Method for vehicle scheduling and related products thereof

Abstract

The invention discloses a vehicle scheduling method, electronic equipment and a readable storage medium, and the method comprises the steps: receiving task information which comprises a task amount, target information and a special requirement; selecting a preset algorithm model based on the task load; based on the target information, performing calculation by using a preset algorithm model to obtain an initial scheduling scheme; based on the special requirements, further screening the preliminary scheduling scheme to obtain a final scheduling scheme; and scheduling the vehicles according to the final scheduling scheme. By utilizing the scheme disclosed by the invention, a large amount of data can be quickly processed, and optimal vehicle arrangement and route planning are provided, so that the efficiency is improved.

Description

Technical Field

[0001] The present disclosure generally relates to the field of vehicle dispatch technology. More specifically, the present disclosure relates to a method for vehicle dispatch, an electronic device, and a computer-readable storage medium. Background Art

[0002] With the rapid development of my country's pig farming industry, the demand for pig transportation is growing. Pig transportation is an indispensable link in pig farming, slaughtering, and sales. However, there are many problems with traditional pig transportation methods, such as low scheduling efficiency, high transportation costs, and untimely pig transportation, which have affected the healthy development of the pig farming industry.

[0003] In the traditional pig transportation process, manual scheduling is mainly relied on. Manual scheduling usually requires staff to judge the arrangement of vehicles and the selection of routes based on experience, which has great limitations. First, manual scheduling is inefficient, and staff need to spend a lot of time processing various information, which is prone to omissions and errors. Secondly, due to the lack of effective data support, it is difficult for manual scheduling to optimize the arrangement of routes and vehicles, resulting in high transportation costs. In addition, manual scheduling is affected by work experience, personal character, work ability, etc., and cannot guarantee uniform quality. The scheduling results and execution process are uneven.

[0004] In order to solve these problems, some companies have begun to try to use information technology to improve the transportation and scheduling of live pigs. At present, the technical solution closest to the present invention is to use a GPS positioning system and a simple scheduling software to assist in the transportation of live pigs. This solution can achieve real-time positioning and tracking of vehicles, and staff can adjust the transportation plan according to the real-time location of the vehicle. However, this solution still has great limitations. First, it lacks consideration of the special physiological needs of live pigs, and cannot reasonably plan routes according to special needs such as the status of live pigs and living biological epidemic prevention. Secondly, it lacks a comprehensive consideration of the global distribution of farms of large-scale live pig breeding enterprises, and cannot guarantee the lowest global cost and fastest time arrangement of vehicles after multiple farms simultaneously report their transportation needs.

[0005] In view of this, it is urgent to provide a method for vehicle scheduling in order to achieve comprehensive optimization of the pig transportation process, improve transportation efficiency and reduce costs. It can provide an efficient, low-cost and intelligent pig transportation scheduling solution to promote the healthy and sustainable development of the pig farming industry. Summary of the invention

[0006] In order to at least solve one or more technical problems mentioned above, the present disclosure proposes a method for vehicle scheduling, an electronic device for vehicle scheduling, and a computer-readable storage medium in multiple aspects.

[0007] In a first aspect, the present disclosure provides a method for vehicle scheduling, the method comprising: receiving task information, wherein the task information comprises task quantity, target information and special requirements; selecting a preset algorithm model based on the task quantity; calculating using the preset algorithm model based on the target information to obtain an initial scheduling plan; further screening the preliminary scheduling plan based on the special requirements to obtain a final scheduling plan; and scheduling vehicles according to the final scheduling plan.

[0008] In some embodiments, the task volume includes a combination of a planned quantity and a number of vehicles, wherein the selection of a preset algorithm model includes: if the combination of the planned quantity and the number of vehicles is less than a preset threshold, selecting an integer linear programming algorithm; if the combination of the planned quantity and the number of vehicles is greater than a preset threshold, selecting a genetic algorithm.

[0009] In some embodiments, the task information also includes vehicle management information, wherein the calculation based on the target information using a preset algorithm model to obtain an initial scheduling solution includes: if an integer linear programming algorithm is selected, then an objective function is established based on the target information and the vehicle management information, wherein the objective function includes:

[0010]

[0011] Among them, k is the counting number of the plan, i is the counting number of the vehicle, and q i is the arrival distance of vehicle i, s i is the time required for vehicle i to change from an unavailable state to an available state, p i,k The factor that determines whether vehicle i executes plan k.

[0012] In some embodiments, the target information includes a target requirement, and the method further includes: adjusting the parameters in the target function based on the target requirement, wherein the target requirement includes a shortest time requirement and a minimum cost requirement, wherein the parameters include q i 、s i 、p i,k and / or k .

[0013] In some embodiments, based on the target information, calculating using a preset algorithm model also includes: if a genetic algorithm is selected, then based on the target information and vehicle management information, a genetic strategy is selected to perform genetic operations, wherein the genetic strategy includes a proportional selection strategy or an essence strategy.

[0014] In some embodiments, based on the special requirements, the preliminary scheduling plan is further screened to obtain a final scheduling plan, including: based on the special requirements, determining whether the initial scheduling plan meets the special requirements; in response to the initial scheduling plan meeting the special requirements, the initial scheduling plan is the final scheduling plan.

[0015] In some embodiments, scheduling vehicles according to the final scheduling plan includes: planning vehicle paths based on the final scheduling plan and preset rules.

[0016] In some embodiments, dispatching the vehicle according to the final dispatch plan further includes providing sensors on the vehicle to monitor the temperature and humidity of the vehicle.

