining the influence value of a second influence object based on a weight function and a security inspection rate function in one embodiment;

[0048] Figure 5 A flowchart of determining an influence value of a first influencing object based on multiple objective functions matched by multiple object targets in one embodiment;

[0049] Figure 6 A flow chart for determining a gas cylinder delivery path in one embodiment;

[0050] Figure 7 A flowchart of determining a distribution path of a gas cylinder from an initial path in one embodiment;

[0051] Figure 8 A flowchart of updating a merged population in one embodiment;

[0052] Fig. 9 A flowchart of performing path adjustment in response to a trigger condition in one embodiment;

[0053] Fig.10 FIG. 4 is a diagram showing the internal structure of an electronic device in one embodiment. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0055] like Figure 1 The application scenario shown includes a collection module 101, a control module 102 and an intelligent delivery vehicle 103. The intelligent and precise delivery method for gas cylinders provided in an embodiment of the present invention is integrated in the control module 102. The control module 102 establishes data exchange with the intelligent delivery vehicle 103 through a communication network. Among them, the control module 102 can be a server, which can be responsible for storing and calculating data, and the data storage system can store data that the control module 102 needs to process. The data storage system can be integrated on the control module 102, or it can be placed on the cloud or other network servers. The collection module 101 is responsible for collecting delivery data related to delivery and transmitting the delivery data to the control module 102. The control module 102 determines the delivery path of the gas cylinder based on the delivery data, and sends the delivery path information of the gas cylinder to the display screen of the intelligent delivery vehicle 103. The delivery path of the gas cylinder can also be sent to the user's terminal device for reference, including but not limited to smart phones, tablet computers, and smart watches.

[0056] In one embodiment, Figure 2 As shown, a method for intelligent and precise distribution of gas cylinders is provided, which specifically includes the following steps:

[0057] Step 201: Obtaining the distribution data of the gas cylinders, wherein the distribution data at least includes the distribution point and the distribution quantity;

[0058] Specifically, the delivery data of the gas cylinder is obtained, and the delivery data includes the delivery point and the delivery quantity. Exemplarily, the delivery data may also include the expected delivery time, the delivery person information, the delivery vehicle information, and the like.

[0059] Step 202: generating an initialization population according to the delivery data, wherein the initialization population includes a plurality of initial routes;

[0060] Specifically, using the distribution data such as the distribution points and distribution quantities obtained in step 201, an initialization population containing multiple initial paths can be generated. Among them, the initial path can be calculated based on the geographical location between the distribution points and the distribution quantity of the gas cylinders, and each initial path can represent a distribution route. The distribution points and the distribution quantity directly determine the basic framework of the path planning, that is, the starting point and the end point of the distribution task. Exemplarily, the expected delivery time provides a time dimension constraint for the path planning to ensure that the path planning meets the time requirements; the delivery personnel information reflects the work characteristics of the delivery personnel and affects the path allocation and planning; the distribution vehicle information involves parameters such as the vehicle's load, fuel efficiency, etc., which have a direct impact on the feasibility and efficiency of the distribution path.

[0061] Step 203: for any initial path, obtain the first influencing object and the second influencing object corresponding to the initial path, wherein the first influencing object includes a plurality of object targets, each of which is matched with an objective function, and the second influencing object includes at least a weight target, and the weight target is matched with a weight function;

[0062] Specifically, for each initial path, two influencing objects are obtained, namely the first influencing object and the second influencing object. Among them, the first influencing object includes multiple object targets, which can refer to important factors in the distribution path, such as distribution time, path length, cost, weather factors, etc. Each object target is matched with an objective function, and the objective function can be used to evaluate and optimize the performance of these specific targets. The second influencing object includes at least a weight target, which can refer to the weight of a gas cylinder. There is a weight function that matches the weight target, and the weight function can be used to calculate weight-related parameters in the distribution process.

[0063] Step 204: for any initial path, determine the fitness value of the initial path based on the influence value of the first influencing object and the influence value of the second influencing object; wherein the influence value of the first influencing object is determined based on multiple objective functions matched by multiple object targets, and the influence value of the second influencing object is determined based on at least a weight function, and the higher the current gas cylinder load, the greater the influence value of the second influencing object;

[0064] Specifically, for any initial path, the fitness value of the initial path can be determined by combining the influence value of the first influencing object and the influence value of the second influencing object. Among them, the influence value of the first influencing object can be determined based on an objective function that matches multiple object targets. The object targets may include delivery time, path length, cost, weather factors, etc. Each object target has a corresponding objective function to calculate its contribution to the path fitness; the influence value of the second influencing object is determined at least based on the weight function. The weight function can be determined based on the load capacity of the gas cylinder. If the load capacity of the gas cylinder increases, the influence value of the second influencing object will also increase accordingly. By comprehensively calculating the influence value of the first influencing object and the influence value of the second influencing object, the fitness value of any initial path can be determined.

[0065] Step 205: determining a distribution path for gas cylinders from the initial paths according to the fitness values ​​of the multiple initial paths;

[0066] Specifically, based on the fitness value of each initial path obtained in step 204, the fitness value of each initial path is compared, and the distribution path of the gas cylinder is determined from the initial paths.

