WO2018196525A1 - 货物搬运方法和装置 - Google Patents

货物搬运方法和装置 Download PDF

Info

Publication number
WO2018196525A1
WO2018196525A1 PCT/CN2018/080458 CN2018080458W WO2018196525A1 WO 2018196525 A1 WO2018196525 A1 WO 2018196525A1 CN 2018080458 W CN2018080458 W CN 2018080458W WO 2018196525 A1 WO2018196525 A1 WO 2018196525A1
Authority
WO
WIPO (PCT)
Prior art keywords
shelf
vehicle
information
transported
goods
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2018/080458
Other languages
English (en)
French (fr)
Inventor
王天文
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Jingdong Century Trading Co Ltd
Beijing Jingdong Shangke Information Technology Co Ltd
Original Assignee
Beijing Jingdong Century Trading Co Ltd
Beijing Jingdong Shangke Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Jingdong Century Trading Co Ltd, Beijing Jingdong Shangke Information Technology Co Ltd filed Critical Beijing Jingdong Century Trading Co Ltd
Publication of WO2018196525A1 publication Critical patent/WO2018196525A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/12—Computing arrangements based on biological models using genetic models
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/12—Computing arrangements based on biological models using genetic models
    • G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management

Definitions

  • the present application relates to the field of warehousing technology, and in particular to the field of logistics and distribution technology, and in particular to a cargo handling method and device.
  • the unmanned warehouse is a smart warehouse that integrates more advanced automated logistics equipment and is attended by a small number of maintenance personnel.
  • a complete automated warehouse system generally including stackers, logistics management software, conveyor systems, and racking systems.
  • the goods are automatically unloaded, automatically accepted, automatically unpacked to the robot code box, the tote into the storage, the tote selection, the outbound, the robot picking, then the goods are automatically packaged, automatically sorted, and finally loaded and shipped , all automated.
  • the purpose of the present application is to propose an improved cargo handling method and apparatus to solve the technical problems mentioned in the background section above.
  • an embodiment of the present application provides a cargo handling method, the method comprising: acquiring a vehicle information set, a shelf information set, and order information, wherein the vehicle information includes a car number, a car location, and the shelf information includes a shelf number and a shelf.
  • Location, type and quantity of goods carried, order information includes the type and quantity of goods to be transported; determined according to the type and quantity of goods to be transported in the order information, and the type and quantity of goods carried in each shelf information a shelf set to be transported; determining, according to the position of the vehicle in each vehicle information and the shelf position in each shelf information, the shelf number of the shelf to be transported and the vehicle number of the vehicle to be transported with the lowest transportation cost from the set of shelves to be transported; The vehicle corresponding to the vehicle number transmits an instruction for carrying the shelf corresponding to the determined shelf number.
  • the set of shelves to be transported is determined according to the type and quantity of the goods to be transported in the order information, the kind and quantity of the goods carried in each shelf information, including: utilizing the vehicle information set, the shelf information set, and The order information establishes an integer programming model, wherein the integer programming model is used to characterize the type and quantity of goods to be transported in the order information and the relationship between the type and quantity of goods carried in the shelf information and the shelves to be transported, and vehicle information. The relationship between the car position and the shelf position in the shelf information and the handling cost.
  • the shelf number of the shelf to be transported and the vehicle number of the vehicle to be transported with the least transportation cost are determined from the set of shelves to be transported according to the position of the vehicle in each vehicle information and the shelf position in each shelf information, including: The shelf number of the rack to be transported when the carrying cost in the integer plan model is minimized and the vehicle number of the vehicle for carrying the rack to be transported are determined.
  • the method further comprises: obtaining vehicle information of the vehicle that is carrying the rack, and updating the type and quantity of the goods carried by the rack carried by the vehicle that is carrying the rack according to the order information; in response to receiving the new The order information determines whether the type and quantity of the updated goods match the new order information; if it matches, corrects the handling cost in the integer programming model and re-determines the to-be-handled when the handling cost in the modified integer programming model is the lowest
  • the shelf number of the shelf and the vehicle number of the vehicle for carrying the shelf to be transported, and an instruction for carrying the shelf corresponding to the re-determined shelf number is transmitted to the vehicle corresponding to the re-determined car number.
  • determining a shelf number of a shelf to be transported when the handling cost is minimized in the integer programming model and a vehicle number of the vehicle for carrying the shelf to be transported includes: converting the vehicle number of the vehicle into a genetic algorithm based on a genetic algorithm The gene locus of the chromosome, and convert the shelf number of the shelf into the gene of the chromosome; generate a random number and determine the fitness value interval where the random number is located; use the fitness proportional method to select the candidate chromosome set from the fitness value interval; The chromosomes in the candidate chromosome set are cross-processed; the chromosomes in the cross-processed candidate chromosome set are subjected to mutation processing to obtain the target chromosome; and the vehicle number and the shelf number of the shelf are extracted from the target chromosome.
  • the method further comprises: correcting the target chromosome according to the chromosome in the cross-processed candidate chromosome set.
  • converting the vehicle number of the vehicle to a genetic locus of the chromosome based on a genetic algorithm and converting the shelf number of the shelf into a gene of the chromosome includes: generating a virtual shelf when the number of vehicles is greater than the number of shelves The number is used as a gene locus of a chromosome; when the number of vehicles is smaller than the number of shelves, a virtual car number is generated as a gene of a chromosome.
  • the embodiment of the present application provides a cargo handling device, comprising: an obtaining unit, configured to acquire a vehicle information set, a shelf information set, and order information, wherein the vehicle information includes a car number, a car position, and shelf information. Including the shelf number, the shelf position, the type and quantity of the goods carried, the order information includes the kind and quantity of the goods to be transported; the shelf determining unit is configured to use the type and quantity of the goods to be carried in the order information, and the shelf information.
  • the type and quantity of the loaded goods determine the set of shelves to be transported; the vehicle determining unit is configured to determine the minimum carrying cost from the set of shelves to be transported according to the position of the vehicle in each vehicle information and the position of the shelves in each shelf information a shelf number of the shelf to be transported and a vehicle number of the vehicle; and a transmitting unit configured to transmit, to the vehicle corresponding to the determined vehicle number, an instruction to transport the shelf corresponding to the determined shelf number.
  • the shelf determination unit is further configured to: establish an integer programming model using the vehicle information set, the shelf information set, and the order information, wherein the integer programming model is used to characterize the type and quantity of the goods to be handled in the order information and The relationship between the type and quantity of goods carried in the shelf information and the shelf to be transported, and the relationship between the position of the car in the vehicle information and the shelf position in the shelf information and the handling cost.
  • the vehicle determining unit is further configured to: determine a shelf number of the shelf to be transported when the handling cost is minimized in the integer programming model, and a car number of the vehicle for carrying the shelf to be transported.
  • the apparatus further includes: an updating unit, configured to acquire vehicle information of the vehicle that is carrying the shelf, and update the type and quantity of the goods carried by the shelf carried by the vehicle that is carrying the shelf according to the order information; a unit, configured to determine, according to the receipt of the new order information, whether the type and quantity of the updated goods match the new order information; and a modifying unit, configured to match when the type and quantity of the updated goods match the new order information , correcting the handling cost in the integer programming model and re-determining the shelf number of the shelf to be transported when the handling cost in the modified integer programming model is the lowest, and the vehicle number of the vehicle for carrying the rack to be transported, and re-determining The vehicle corresponding to the car number of the vehicle transmits an instruction for carrying the shelf corresponding to the re-determined shelf number.
  • an updating unit configured to acquire vehicle information of the vehicle that is carrying the shelf, and update the type and quantity of the goods carried by the shelf carried by the vehicle that is carrying the shelf according to the order information
  • a unit configured to determine, according
  • the vehicle determining unit includes: a conversion subunit for converting a vehicle number of the vehicle into a genetic locus of the chromosome based on a genetic algorithm, and converting the shelf number of the shelf into a gene of the chromosome; a random subunit, And generating a random number and determining a fitness value interval in which the random number is located; selecting a subunit for selecting a candidate chromosome set from the fitness value interval by using the fitness proportional device; and crossing the subunit for selecting the selected candidate chromosome set
  • the chromosome is cross-processed; the mutated subunit is used to mutate the chromosome in the cross-processed candidate chromosome set to obtain the target chromosome; and the extraction sub-unit is used to extract the vehicle number and the shelf number of the shelf from the target chromosome.
  • the variant subunit is further configured to: after mutating the chromosomes in the cross-processed candidate chromosome set to obtain the target chromosome, correcting the target chromosome according to the chromosomes in the cross-processed candidate chromosome set.
  • the conversion subunit is further configured to: when the number of vehicles is greater than the number of shelves, generate a virtual shelf number as a genetic locus of the chromosome; when the number of vehicles is less than the number of shelves, generate a virtual number A gene that is a chromosome.
  • an embodiment of the present application provides an apparatus, including: one or more processors; a storage device, configured to store one or more programs, when one or more programs are executed by one or more processors, One or more processors are caused to implement the method of any of the first aspects.
  • an embodiment of the present application provides a computer readable storage medium having stored thereon a computer program, wherein the program is executed by a processor to implement the method of any of the first aspects.
  • the cargo handling method and device provided by the embodiments of the present application allocates resources (shelves and vehicles) to all orders according to all the outbound order requirements, all resources (shelves inventory goods and vehicles, etc.), so as to achieve total handling.
  • the goal of the lowest cost and the minimum number of robots is to maximize the "robot manpower" under the premise of ensuring the efficiency of the delivery.
  • FIG. 1 is an exemplary system architecture diagram to which the present application can be applied;
  • FIG. 2 is a flow chart of one embodiment of a cargo handling method in accordance with the present application.
  • FIG. 3 is a schematic diagram of an application scenario of a cargo handling method according to the present application.
  • FIG. 4 is a flow chart of still another embodiment of a cargo handling method in accordance with the present application.
  • Figure 5 is a schematic structural view of an embodiment of a cargo handling device according to the present application.
  • FIG. 6 is a block diagram showing the structure of a computer system suitable for implementing the server of the embodiment of the present application.
  • FIG. 1 illustrates an exemplary system architecture 100 in which embodiments of the cargo handling method or cargo handling apparatus of the present application may be applied.
  • system architecture 100 can include terminal devices 101, 102, servers 103, vehicles 104, 105, 106, shelves 107, 108, 109, and workbench 110.
  • the network may include various connection types such as wired, wireless communication links or fiber optic cables and the like.
  • the user can interact with the server 103 over the network using the terminal devices 101, 102 to receive or send messages and the like.