[0017] In a second aspect, the present disclosure provides an electronic device for vehicle dispatching, characterized in that it includes: a processor; and a memory on which computer instructions for vehicle dispatching are stored, and when the computer instructions are executed by the processor, the method according to any one of claims 1 to 8 is implemented.

[0018] In a third aspect, the present disclosure provides a computer program having stored thereon instructions for vehicle dispatching, which when executed by one or more processors, implement the method according to any one of claims 1-8.

[0019] Through an electronic device for vehicle scheduling and a computer-readable storage medium as provided above, the disclosed embodiment receives task information, wherein the task information includes task quantity, target information and special requirements; based on the task quantity, selects a preset algorithm model; based on the target information, uses the preset algorithm model to calculate and obtain an initial scheduling plan; based on the special requirements, further screens the preliminary scheduling plan to obtain a final scheduling plan; and schedules vehicles according to the final scheduling plan. Transfer scheduling can be performed from a global perspective to meet the transfer needs reported by multiple farms at the same time, and the global transportation cost can be minimized, while the vehicle arrangement with the fastest time efficiency can also be performed. In addition, the present invention adopts an automatic scheduling system based on an intelligent algorithm, which can quickly process large amounts of data and provide optimal vehicle arrangements and route planning. Compared with manual scheduling, the scheduling efficiency can be greatly improved, thereby reducing the time and labor intensity of staff processing information. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] By reading the detailed description below with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present disclosure will become readily understood. In the accompanying drawings, several embodiments of the present disclosure are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0021] Figure 1 An exemplary flow chart of a vehicle dispatching method according to an embodiment of the present disclosure is shown;

[0022] Figure 2 An exemplary flow chart of selecting a preset algorithm model according to an embodiment of the present disclosure is shown;

[0023] Figure 3 An exemplary framework diagram using an integer linear programming algorithm according to an embodiment of the present disclosure is shown;

[0024] Figure 4 An exemplary flowchart of using a genetic algorithm according to an embodiment of the present disclosure is shown;

[0025] Figure 5 A schematic block diagram of an electronic device 500 for vehicle dispatching according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present disclosure.

[0027] It should be understood that the terms "include" and "comprising" used in the specification and claims of the present disclosure indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0028] It should also be understood that the terms used in this disclosure are only for the purpose of describing specific embodiments and are not intended to limit the disclosure. As used in this disclosure and claims, the singular forms of "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should also be further understood that the term "and / or" used in this disclosure and claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations.

[0029] As used in this specification and claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0030] The specific implementation of the present disclosure is described in detail below with reference to the accompanying drawings.

[0031] Figure 1 FIG. 2 shows an exemplary flow chart of a vehicle dispatching method according to an embodiment of the present disclosure. Figure 1 As shown, the aforementioned method for vehicle scheduling includes: in operation S101, receiving task information, wherein the task information includes task quantity, target information and special requirements; in operation S102, selecting a preset algorithm model based on the task quantity; in operation S103, based on the aforementioned target information, using the preset algorithm model to perform calculations to obtain an initial scheduling plan; in operation S104, based on the aforementioned special requirements, further screening the aforementioned preliminary scheduling plan to obtain a final scheduling plan; and in operation S105, scheduling vehicles according to the final scheduling plan.

[0032] Specifically, at step S101, the aforementioned task information can be released by the cargo owner according to demand. In one embodiment, the cargo owner can be a staff member of the company's internal farm or a staff member of a third-party farm. The task volume can include a combination of a planned quantity and a number of vehicles. In one embodiment, the aforementioned combination can include the product of the planned quantity (N) and the number of vehicles (M). The aforementioned target information can include target requirements, and the aforementioned target requirements can include the starting point and destination of the transport vehicle. The aforementioned special requirements can include requiring that the transport vehicle has not pulled dead pigs or sick pigs in the past two weeks, requiring that the transport vehicle is two-layer, or requiring that the transport vehicle must include a fence, etc. It should be noted that the aforementioned special requirements are only exemplary descriptions. The vehicle management information can include a vehicle analysis library, and the aforementioned vehicle analysis library can be used to score the vehicle. The higher the aforementioned score, the better the comprehensive performance of the vehicle. Preferably, the vehicle score can be determined by the weight of the indicator and the score of the indicator. When selecting a vehicle, it can be selected in order from high to low according to the vehicle score. Specifically, the score can be calculated by the following formula:

[0033]

[0034] Among them, score is the score of the vehicle, w i is the weight of the i-th indicator, fi is the score of the i-th indicator, n is the number of indicators in the scoring model, i is the index of the indicator, and w i and f i The value range is [0, 1].

[0035] In one embodiment, the aforementioned indicators may include cycle income, cycle trips, vehicle type, vehicle source, and waiting time. The aforementioned vehicle types may include vans, constant temperature transport vehicles, refrigerated trucks, livestock and poultry transport vehicles, and special pig-pulling vehicles, wherein the score of the special pig-pulling vehicle may be 100 points, the score of the livestock and poultry transport vehicle and the constant temperature transport vehicle may be 95 points, the score of the van may be 90 points, and the score of the refrigerated truck may be 85 points. The weight of the aforementioned vehicle type may be 0.2. The aforementioned vehicle source may include vehicles from within the company, vehicles from self-employed individuals outside the company, and vehicles from third-party logistics. The score of vehicles from within the company may be 100 points, the score of vehicles from self-employed individuals outside the company may be 90 points, and the score of vehicles from third-party logistics may be 80 points. The weight of the aforementioned vehicle source may be 0.3. . The aforementioned waiting time may include the waiting time of the vehicle, and the shorter the waiting time, the higher the score. In one embodiment, the score for a waiting time within 3 days may be 100 points, the score for a waiting time between 3 and 5 days may be 90 points, and the score for a waiting time exceeding 5 days may be 80 points, wherein the weight of the waiting time may be 0.2.