[0067] In this embodiment, the method obtains distribution data including distribution points and distribution quantities, and generates an initialization population including multiple initial paths based on these data. For each initial path, a first influencing object and a second influencing object are obtained. The fitness value of each initial path is determined based on the influence values ​​of the first influencing object and the second influencing object, wherein the influence value of the first influencing object is determined by multiple objective functions, and the influence value of the second influencing object is determined by a weight function, and the higher the load, the greater its influence value. The distribution path of the gas cylinder is determined from the initial path according to the fitness value. By considering multiple factors such as distribution efficiency, cost, and safety, this method can ensure that the selected distribution path maximizes efficiency and safety while meeting various distribution needs.

[0068] In one embodiment, Figure 3 As shown, determining the fitness value of the initial path based on the influence value of the first influencing object and the influence value of the second influencing object includes the following steps:

[0069] Step 301: subtract the influence value of the second influencing object from the influence value of the first influencing object to obtain an influence difference;

[0070] Specifically, the influence value of the first influencing object is subtracted from the influence value of the second influencing object to obtain an influence difference.

[0071] Step 302: Determine the fitness value of the initial path based on the influence difference; wherein, at least one of the multiple object targets can represent the delivery efficiency of the initial path and at least one of the object targets can represent the delivery cost of the initial path, and the smaller the fitness value, the greater the probability that the corresponding initial path is selected as the delivery path for the gas cylinders.

[0072] Specifically, the influence value of the first influencing object is calculated. The influence value of the first influencing object may include at least one object target that can represent the distribution efficiency and one object target that can represent the distribution cost, and each object target is matched with the corresponding objective function. Among them, the distribution efficiency may include factors such as distribution time or path length, and the distribution cost may include money-related expenses, such as labor costs, transportation costs, etc. The influence values ​​of these object targets are compared with the influence value of the second influencing object to obtain an influence difference. The fitness value of each initial path is determined based on the influence difference. It should be noted that the smaller the fitness value, the greater the probability that the corresponding initial path is selected as the distribution path of the gas cylinder.

[0073] In this embodiment, the method calculates the influence value of the first influencing object, and the influence value of the first influencing object involves multiple object targets, including at least one object target that can represent the distribution efficiency and one object target that can represent the distribution cost. The influence value of the first influencing object is subtracted from the influence value of the second influencing object to obtain an influence difference. The fitness value of each initial path is determined based on the influence difference, and the smaller the fitness value, the greater the probability that the corresponding initial path is selected as the distribution path of the gas cylinder. This method not only considers the efficiency and cost of distribution, but also fully considers the impact of load weight on distribution safety, ensuring the efficiency and economy of the entire distribution process.

[0074] In one embodiment, the weight function includes a weight factor, which is proportional to the current load of the gas cylinder; the influence of the influence value of the second influencing object on the fitness value when the weight factor is less than a first threshold, is less than the influence of the influence value of the second influencing object on the fitness value when the weight factor is equal to or greater than 1, wherein the first threshold is less than 0.5.

[0075] Specifically, the weight function includes a weight factor, which is proportional to the current load of the gas cylinder. That is, when the current load of the gas cylinder increases, the weight factor will also increase accordingly. When the weight factor is less than the first threshold (ie, close to 0), the influence of the influence value of the second influencing object on the fitness value is less than the influence of the influence value of the second influencing object on the fitness value when the weight factor is equal to or greater than 1. It can be obtained that when the weight factor is close to 0, that is, the load is very light, the influence of the influence value of the second influencing object on the fitness value is relatively small; when the weight factor is equal to (ie, close to) or greater than 1, that is, the load is heavy, the influence of the influence value of the second influencing object on the fitness value increases significantly.

[0076] In this embodiment, the method determines that the weight factor is proportional to the load of the gas cylinder, calculates the influence value of the second influencing object based on this weight factor, and uses it to adjust the fitness value of the initial path. When the weight factor is small, that is, the load is light, the influence value of the second influencing object has a small impact on the fitness value; and when the weight factor is large, that is, the load is heavy, the influence value of the second influencing object has a greater impact on the fitness value. This method can flexibly adjust the importance of the weight factor in path selection according to different loads.

[0077] In one embodiment, the weight factor is determined based on the ratio of the current gas cylinder load to the safety threshold load. If the current gas cylinder load is equal to or exceeds the safety threshold, the weight factor is equal to or greater than 1. The weight function also includes a safety factor, which is used at least to indicate the smoothness of the path. When the gas cylinder load is the same, the greater the safety factor, the greater the impact value of the second influencing object.

[0078] Specifically, the weight factor can be determined based on the ratio between the current load of the gas cylinder and the set safety threshold load, which reflects the proportion of the gas cylinder load relative to the safety threshold. When the gas cylinder load is equal to (i.e. close to) or exceeds this safety threshold, the weight factor will be equal to (i.e. close to) or greater than 1, which means that the gas cylinder load can become a key factor affecting the selection of the distribution path. In addition, the weight function also includes a safety factor, which is used to indicate the stability of the path, that is, the safety of the path. Exemplarily, when the load is the same, the larger the safety factor, that is, the better the stability of the path, and therefore the greater the impact value of the second influencing object.

[0079] In this embodiment, the fitness value of the distribution path is determined by comprehensively considering the weight factor and the safety factor. The weight factor is determined based on the ratio of the current load of the gas cylinder to the safety threshold load. When the load is equal to or exceeds the safety threshold, the weight factor is equal to or greater than 1, indicating that the influence of the load on the path selection has increased significantly. The safety factor included in the weight function is used to indicate the stability of the path, that is, under the same load, the larger the safety factor, the more stable the path, and the greater the influence value of the second influencing object. The selection of the distribution path not only considers the impact of the load on safety, but also considers the stability of the path itself, so that the distribution plan can flexibly respond to different load conditions and path conditions while ensuring safety.