  • Various communication client applications such as a web browser application, a shopping application, a search application, an instant communication tool, a mailbox client, a social platform software, and the like, may be installed on the terminal devices 101, 102, and 103.
  • the user transmits order information to the server 103 through the shopping application of the terminal devices 101, 102.
  • the server 103 instructs the vehicle and the workbench to pick the order according to the order, and updates the logistics status of the order after the picking is completed for the terminal device 101, 102 to query.
  • the vehicles 104, 105, 106 are used to transport the shelves 107, 108, 109 to the workbench 110, and the workbench 110 removes the corresponding kind and quantity of goods from the shelf based on the various types and quantities of goods in the order information.
  • Server 103 may be a server that provides various services, such as a logistics server that provides support for logistics information displayed on terminal devices 101, 102.
  • the logistics server can analyze the received order request and other data, select the shelves and vehicles to be transported according to the order information, and process the results (such as logistics status) after the vehicle moves the shelves to the workbench and sorts the goods. Feedback to the terminal device.
  • the cargo handling method provided by the embodiment of the present application is generally performed by the server 103. Accordingly, the cargo handling device is generally disposed in the server 103.
  • terminal devices servers, vehicles, shelves, and work stations in Figure 1 are merely illustrative. Depending on the implementation needs, there can be any number of terminal devices, servers, vehicles, shelves, work stations.
  • the cargo handling method comprises the following steps:
  • Step 201 Acquire a vehicle information set, a shelf information set, and order information.
  • the electronic device (for example, the server shown in FIG. 1) on which the cargo handling method runs can receive order information from a terminal through which the user performs online shopping by using a wired connection or a wireless connection, and the order information includes The type and quantity of the goods to be transported, for example, one piece of goods to be transported A and two pieces of goods B.
  • the vehicle information includes a car number, a car position, and the car number is numbered by a natural number, for example, 1, 2, 3, .
  • the shelf information includes the frame number, the shelf position, the type and quantity of the goods carried, and the shelf number is also numbered from 1 according to the natural number.
  • the types of goods carried on the shelves and the types in the order information are classified according to the same rules.
  • the car position can be dynamically changed, and the type and quantity of goods carried in the shelf information are also dynamically changed.
  • the position of the table is unchanged, so the position of the car and the position of the shelf can be either absolute or relative to the table. Through the positional relationship between the three, it is possible to determine the walking route of the vehicle when carrying the rack.
  • Step 202 Determine a shelf set to be transported according to the type and quantity of the goods to be transported in the order information, and the type and quantity of the goods carried in each shelf information.
  • each vehicle in order to reduce the transportation cost, it is necessary to assign up to one vehicle for each shelf for transportation, and each vehicle can serve at most one shelf. According to the inventory of the goods on the shelf to meet the situation and order information, positioning the goods one by one, try to locate multiple orders on the same shelf (the smallest number of shelves can cover as many orders as possible).
  • the order 001 information and the inventory of the shelf HJ001, the shelf HJ002, the shelf HJ003, and the shelf HJ004 need to be determined on which shelves the decision order is located.
  • the cargo Sku_A can be located first, and the shelf containing the cargo Sku_A, the inventory quantity is satisfied, and the inventory quantity is the smallest, which has been positioned, can be selected to obtain the shelf HJ001.
  • Relocate the goods Sku_B select the shelves containing the goods Sku_B, the inventory is satisfied and the inventory is the smallest, and the shelves have been positioned to obtain the shelf HJ002.
  • Relocate the goods Sku_C select the shelves containing the goods Sku_C, the inventory is satisfied and the inventory is the smallest, and the shelves have been positioned to obtain the shelf HJ003. That is, a total of three shelves (HJ001, HJ002, HJ003) were positioned to meet the order 001 order requirements.
  • Step 203 Determine, according to the vehicle position in each vehicle information and the shelf position in each shelf information, the shelf number of the shelf to be transported and the vehicle number of the vehicle with the lowest transportation cost from the set of shelves to be transported.
  • the transportation cost is the amount of electricity or oil consumed during the transportation of the rack, and the transportation cost is proportional to the length of the transportation route.
  • Assigning a nearby vehicle (the vehicle closest to the shelf) to the shelf performs a handling task and sends it to the workbench.
  • Use the shortest path algorithm (such as the Dijkstra algorithm) to calculate the shortest distance between any two points in the warehouse to find the nearest vehicle to the shelf and assign it.
  • the transportation cost (car to shelf + shelf to workstation) is 3, 2, 2, respectively.
  • the total handling cost for the secondary schedule is 7.
  • Step 204 Send an instruction for transporting the shelf corresponding to the determined shelf number to the vehicle corresponding to the determined car number.
  • the instructions for transporting the shelves HJ001, HJ002, and HJ003 are transmitted by the vehicle number 01, the car number 02, and the car number 03 in the upper example, respectively. After the vehicle number 01, the car number 02, and the car number 03 receive the transport command, the corresponding rack is transported to the workbench for sorting the goods.
  • FIG. 3 is a schematic diagram of an application scenario of the cargo handling method according to the present embodiment.
  • the server 301 acquires the information of the order information, the vehicles 302, 303, and 304, and the information of the shelves 305, 306, and 307. It is determined in accordance with steps 202-203 that the vehicles 302, 303, 304 need to carry the shelves 305, 306, 307, respectively.
  • the server 301 then sends instructions to the vehicles 302, 303, 304 to transport the shelves 305, 306, 307, respectively, such that the vehicles 302, 303, 307 carry the shelves 305, 306, 307 to the workbench in accordance with the shortest route. 308.
  • the above embodiment of the present application provides a method for reducing the handling cost, increasing the sorting speed of the goods, and improving the entire logistics distribution process by distributing the order to as few shelves as possible and assigning the nearest vehicle handling rack. effectiveness.
  • the process 400 of the cargo handling method includes the following steps:
  • Step 401 Acquire a vehicle information set, a shelf information set, and order information.
  • Step 401 is substantially the same as step 201, and therefore will not be described again.
  • Step 402 Establish an integer programming model by using a vehicle information set, a shelf information set, and order information.
  • the variables (all or part of) in the plan are limited to integers, which are called integer plans.
  • the variable is limited to an integer in a linear model, it is called integer linear programming.
  • the integer programming model is used to characterize the type and quantity of goods to be transported in the order information and the relationship between the type and quantity of goods carried in the shelf information and the rack to be transported, and the vehicle position and shelf information in the vehicle information. The relationship between shelf location and handling costs.
  • the integer programming model can be expressed as a combination optimization problem or a 0-1 planning problem, both of which are the best solutions for satisfying certain constraints in a limited number of alternatives.
  • the constraint condition may be: constraining each shelf to be assigned at most one vehicle, and constraining each vehicle to serve at most one shelf; constraining the shelf inventory being carried out in the warehouse to participate in positioning, but the vehicle-shelf matching relationship cannot be changed, that is, handling The shelves in the warehouse can be located out of the warehouse, but can not be changed; the constraints try to meet the order requirements of the goods.
  • the integer programming model can determine:
  • integer programming model can be as follows:
  • n The total number of shelves in each inventory s in the order task.
  • d js the stock of goods s on shelf j, j ⁇ J, s ⁇ S.
  • U s the demand for the goods s out of the warehouse, the demand for the entire work area out of the warehouse according to the order
  • the goods s are summed up to obtain the demand for each type of goods.
  • C ij The transportation cost required for the car i to walk to the shelf j, i ⁇ I, j ⁇ J.
  • D j The transportation cost of the rack j being transported to the workbench.
  • I c (i, l) ⁇ I c , indicating that the vehicle i is carrying the shelf j, and the inventory is in the state of being shipped.
  • a 1 Weight, used to balance “the shortest distance” and “the least number of shelves”.
  • a 2 Weight, used to balance “the shortest distance” and “the least number of shelves”.
  • Equation (2-1) is the objective function, which means minimizing the total cost of transportation and minimizing the number of matching shelves (using the number of small vehicles to be transported). At the same time, try to meet the order requirements of each cargo. That is to achieve the optimization goal of doing the most things with the least "person (handling robot)".
  • Equation (2-2) is constrained to assign up to one car per shelf.
  • Equation (2-3) is constrained to serve up to one shelf per vehicle.
  • Formula (2-4) is constrained to be in the inventory of the shelf being transported, and can participate in the positioning, but the car-shelf matching relationship cannot be changed. That is, the shelves in transit can be located out of the warehouse, but cannot be changed.
  • Equation (2-5) is constrained to satisfy the order requirements of the goods s.
  • Step 203 determining the shelf number of the shelf to be transported when the transportation cost is minimized in the integer programming model and the vehicle number of the vehicle for carrying the shelf to be transported.
  • the solution to the integer programming can usually generate a related problem gradually, which is called a derivative problem of the original problem.
  • Each derivative problem is accompanied by a slack problem that is easier to solve than it (the derivative problem is called the source problem of the slack problem).
  • the solution to the source problem is determined by the solution of the slack problem, that is, the source problem should be discarded, or one or more derivative problems of its own should be generated instead. Then, select a derivative problem of the original problem that has not been abandoned or replaced, and repeat the above steps until there are no unresolved derivative problems left.
  • the method of the branch and bound method, the cut plane method, or the Hungarian method can be used to determine the shelf number of the rack to be transported when the transport cost is minimized in the integer plan model and the vehicle number of the vehicle for carrying the rack to be transported.
  • the shelf number of the shelf to be transported when the handling cost is minimized in the integer programming model and the vehicle number of the vehicle for carrying the rack to be transported may be determined by a genetic algorithm.
  • the Genetic Algorithm is a computational model that simulates the natural evolution of Darwin's biological evolution and the evolutionary process of genetics. It is a method of searching for optimal solutions by simulating natural evolutionary processes.
  • the vehicle number of the vehicle is converted into a genetic locus of the chromosome, and the shelf number of the shelf is converted into a gene of the chromosome.
  • the code for solving "car number 1 - shelf number 3, car number 2 - shelf number 1, car number 3 - shelf number 2" is (3, 1, 2).
  • a virtual shelf number is generated as a genetic locus of the chromosome; when the number of vehicles is smaller than the number of shelves, a virtual car number is generated as a gene of the chromosome.
  • the virtual car number (or virtual shelf number) is added to facilitate the subsequent genetic operation without losing the feasible solution.
  • the shelves (or cars) that are the virtual car (or virtual shelf) are represented by the shelves (or cars) being rounded, that is, there is no matching relationship in this decision.
  • a random number is generated.
  • the random number can be a decimal between 0-1.
  • the fitness function is the reciprocal of the objective function (Equation 2-1).
  • the choice of winning individuals from the group and the elimination of inferior individuals is called selection.
  • the selection operator is sometimes referred to as the reproduction operator.
  • the purpose of the selection is to directly pass the optimized individual (or solution) to the next generation or to generate a new individual through pairing to regenerate to the next generation.
  • the selection operation is based on the evaluation of the individual's fitness in the group.
  • the fitness ratio method the random traversal sampling method, and the local selection method.
  • roulette wheel selection is the simplest and most common choice.