[0036] The periodic income may include the income of all transport vehicles in the origin and destination areas within a month. In one embodiment, the periodic income may be calculated by the following formula:

[0037]

[0038] Wherein, score_a may represent the score of periodic income, revenue may include the average income in the region, and max(revenue) may include the maximum income in the region. It can be understood that the closer the average income in the region is to the maximum income, the lower the score of periodic income, wherein the weight of the aforementioned periodic income may be 0.2.

[0039] The cycle trip count may include the number of times all vehicles perform tasks within the origin and destination areas within a month. In one embodiment, the calculation formula for the vehicle cycle trip count score is as follows:

[0040]

[0041] Wherein, score_b may represent the score of the cycle trips, trips may include the number of times the vehicle performs the task, and max(trips) may include the maximum number of times the vehicle performs the task. It can be understood that the closer the average number of vehicle operations in the area is to the maximum number of operations, the lower the score of the cycle trips, wherein the weight of the aforementioned cycle trips may be 0.1.

[0042] At step S102, based on the task volume, a preset algorithm model is selected, wherein the aforementioned algorithm model may include an integer linear programming algorithm and a genetic algorithm. In one embodiment, the selection of the preset algorithm model includes: if the combination of the planned quantity and the number of vehicles is less than a preset threshold, an integer linear programming algorithm is selected; if the combination of the planned quantity and the number of vehicles is greater than a preset threshold, a genetic algorithm is selected. In one embodiment, the aforementioned task information may include multiple tasks at the same time, the aforementioned multiple plans may be recorded as a plan pool, and a feasibility analysis may be performed on the aforementioned plan pool to determine whether the company's internal vehicles can meet the requirements, wherein the aforementioned feasibility analysis may include a technical evaluation. In one embodiment, the aforementioned technical evaluation may include an evaluation of whether the company's internal vehicles meet special requirements, wherein the special requirements may include a requirement that the transport vehicle has not pulled dead pigs or sick pigs in the past two weeks, a requirement that the transport vehicle is two-layered, or a requirement that the transport vehicle must include a hoarding. In one embodiment, if the company's internal vehicles meet the requirements of the target information, the company's internal vehicles may be selected; if the company's internal vehicles do not meet the requirements of the target vehicles, a vehicle may be selected from a third-party software platform.

[0043] After selecting the algorithm model, proceed to step S103, and based on the target information, use the preset algorithm model to calculate and obtain the initial scheduling plan. The aforementioned target information comes from the task information, and the aforementioned task information can also include vehicle management information, and the aforementioned vehicle management information can come from the vehicle source pool. In one embodiment, the aforementioned vehicle source pool can include all internal company vehicle data and external third-party vehicle data. The aforementioned vehicle data can include the location information of the vehicle, the license plate number, the phone information of the owner, the location of the vehicle, the capacity of the vehicle, the model of the vehicle, the total mass of the vehicle, the total load of the vehicle, and the cargo license number, etc. When the company does not have enough internal vehicles, the aforementioned external third party can be selected for vehicle selection. The aforementioned vehicle source pool can also include a vehicle analysis library. After each order is completed, the mileage of the vehicle, the income situation, and the evaluation of the aforementioned vehicle by the passengers can be stored in the aforementioned vehicle analysis library.

[0044] In one embodiment, if the integer linear programming algorithm is selected, an objective function may be established based on the target information and the vehicle management information, wherein the objective function includes:

[0045]

[0046] Among them, k is the counting number of the plan, i is the counting number of the vehicle, and q i is the arrival distance of vehicle i, s i is the time required for vehicle i to change from an unavailable state to an available state, p i,k The factor that determines whether vehicle i executes plan k.

[0047] In one embodiment, the aforementioned objective function can be constrained based on the constraints of "whether the vehicle is assigned to a specific plan", "the vehicle is assigned in the order of the plans", and "all plans should be assigned to the same vehicle".

[0048] The above “whether the vehicle is assigned to a specific plan” may include judging whether the vehicle meets the special requirements in the task information based on the task information. Specifically, it can be expressed as follows:

[0049]

[0050] Among them, p i,k It can indicate whether the i-th vehicle meets the requirements of plan k. In one embodiment, if the special requirement of plan k is that the vehicle has a fender, then p i,k =1 means that the i-th vehicle meets the requirement that the vehicle must have a fender. Then p i,k =0 may indicate that the i-th vehicle does not meet the requirement that the vehicle must have a fender.

[0051] The above-mentioned “the vehicles are allocated in the order of the plan” may include arranging the vehicles according to the length of the preparation time. Preferably, the vehicle with the shortest preparation time may be allocated first. The specific constraint conditions may include:

[0052]

[0053] Among them, k is the counting number of the plan, i is the counting number of the vehicle, and q i is the arrival distance of vehicle i, s i is the time required for vehicle i to change from an unavailable state to an available state, p i,k is the factor that determines whether vehicle i executes plan k, g k is the simulated speed of the vehicle from the cleaning and disinfection position to the loading position, D s is the weight of the cleaning and disinfection status, d i is the estimated time, d r Add weight to strong restrictions.