[0080] In one embodiment, the second influencing object also includes a security inspection rate target, the security inspection rate target is matched with a security inspection rate function, the influence value of the second influencing object is determined based on the weight function and the security inspection rate function, and the higher the security inspection rate, the greater the influence value of the second influencing object.

[0081] Specifically, the second influencing object includes not only the weight target but also the security inspection rate target, that is, when evaluating the fitness value of the delivery path, in addition to considering the weight factor, the security inspection rate of the delivery path also needs to be considered. The security inspection rate target is a target related to the frequency and quality of security inspections on the delivery path, and the security inspection rate function matching the security inspection rate target can be the influence value for calculating the security inspection rate target. When determining the influence value of the second influencing object, the results of the weight function and the security inspection rate function are comprehensively considered. Among them, the weight function includes the weight factor and the safety factor, which can be used to evaluate the impact of the load and path stability on the delivery path; and the security inspection rate function can be used to evaluate the security inspection quality of the delivery path. The influence value of the second influencing object is determined based on the weight function and the security inspection rate function, reflecting the comprehensive impact of the delivery path in terms of weight and security inspection. Among them, the higher the security inspection rate, the higher the security inspection quality of the delivery path, that is, the greater the influence value on the second influencing object.

[0082] In this embodiment, the second influencing object includes not only the weight target but also the security inspection rate target, wherein the weight target is evaluated by the weight function and the security inspection rate target is evaluated by the security inspection rate function. These two functions jointly determine the influence value of the second influencing object, and the higher the security inspection rate, the greater the influence value of the second influencing object, reflecting the preference for the path with high security inspection rate.

[0083] In one embodiment, Figure 4 As shown, for any initial path, determining the influence value of the second influencing object based on the weight function and the security inspection rate function includes the following steps:

[0084] Step 401: for any initial path, obtain the current gas cylinder load, the safety factor corresponding to the initial path, and the safety inspection rate corresponding to the initial path;

[0085] Specifically, for each initial path, three key data are obtained: the current load capacity of the gas cylinder, the safety factor corresponding to the path, and the safety inspection rate corresponding to the path. The current load capacity of the gas cylinder may refer to the weight carried by the gas cylinder during the distribution process; the safety factor may be an indicator of the smoothness of the path, which may include factors such as road conditions and traffic conditions, and is used to evaluate the safety of the path; the safety inspection rate may refer to the frequency and quality of safety inspections of gas cylinders during the distribution process, and the safety inspection rate reflects the strictness of the safety inspection of the distribution path.

[0086] Step 402: Determine a weight factor based on the ratio of the current gas cylinder load to the safety threshold load, substitute the weight factor and the safety factor of the initial path into the weight function, and obtain a first target value of the second influencing object;

[0087] Specifically, the weight factor is determined based on the ratio between the actual load of the current gas cylinder and the preset safety threshold load. The weight factor reflects the ratio of the current load to the safety upper limit and is an important parameter for evaluating the safety of the distribution path. The calculated weight factor and the safety factor of the initial path are substituted into the weight function. Among them, the safety factor represents the stability and safety of the path in the weight function. By substituting the two parameters of weight factor and safety factor into the weight function, the first target value of the second influencing object can be calculated, that is, a value that comprehensively reflects the load and path safety characteristics.

[0088] Step 403: Substitute the security inspection rate and the security inspection rate weight coefficient corresponding to the initial path into the security inspection rate function to obtain the second target value of the second influencing object;

[0089] Specifically, the security inspection rate and security inspection weight coefficient corresponding to the current initial path are obtained. The security inspection rate can reflect the frequency and quality of security inspections on the path, and the security inspection rate weight coefficient can be used to indicate the importance of the security inspection rate in the overall path fitness evaluation. Substitute the security inspection rate and the security inspection rate weight coefficient into the security inspection rate function. The security inspection rate function can be used to calculate the contribution of the security inspection rate to the impact value of the second influencing object. By substituting the security inspection rate and the security inspection rate weight coefficient into the security inspection rate function, the second target value of the second influencing object can be obtained, and the second target value can reflect the role of the security inspection rate in path selection.

[0090] Step 404: Determine the influence value of the second influence object based on the sum of the first target value of the second influence object and the second target value of the second influence object.

[0091] Specifically, two target values ​​of the second influencing object, the first target value and the second target value, are calculated through the previous steps. The first target value is calculated based on the weight function, and the second target value is calculated based on the security check rate function. The first target value and the second target value are added together, that is, the values ​​of the first target value and the second target value are combined to determine the total impact value of the second influencing object, which can reflect the comprehensive impact of the distribution path in terms of weight and security check.