  • the individual's selection probabilities are proportional to their fitness values. Probability reflects the proportion of individual fitness in the total individual fitness of the entire population. The greater the individual's fitness. The higher the probability of being selected, and vice versa.
  • each round produces a uniform random number between [0, 1], which is used as a selection pointer to determine the selected individual. After the individuals are selected, they can be randomly paired for later crossover operations.
  • the central role of biological evolution in nature is the recombination of biological genes (plus mutations).
  • the central role of genetic algorithms is the crossover operator of genetic operations.
  • the so-called crossover refers to the operation of replacing the partial structure of two parent individuals to generate a new individual.
  • the basic content of variation is the variation of gene values at certain loci of individual strings in a population.
  • the second is to enable genetic algorithms to maintain group diversity to prevent immature convergence. At this point, the convergence probability should take a larger value. For example, progeny genes can be altered by small probability perturbations.
  • the chromosome needs to be modified. For example (3,1, 4, 2) ⁇ variation: (3,1, 2, 2) ⁇ correction feasibility: (3,1,2, 4). Since two 2s appear after the mutation, this is not feasible, so correct one of them to 4.
  • step 5 Obtained in step 5) (3,1,2, 4) can be extracted out of the bus number and the correspondence relationship shelf: the shelf 3 1- license plate, license plate shelf 1 2-, 3- shelf vehicle number 2, number 4 - Shelf 4.
  • the method further includes: acquiring vehicle information of the vehicle that is carrying the shelf, and updating the type and quantity of the goods carried by the shelf carried by the vehicle that is carrying the shelf according to the order information. Responding to receiving new order information, determining whether the type and quantity of the updated goods match the new order information; if matching, correcting the handling cost in the integer programming model and re-determining the modified integer programming model The shelf number of the rack to be transported when the transportation cost is the lowest, the vehicle number of the vehicle for transporting the rack to be transported, and the rack corresponding to the re-determined rack number is sent to the vehicle corresponding to the re-determined car number Instructions.
  • the car 1 carries the cargo shelf 3 to obtain the cargo A2
  • the shelf 3 originally carries 10 cargo A
  • the number of the cargo A on the shelf 3 after being transported is 8 pieces.
  • the shelves in the delivery are preferentially positioned.
  • the flow 400 of the cargo handling method in the present embodiment highlights the steps of determining the shelf number of the shelf to be handled and the vehicle number of the vehicle, which are the least costly to handle, as compared to the embodiment corresponding to FIG. .
  • the solution described in this embodiment can introduce a faster and more accurate determination of the correspondence between the vehicle and the shelf, so that the handling cost is minimized.
  • the present application provides an embodiment of a cargo handling device, which corresponds to the method embodiment shown in FIG. 2, and the device may specifically Used in a variety of electronic devices.
  • the cargo handling apparatus 500 of the present embodiment includes an acquisition unit 501, a shelf determination unit 502, a vehicle determination unit 503, and a transmission unit 504.
  • the acquiring unit 501 is configured to acquire a vehicle information set, a shelf information set, and order information, where the vehicle information includes a car number and a car position, and the shelf information includes a shelf number, a shelf position, a type and quantity of the carried goods, and the order information includes The type and quantity of the goods to be transported;
  • the shelf determining unit 502 is configured to determine the set of shelves to be transported according to the type and quantity of the goods to be transported in the order information, the type and quantity of the goods carried in each shelf information;
  • the unit 503 is configured to determine, according to the vehicle position in each vehicle information and the shelf position in each shelf information, the shelf number of the shelf to be transported and the vehicle number of the vehicle to be transported with the lowest transportation cost from the shelf set to be transported;
  • the instruction for transporting the shelf corresponding to the determined shelf number is transmitted to the vehicle
  • the specific processing of the acquiring unit 501, the shelf determining unit 502, the vehicle determining unit 503, and the sending unit 504 of the cargo handling 500 may refer to step 201, step 202, step 203, and step 204 in the corresponding embodiment of FIG. 2 . .
  • the shelf determining unit 502 is further configured to: establish an integer programming model by using a vehicle information set, a shelf information set, and order information, where the integer programming model is used to represent the waiting in the order information.
  • the vehicle determining unit 503 is further configured to: determine a shelf number of the shelf to be transported when the transportation cost is minimized in the integer programming model, and a vehicle for carrying the shelf to be transported Car number.
  • the apparatus 500 further includes: an updating unit (not shown), configured to acquire vehicle information of the vehicle that is carrying the shelf, and update the vehicle that is carrying the shelf according to the order information.
  • the type and quantity of goods carried by the shelf ;
  • Not shown when the new order information of the type and quantity of the updated goods is matched, correcting the handling cost in the integer programming model and re-determining the to-be-handled when the handling cost in the modified integer programming model is the lowest
  • the shelf number of the shelf and the vehicle number of the vehicle for transporting the shelf to be transported, and an instruction for transporting the shelf corresponding to the re-determined shelf number is transmitted to the vehicle corresponding to the re-determined car number.
  • the vehicle determining unit 503 includes: a conversion subunit for converting a vehicle number of the vehicle into a genetic locus of the chromosome based on a genetic algorithm, and converting the shelf number of the shelf into a chromosome a gene; a random subunit for generating a random number and determining a fitness value interval in which the random number is located; a selection subunit for selecting a candidate chromosome set from the fitness value interval using the fitness proportional device; and a cross subunit for Cross-processing the chromosomes in the selected candidate chromosome set; the mutation sub-unit is used for mutating the chromosomes in the cross-processed candidate chromosome set to obtain the target chromosome; and extracting the sub-unit for extracting the vehicle from the target chromosome The number of the car and the shelf number of the shelf.
  • the variant subunit is further configured to: after the chromosome in the candidate chromosome set after the cross processing is subjected to mutation processing to obtain the target chromosome, according to the candidate chromosome set in the cross processing The chromosome corrects the target chromosome.
  • the conversion subunit is further configured to: when the number of vehicles is greater than the number of shelves, generate a virtual shelf number as a genetic locus of the chromosome; when the number of vehicles is less than the number of shelves At the time, a virtual car number is generated as a gene for the chromosome.
  • FIG. 6 a block diagram of a computer system 600 suitable for use in implementing a server of an embodiment of the present application is shown.
  • the server shown in FIG. 6 is merely an example, and should not impose any limitation on the function and scope of use of the embodiments of the present application.
  • computer system 600 includes a central processing unit (CPU) 601 that can be loaded into a program in random access memory (RAM) 603 according to a program stored in read only memory (ROM) 602 or from storage portion 608. And perform various appropriate actions and processes.
  • RAM random access memory
  • ROM read only memory
  • RAM random access memory
  • various programs and data required for the operation of the system 600 are also stored.
  • the CPU 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604.
  • An input/output (I/O) interface 605 is also coupled to bus 604.
  • the following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, etc.; an output portion 607 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), and the like, and a storage portion 608 including a hard disk or the like. And a communication portion 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the Internet.
  • Driver 610 is also coupled to I/O interface 605 as needed.
  • a removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory or the like, is mounted on the drive 610 as needed so that a computer program read therefrom is installed into the storage portion 608 as needed.
  • an embodiment of the present disclosure includes a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for executing the method illustrated in the flowchart.
  • the computer program can be downloaded and installed from the network via communication portion 609, and/or installed from removable media 611.
  • the central processing unit (CPU) 601 the above-described functions defined in the method of the present application are performed.
  • the computer readable medium described herein may be a computer readable signal medium or a computer readable storage medium or any combination of the two.
  • the computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of computer readable storage media may include, but are not limited to, electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable Programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing.
  • a computer readable storage medium may be any tangible medium that can contain or store a program, which can be used by or in connection with an instruction execution system, apparatus or device.
  • a computer readable signal medium may include a data signal that is propagated in the baseband or as part of a carrier, carrying computer readable program code. Such propagated data signals can take a variety of forms including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • the computer readable signal medium can also be any computer readable medium other than a computer readable storage medium, which can transmit, propagate, or transport a program for use by or in connection with the instruction execution system, apparatus, or device.
  • Program code embodied on a computer readable medium can be transmitted by any suitable medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination of the foregoing.
  • each block of the flowchart or block diagram can represent a module, a program segment, or a portion of code that includes one or more of the logic functions for implementing the specified.
  • Executable instructions can also occur in a different order than that illustrated in the drawings. For example, two successively represented blocks may in fact be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowcharts, and combinations of blocks in the block diagrams and/or flowcharts can be implemented in a dedicated hardware-based system that performs the specified function or operation. Or it can be implemented by a combination of dedicated hardware and computer instructions.
  • the units involved in the embodiments of the present application may be implemented by software or by hardware.
  • the described unit may also be provided in the processor, for example, as a processor including an acquisition unit, a shelf determination unit, a vehicle determination unit, and a transmission unit.
  • the names of these units do not constitute a limitation on the unit itself under certain circumstances.
  • the acquisition unit may also be described as “a unit that acquires a vehicle information set, a shelf information set, and order information”.
  • the present application also provides a computer readable medium, which may be included in the apparatus described in the above embodiments, or may be separately present and not incorporated into the apparatus.
  • the computer readable medium carries one or more programs, when the one or more programs are executed by the device, causing the device to: acquire a vehicle information set, a shelf information set, and order information, wherein the vehicle information includes a car number, Vehicle location, shelf information includes shelf number, shelf location, type and quantity of goods carried, order information includes the type and quantity of goods to be transported; according to the type and quantity of goods to be transported in the order information, each shelf information
  • the type and quantity of the carried goods determine the set of shelves to be transported; according to the position of the vehicle in each vehicle information and the position of the shelves in each shelf information, the shelf of the shelf to be transported with the least transportation cost is determined from the set of shelves to be transported And the vehicle number of the vehicle; and an instruction for transporting the shelf corresponding to the determined shelf number is transmitted to the vehicle corresponding to the determined vehicle number.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Theoretical Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Physics & Mathematics (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Development Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Biophysics (AREA)
  • Game Theory and Decision Science (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Biomedical Technology (AREA)
  • Evolutionary Computation (AREA)
  • Genetics & Genomics (AREA)
  • Artificial Intelligence (AREA)
  • Educational Administration (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Software Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Physiology (AREA)