[0054] The aforementioned “all plans should be assigned to one vehicle” may include that when there are multiple transport tasks, the aforementioned multiple transport tasks can be performed by the same vehicle. In one embodiment, the constraint condition can be expressed by the following formula:

[0055]

[0056] Among them, the aforementioned p i,k It can be said that the i-th car implements the k-th plan. After obtaining the objective function, the parameters in the objective function can be adjusted based on the target requirements, where the target requirements include the shortest time requirement and the lowest cost requirement, and the parameters include q i 、s i 、p i,k and / or k In one embodiment, the shortest time requirement may include selecting a scheduling solution with the shortest total time when scheduling vehicles. Specifically, the shortest time requirement may be achieved by adjusting the parameter q i 、s i The aforementioned minimum cost requirement may include selecting the scheduling scheme with the lowest total cost when scheduling vehicles. Specifically, the minimum cost requirement may be achieved by adjusting the parameter p i,k *g k to achieve.

[0057] In one embodiment, if a genetic algorithm is selected, a genetic strategy is selected for genetic operation based on the target information and vehicle management information, wherein the genetic strategy includes a proportional selection strategy or an elite strategy, wherein the proportional selection strategy is a strategy for selection based on individual fitness. The basic idea is that the probability of each individual being selected is proportional to its fitness. The specific operation steps are as follows: calculate the fitness value of each individual in the population; calculate the probability of each individual being inherited to the next generation population according to the fitness value of each individual and generate a random number, select the corresponding individual according to the relationship between the random number and the individual probability, and repeat the process until the required number of individuals is obtained. The aforementioned proportional selection strategy can effectively retain individuals with higher fitness, thereby improving the overall quality of the population.

[0058] After obtaining the initial scheduling plan, the aforementioned initial scheduling plan can be optionally screened, which can specifically include screening based on the influence operator and internal and external balance, wherein the aforementioned influence factor can include calculating whether the vehicles in the aforementioned initial scheduling plan will affect the fairness of income. In one embodiment, the same vehicle is scheduled three times in a row or the same vehicle is not scheduled three times in a row. Both can affect the fairness of income, wherein the aforementioned internal and external balance operator can include that when the vehicle combination in the aforementioned initial scheduling plan includes multiple combinations, the company's internal vehicles are given priority, and when the company's internal vehicles do not meet the invitation, the vehicles of the third-party platform are selected. It can be understood that the specific implementation of the aforementioned influence operator and internal and external balance operator is only exemplary and not restrictive.

[0059] At step S104, based on the special requirements, the preliminary scheduling plan is further screened to obtain the final scheduling plan. In one embodiment, the aforementioned special requirements may include selecting double-decker vehicles, selecting vehicles with panels, whether to accept high-risk vehicles, whether to accept low-toxic special vehicles, etc., wherein high-risk vehicles may include vehicles that have pulled sick pigs within 7 days, these vehicles may carry viruses, require special treatment, and cannot be used for normal transportation, wherein low-toxic special vehicles refer to vehicles specially used to transport low-toxic substances, and low-toxic special vehicles are mainly used to transport specific low-toxic substances or pigs with pathogens, such as pigs containing low-toxic strains of African swine fever virus, and strict management and disinfection measures are required during use to ensure safety and prevent virus transmission.

[0060] In one embodiment, the aforementioned preliminary scheduling scheme may include multiple results. In this case, the aforementioned results may be subjected to linear programming, and convex optimization may be selected for solution, wherein the aforementioned convex optimization is a mathematical optimization method that focuses on solving optimization problems in which both the objective function and the constraints are convex sets. A convex set refers to a set in which, for any two points in the set, all points on the line segment are within the set. In one embodiment, the aforementioned further screening of the preliminary scheduling scheme to obtain the final scheduling scheme may include determining whether the initial scheduling scheme meets the special requirements based on the special requirements. In response to the initial scheduling scheme meeting the special requirements, the initial scheduling scheme is the final scheduling scheme.

[0061] At step S105, the vehicles are dispatched according to the final dispatch plan, wherein the dispatching of the vehicles according to the final dispatch plan may include transmitting the final dispatch plan to the logistics platform, the logistics platform checking the final dispatch plan and dispatching the vehicles. Optionally, a secondary inspection may be performed before the vehicles are dispatched. The secondary inspection may include sending the final dispatch plan to the dispatch process to confirm whether the vehicle information in the final dispatch plan is correct, so as to eliminate errors that occur when uploading vehicle information.

[0062] In one embodiment, dispatching vehicles according to the final dispatching scheme may include planning vehicle routes based on the final dispatching scheme and preset rules. The aforementioned preset rules may include live epidemic prevention rules, wherein live epidemic prevention rules may include strict quarantine and disinfection, handling relevant certificates, escort training, restricting the flow of personnel and vehicles, vaccination, standardized transportation management, and isolated feeding, etc., wherein strict quarantine and disinfection may include strictly implementing relevant animal epidemic prevention conditions when transporting live pigs, improving transportation vehicle cleaning and disinfection facilities and equipment, and resolutely eliminating the risk of transportation vehicles spreading the epidemic. The carrier shall thoroughly clean and disinfect the vehicle before loading and after unloading. Handling relevant certificates may include the need to apply for an "Animal Quarantine Certificate" for transporting live livestock. In addition, units and individuals and vehicles engaged in animal transportation shall apply to relevant departments and obtain corresponding permits, wherein escorts may include escorts who have passed the customs training and assessment for the transportation of live pigs, and escorts must do a good job of feeding management and epidemic prevention and disinfection during transportation, and shall not cross vehicles, and shall not abandon or sell sick, disabled, or dead pigs along the way. In one embodiment, restricting the flow of people and vehicles may include taking measures to reduce the flow of people, vehicles, materials, pigs, etc., restricting the entry and exit of irrelevant personnel, strictly implementing the hygiene system of changing clothes and shoes, washing and showering for pig farm personnel entering and exiting, and outside vehicles are not allowed to enter the pig farm. Among them, vaccination and immunization may include foot-and-mouth disease, classical swine fever, pseudorabies, porcine transmissible gastroenteritis and porcine epidemic diarrhea, etc., which can be prevented by vaccination. Among them, standardized transportation management may include the "Technical Requirements for Pig Transportation Management" national standard issued by the State Administration for Market Regulation, which stipulates the basic requirements for pig transportation, vehicle equipment requirements, transportation operation requirements, identification and accompanying document requirements, and is applicable to the transportation management of pigs transported by road, and focuses on animal epidemic prevention management during transportation. Among them, isolation feeding may include that when sick pigs are found, the sick pigs should be immediately moved to isolation pens and raised separately, and clinical samples should be collected for laboratory testing, and corresponding prevention and control measures should be taken according to the diagnosis results.