[0092] In this embodiment, for each initial path, the load capacity of the current gas cylinder, the safety factor corresponding to the path, and the safety inspection rate are collected; the weight factor is determined according to the ratio of the load capacity to the safety threshold load capacity, and the factor and the safety factor are substituted into the weight function to calculate the first target value of the second influencing object; the safety inspection rate of the path and the safety inspection rate weight coefficient are substituted into the safety inspection rate function to obtain the second target value; these two target values ​​are added to obtain the total impact value of the second influencing object. This method can comprehensively evaluate the comprehensive performance of the distribution path in terms of load safety and safety inspection. By accurately calculating the impact of the weight factor and the safety inspection rate on the path fitness, it ensures that the distribution path selection not only considers the impact of the load on safety, but also considers the strictness of the safety inspection, thereby improving the accuracy and safety of the distribution path selection.

[0093] In one embodiment, Figure 5 As shown, for any initial path, determining the influence value of the first influencing object based on multiple objective functions matched by multiple object targets includes the following steps:

[0094] Step 501: for any initial path, based on the delivery points on the initial path, a first objective function is calculated to obtain a first objective value of a first influencing object; wherein the first objective function is an objective function representing the object target matching of the initial path delivery efficiency;

[0095] Specifically, for each initial path, the first objective function is calculated based on the delivery points on the initial path. By calculating the first objective function, the first objective value of the first influencing object can be obtained, that is, a quantitative value representing the performance of the initial path in terms of delivery efficiency. Among them, substituting the delivery data into the objective function corresponding to the delivery time can obtain a target value, and substituting the delivery data into the objective function corresponding to the delivery path length can obtain another target value. Adding these two target values, the target value of the first objective function of the first influencing object that matches the initial path delivery efficiency is obtained.

[0096] Among them, the target value corresponding to the delivery time can be:

[0097] ,in Represents the delivery time between delivery points i and i+1.

[0098] The target value corresponding to the path length can be:

[0099] ,in Represents the path length between delivery points i and i+1.

[0100] Step 502: for any initial path, obtain multiple cost coefficients of the initial path, and calculate a second objective function based on the multiple cost coefficients to obtain a second objective value of the first influencing object; wherein the second objective function is an objective function matched by the object target representing the initial path delivery cost;

[0101] Specifically, for any initial path, multiple cost coefficients of the initial path are obtained, and the second objective function is calculated based on the multiple cost coefficients to obtain the second objective value of the first influencing object. The second objective function is an objective function matched by the object target representing the delivery cost of the initial path, wherein the delivery cost can be composed of electricity costs, labor costs and other costs. Therefore, the second objective value of the first influencing object can be:

[0102] f3(p)=α·electricity fee+β·labor fee+γ·other fees, where α, β, and γ are the cost coefficients corresponding to each fee. Substituting the delivery data into the second objective function can obtain the second objective value of the first influencing object.

[0103] Step 503: Determine the influence value of the first influence object based on the first target value of the first influence object and the second target value of the first influence object.

[0104] Specifically, based on step 501, a first target value is obtained, which is obtained by calculating an objective function related to distribution efficiency, and reflects the distribution efficiency of each initial path. Based on step 502, a second target value is obtained, which is calculated based on multiple cost coefficients and represents the distribution cost of each initial path. By integrating the first target value and the second target value, the influence value of the first influencing object can be determined by a mathematical method of summation, that is, the influence value of the first influencing object can be f1(p)+f2(p)+f3(p).

[0105] In this embodiment, the method calculates the first objective function based on the distribution data for each initial path to obtain a first objective value representing the distribution efficiency. Multiple cost coefficients of the path are obtained, and the second objective function is calculated to obtain a second objective value representing the distribution cost. The two objective values ​​are combined to determine the impact value of the first influencing object. This method can comprehensively evaluate the performance of the distribution path in the two key dimensions of efficiency and cost, ensuring that the distribution plan is both efficient and economical.

[0106] In one embodiment, the fitness value of the initial path is determined based on the influence value of the first influencing object and the influence value of the second influencing object, that is, the influence value of the first influencing object is subtracted from the influence value of the second influencing object to obtain the fitness value of the initial path, and the following formula can be used:

[0107] Score(p)=f1(p)+f2(p)+f3(p)-λ security inspection rate-δ·(weight factor·safety factor).

[0108] Among them, f1(p), f2(p) and f3(p) correspond to the target values ​​of delivery time, path length and cost respectively. λ is the weight coefficient of the security inspection rate, which is used to indicate the importance of the security inspection rate in the overall path fitness evaluation. δ is a coefficient used to reflect the numerical value of the load and path safety characteristics.

[0109] Exemplarily, the influence value of the first influencing object is subtracted from the influence value of the second influencing object to obtain the fitness value of the initial path. The following formula may also be used:

[0110] Score(p)=f1(p)+f2(p)+f3(p)-λ(service evaluation+security inspection rate)-δ·(weight factor·safety factor). Service evaluation is an indicator to measure the quality of delivery service, usually based on historical service data, reflecting the performance of delivery punctuality, accuracy and customer satisfaction. In delivery route optimization, service evaluation is used to evaluate the service quality of each route, and together with the security inspection rate, it is an important basis for route selection.

[0111] It should be noted that paths with higher service evaluation and security inspection rates will be given higher priority to ensure that paths with better service evaluation and safety quality are selected. That is, in the case of high load, the safety weight increases, making the fitness value of safer paths lower and can be selected first; in the case of low load, more attention can be paid to time and distance, but safety factors still need to be considered.