Abstract

本申请公开了货物搬运方法和装置。该方法的一具体实施方式包括：获取车辆信息集合、货架信息集合和订单信息，其中，车辆信息包括车号、车位置，货架信息包括货架号、货架位置、承载的货物的种类和数量，订单信息包括待搬运的货物的种类和数量；根据订单信息中的待搬运的货物的种类和数量、各货架信息中的承载的货物的种类和数量确定待搬运的货架集合；根据各车辆信息中的车位置和各货架信息中的货架位置，从待搬运的货架集合中确定搬运成本最小的待搬运的货架的货架号和车辆的车号；向确定出的车号对应的车辆发送用于搬运确定出的货架号对应的货架的指令。该实施方式实现了使用最少的车辆搬运货物并且搬运成本最小。

Description

货物搬运方法和装置
相关申请的交叉引用
本专利申请要求于2017年4月27日提交的、申请号为201710287833.4、申请人为北京京东尚科信息技术有限公司和北京京东世纪贸易有限公司、发明名称为“货物搬运方法和装置”的中国专利申请的优先权，该申请的全文以引用的方式并入本申请中。
技术领域
本申请涉及仓储技术领域，具体涉及物流配送技术领域，尤其涉及货物搬运方法和装置。
背景技术
无人仓储库房是集成了更多先进的自动化物流设备，由少量维护人员参与的智能化库房。一套完整的自动化仓储系统，一般包括堆垛机、物流管理软件、输送系统、货架系统等。货物从自动卸货、自动验收、自动拆箱到机器人码箱、周转箱入存储库、周转箱入拣选库、出库、机器人拣货，接着货物完成自动包装、自动分拣，最后装车发货，全部自动化完成。
在自动化设备的无人仓储库房中，需要规划合理的搬运指派关系，即指派哪辆小车去驮哪个货架生产哪个订单。从成本和出库效率的角度上，需要考虑使用尽量少的机器人生产尽量多的出库单量，即需要提升“机器人人效”。
发明内容
本申请的目的在于提出一种改进的货物搬运方法和装置，来解决以上背景技术部分提到的技术问题。
第一方面，本申请实施例提供了一种货物搬运方法，该方法包括： 获取车辆信息集合、货架信息集合和订单信息，其中，车辆信息包括车号、车位置，货架信息包括货架号、货架位置、承载的货物的种类和数量，订单信息包括待搬运的货物的种类和数量；根据订单信息中的待搬运的货物的种类和数量、各货架信息中的承载的货物的种类和数量确定待搬运的货架集合；根据各车辆信息中的车位置和各货架信息中的货架位置，从待搬运的货架集合中确定搬运成本最小的待搬运的货架的货架号和车辆的车号；向确定出的车号对应的车辆发送用于搬运确定出的货架号对应的货架的指令。
在一些实施例中，根据订单信息中的待搬运的货物的种类和数量、各货架信息中的承载的货物的种类和数量确定待搬运的货架集合，包括：利用车辆信息集合、货架信息集合和订单信息建立整数规划模型，其中，整数规划模型用于表征订单信息中的待搬运的货物的种类和数量和货架信息中的承载的货物的种类和数量与待搬运的货架的关系，以及车辆信息中的车位置和货架信息中的货架位置与搬运成本之间的关系。
在一些实施例中，根据各车辆信息中的车位置和各货架信息中的货架位置，从待搬运的货架集合中确定搬运成本最小的待搬运的货架的货架号和车辆的车号，包括：确定使整数规划模型中搬运成本最低时的待搬运的货架的货架号和用于搬运待搬运的货架的车辆的车号。
在一些实施例中，该方法还包括：获取正在搬运货架的车辆的车辆信息，并根据订单信息更新正在搬运货架的车辆所搬运的货架所承载的货物的种类和数量；响应于接收到新的订单信息，确定更新后的货物的种类和数量是否与新的订单信息匹配；若匹配，则修正整数规划模型中的搬运成本并重新确定使修正后的整数规划模型中搬运成本最低时的待搬运的货架的货架号和用于搬运待搬运的货架的车辆的车号，并向重新确定出的车号对应的车辆发送用于搬运重新确定出的货架号对应的货架的指令。
在一些实施例中，确定使整数规划模型中搬运成本最低时的待搬运的货架的货架号和用于搬运待搬运的货架的车辆的车号，包括：基于遗传算法将车辆的车号转换成染色体的基因位点，并将货架的货架 号转换成染色体的基因；生成随机数并确定随机数所在的适应度值区间；采用适应度比例方法从适应度值区间选取候选染色体集合；对所选取的候选染色体集合中的染色体进行交叉处理；对交叉处理后的候选染色体集合中的染色体进行变异处理得到目标染色体；从目标染色体中提取车辆的车号和货架的货架号。
在一些实施例中，在对交叉处理后的候选染色体集合中的染色体进行变异处理得到目标染色体之后，该方法还包括：根据交叉处理后的候选染色体集合中的染色体对目标染色体进行修正。
在一些实施例中，基于遗传算法将车辆的车号转换成染色体的基因位点，并将货架的货架号转换成染色体的基因，包括：当车辆的数量大于货架的数量时，生成虚拟的货架号作为染色体的基因位点；当车辆的数量小于货架的数量时，生成虚拟的车号作为染色体的基因。
第二方面，本申请实施例提供了一种货物搬运装置，该装置包括：获取单元，用于获取车辆信息集合、货架信息集合和订单信息，其中，车辆信息包括车号、车位置，货架信息包括货架号、货架位置、承载的货物的种类和数量，订单信息包括待搬运的货物的种类和数量；货架确定单元，用于根据订单信息中的待搬运的货物的种类和数量、各货架信息中的承载的货物的种类和数量确定待搬运的货架集合；车辆确定单元，用于根据各车辆信息中的车位置和各货架信息中的货架位置，从待搬运的货架集合中确定搬运成本最小的待搬运的货架的货架号和车辆的车号；发送单元，用于向确定出的车号对应的车辆发送用于搬运确定出的货架号对应的货架的指令。
在一些实施例中，货架确定单元进一步用于：利用车辆信息集合、货架信息集合和订单信息建立整数规划模型，其中，整数规划模型用于表征订单信息中的待搬运的货物的种类和数量和货架信息中的承载的货物的种类和数量与待搬运的货架的关系，以及车辆信息中的车位置和货架信息中的货架位置与搬运成本之间的关系。
在一些实施例中，车辆确定单元进一步用于：确定使整数规划模型中搬运成本最低时的待搬运的货架的货架号和用于搬运待搬运的货架的车辆的车号。
在一些实施例中，该装置还包括：更新单元，用于获取正在搬运货架的车辆的车辆信息，并根据订单信息更新正在搬运货架的车辆所搬运的货架所承载的货物的种类和数量；接收单元，用于响应于接收到新的订单信息，确定更新后的货物的种类和数量是否与新的订单信息匹配；修改单元，用于当更新后的货物的种类和数量新的订单信息匹配时，修正整数规划模型中的搬运成本并重新确定使修正后的整数规划模型中搬运成本最低时的待搬运的货架的货架号和用于搬运待搬运的货架的车辆的车号，并向重新确定出的车号对应的车辆发送用于搬运重新确定出的货架号对应的货架的指令。
在一些实施例中，车辆确定单元包括：转换子单元，用于基于遗传算法将车辆的车号转换成染色体的基因位点，并将货架的货架号转换成染色体的基因；随机子单元，用于生成随机数并确定随机数所在的适应度值区间；选择子单元，用于采用适应度比例装置从适应度值区间选取候选染色体集合；交叉子单元，用于对所选取的候选染色体集合中的染色体进行交叉处理；变异子单元，用于对交叉处理后的候选染色体集合中的染色体进行变异处理得到目标染色体；提取子单元，用于从目标染色体中提取车辆的车号和货架的货架号。
在一些实施例中，变异子单元进一步用于：在对交叉处理后的候选染色体集合中的染色体进行变异处理得到目标染色体之后，根据交叉处理后的候选染色体集合中的染色体对目标染色体进行修正。
在一些实施例中，转换子单元进一步用于：当车辆的数量大于货架的数量时，生成虚拟的货架号作为染色体的基因位点；当车辆的数量小于货架的数量时，生成虚拟的车号作为染色体的基因。
第三方面，本申请实施例提供了一种设备，包括：一个或多个处理器；存储装置，用于存储一个或多个程序，当一个或多个程序被一个或多个处理器执行，使得一个或多个处理器实现如第一方面中任一的方法。
第四方面，本申请实施例提供了一种计算机可读存储介质，其上存储有计算机程序，其特征在于，该程序被处理器执行时实现如第一方面中任一的方法。
本申请实施例提供的货物搬运方法和装置，通过根据所有出库订单需求、所有资源(货架上库存货物及车辆等)等情况，为所有订单合理分配资源(货架和车辆)，以达到总搬运成本最低、机器人占用数最少的目标效果，即保证出库效率的前提下，“机器人人效”最大化。
附图说明
通过阅读参照以下附图所作的对非限制性实施例所作的详细描述，本申请的其它特征、目的和优点将会变得更明显：
图1是本申请可以应用于其中的示例性系统架构图；
图2是根据本申请的货物搬运方法的一个实施例的流程图；
图3是根据本申请的货物搬运方法的一个应用场景的示意图；
图4是根据本申请的货物搬运方法的又一个实施例的流程图；
图5是根据本申请的货物搬运装置的一个实施例的结构示意图；
图6是适于用来实现本申请实施例的服务器的计算机系统的结构示意图。
具体实施方式
下面结合附图和实施例对本申请作进一步的详细说明。可以理解的是，此处所描述的具体实施例仅仅用于解释相关发明，而非对该发明的限定。另外还需要说明的是，为了便于描述，附图中仅示出了与有关发明相关的部分。
需要说明的是，在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互组合。下面将参考附图并结合实施例来详细说明本申请。
图1示出了可以应用本申请的货物搬运方法或货物搬运装置的实施例的示例性系统架构100。
如图1所示，系统架构100可以包括终端设备101、102，服务器103，车辆104、105、106，货架107、108、109和工作台110。终端设备101、102和服务器103之间，车辆104、105、106和服务器103之间，通过网络连接，网络可以包括各种连接类型，例如有线、无线 通信链路或者光纤电缆等等。
用户可以使用终端设备101、102通过网络与服务器103交互，以接收或发送消息等。终端设备101、102、103上可以安装有各种通讯客户端应用，例如网页浏览器应用、购物类应用、搜索类应用、即时通信工具、邮箱客户端、社交平台软件等。例如，用户通过终端设备101、102的购物类应用发送订单信息给服务器103。服务器103指示车辆和工作台按照订单拣货，并在拣货完毕后更新订单的物流状态以便终端设备101、102查询。
车辆104、105、106用于将货架107、108、109搬运到工作台110，并由工作台110根据订单信息中的货物的各类和数量从货架上取下相应种类和数量的货物。
服务器103可以是提供各种服务的服务器，例如对终端设备101、102上显示的物流信息提供支持的物流服务器。物流服务器可以对接收到的订单请求等数据进行分析等处理，按照订单信息选取待搬运的货架和车辆，在车辆将货架搬至工作台并分拣完货物后，将处理结果(例如物流状态)反馈给终端设备。
需要说明的是，本申请实施例所提供的货物搬运方法一般由服务器103执行，相应地，货物搬运装置一般设置于服务器103中。
应该理解，图1中的终端设备、服务器、车辆、货架和工作台的数目仅仅是示意性的。根据实现需要，可以具有任意数目的终端设备、服务器、车辆、货架、工作台。
继续参考图2，示出了根据本申请的货物搬运方法的一个实施例的流程200。该货物搬运方法，包括以下步骤：