[0063] In one embodiment, the aforementioned dispatching of vehicles according to the final dispatching plan may also include setting sensors on the vehicles for monitoring the temperature and humidity of the vehicles, wherein the temperature and humidity detected by the aforementioned sensors may be transmitted to the Internet of Things system for detecting the transportation environment, wherein the aforementioned Internet of Things system may provide functions such as real-time positioning, status monitoring, data collection, communication, and driver terminals of the vehicles to be provided, and its main hardware carriers may be vehicle-mounted embedded devices and vehicle-mounted monitoring, communication equipment, and driver terminals provided by external suppliers. The aforementioned Internet of Things system may also upload sensor monitoring data of the air filtration conditions inside the vehicle, the rotation speed of the vehicle fan, the carbon dioxide concentration inside the vehicle, and the temperature and humidity inside the vehicle.

[0064] Furthermore, vents and spray equipment can be added to the vehicle, and based on the aforementioned temperature and humidity detection, the vents can be adjusted and the spray equipment can be turned on to increase the comfort of the pigs. The aforementioned vehicle can also include a non-slip floor to prevent the pigs from splitting and slipping.

[0065] Figure 2 A flow chart of selecting a preset algorithm model in an embodiment of the present disclosure is shown. At step S201, if the combination of the planned quantity and the number of vehicles is less than a preset threshold, an integer linear programming algorithm is selected, wherein selecting the integer linear programming algorithm may include establishing an objective function based on the target information and the vehicle management information, wherein the objective function includes:

[0066]

[0067] Among them, k is the counting number of the plan, i is the counting number of the vehicle, and q i is the arrival distance of vehicle i, s i is the time required for vehicle i to change from an unavailable state to an available state, p i,k The factor that determines whether vehicle i executes plan k.

[0068] The allocation of vehicles according to the planned sequence may include arranging the vehicles according to the length of the preparation time. Preferably, the vehicles with the shortest preparation time may be allocated first. The specific constraints may include:

[0069]

[0070] Among them, k is the counting number of the plan, i is the counting number of the vehicle, and q i is the arrival distance of vehicle i, s i is the time required for vehicle i to change from an unavailable state to an available state, p i,k is the factor that determines whether vehicle i executes plan k, g k is the simulated speed of the vehicle from the cleaning and disinfection position to the loading position, D s is the weight of the cleaning and disinfection status, d i is the estimated time, d r Add weight to strong restrictions.

[0071] The aforementioned constraints can also include that each vehicle can only be assigned to one plan, which can be defined by the following equation: Among them, x ij It can be indicated that the j-th vehicle is assigned to plan i.

[0072] The aforementioned constraints may include whether a vehicle is assigned to a specific plan, which can be defined by the following equation: Among them, p i,k The factor that determines whether vehicle i executes plan k.

[0073] The above constraints can also include that all plans should be assigned to one vehicle, which can be limited by the following equation: Among them, p i,k The factor that determines whether vehicle i executes plan k.

[0074] After obtaining the above objective function, the parameters in the objective function are adjusted based on the objective requirements, wherein the objective requirements include the shortest time requirement and the lowest cost requirement, wherein the parameters include q i 、s i 、p i,k and / or k .

[0075] Figure 3 An exemplary framework diagram of an embodiment of the present disclosure using an integer linear programming algorithm is shown. In one embodiment, the aforementioned integer linear programming algorithm can be used for a live pig sales model, a live pig procurement model, and a production and transportation model.

[0076] At 301, the pig sales model may include a problem definition, model assumptions, modeling objectives, and planning constraints. The aforementioned problem definition may include data such as the length, load capacity, location, preparation status, number, and belonging area of ​​the task vehicle, wherein the length of the vehicle may include 4.2 meters, 6.8 meters, or 9.6 meters, and the corresponding load capacity is 5 tons, 10 tons, and 15 tons, respectively. The aforementioned location may be a latitude and longitude value. The aforementioned preparation status may include 0-7, and the larger the value, the more fully prepared the vehicle is, and the earlier the departure time is. The aforementioned belonging area may include an array. In one embodiment, [1, 2, 3] may indicate that the vehicle can be used in areas 1, 2, and 3. The aforementioned problem definition may also include a total of m plans, in which the total weight, shipping location, start time, and allowed use area data may be set as an array. In one embodiment, the aforementioned problem definition may also include "the belonging area of ​​the vehicle meets the allowed use area of ​​the plan", specifically, each vehicle can travel within the belonging area of ​​the vehicle to prevent the problem of cross-regional infection if the vehicle carries a virus. The aforementioned problem definition includes "the vehicles are allocated in the order of the plans", which may specifically include arranging the vehicles according to the length of the preparation time, and preferably, the vehicle with the shortest preparation time may be allocated first. The aforementioned problem definition may also include "all plans should be allocated to one vehicle", which may specifically include that when there are multiple transport tasks, the same vehicle may perform the aforementioned multiple transport tasks.