[0112] In one embodiment, Figure 6 As shown, according to the fitness values ​​of multiple initial paths, the distribution path of the gas cylinder is determined from the initial paths, including the following steps:

[0113] Step 601: selecting an initial path according to the fitness values ​​of multiple initial paths and the selection strategy of the tournament to form a target population; wherein the target population includes multiple initial paths;

[0114] Specifically, assuming that there is a population consisting of 100 initial paths, 10 paths need to be selected from them to form a target population, a tournament selection strategy can be used. Exemplarily, the number of paths participating in each tournament is determined, and the scale can be 2, 3, 5 or more. For example, 5 can be selected as the scale of the tournament, that is, 5 paths are selected for comparison each time. Five paths are randomly selected from the 100 paths to participate in the tournament. Among these 5 paths, the fitness value of each path is compared. In the tournament, the path with the highest fitness value is selected as the winner and enters the target population. This process is repeated until there are 10 paths in the target population. By repeating the above steps, a target population containing 10 paths will eventually be obtained, and each path is the winner of its own tournament. The advantage of the tournament selection strategy is that it is simple and easy to implement, and can ensure that the paths in the target population are relatively excellent and maintain the diversity of the population.

[0115] Step 602: Perform a crossover operation on the initial paths in the target population to generate a transition path; wherein the calculation formula for generating the transition path is: , For the transition path, is a control parameter, at least used to adjust the cross-operation strength, p i and p j are any two initial paths in the target population;

[0116] Specifically, the crossover operation step may refer to combining the initial paths in the target population to generate a new transition path. That is, two initial paths are randomly selected from the target population, denoted as p i and p j Next, a new transition path p′ is generated using the simulated binary crossover operator (SBX), which is:

[0117] .

[0118] Among them, η is a control parameter that can be used to adjust the strength of the crossover operation and affect the new path p′ and the parent path p i and p j When the value of η is large, the newly generated transition path p′ will inherit more of p i When the value of η is small, p′ will inherit the characteristics of p relatively evenly. i and p j characteristics.

[0119] It should be noted that in the simulated binary crossover (SBX) algorithm, the parameter η plays a key role, mainly in controlling the crossover range and adjusting the crossover strength. Specifically, η controls the search range of the parent path during the crossover process. A larger η value means that the child path can search more widely based on the parent path. η affects the intensity of the crossover operation. A smaller η value will cause the child path to be closer to the parent path, maintaining the diversity of the population, while a larger η value will produce more diverse offspring and increase the exploration ability of the population.

[0120] Step 603: Perform mutation operation on all paths in the reference population to generate a first generation of offspring population; wherein the paths of the reference population include transition paths and initial paths in the target population; wherein the calculation formula of the mutation operation is: , is the path obtained after the mutation operation, δ is the mutation intensity parameter, and p max and p min are the paths with the largest and smallest fitness values ​​in the benchmark population;

[0121] Specifically, the mutation operation is to randomly change the paths in the reference population to generate the first generation of the offspring population. The reference population consists of two parts, one part is based on the transition path generated by the crossover operation in step 502, and the other part is the initial path in the target population. In the mutation operation, the mutation operation is applied to each path in the reference population, and a specific calculation formula can be used to generate a new path, the formula is:

[0122] ,

[0123] Where p′′ is the new path obtained after the mutation operation, p is the original path selected for mutation, and δ is the mutation intensity parameter, which controls the degree of mutation, that is, the difference between the new path and the original path. max and p min They are respectively the path with the largest and the path with the smallest fitness value in the benchmark population.

[0124] Among them, δ is used to control the intensity of the mutation operation, which determines the degree of adjustment of the distribution path parameters in the mutation stage of the genetic algorithm, and affects the difference between the new path and the original path. Setting a smaller δ value will make the path parameters change slightly, which is helpful for local search near the current excellent path; while setting a larger δ value will cause a larger change in the path parameters, increasing the possibility of exploring new potential paths.

[0125] Step 604: merge the first generation offspring population with the initialization population to generate a merged population, and optimize the merged population using a hill climbing algorithm based on the paths in the merged population;

[0126] Specifically, the first generation offspring population, i.e., the path generated based on the mutation operation in step 603, is merged with the initial target population to form a merged population. The merged population combines the original initial path, the transition path generated by the crossover operation, and the path after the mutation operation, and has a wider range of path selection and higher diversity. The hill climbing algorithm can be used to optimize each path in the merged population. It should be noted that the hill climbing algorithm will select a path in the merged population as the starting point, explore other possible paths in its neighborhood, and update the current path when a better path is found. This process is repeated throughout the merged population until the preset number of iterations is reached or it is determined that there is no further room for improvement, thereby completing the optimization of all paths in the merged population.

[0127] Step 605: Perform selection, crossover and mutation operations on the optimized merged population to generate a second-generation offspring population, and execute iteratively. When the maximum number of generations is reached or the fitness converges, the optimized path is output; wherein the optimized path serves as the distribution path of the gas cylinders.

[0128] Specifically, a selection operation is performed on the paths in the merged population, i.e., the tournament selection strategy in step 601, and a path with a higher fitness value is selected as the parent. A crossover operation is performed on these selected paths, i.e., the process described in step 602, to generate a new transition path by combining two parent paths. A mutation operation is performed on these newly generated transition paths and other paths in the merged population, i.e., the process in step 603, to introduce random changes to increase the diversity of the population. The set of paths generated by the selection, crossover and mutation operations constitutes the second-generation offspring population. The process is continuously iterated, and a new offspring population is generated in each generation, and the new offspring population is evaluated and optimized. And the iteration continues until one of the two stop conditions is met, the preset maximum number of generations is reached, that is, a sufficient number of iterations are performed; or the fitness converges, that is, the fitness value of the path in consecutive generations has not been significantly improved, indicating that it has approached the optimal path. When at least one of the conditions is met, the final optimized path is output as the distribution path of the gas cylinder.