步骤201，获取车辆信息集合、货架信息集合和订单信息。
在本实施例中，货物搬运方法运行于其上的电子设备(例如图1所示的服务器)可以通过有线连接方式或者无线连接方式从用户利用其进行网络购物的终端接收订单信息，订单信息包括待搬运的货物的种类和数量，例如，待搬运货物A一件，货物B两件。并获取静止的或者行驶中的车辆的车辆信息，车辆信息包括车号、车位置，车号按自然数编号，例如，1、2、3……。并获取货架信息，货架信息包括货 架号、货架位置、承载的货物的种类和数量，货架号也是按自然数从1开始编号。货架承载的货物的种类和订单信息中的种类是按相同的规则分类的。车位置可以是动态变化的，货架信息中承载的货物的种类和数量也是动态变化的。工作台的位置不变，因此车位置和货架位置可以是绝对位置也可以是相对于工作台的位置。通过它们三者之间的位置关系，可以确定搬运货架时车辆的行走路线。
步骤202，根据订单信息中的待搬运的货物的种类和数量、各货架信息中的承载的货物的种类和数量确定待搬运的货架集合。
在本实施例中，为了减少搬运成本，需要为每个货架最多指派一辆车进行搬运，每辆车最多服务一个货架。根据货架上的货物的库存量满足情况及订单信息，逐个货物定位，尽量让多个订单定位到相同货架上(尽量少的货架可以覆盖尽量多的订单)。
举例：已知订单001信息及货架HJ001、货架HJ002、货架HJ003、货架HJ004的库存情况，需要决策订单定位到哪几个货架上。
订单001
货物 数量  
Sku_A 5  
Sku_B 4  
Sku_C 6  
表1
库存
货架HJ001
货物 数量
Sku_A 10
Sku_D 20
Sku_E 15
表2
货架HJ002
货物 数量
Sku_B 10
Sku_F 15
表3
货架HJ003
货物 数量
Sku_C 10
Sku_H 15
表4
货架HJ004
货物 数量
Sku_A 15
Sku_B 15
Sku_C 20
表5
可以先定位货物Sku_A，选取包含货物Sku_A、库存量满足且库存量最小、已被定位的货架，得到货架HJ001。再定位货物Sku_B，选取包含货物Sku_B、库存量满足且库存量最小、已被定位的货架，得到货架HJ002。再定位货物Sku_C，选取包含货物Sku_C、库存量满足且库存量最小、已被定位的货架，得到货架HJ003。即共定位了3个货架(HJ001,HJ002,HJ003)满足订单001订单需求。
步骤203，根据各车辆信息中的车位置和各货架信息中的货架位置，从待搬运的货架集合中确定搬运成本最小的待搬运的货架的货架号和车辆的车号。
在本实施例中，搬运成本为搬运货架过程中耗费的电量或者油量，搬运成本与搬运路线长度成正比。为货架指派附近车辆(距离货架最近的车辆)执行搬运任务，送至工作台。使用最短路算法(例如Dijkstra(迪杰斯特拉)算法)计算仓库任意两点之间最短距离，从而找到距离货架最近的车辆，并进行指派。举例：逐个为货架HJ001、HJ002、HJ003推荐距离货架最近的车辆的车号01、车号02、车号03，搬运成本(车到货架+货架到工作站)分别是3、2、2，从而此次调度的总搬运成本是7。
步骤204，向确定出的车号对应的车辆发送用于搬运确定出的货架号对应的货架的指令。
在本实施例中，分别向上例中的车辆车号01、车号02、车号03发送搬运货架HJ001、HJ002、HJ003的指令。车辆车号01、车号02、车号03接收搬运指令后去搬运对应的货架到工作台进行货物分拣。
继续参见图3，图3是根据本实施例的货物搬运方法的应用场景的一个示意图。在图3的应用场景中，服务器301获取了订单信息、车辆302、303、304的信息，货架305、306、307的信息。根据步骤202-203确定出车辆302、303、304需要分别搬运货架305、306、307。然后服务器301分别向车辆302、303、304发送搬运货架305、306、307的指令，使得车辆302、303、304将货架305、306、307按照最短路线将货架305、306、307搬运到工作台308。
本申请的上述实施例提供的方法通过将订单分给尽量少的货架，并指派距离最近的车辆搬运货架，从而降低了搬运成本，并提高了货物的分拣速度，提高整个物流配送过程的工作效率。
进一步参考图4，其示出了货物搬运方法的又一个实施例的流程400。该货物搬运方法的流程400，包括以下步骤：
步骤401，获取车辆信息集合、货架信息集合和订单信息。
步骤401与步骤201基本相同，因此不再赘述。
步骤402，利用车辆信息集合、货架信息集合和订单信息建立整数规划模型。
在本实施例中，规划中的变量(全部或部分)限制为整数，称为整数规划。若在线性模型中，变量限制为整数，则称为整数线性规划。整数规划模型用于表征订单信息中的待搬运的货物的种类和数量和货架信息中的承载的货物的种类和数量与待搬运的货架的关系，以及车辆信息中的车位置和货架信息中的货架位置与搬运成本之间的关系。整数规划模型可表现为组合最优化问题或0—1规划问题，这两者都是在有限个可供选择的方案中，寻找满足一定约束的最好方案。约束条件可为：约束每个货架最多被指派一辆车、约束每辆车最多服务一个货架；约束正在被出库搬运中的货架库存可参与定位，但车-货架匹配 关系不可变更，即搬运中的货架可以被出库定位，但不能换车；约束尽量满足货物s的订单需求。该整数规划模型可以确定：
①哪个货架被订单需求定位，及应从货架取下的货物的种类和数量；
②哪个货架被指派哪台车服务。
可保证这一批订单需求的总搬运成本最小、机器人占用数最少的目标效果。即保证出库效率的前提下，“机器人人效”最大化。
可选的，整数规划模型可如下式所示：
1)参数
m：小车总数量。
n：订单任务中每种货物s在库存中的货架总数量。
I：所有小车的集合，I＝{1,2,...,m}。
J：所有货架的集合，J＝{1,2,...,n}。
S：订单任务中每种货物s的集合，s∈S。
J s：包含货物s的所有货架集合。
d js：货架j上货物s的库存量，j∈J,s∈S。
U s：货物s的需求出库量，将整个工作区的需求出库量按订单需
求的货物s做汇总，得到每种货物s的需求出库量。
C ij：车i行走至货架j所需耗的搬运成本，i∈I,j∈J。
D j：货架j被搬运到工作台的搬运成本。
I c：(i,l)∈I c，表示车i正在搬运货架j，且库存为出库搬运中状态。
A 1：权值，用于平衡“距离最短”与“货架数最少”。
A 2：权值，用于平衡“距离最短”与“货架数最少”。
2)决策变量
Figure PCTCN2018080458-appb-000001
当小车i服务于货架j时，x ij＝1；其他情况，x ij＝0
3)数学模型
Figure PCTCN2018080458-appb-000002
约束条件：
Figure PCTCN2018080458-appb-000003
其中j∈J；            (2-2)
Figure PCTCN2018080458-appb-000004
其中i∈I；            (2-3)
Figure PCTCN2018080458-appb-000005
其中(i,l)∈I c；             (2-4)
Figure PCTCN2018080458-appb-000006
其中
Figure PCTCN2018080458-appb-000007
x ij＝{0,1},其中i∈I；j∈J；          (2-6)
其中，z s为每种货物s的松驰系数，式(2-1)是目标函数，表示最小化搬运总成本、最小化匹配货架数(使用搬运小车辆数)。同时，尽量满足每个货物的订单需求。即达到用最少的“人(搬运机器人)”做最多的事的优化目标。
式(2-2)约束为每个货架最多被指派一辆车。
式(2-3)约束为每辆车最多服务一个货架。
式(2-4)约束为正在被出库搬运中的货架库存可参与定位，但车-货架匹配关系不可变更。即搬运中的货架可以被出库定位，但不能换车。
式(2-5)约束为尽量满足货物s的订单需求。
式(2-6)约束了决策变量的取值范围：当小车i服务于货架j时，x ij＝1；其他情况，x ij＝0。
步骤203，确定使整数规划模型中搬运成本最低时的待搬运的货架的货架号和用于搬运待搬运的货架的车辆的车号。
在本实施例中，解整数规划通常可以逐步生成一个相关的问题，称它是原问题的衍生问题。对每个衍生问题又伴随一个比它更易于求解的松弛问题(衍生问题称为松弛问题的源问题)。通过松弛问题的解来确定它的源问题的归宿，即源问题应被舍弃，还是再生成一个或多个它本身的衍生问题来替代它。随即，再选择一个尚未被舍弃的或替代的原问题的衍生问题，重复以上步骤直至不再剩有未解决的衍生问题为止。可采用分支定界法、割平面法或匈牙利方法等方法，确定使整数规划模型中搬运成本最低时的待搬运的货架的货架号和用于搬运 待搬运的货架的车辆的车号。
在本实施例的一些可选的实现方式中，可通过遗传算法确定使整数规划模型中搬运成本最低时的待搬运的货架的货架号和用于搬运待搬运的货架的车辆的车号。遗传算法(Genetic Algorithm)是模拟达尔文生物进化论的自然选择和遗传学机理的生物进化过程的计算模型，是一种通过模拟自然进化过程搜索最优解的方法。
具体过程如下所示：
1)基于遗传算法将车辆的车号转换成染色体的基因位点，并将货架的货架号转换成染色体的基因。
比如对于解“车号1-货架号3，车号2-货架号1，车号3-货架号2”的编码为(3,1,2)。
当车辆的数量大于货架的数量时，生成虚拟的货架号作为染色体的基因位点；当车辆的数量小于货架的数量时，生成虚拟的车号作为染色体的基因。车总数和货架总数不相等时，补充虚拟车号(或虚拟货架号)，以方便后续遗传运算时，不丢失可行解。被轮到虚拟车(或虚拟货架)的货架(或车)代表货架(或车)被轮空，即此次决策中没有匹配关系。
比如，
当车总数为4>货架总数为3时，对于解“车号1-货架号3，车号2-货架号1，车号4-货架号2”的编码为(3,1,4,2)，其中“车号3被轮到虚拟货架4”代表此次决策中“车号3不搬运任何货架”。
当车总数为3<货架总数为4时，对于解“车号1-货架号3，车号2-货架号1，车号3-货架号4”的编码为(3,1,4,2)，其中“货架2被轮到虚拟车号4”代表此次决策中“货架不被定位搬运”。
2)生成随机数并确定随机数所在的适应度值区间。
如果遗传算法计算未达到停止准则，例如，最大迭代次数500，或最优解变化百分比低于阈值1％，则生成随机数。随机数可以是0-1之间的小数。适应度函数为目标函数(式2-1)的倒数。
3)采用适应度比例方法从适应度值区间选取候选染色体集合。
从群体中选择优胜的个体，淘汰劣质个体的操作叫选择。选择算 子有时又称为再生算子(reproduction operator)。选择的目的是把优化的个体(或解)直接遗传到下一代或通过配对交叉产生新的个体再遗传到下一代。选择操作是建立在群体中个体的适应度评估基础上的，目前常用的选择算子有以下几种：适应度比例方法、随机遍历抽样法、局部选择法。其中轮盘赌选择法(roulette wheel selection)是最简单也是最常用的选择方法。在该方法中，各个个体的选择概率和其适应度值成比例。概率反映了个体的适应度在整个群体的个体适应度总和中所占的比例。个体适应度越大。其被选择的概率就越高、反之亦然。计算出群体中各个个体的选择概率后，为了选择交配个体，需要进行多轮选择。每一轮产生一个[0，1]之间均匀随机数，将该随机数作为选择指针来确定被选个体。个体被选后，可随机地组成交配对，以供后面的交叉操作。