[0077] The aforementioned model assumptions for live pig sales may include pre-setting that the reserved vehicle is an available vehicle and that the usage status of the vehicle will not change. Specifically, when selecting a vehicle, if the vehicle is currently available, then if the vehicle is selected for a transportation task, the vehicle should remain available until it is scheduled, and cannot be scheduled by other tasks during this period; the assumption model can pre-set that the waiting time for vehicles caused by third-party vehicles at the cleaning point, disinfection station, second drying point, pig loading location, and pig unloading location can be ignored; it can pre-set that vehicle transportation abnormalities caused by special factors can be ignored; and it can also be set that the cleaning and disinfection time can be preset to 40 minutes. In the live pig sales model, the planning constraints can include that the sum of the load weights of the individual vehicles assigned to each plan must be greater than or equal to the total weight of the plan, which can be specifically obtained by the following formula:

[0078]

[0079] Among them, x ij It can indicate that the j-th vehicle is assigned to plan i, load can indicate the load of a single vehicle, and planload can indicate the total weight of the plan.

[0080] The aforementioned integer linear programming algorithm can also be used in the live pig procurement model 302, which can include vehicle variable definition, driver variable definition, plan variable definition, problem definition, and constraints.

[0081] The aforementioned vehicle variable definition may include selecting a parent company or a subsidiary company to indicate the area in which the vehicle participates in the distribution plan. The vehicle variable definition may also include selecting a transport vehicle with a length of 9.6 meters. In one embodiment, the vehicle variable definition may also include determining the location of the vehicle, and the aforementioned location may include the longitude and latitude of the location, and the aforementioned longitude and latitude may come from GPS data or third-party map service data.

[0082] The driver variable definition may include the driver's number, monthly trips, monthly income, monthly attendance rate, the number of normal deaths of pigs, the number of stress deaths of pigs, etc., wherein the driver's number is used to display the driver's name and code. The monthly trips may include the number of times the driver participated in the transportation in that month, the monthly income may include the transportation income of the driver in that month, the number of normal deaths of pigs may include the number of normal deaths of pigs during the transportation process, and the stress deaths of pigs may include the number of deaths of pigs due to emergency during the transportation process.

[0083] In one embodiment, the aforementioned plan variable definition may include the longitude and latitude of the cleaning and disinfection site and the longitude and latitude of the shipping location.

[0084] In one embodiment, the problem definition of the live pig procurement model may include a scheduling target. Specifically, the aforementioned scheduling target may include "selecting the shortest total arrival time", "giving priority to high-quality drivers", and "balancing the number of trips and income as much as possible", wherein the aforementioned shortest total arrival time may include the shortest vehicle preparation time and the shortest time for the vehicle to travel from the starting position to the end position. The aforementioned high-quality driver priority may include scoring the driver based on the evaluation of the aforementioned vehicle by the passengers in the vehicle analysis library, and the aforementioned score is higher than 90 points for high-quality drivers. The aforementioned balance between the number of trips and income as much as possible may include giving priority to vehicles with fewer trips or vehicles with less income based on the income and number of trips in the area in the aforementioned vehicle analysis library. The constraint conditions for live pig procurement may include "no orders will be dispatched within 1 day if the pig dies normally during the transportation journey". Specifically, if a vehicle has a normal death of pigs during the transportation process, no orders will be dispatched to the vehicle within 1 day. The constraint conditions may also include "no orders will be dispatched within 3 days if the pig dies due to stress during the transportation journey". Specifically, if a vehicle has a stress death of pigs during the transportation process, no orders will be dispatched to the vehicle within 3 days. The constraints include "a driver who receives two consecutive long-distance orders will not be assigned orders". Specifically, if a driver receives a second order within one day after completing an order, the driver will not receive new orders within two days after completing the second order. The constraints also include "data constraints", where the aforementioned data constraints can include average allocation in the first 10 days of each month and differential allocation based on the data of the previous ten days starting from the 11th of each month.

[0085] In one embodiment, the constraints of the live pig procurement model may include "whether the vehicle is allocated to a specific plan", "the early start plan should be allocated with the vehicle that has been prepared earlier as much as possible", and "all plans should be allocated to one vehicle", wherein whether the vehicle is allocated to a specific plan may include: where p i,k is the factor that determines whether vehicle i executes plan k. In one embodiment, “all plans should be assigned to one vehicle” may include that when there are multiple transport tasks, the same vehicle can execute the aforementioned multiple transport tasks. In one embodiment, the constraint condition can be expressed by the following formula:

[0086]

[0087] Among them, the aforementioned p i,k It can be said that the i-th car implements the k-th plan.

[0088] At 303, the integer linear programming algorithm can also be used for production transportation 303. The aforementioned production transportation 303 may include a scheduling target and a constraint condition, wherein the scheduling target may include "the shortest total arrival time", specifically, the aforementioned shortest total arrival time may include the shortest vehicle preparation time and the shortest time for the vehicle to travel from the starting position to the end position. The aforementioned constraint condition may include "whether the vehicle is assigned to a specific plan", specifically, it may include judging whether the vehicle meets the special requirements in the task information based on the task information. Specifically, it can be expressed according to the following formula:

[0089]

[0090] Among them, p i,k It can indicate whether the i-th vehicle meets the requirements of plan k. In one embodiment, if the special requirement of plan k is that the vehicle has a fender, then p i,k =1 means that the i-th vehicle meets the requirement that the vehicle must have a fender. Then p i,k =0 may indicate that the i-th vehicle does not meet the requirement that the vehicle must have a fender.