[0129] In this embodiment, the method uses a tournament selection strategy based on fitness values ​​to select a target population from multiple initial paths. A crossover operation is performed on the paths in the target population to generate a transition path, wherein the calculation formula of the crossover operation takes into account the control parameter η to adjust the strength of the path combination. A mutation operation is performed on the reference population containing the transition path and the initial path to generate a first-generation offspring population, and the calculation formula of the mutation operation is adjusted by the mutation intensity parameter δ and the path with the maximum and minimum fitness values ​​in the reference population. Afterwards, the first-generation offspring population is merged with the initial population, and the merged population is optimized using a hill climbing algorithm. The selection, crossover and mutation operations are repeated on the optimized merged population to form a second-generation offspring population, and this process is iterated until the maximum number of generations or fitness convergence conditions are met, and the optimized distribution path is finally output as the distribution path of the gas cylinder. This method can effectively balance multiple factors in path selection, and finally determine a gas cylinder distribution path that is both efficient and economical while meeting safety requirements.

[0130] In one embodiment, according to the fitness values ​​of multiple initial paths, the implementation method of determining the distribution path of the gas cylinder from the initial paths is as follows: Figure 7 As shown, the following steps are included:

[0131] Step 701: Obtain an initialization population;

[0132] Step 702: Select an initial path to form a target population;

[0133] Step 703: performing a crossover operation on the initial path of the target population to generate a transition path;

[0134] Step 704: performing mutation operation on the paths of the benchmark population to generate the first generation sub-population;

[0135] Step 705: merge the first generation sub-population with the initialization population to generate a merged population;

[0136] Step 706: performing selection, crossover, and mutation operations on the merged population to generate a second-generation sub-population;

[0137] Step 707: Determine whether the subpopulation generation has reached the maximum generation or the fitness has converged;

[0138] Step 708: If the maximum number of generations is reached or the fitness converges, the delivery path is output;

[0139] Step 709: If the maximum number of generations is not reached or the fitness converges, continue to iterate to generate the next generation of sub-populations.

[0140] It should be noted that the iteration process also includes the operations of fast non-dominated sorting and congestion calculation. Among them, fast non-dominated sorting is used to evaluate the advantages and disadvantages of multiple distribution paths in the precise distribution method of gas cylinders. By stratifying the paths according to non-dominated relationships, those paths that are not dominated by other paths in terms of distribution efficiency and safety are given priority. The calculation of congestion is used to measure the distribution density of paths at the same level, ensuring that the selected paths are evenly distributed in space and avoid aggregation, thereby maintaining population diversity and providing a broad selection basis for subsequent path optimization.

[0141] In one embodiment, the specific real-time method of updating the merged population is as follows: Figure 8 As shown, the following steps are included:

[0142] Step 801: Obtain a merged population;

[0143] Step 802: Generate a domain path;

[0144] Step 803: Calculate the fitness value of the neighborhood path;

[0145] Step 804: Generate a better domain path;

[0146] Step 805: Determine whether the number of iterations has been reached or there is no better domain path;

[0147] Step 806: If the number of iterations has not been reached or there is a better field path, continue to generate a new better field path; if the number of iterations has been reached or there is no better field path, output the field path and update it to the merged population.

[0148] Specifically, after obtaining the merged population, the system generates a domain path by making small adjustments based on the path of the merged population, such as exchanging, inserting or deleting delivery points. The fitness values ​​of these neighborhood paths are calculated to evaluate their performance. Based on the fitness values, the better domain paths are identified and retained. It is determined whether the preset number of iterations has been reached or whether there is a better domain path. If the number of iterations has not been reached and there is still a better path, the system will continue to generate a new domain path; if the number of iterations has been reached or there is no better path, the current best domain path will be updated to the merged population.

[0149] In one embodiment, Fig. 9 As shown, the method further includes: performing path adjustment in response to a trigger condition, the path adjustment including the following steps:

[0150] Step 901: For the paths in the merged population, exchange, insert, delete or add distribution points to generate a domain path;

[0151] Specifically, when there are certain trigger conditions, such as order changes, traffic status updates, or safety events, the paths in the merged population will be adjusted. The existing paths will be modified to generate new domain paths, which may include exchanging the order of delivery points, inserting new delivery points in the path, deleting certain delivery points from the path, or adding additional delivery points. Through these operations, the system is able to explore new paths adjacent to the current path, thereby finding a potentially better delivery solution.

[0152] Step 902: Calculate the fitness value of the domain path. If the fitness value of the domain path is better than the fitness value of the path in the merged population, update the domain path to the merged population.

[0153] Specifically, the fitness value of each field path is calculated. If the fitness value of a field path is better than the fitness value of the existing path in the merged population, it means that the field path has better distribution performance. Then the field path will be updated to the merged population to replace the original path with a lower fitness value.

[0154] Step 903: until the preset number of iterations is reached or there is no better path in the domain path, determine the updated merged population.