4)对所选取的候选染色体集合中的染色体进行交叉处理。
在自然界生物进化过程中起核心作用的是生物遗传基因的重组(加上变异)。同样，遗传算法中起核心作用的是遗传操作的交叉算子。所谓交叉是指把两个父代个体的部分结构加以替换重组而生成新个体的操作。通过交叉，遗传算法的搜索能力得以飞跃提高。交叉算子根据交叉率将种群中的两个个体随机地交换某些基因，能够产生新的基因组合，期望将有益基因组合在一起。例如，设定交叉概率P c＝0.9，选择父代进行交叉运算，并采用双切点交叉。
5)对交叉处理后的候选染色体集合中的染色体进行变异处理得到目标染色体。
变异的基本内容是对群体中的个体串的某些基因座上的基因值作变动。遗传算法引入变异的目的有两个：一是使遗传算法具有局部的随机搜索能力。当遗传算法通过交叉算子已接近最优解邻域时，利用变异算子的这种局部随机搜索能力可以加速向最优解收敛。显然，此种情况下的变异概率应取较小值，否则接近最优解的积木块会因变异而遭到破坏。二是使遗传算法可维持群体多样性，以防止出现未成熟收敛现象。此时收敛概率应取较大值。例如，可将子代基因按照小概率扰动产生变化。变异后，需对染色体进行可行性修正。比如(3,1, 4,2)→ 变异:(3,1, 2,2)→可行性修正:(3,1,2, 4)。由于变异后出现两个2，这是不可行的，因此将其中一个2修正为4。
6)从目标染色体中提取车辆的车号和货架的货架号。染色体的基因位点表示车号，对应基因表示对应车号的货架号。
通过步骤5)得到的(3,1,2, 4)可提取出车号与货架的对应关系：车号1-货架3，车号2-货架1，车号3-货架2，车号4-货架4。
在本实施例的一些可选的实现方式中，该方法还包括：获取正在搬运货架的车辆的车辆信息，并根据订单信息更新正在搬运货架的车辆所搬运的货架所承载的货物的种类和数量；响应于接收到新的订单信息，确定更新后的货物的种类和数量是否与新的订单信息匹配；若匹配，则修正整数规划模型中的搬运成本并重新确定使修正后的整数规划模型中搬运成本最低时的待搬运的货架的货架号和用于搬运待搬运的货架的车辆的车号，并向重新确定出的车号对应的车辆发送用于搬运重新确定出的货架号对应的货架的指令。例如，根据原订单，车1搬运货货架3从而取得货物A2件，货架3上原承载10件货物A，被搬运后更新货架3上的货物A的数量为8件。此时如果收到新的订单，要搬运货物A4件，则无需再指定其它车辆搬运其它货架，而直接从正被搬运的货架3上取出4件即可。为了避免车辆在生产区(高频交通区)来回游走，从而浪费道路资源情况，希望出库搬运中的货架被优先定位。可通过修正货架搬运成本D j→0.3*D j的方式，获得优先定位出库搬运中货架的最优决策。
从图4中可以看出，与图2对应的实施例相比，本实施例中的货物搬运方法的流程400突出了确定搬运成本最小的待搬运的货架的货架号和车辆的车号的步骤。由此，本实施例描述的方案可以引入更快、更准确地确定出车辆与货架的对应关系，使得搬运成本最小化。
进一步参考图5，作为对上述各图所示方法的实现，本申请提供了一种货物搬运装置的一个实施例，该装置实施例与图2所示的方法实施例相对应，该装置具体可以应用于各种电子设备中。
如图5所示，本实施例的货物搬运装置500包括：获取单元501、货架确定单元502、车辆确定单元503和发送单元504。其中，获取单 元501用于获取车辆信息集合、货架信息集合和订单信息，其中，车辆信息包括车号、车位置，货架信息包括货架号、货架位置、承载的货物的种类和数量，订单信息包括待搬运的货物的种类和数量；货架确定单元502用于根据订单信息中的待搬运的货物的种类和数量、各货架信息中的承载的货物的种类和数量确定待搬运的货架集合；车辆确定单元503用于根据各车辆信息中的车位置和各货架信息中的货架位置，从待搬运的货架集合中确定搬运成本最小的待搬运的货架的货架号和车辆的车号；发送单元504用于向确定出的车号对应的车辆发送用于搬运确定出的货架号对应的货架的指令。
在本实施例中，货物搬运500的获取单元501、货架确定单元502、车辆确定单元503和发送单元504的具体处理可以参考图2对应实施例中的步骤201、步骤202、步骤203、步骤204。
在本实施例的一些可选的实现方式中，货架确定单元502进一步用于：利用车辆信息集合、货架信息集合和订单信息建立整数规划模型，其中，整数规划模型用于表征订单信息中的待搬运的货物的种类和数量和货架信息中的承载的货物的种类和数量与待搬运的货架的关系，以及车辆信息中的车位置和货架信息中的货架位置与搬运成本之间的关系。
在本实施例的一些可选的实现方式中，车辆确定单元503进一步用于：确定使整数规划模型中搬运成本最低时的待搬运的货架的货架号和用于搬运待搬运的货架的车辆的车号。
在本实施例的一些可选的实现方式中，装置500还包括：更新单元(未示出)，用于获取正在搬运货架的车辆的车辆信息，并根据订单信息更新正在搬运货架的车辆所搬运的货架所承载的货物的种类和数量；接收单元(未示出)，用于响应于接收到新的订单信息，确定更新后的货物的种类和数量是否与新的订单信息匹配；修改单元(未示出)，用于当更新后的货物的种类和数量新的订单信息匹配时，修正整数规划模型中的搬运成本并重新确定使修正后的整数规划模型中搬运成本最低时的待搬运的货架的货架号和用于搬运待搬运的货架的车辆的车号，并向重新确定出的车号对应的车辆发送用于搬运重新确定出的货 架号对应的货架的指令。
在本实施例的一些可选的实现方式中，车辆确定单元503包括：转换子单元，用于基于遗传算法将车辆的车号转换成染色体的基因位点，并将货架的货架号转换成染色体的基因；随机子单元，用于生成随机数并确定随机数所在的适应度值区间；选择子单元，用于采用适应度比例装置从适应度值区间选取候选染色体集合；交叉子单元，用于对所选取的候选染色体集合中的染色体进行交叉处理；变异子单元，用于对交叉处理后的候选染色体集合中的染色体进行变异处理得到目标染色体；提取子单元，用于从目标染色体中提取车辆的车号和货架的货架号。
在本实施例的一些可选的实现方式中，变异子单元进一步用于：在对交叉处理后的候选染色体集合中的染色体进行变异处理得到目标染色体之后，根据交叉处理后的候选染色体集合中的染色体对目标染色体进行修正。
在本实施例的一些可选的实现方式中，转换子单元进一步用于：当车辆的数量大于货架的数量时，生成虚拟的货架号作为染色体的基因位点；当车辆的数量小于货架的数量时，生成虚拟的车号作为染色体的基因。
下面参考图6，其示出了适于用来实现本申请实施例的服务器的计算机系统600的结构示意图。图6示出的服务器仅仅是一个示例，不应对本申请实施例的功能和使用范围带来任何限制。
如图6所示，计算机系统600包括中央处理单元(CPU)601，其可以根据存储在只读存储器(ROM)602中的程序或者从存储部分608加载到随机访问存储器(RAM)603中的程序而执行各种适当的动作和处理。在RAM 603中，还存储有系统600操作所需的各种程序和数据。CPU 601、ROM 602以及RAM 603通过总线604彼此相连。输入/输出(I/O)接口605也连接至总线604。
以下部件连接至I/O接口605：包括键盘、鼠标等的输入部分606；包括诸如阴极射线管(CRT)、液晶显示器(LCD)等以及扬声器等的输出部分607；包括硬盘等的存储部分608；以及包括诸如LAN卡、 调制解调器等的网络接口卡的通信部分609。通信部分609经由诸如因特网的网络执行通信处理。驱动器610也根据需要连接至I/O接口605。可拆卸介质611，诸如磁盘、光盘、磁光盘、半导体存储器等等，根据需要安装在驱动器610上，以便于从其上读出的计算机程序根据需要被安装入存储部分608。
特别地，根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信部分609从网络上被下载和安装，和/或从可拆卸介质611被安装。在该计算机程序被中央处理单元(CPU)601执行时，执行本申请的方法中限定的上述功能。需要说明的是，本申请所述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本申请中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本申请中，计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读的信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：无线、电线、光缆、RF等 等，或者上述的任意合适的组合。
附图中的流程图和框图，图示了按照本申请各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本申请实施例中所涉及到的单元可以通过软件的方式实现，也可以通过硬件的方式来实现。所描述的单元也可以设置在处理器中，例如，可以描述为：一种处理器包括获取单元、货架确定单元、车辆确定单元和发送单元。其中，这些单元的名称在某种情况下并不构成对该单元本身的限定，例如，获取单元还可以被描述为“获取车辆信息集合、货架信息集合和订单信息的单元”。
作为另一方面，本申请还提供了一种计算机可读介质，该计算机可读介质可以是上述实施例中描述的装置中所包含的；也可以是单独存在，而未装配入该装置中。上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该装置执行时，使得该装置：获取车辆信息集合、货架信息集合和订单信息，其中，车辆信息包括车号、车位置，货架信息包括货架号、货架位置、承载的货物的种类和数量，订单信息包括待搬运的货物的种类和数量；根据订单信息中的待搬运的货物的种类和数量、各货架信息中的承载的货物的种类和数量确定待搬运的货架集合；根据各车辆信息中的车位置和各货架信息中的货架位置，从待搬运的货架集合中确定搬运成本最小的待搬运的货架的货架号和车辆的车号；向确定出的车号对应的车辆发送用于搬运确定出的货架号对应的货架的指令。
以上描述仅为本申请的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本申请中所涉及的发明范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离所述发明构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本申请中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。