[0091] Back to Figure 2 , at step S202, if the combination of the planned number and the number of vehicles is greater than the preset threshold, a genetic algorithm is selected. Specifically, the selection of the genetic algorithm may include selecting a genetic strategy for genetic operation based on the target information and the vehicle management information, wherein the genetic strategy includes a proportional selection strategy or an essence strategy, wherein the genetic algorithm is a heuristic search algorithm, which is inspired by the theory of biological evolution and optimizes complex problems by simulating natural selection and genetic mechanisms, wherein the proportional selection strategy is a strategy for selection based on individual fitness. The basic idea is that the probability of each individual being selected is proportional to its fitness. The specific operation steps are as follows: calculate the fitness value of each individual in the population; calculate the probability of each individual being inherited to the next generation population according to the fitness value of each individual and generate a random number, select the corresponding individual according to the relationship between the random number and the individual probability, and repeat the process until the required number of individuals is obtained. The aforementioned proportional selection strategy can effectively retain individuals with higher fitness, thereby improving the overall quality of the population.

[0092] Figure 4 An exemplary flowchart of using a genetic algorithm in an embodiment of the present disclosure is shown. In one embodiment, the genetic algorithm may include initializing a population, setting genetic algorithm parameters, determining whether a termination condition is satisfied, calculating fitness, selecting a genetic operation according to probability, performing a crossover operation on a chromosome, performing a mutation operation on a chromosome, and performing an update operation on the population.

[0093] At step S401, the population is initialized. The aforementioned initialization of the population may include randomly generating a set of possible vehicle-plan transportation schemes as the initial population. Each of the aforementioned vehicle-plan schemes may represent a chromosome, and the aforementioned chromosome may include multiple genes, and the gene encoding of the chromosome may represent the order and selection of routes. In one embodiment, the chromosome GEN may be represented by a natural number encoding, and the aforementioned initial population may include GEN=0. After obtaining the initial population, step S402 may be performed to set the genetic algorithm parameters. Specifically, it may include setting the crossover probability, mutation probability, population size, preset number of iterations, and setting the termination condition, wherein the aforementioned setting of the termination condition may include that the highest fitness in the population no longer improves.

[0094] After setting the genetic algorithm parameters, you can proceed to step S404 to calculate the fitness. The aforementioned fitness can be used to measure the degree of survival advantage of an individual in a population. Specifically, fitness is the main indicator that describes individual performance, and the evolution of the genetic algorithm is driven by evaluating the quality of the individual. The higher the fitness value, the more superior the individual, and vice versa. In one embodiment, the fitness calculation can be based on factors such as the total distance, estimated time, and cost of the route. By calculating the fitness, the chromosome with the highest fitness can be found, that is, the optimal vehicle-plan allocation scheme can be found.

[0095] Step S405, select genetic operation according to probability. Specifically, the aforementioned genetic operation may include performing a crossover operation on the chromosome, performing a mutation operation on the chromosome, and performing a mutation operation on the chromosome. If the crossover operation is selected, then step S406 is entered to perform a crossover operation on the chromosome. Specifically, a group of the aforementioned parent chromosomes may be randomly selected, and the genes of the group of chromosomes may be crossover operated to generate new offspring chromosomes. The crossover operation may include selecting a random position of the aforementioned chromosome gene, exchanging the genes of the parent chromosome after the random position, thereby generating new chromosome genes, that is, generating a new transportation route plan. The aforementioned crossover operation may include randomly setting two crossover points in the individual chromosome, and then performing partial gene exchange. The aforementioned crossover operation may also include setting multiple crossover points on a chromosome, and performing gene exchange between these points. If the mutation operation is selected, step S407 is entered to perform a mutation operation on the chromosome. Specifically, the chromosome genes after the aforementioned crossover may be subjected to a mutation operation to increase the diversity of the population, wherein the aforementioned mutation operation may include randomly modifying a certain position of the gene on the chromosome, and preferably, the aforementioned mutation operation may be achieved by inverting the gene value at the position. By performing mutation operations, diversity can be increased, which can prevent the algorithm from falling into a local optimal situation.

[0096] At step S408, the population is updated. Specifically, the chromosomes in the current population are replaced with the newly generated offspring chromosomes, so that a new population can be formed. After the new population is formed, the process proceeds to step S403 to determine whether the termination condition is met. When the termination condition is not met, the process proceeds to step S404. When the aforementioned termination condition is met or the preset number of iterations is reached, the update step is terminated, and the process proceeds to step S409 to output the optimal solution, wherein the aforementioned termination condition may include that the highest fitness in the population is no longer improved. Through the aforementioned genetic algorithm, the chromosome with the highest fitness, i.e., the optimal transportation route plan, can be obtained.

[0097] Figure 5 FIG. 5 is a schematic block diagram of an electronic device 500 for vehicle dispatching according to an embodiment of the present disclosure. Figure 5 As shown, the electronic device 500 may include a processor 501 and a memory 502, wherein the processor 501 and the memory 502 communicate with each other via a bus. The memory 502 stores computer instructions for simulating vehicle scheduling. When the aforementioned computer instructions are executed by the processor 501, the electronic device 500 implements the method steps described in the foregoing text in combination with the accompanying drawings: receiving task information, wherein the task information includes task volume, target information and special requirements; selecting a preset algorithm model based on the task volume; calculating using the preset algorithm model based on the target information to obtain an initial scheduling plan; further screening the preliminary scheduling plan based on the special requirements to obtain a final scheduling plan; and scheduling vehicles according to the final scheduling plan. According to the above description in combination with the accompanying drawings, those skilled in the art can also understand that the embodiments of the present application can also be implemented by a software program. Therefore, the present application also provides a computer-readable storage medium. The computer-readable storage medium stores thereon computer-readable instructions for automatic construction of the ontology. When the computer-readable instructions are executed by one or more processors, the present application in combination with the attached drawings is implemented. Figure 1 A simulation method for vehicle scheduling is described.