[0155] Specifically, the merged population is continuously exchanged, inserted, deleted or added with distribution points to generate new field paths, and the fitness values ​​of these new field paths are calculated. If the fitness value of a field path is better than the fitness value of the existing path in the merged population, the field path will be updated to the merged population. This process will continue until the preset number of iterations is reached or no better path is found in the field path. When one of these two conditions is met, the updated merged population is determined, which contains the path after multiple rounds of iterative optimization.

[0156] In this embodiment, when trigger conditions such as the addition of new distribution points, changes in distribution points, vehicle failures or insufficient quantities occur, the paths in the merged population are adjusted, including the generation of new domain paths by exchanging, inserting, deleting or adding distribution points, and the fitness values ​​of these domain paths are calculated. If the fitness value of a domain path is better than the fitness value of an existing path in the merged population, the domain path will be updated to the merged population. This process will continue until the preset number of iterations is reached or no better path can be found in the domain path, and the updated merged population is finally determined. This method can flexibly respond to various emergencies and changes, adjust the distribution plan in a timely manner, and ensure the continuity and completion of the distribution task.

[0157] In one embodiment, the trigger condition includes at least one of the following:

[0158] A new delivery point is detected and needs to be added to the delivery route;

[0159] Changes to existing delivery points are detected;

[0160] A delivery vehicle is detected to have experienced a breakdown;

[0161] It was detected that the number of gas cylinders in the delivery vehicle was insufficient to complete the delivery requirements.

[0162] Specifically, when it is detected that a new distribution point needs to be added to the existing distribution route, this may be due to the generation of new orders or unplanned changes in demand; if the existing distribution point changes, such as changes in the distribution address or adjustments to the expected delivery time; when the distribution vehicle encounters a failure and cannot continue to perform the current distribution task, it is necessary to re-plan the route or replace the vehicle; if it is detected that the number of gas cylinders in the distribution vehicle is insufficient and cannot meet the needs of the remaining distribution points, the distribution plan also needs to be adjusted. The setting of these trigger conditions enables the distribution system to flexibly respond to changes in the actual distribution process and ensure that the distribution task can proceed smoothly. Exemplarily, the intelligent distribution vehicle can also include an alarm module. If the alarm module generates a warning, it means that a certain data exceeds or falls below the standard threshold, such as the vehicle speed is too high or the temperature and pressure of the gas cylinder exceed or fall below the standard threshold. The module generates an alarm message and uploads the alarm data items, alarm values, etc. to the intelligent distribution vehicle, and the intelligent distribution vehicle needs to re-adjust the distribution route.

[0163] In this embodiment, the method dynamically adjusts the delivery path by real-time monitoring and responding to a series of trigger conditions to ensure delivery efficiency and safety. Trigger conditions include detecting a new delivery point that needs to be added to the delivery path; detecting a change in an existing delivery point; detecting a failure in the delivery vehicle; and detecting that the number of gas cylinders in the delivery vehicle is insufficient to complete the delivery needs. When one of these conditions is triggered, the path adjustment process will be initiated, including generating a new domain path, calculating the fitness value, and updating the merged population when necessary, until the preset number of iterations is reached or there is no better path. This method can flexibly adapt to emergencies and changes in the delivery process, adjust the delivery plan in a timely manner, and ensure the continuity and completion of the delivery task.

[0164] Based on the same concept, the present application also provides an intelligent and precise distribution system for gas cylinders, which includes an electronic device and a distribution vehicle; wherein the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements a precise distribution method for gas cylinders when executing the computer program; the distribution vehicle is configured to distribute gas cylinders according to the distribution path sent by the electronic device.

[0165] In one embodiment, an electronic device is provided, including a memory and a processor. The electronic device may be a terminal, and its internal structure diagram may be as follows: Fig.10As shown. The electronic device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the electronic device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for intelligent and precise distribution of gas cylinders is realized. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the housing of the electronic device, or an external keyboard, touchpad or mouse.

[0166] Those skilled in the art will understand that Fig.10 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the electronic device to which the scheme of the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0167] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0168] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for intelligent and precise distribution of gas cylinders, characterized in that: The method comprises: Obtaining the distribution data of the gas cylinders, wherein the distribution data at least includes the distribution point and the distribution quantity corresponding to the distribution point; generating an initialization population according to the delivery data, wherein the initialization population includes a plurality of initial routes; For any initial path, obtain the first influencing object and the second influencing object corresponding to the initial path; wherein the first influencing object includes a plurality of object targets, each of which is matched with an objective function, and the second influencing object includes at least a weight target, and the weight target is matched with a weight function; For any initial path, the fitness value of the initial path is determined based on the influence value of the first influencing object and the influence value of the second influencing object; wherein the influence value of the first influencing object is determined based on a plurality of objective functions matched by the plurality of object targets, the influence value of the second influencing object is determined based at least on the weight function, and the higher the current gas cylinder load, the greater the influence value of the second influencing object; Determining a delivery path for the gas cylinder from the initial paths according to the fitness values ​​of the multiple initial paths; Among them, determining the fitness value of the initial path based on the influence value of the first influencing object and the influence value of the second influencing object includes: subtracting the influence value of the second influencing object from the influence value of the first influencing object to obtain an influence difference; and determining the fitness value of the initial path based on the influence difference.

2. The intelligent and precise gas cylinder distribution method according to claim 1 is characterized in that: At least one of the multiple object targets can represent the delivery efficiency of the initial path and at least one of the object targets can represent the delivery cost of the initial path. The smaller the fitness value, the greater the probability that the corresponding initial path is selected as the delivery path for gas cylinders.