Claims (16)

  1. 一种货物搬运方法，其特征在于，所述方法包括：
    获取车辆信息集合、货架信息集合和订单信息，其中，车辆信息包括车号、车位置，货架信息包括货架号、货架位置、承载的货物的种类和数量，订单信息包括待搬运的货物的种类和数量；
    根据所述订单信息中的待搬运的货物的种类和数量、各货架信息中的承载的货物的种类和数量确定待搬运的货架集合；
    根据各车辆信息中的车位置和各货架信息中的货架位置，从所述待搬运的货架集合中确定搬运成本最小的待搬运的货架的货架号和车辆的车号；
    向确定出的车号对应的车辆发送用于搬运确定出的货架号对应的货架的指令。
  2. 根据权利要求1所述的方法，其特征在于，所述根据所述订单信息中的待搬运的货物的种类和数量、各货架信息中的承载的货物的种类和数量确定待搬运的货架集合，包括：
    利用所述车辆信息集合、所述货架信息集合和所述订单信息建立整数规划模型，其中，所述整数规划模型用于表征订单信息中的待搬运的货物的种类和数量和货架信息中的承载的货物的种类和数量与待搬运的货架的关系，以及车辆信息中的车位置和货架信息中的货架位置与搬运成本之间的关系。
  3. 根据权利要求2所述的方法，其特征在于，所述根据各车辆信息中的车位置和各货架信息中的货架位置，从所述待搬运的货架集合中确定搬运成本最小的待搬运的货架的货架号和车辆的车号，包括：
    确定使所述整数规划模型中搬运成本最低时的待搬运的货架的货架号和用于搬运所述待搬运的货架的车辆的车号。
  4. 根据权利要求3所述的方法，其特征在于，所述方法还包括：
    获取正在搬运货架的车辆的车辆信息，并根据所述订单信息更新所述正在搬运货架的车辆所搬运的货架所承载的货物的种类和数量；
    响应于接收到新的订单信息，确定更新后的货物的种类和数量是否与所述新的订单信息匹配；
    若匹配，则修正所述整数规划模型中的搬运成本并重新确定使修正后的整数规划模型中搬运成本最低时的待搬运的货架的货架号和用于搬运所述待搬运的货架的车辆的车号，并向重新确定出的车号对应的车辆发送用于搬运重新确定出的货架号对应的货架的指令。
  5. 根据权利要求3或4所述的方法，其特征在于，所述确定使所述整数规划模型中搬运成本最低时的待搬运的货架的货架号和用于搬运所述待搬运的货架的车辆的车号，包括：
    基于遗传算法将车辆的车号转换成染色体的基因位点，并将货架的货架号转换成染色体的基因；
    生成随机数并确定所述随机数所在的适应度值区间；
    采用适应度比例方法从所述适应度值区间选取候选染色体集合；
    对所选取的候选染色体集合中的染色体进行交叉处理；
    对交叉处理后的候选染色体集合中的染色体进行变异处理得到目标染色体；
    从所述目标染色体中提取车辆的车号和货架的货架号。
  6. 根据权利要求5所述的方法，其特征在于，在对交叉处理后的候选染色体集合中的染色体进行变异处理得到目标染色体之后，所述方法还包括：
    根据所述交叉处理后的候选染色体集合中的染色体对所述目标染色体进行修正。
  7. 根据权利要求5所述的方法，其特征在于，基于遗传算法将车辆的车号转换成染色体的基因位点，并将货架的货架号转换成染色体的基因，包括：
    当车辆的数量大于货架的数量时，生成虚拟的货架号作为染色体的基因位点；
    当车辆的数量小于货架的数量时，生成虚拟的车号作为染色体的基因。
  8. 一种货物搬运装置，其特征在于，所述装置包括：
    获取单元，用于获取车辆信息集合、货架信息集合和订单信息，其中，车辆信息包括车号、车位置，货架信息包括货架号、货架位置、承载的货物的种类和数量，订单信息包括待搬运的货物的种类和数量；
    货架确定单元，用于根据所述订单信息中的待搬运的货物的种类和数量、各货架信息中的承载的货物的种类和数量确定待搬运的货架集合；
    车辆确定单元，用于根据各车辆信息中的车位置和各货架信息中的货架位置，从所述待搬运的货架集合中确定搬运成本最小的待搬运的货架的货架号和车辆的车号；
    发送单元，用于向确定出的车号对应的车辆发送用于搬运确定出的货架号对应的货架的指令。
  9. 根据权利要求8所述的装置，其特征在于，所述货架确定单元进一步用于：
    利用所述车辆信息集合、所述货架信息集合和所述订单信息建立整数规划模型，其中，所述整数规划模型用于表征订单信息中的待搬运的货物的种类和数量和货架信息中的承载的货物的种类和数量与待搬运的货架的关系，以及车辆信息中的车位置和货架信息中的货架位置与搬运成本之间的关系。
  10. 根据权利要求9所述的装置，其特征在于，所述车辆确定单元进一步用于：
    确定使所述整数规划模型中搬运成本最低时的待搬运的货架的货架号和用于搬运所述待搬运的货架的车辆的车号。
  11. 根据权利要求10所述的装置，其特征在于，所述装置还包括：
    更新单元，用于获取正在搬运货架的车辆的车辆信息，并根据所述订单信息更新所述正在搬运货架的车辆所搬运的货架所承载的货物的种类和数量；
    接收单元，用于响应于接收到新的订单信息，确定更新后的货物的种类和数量是否与所述新的订单信息匹配；
    修改单元，用于当更新后的货物的种类和数量所述新的订单信息匹配时，修正所述整数规划模型中的搬运成本并重新确定使修正后的整数规划模型中搬运成本最低时的待搬运的货架的货架号和用于搬运所述待搬运的货架的车辆的车号，并向重新确定出的车号对应的车辆发送用于搬运重新确定出的货架号对应的货架的指令。
  12. 根据权利要求10或11所述的装置，其特征在于，所述车辆确定单元包括：
    转换子单元，用于基于遗传算法将车辆的车号转换成染色体的基因位点，并将货架的货架号转换成染色体的基因；
    随机子单元，用于生成随机数并确定所述随机数所在的适应度值区间；
    选择子单元，用于采用适应度比例装置从所述适应度值区间选取候选染色体集合；
    交叉子单元，用于对所选取的候选染色体集合中的染色体进行交叉处理；
    变异子单元，用于对交叉处理后的候选染色体集合中的染色体进行变异处理得到目标染色体；
    提取子单元，用于从所述目标染色体中提取车辆的车号和货架的货架号。
  13. 根据权利要求12所述的装置，其特征在于，所述变异子单元进一步用于：
    在对交叉处理后的候选染色体集合中的染色体进行变异处理得到目标染色体之后，根据所述交叉处理后的候选染色体集合中的染色体对所述目标染色体进行修正。
  14. 根据权利要求12所述的装置，其特征在于，所述转换子单元进一步用于：
    当车辆的数量大于货架的数量时，生成虚拟的货架号作为染色体的基因位点；
    当车辆的数量小于货架的数量时，生成虚拟的车号作为染色体的基因。
  15. 一种设备，包括：
    一个或多个处理器；
    存储装置，用于存储一个或多个程序，
    当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现如权利要求1-7中任一所述的方法。
  16. 一种计算机可读存储介质，其上存储有计算机程序，其特征在于，该程序被处理器执行时实现如权利要求1-7中任一所述的方法。
PCT/CN2018/080458 2017-04-27 2018-03-26 货物搬运方法和装置 Ceased WO2018196525A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710287833.4 2017-04-27
CN201710287833.4A CN108805316B (zh) 2017-04-27 2017-04-27 货物搬运方法和装置

Publications (1)

Publication Number Publication Date
WO2018196525A1 true WO2018196525A1 (zh) 2018-11-01

Family

ID=63918019

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/080458 Ceased WO2018196525A1 (zh) 2017-04-27 2018-03-26 货物搬运方法和装置

Country Status (2)

Country Link
CN (1) CN108805316B (zh)
WO (1) WO2018196525A1 (zh)

Cited By (27)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109598444A (zh) * 2018-12-05 2019-04-09 北京极智嘉科技有限公司 货物分发方法、系统、控制服务器及计算机存储介质
CN110533279A (zh) * 2019-07-15 2019-12-03 合肥工业大学 用于调度云物流平台运力的方法、系统及存储介质
CN110580606A (zh) * 2019-09-12 2019-12-17 东方钢铁电子商务有限公司 铁路运输数据的匹配方法
CN110992129A (zh) * 2019-11-18 2020-04-10 浙江大搜车软件技术有限公司 车辆订单匹配方法、装置、计算机设备和存储介质
CN111080187A (zh) * 2019-11-13 2020-04-28 北京旷视机器人技术有限公司 订单分配方法、装置、计算机设备和存储介质
CN111598499A (zh) * 2020-04-08 2020-08-28 北京旷视机器人技术有限公司 订单分配策略的确定方法、装置及电子设备
CN111612387A (zh) * 2019-02-26 2020-09-01 顺丰科技有限公司 一种流向分配方法、装置、设备和存储介质
CN111652407A (zh) * 2020-04-13 2020-09-11 北京旷视机器人技术有限公司 仓库中的任务处理方法、装置、介质、电子设备与系统
CN111768136A (zh) * 2019-06-10 2020-10-13 北京京东尚科信息技术有限公司 库存调度方法和装置
CN111800900A (zh) * 2019-04-01 2020-10-20 罗伯特·博世有限公司 用于操作轨道引导系统的方法
CN111832802A (zh) * 2020-04-15 2020-10-27 北京旷视机器人技术有限公司 控制货品搬运车辆的方法、装置、系统、设备及介质
CN112330235A (zh) * 2020-03-04 2021-02-05 北京沃东天骏信息技术有限公司 用于库存管理的数据处理方法、装置、电子设备及介质
CN112396139A (zh) * 2019-08-13 2021-02-23 北京京东乾石科技有限公司 一种货架进场的方法和装置
CN112678409A (zh) * 2020-12-24 2021-04-20 深圳市海柔创新科技有限公司 货物处理方法、装置、设备、系统、存储介质及程序产品
CN112966911A (zh) * 2021-02-25 2021-06-15 杭州拼便宜网络科技有限公司 物品运输方法、装置、电子设备和计算机可读介质
CN113065820A (zh) * 2021-03-25 2021-07-02 北京京东乾石科技有限公司 信息生成方法、装置、电子设备和计算机可读介质
CN113240226A (zh) * 2021-03-05 2021-08-10 中国人民解放军61096部队 一种卫星地面站间的资源分配方法及装置
CN113759893A (zh) * 2020-10-15 2021-12-07 北京京东乾石科技有限公司 用于搬运物品的方法和装置
CN113792902A (zh) * 2020-11-30 2021-12-14 北京京东振世信息技术有限公司 商品的出库方法及相关设备
CN114417696A (zh) * 2021-12-07 2022-04-29 长春工业大学 一种基于遗传算法的自动化立体仓库货位分配优化方法
CN114429243A (zh) * 2021-12-28 2022-05-03 北京百度网讯科技有限公司 卸车流程方案生成方法、装置、存储介质和电子设备
CN114493156A (zh) * 2021-12-30 2022-05-13 深圳云天励飞技术股份有限公司 物流搬运方法、装置、电子设备及存储介质
CN114817534A (zh) * 2022-04-21 2022-07-29 深圳市升蓝物流有限公司 一种基于大数据的物流管理系统及其方法
CN115115256A (zh) * 2022-07-15 2022-09-27 南京邮电大学 一种医药仓库货位分配方法
CN115330552A (zh) * 2022-08-12 2022-11-11 墨点狗智能科技（东莞）有限公司 多参数融合排产决策方法、系统、存储介质及电子设备
CN115759657A (zh) * 2022-11-24 2023-03-07 北京航空航天大学杭州创新研究院 仓库搬运车调度方法及装置、计算机设备和可读存储介质
WO2023226756A1 (zh) * 2022-05-25 2023-11-30 北京旷视机器人技术有限公司 设备调度方法、电子设备及存储介质