[0098] According to the above description in combination with the accompanying drawings, those skilled in the art can also understand that the embodiments of the present application can also be implemented by a software program. The present invention also discloses a computer-readable storage medium, in which program instructions for vehicle scheduling are stored, and the program instructions are suitable for being loaded and executed by a processor: using test data to perform operations on operators in the neural network to obtain test results for the operators, wherein the operators are associated with layers in the neural network; comparing the test results with benchmark results for the operators to determine the difference between the test results and the benchmark results; and evaluating the difference according to an evaluation criterion to determine the accuracy level of the operator.

[0099] The computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as RRAM (Resistive Random Access Memory), DRAM (Dynamic Random Access Memory), SRAM (Static Random-Access Memory), EDRAM (Enhanced Dynamic Random Access Memory), HBM (High-Bandwidth Memory), HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by the application, module, or both. Any such computer storage medium may be part of the device or accessible or connectable to the device. Any application or module described in the present invention may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.

[0100] It should also be understood that any module, unit, component, server, computer, terminal or device that executes instructions of the present invention examples may include or otherwise access computer-readable media, such as storage media, computer storage media or data storage devices (removable) and / or non-removable) such as disks, optical disks or tapes. Computer storage media may include volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules or other data.

[0101] In summary, the disclosed embodiment receives task information, wherein the task information includes task quantity, target information and special requirements; selects a preset algorithm model based on the task quantity; calculates using the preset algorithm model based on the target information to obtain an initial scheduling plan; further screens the preliminary scheduling plan based on the special requirements to obtain a final scheduling plan; and schedules vehicles according to the final scheduling plan. Transfer scheduling can be performed from a global perspective to meet the transfer needs reported by multiple farms at the same time, and the global transportation cost can be minimized, while the vehicle arrangement can also be performed in the fastest time. In addition, the present invention adopts an automatic scheduling system based on an intelligent algorithm, which can quickly process large amounts of data and provide optimal vehicle arrangements and route planning. Compared with manual scheduling, the scheduling efficiency can be greatly improved, thereby reducing the time and labor intensity of staff in processing information.

[0102] Although multiple embodiments of the present disclosure have been shown and described herein, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art may think of many changes, modifications, and alternatives without departing from the thought and spirit of the present disclosure. It should be understood that in the process of practicing the present disclosure, various alternatives to the embodiments of the present disclosure described herein may be adopted. The attached claims are intended to define the scope of protection of the present disclosure, and therefore cover equivalents or alternatives within the scope of these claims.

Claims

1. A method for vehicle dispatching, characterized in that: The method comprises: Receiving task information, wherein the task information includes task quantity, target information and special requirements; Based on the amount of tasks, select the preset algorithm model; Based on the target information, a preset algorithm model is used to perform calculations to obtain an initial scheduling plan; Based on the special requirements, further screening the preliminary scheduling plan to obtain a final scheduling plan; and The vehicles are dispatched according to the final dispatch plan.

2. The method according to claim 1, characterized in that The task volume includes a combination of a planned quantity and a vehicle quantity, wherein the selection of a preset algorithm model includes: If the combination of the planned quantity and the number of vehicles is less than a preset threshold, an integer linear programming algorithm is selected; If the combination of the planned quantity and the number of vehicles is greater than a preset threshold, a genetic algorithm is selected.

3. The method according to claim 2, characterized in that The task information also includes vehicle management information, wherein the initial scheduling scheme obtained by calculating based on the target information using a preset algorithm model includes: If the integer linear programming algorithm is selected, an objective function is established based on the target information and the vehicle management information, wherein the objective function includes: Among them, k is the counting number of the plan, i is the counting number of the vehicle, and q i is the arrival distance of vehicle i, s i is the time required for vehicle i to change from an unavailable state to an available state, p i, The factor that determines whether vehicle i executes plan k.

4. The method according to claim 3, wherein the target information includes target requirements, and the method further comprises: Based on the target requirements, the parameters in the target function are adjusted, wherein the target requirements include the shortest time requirement and the lowest cost requirement, wherein the parameters include q i 、s i 、p i, and / or k .

5. The method according to claim 3, characterized in that: Based on the target information, calculating using a preset algorithm model also includes: If a genetic algorithm is selected, a genetic strategy is selected to perform genetic operations based on the target information and the vehicle management information, wherein the genetic strategy includes a proportional selection strategy or an elite strategy.

6. The method according to claim 1, characterized in that Based on the special requirements, the preliminary scheduling plan is further screened to obtain the final scheduling plan including: Based on the special requirements, determining whether the initial scheduling solution meets the special requirements; In response to the initial scheduling plan meeting the special requirements, the initial scheduling plan is the final scheduling plan.

7. The method according to claim 1, characterized in that The dispatching of vehicles according to the final dispatching plan includes: planning vehicle paths based on the final dispatching plan and preset rules.

8. The method according to claim 1, characterized in that: The dispatching of vehicles according to the final dispatching plan also includes providing sensors on the vehicles for monitoring the temperature and humidity of the vehicles.

9. An electronic device for vehicle dispatching, characterized in that: include: processor; as well as A memory having computer instructions for vehicle dispatch stored thereon, which, when executed by a processor, implement the method according to any one of claims 1-8.

10. A computer-readable storage medium, characterized in that: Computer program instructions for vehicle dispatch are stored thereon, and when the computer program instructions are executed by one or more processors, the method according to any one of claims 1-8 is implemented.

Images