3. The intelligent and precise gas cylinder distribution method according to claim 1 or 2, characterized in that: The weight function includes a weight factor, and the weight factor is proportional to the current load of the gas cylinder; When the weight factor is less than a first threshold, the influence of the influence value of the second influencing object on the fitness value is less than the influence of the influence value of the second influencing object on the fitness value when the weight factor is equal to or greater than 1, wherein the first threshold is less than 0.

5.

4. The intelligent and precise gas cylinder distribution method according to claim 3 is characterized in that: The weight factor is determined based on the ratio of the current gas cylinder load to the safety threshold load. If the current gas cylinder load is equal to or exceeds the safety threshold, the weight factor is equal to or greater than 1. The weight function also includes a safety factor, which is used to at least represent the smoothness of the path. When the load weight of the gas cylinder is the same, the larger the safety factor is, the greater the impact value of the second influencing object is.

5. The intelligent and precise gas cylinder distribution method according to claim 3 is characterized in that: The second influencing object also includes a security inspection rate target, and the security inspection rate target is matched with a security inspection rate function. The influence value of the second influencing object is determined based on the weight function and the security inspection rate function, and the higher the security inspection rate, the greater the influence value of the second influencing object.

6. The intelligent and precise gas cylinder distribution method according to claim 5 is characterized in that: For any initial path, determining the influence value of the second influencing object based on the weight function and the security inspection rate function includes: For any initial path, obtain the current gas cylinder load, the safety factor corresponding to the initial path, and the safety inspection rate corresponding to the initial path; Determine the weight factor based on the ratio of the current gas cylinder load to the safety threshold load, substitute the weight factor and the safety factor of the initial path into the weight function, and obtain the first target value of the second influencing object; Substituting the security inspection rate and the security inspection rate weight coefficient corresponding to the initial path into the security inspection rate function to obtain a second target value of the second influencing object; An influence value of the second influence object is determined based on the sum of the first target value of the second influence object and the second target value of the second influence object.

7. The intelligent and precise gas cylinder distribution method according to claim 1 is characterized in that: For any initial path, determining the influence value of the first influencing object based on a plurality of objective functions matched by the plurality of object targets includes: For any initial path, based on the delivery points on the initial path, a first objective function is calculated to obtain a first objective value of the first influencing object; wherein the first objective function is an objective function matched with the object objective representing the delivery efficiency of the initial path; For any initial path, multiple cost coefficients of the initial path are obtained, and a second objective function is calculated based on the multiple cost coefficients to obtain a second objective value of the first influencing object; wherein the second objective function is an objective function matched by the object target representing the delivery cost of the initial path; An influence value of the first influence object is determined based on a first target value of the first influence object and a second target value of the first influence object.

8. The intelligent and precise gas cylinder distribution method according to claim 1 is characterized in that: According to the fitness values ​​of the multiple initial paths, determining the distribution path of the gas cylinder from the initial paths includes: According to the fitness values ​​of the multiple initial paths, an initial path is selected according to the selection strategy of the tournament to form a target population; wherein the target population includes multiple initial paths; Perform a crossover operation on the initial paths in the target population to generate a transition path; wherein the calculation formula for generating the transition path is: , is the transition path, is a control parameter, at least used to adjust the cross operation strength, the p i and p j are any two initial paths in the target population; The paths in the reference population are mutated to generate the first generation of offspring population; wherein the paths in the reference population include transition paths and the initial paths in the target population; wherein the calculation formula of the mutation operation is: , is the path obtained after the mutation operation, δ is the mutation intensity parameter, and p max and p min are the path with the largest and the path with the smallest fitness value in the benchmark population; Merging the first generation offspring population with the initialization population to generate a merged population, and optimizing the merged population using a hill climbing algorithm based on paths in the merged population; The optimized merged population is subjected to selection, crossover and mutation operations to generate a second-generation offspring population, which is iteratively executed. When the maximum number of generations is reached or the fitness converges, an optimized path is output; wherein the optimized path serves as the distribution path of the gas cylinders.

9. The intelligent and precise gas cylinder distribution method according to claim 8 is characterized in that: The method further includes: performing path adjustment in response to a trigger condition, wherein the path adjustment includes: For the paths in the merged population, exchange, insert, delete or add distribution points to generate a domain path; Calculating the fitness value of the domain path, and if the fitness value of the domain path is better than the fitness value of the path in the merged population, updating the domain path to the merged population; When the preset number of iterations is reached or there is no better path in the field path, the updated merged population is determined.

10. The intelligent and precise gas cylinder distribution method according to claim 9 is characterized in that: The trigger condition includes at least one of the following: A new delivery point is detected and needs to be added to the delivery route; Changes to existing delivery points are detected; A delivery vehicle is detected to have experienced a breakdown; It was detected that the number of gas cylinders in the delivery vehicle was insufficient to complete the delivery requirements.

11. An intelligent and precise gas cylinder distribution system, characterized in that: The distribution system includes electronic equipment and a distribution vehicle; wherein, An electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the intelligent and precise gas cylinder distribution method according to any one of claims 1 to 10 when executing the computer program; The delivery vehicle is configured to deliver the gas cylinders according to the delivery route sent by the electronic device.

Images