Families Citing this family (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111861295B (zh) * 2019-04-28 2024-05-24 北京京东乾石科技有限公司 货物搬运的方法和装置
CN110334949B (zh) * 2019-07-05 2023-05-30 辽宁省交通高等专科学校 一种用于仓库agv数量评估的仿真方法
CN113496327B (zh) * 2020-03-20 2024-12-03 北京旷视机器人技术有限公司 货物搬运方法、装置、系统、控制终端及计算机存储介质
CN113450041A (zh) * 2020-03-25 2021-09-28 日日顺供应链科技股份有限公司 一种物流园区订单管理系统
CN113495557A (zh) * 2020-04-03 2021-10-12 北京京东乾石科技有限公司 确定目标设备数量的方法和装置
CN111340405A (zh) * 2020-05-20 2020-06-26 北京云迹科技有限公司 一种订单配送方法、设备和计算机可读存储介质
CN112085441A (zh) * 2020-08-27 2020-12-15 北京每日优鲜电子商务有限公司 信息生成方法、装置、电子设备和计算机可读介质
CN112036773B (zh) * 2020-09-29 2023-08-15 劢微机器人科技(深圳)有限公司 Agv小车任务分配方法、设备、存储介质及装置
CN114638566B (zh) * 2020-12-16 2024-09-06 南京福佑在线电子商务有限公司 车辆任务配置方法及装置
CN113393022B (zh) * 2021-05-31 2022-05-31 武汉港迪智能技术有限公司 一种物料库区多行车协同作业方法
CN113793096A (zh) * 2021-09-05 2021-12-14 杭州拼便宜网络科技有限公司 供货仓库商品下架规划方法、装置、电子设备和存储介质
CN114399240A (zh) * 2021-12-06 2022-04-26 杭州拼便宜网络科技有限公司 轨迹生成方法、装置、电子设备和计算机可读介质
CN114596042A (zh) * 2022-05-10 2022-06-07 卡奥斯工业智能研究院(青岛)有限公司 一种货物运输的方法、装置、电子设备及存储介质
CN115649722B (zh) * 2022-12-26 2023-04-14 浙江凯乐士科技集团股份有限公司 仓储车辆的调度方法及装置

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101968860A (zh) * 2010-10-09 2011-02-09 北京物资学院 订单拣选方法及系统
CN103593751A (zh) * 2013-11-29 2014-02-19 中国建筑第八工程局有限公司 基于rfid的智能物流管理系统
CN105469201A (zh) * 2015-07-20 2016-04-06 浙江工业大学 一种物流配送中心作业任务处理与调度的方法

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103473616B (zh) * 2013-09-17 2016-06-08 四川航天系统工程研究所 用于处理多品种物资仓储的动态货位分配规划方法与系统
JP6310579B2 (ja) * 2015-02-09 2018-04-11 株式会社日立製作所 搬送システム、搬送システムに用いられるコントローラ、および、搬送方法
CN104809606B (zh) * 2015-04-29 2018-05-04 上海交通大学 具有多导引车调度分配功能的仓库管理系统

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101968860A (zh) * 2010-10-09 2011-02-09 北京物资学院 订单拣选方法及系统
CN103593751A (zh) * 2013-11-29 2014-02-19 中国建筑第八工程局有限公司 基于rfid的智能物流管理系统
CN105469201A (zh) * 2015-07-20 2016-04-06 浙江工业大学 一种物流配送中心作业任务处理与调度的方法

Cited By (34)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109598444A (zh) * 2018-12-05 2019-04-09 北京极智嘉科技有限公司 货物分发方法、系统、控制服务器及计算机存储介质
CN109598444B (zh) * 2018-12-05 2020-10-23 北京极智嘉科技有限公司 货物分发方法、系统、控制服务器及计算机存储介质
CN111612387A (zh) * 2019-02-26 2020-09-01 顺丰科技有限公司 一种流向分配方法、装置、设备和存储介质
CN111800900A (zh) * 2019-04-01 2020-10-20 罗伯特·博世有限公司 用于操作轨道引导系统的方法
CN111768136A (zh) * 2019-06-10 2020-10-13 北京京东尚科信息技术有限公司 库存调度方法和装置
CN110533279B (zh) * 2019-07-15 2023-01-06 合肥工业大学 用于调度云物流平台运力的方法、系统及存储介质
CN110533279A (zh) * 2019-07-15 2019-12-03 合肥工业大学 用于调度云物流平台运力的方法、系统及存储介质
CN112396139A (zh) * 2019-08-13 2021-02-23 北京京东乾石科技有限公司 一种货架进场的方法和装置
CN110580606A (zh) * 2019-09-12 2019-12-17 东方钢铁电子商务有限公司 铁路运输数据的匹配方法
CN110580606B (zh) * 2019-09-12 2023-11-07 上海欧冶供应链有限公司 铁路运输数据的匹配方法
CN111080187A (zh) * 2019-11-13 2020-04-28 北京旷视机器人技术有限公司 订单分配方法、装置、计算机设备和存储介质
CN110992129A (zh) * 2019-11-18 2020-04-10 浙江大搜车软件技术有限公司 车辆订单匹配方法、装置、计算机设备和存储介质
CN112330235A (zh) * 2020-03-04 2021-02-05 北京沃东天骏信息技术有限公司 用于库存管理的数据处理方法、装置、电子设备及介质
CN111598499A (zh) * 2020-04-08 2020-08-28 北京旷视机器人技术有限公司 订单分配策略的确定方法、装置及电子设备
CN111598499B (zh) * 2020-04-08 2023-08-29 北京旷视机器人技术有限公司 订单分配策略的确定方法、装置及电子设备
CN111652407A (zh) * 2020-04-13 2020-09-11 北京旷视机器人技术有限公司 仓库中的任务处理方法、装置、介质、电子设备与系统
CN111652407B (zh) * 2020-04-13 2023-09-05 北京旷视机器人技术有限公司 仓库中的任务处理方法、装置、介质、电子设备与系统
CN111832802A (zh) * 2020-04-15 2020-10-27 北京旷视机器人技术有限公司 控制货品搬运车辆的方法、装置、系统、设备及介质
CN113759893A (zh) * 2020-10-15 2021-12-07 北京京东乾石科技有限公司 用于搬运物品的方法和装置
CN113792902A (zh) * 2020-11-30 2021-12-14 北京京东振世信息技术有限公司 商品的出库方法及相关设备
CN112678409A (zh) * 2020-12-24 2021-04-20 深圳市海柔创新科技有限公司 货物处理方法、装置、设备、系统、存储介质及程序产品
CN112678409B (zh) * 2020-12-24 2024-04-02 深圳市海柔创新科技有限公司 货物处理方法、装置、设备、系统、存储介质及程序产品
CN112966911A (zh) * 2021-02-25 2021-06-15 杭州拼便宜网络科技有限公司 物品运输方法、装置、电子设备和计算机可读介质
CN113240226A (zh) * 2021-03-05 2021-08-10 中国人民解放军61096部队 一种卫星地面站间的资源分配方法及装置
CN113065820A (zh) * 2021-03-25 2021-07-02 北京京东乾石科技有限公司 信息生成方法、装置、电子设备和计算机可读介质
CN114417696A (zh) * 2021-12-07 2022-04-29 长春工业大学 一种基于遗传算法的自动化立体仓库货位分配优化方法
CN114429243A (zh) * 2021-12-28 2022-05-03 北京百度网讯科技有限公司 卸车流程方案生成方法、装置、存储介质和电子设备
CN114493156A (zh) * 2021-12-30 2022-05-13 深圳云天励飞技术股份有限公司 物流搬运方法、装置、电子设备及存储介质
CN114817534A (zh) * 2022-04-21 2022-07-29 深圳市升蓝物流有限公司 一种基于大数据的物流管理系统及其方法
WO2023226756A1 (zh) * 2022-05-25 2023-11-30 北京旷视机器人技术有限公司 设备调度方法、电子设备及存储介质
CN115115256A (zh) * 2022-07-15 2022-09-27 南京邮电大学 一种医药仓库货位分配方法
CN115330552A (zh) * 2022-08-12 2022-11-11 墨点狗智能科技（东莞）有限公司 多参数融合排产决策方法、系统、存储介质及电子设备
CN115330552B (zh) * 2022-08-12 2024-03-22 墨点狗智能科技（东莞）有限公司 多参数融合排产决策方法、系统、存储介质及电子设备
CN115759657A (zh) * 2022-11-24 2023-03-07 北京航空航天大学杭州创新研究院 仓库搬运车调度方法及装置、计算机设备和可读存储介质

Also Published As

Publication number Publication date
CN108805316B (zh) 2022-01-28
CN108805316A (zh) 2018-11-13

Similar Documents

Publication Publication Date Title
WO2018196525A1 (zh) 货物搬运方法和装置
CN110197350B (zh) 一种物品出库方法和装置
CN107235276B (zh) 货物搬运方法和装置
JP7136921B2 (ja) 商品棚を搬送する方法および装置
CN106980955B (zh) 用于输出信息的方法和装置
Dechampai et al. A differential evolution algorithm for the capacitated VRP with flexibility of mixing pickup and delivery services and the maximum duration of a route in poultry industry
CN111553548B (zh) 一种拣货方法和装置
Nastasi et al. Implementation and comparison of algorithms for multi-objective optimization based on genetic algorithms applied to the management of an automated warehouse
CN109840729B (zh) 料箱定位的方法、系统、存储介质及电子设备
CN113259144A (zh) 一种仓储网络规划方法和装置
CN113222205B (zh) 一种路径规划的方法和装置
WO2019090874A1 (zh) 一种用于货物取送的单车调度方法
CN113762664B (zh) 拣货任务的分配方法、装置及计算机可读介质
Lee et al. Winner determination problem in multiple automated guided vehicle considering cost and flexibility
CN113393193A (zh) 出库方法及装置
Ho et al. Demand-driven storage allocation for optimizing order picking processes
CN113256193B (zh) 一种仓库商品布局方法和装置
CN116523221A (zh) 一种智能仓储拣选任务的优化调度方法及系统
Abdirad et al. Three-stage algorithms for the large-scale dynamic vehicle routing problem with industry 4.0 approach
JP2025517796A (ja) 注文書割り当て方法および装置、電子機器、コンピュータ可読媒体並びにコンピュータプログラム
CN113650997B (zh) 一种物品出库定位方法和装置
CN113283826B (zh) 物品的出库方法及系统
CN118780510A (zh) 一种车辆的调度方法和装置
CN113326959B (zh) 一种优化路径的方法和装置
CN110826752A (zh) 集合单分配方法和装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18791162

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 05.02.2020)

122 Ep: pct application non-entry in european phase

Ref document number: 18791162

Country of ref document: EP

Kind code of ref document: A1