WO2021208950A1 - 订单信息处理方法、装置、计算机设备和介质 - Google Patents

订单信息处理方法、装置、计算机设备和介质 Download PDF

Info

Publication number
WO2021208950A1
WO2021208950A1 PCT/CN2021/087173 CN2021087173W WO2021208950A1 WO 2021208950 A1 WO2021208950 A1 WO 2021208950A1 CN 2021087173 W CN2021087173 W CN 2021087173W WO 2021208950 A1 WO2021208950 A1 WO 2021208950A1
Authority
WO
WIPO (PCT)
Prior art keywords
warehouse
item
warehouses
category
information
Prior art date
Application number
PCT/CN2021/087173
Other languages
English (en)
French (fr)
Inventor
康宁轩
许晔
祝捷
陆继任
赵芮
申作军
Original Assignee
北京沃东天骏信息技术有限公司
北京京东尚科信息技术有限公司
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 北京沃东天骏信息技术有限公司, 北京京东尚科信息技术有限公司 filed Critical 北京沃东天骏信息技术有限公司
Priority to US17/995,084 priority Critical patent/US20230245055A1/en
Priority to JP2022559325A priority patent/JP7423816B2/ja
Priority to KR1020227038193A priority patent/KR20230019076A/ko
Publication of WO2021208950A1 publication Critical patent/WO2021208950A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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; CALCULATING OR 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
    • G06Q10/06315—Needs-based resource requirements planning or analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G06Q10/083—Shipping
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G06Q10/083—Shipping
    • G06Q10/0834—Choice of carriers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G06Q10/083—Shipping
    • G06Q10/0834—Choice of carriers
    • G06Q10/08345—Pricing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G06Q10/083—Shipping
    • G06Q10/0835—Relationships between shipper or supplier and carriers
    • G06Q10/08355—Routing methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
    • G06Q30/0635—Processing of requisition or of purchase orders

Definitions

  • the embodiments of the present disclosure relate to the field of computer technology, and more specifically, to an order information processing method, device, computer equipment, and medium.
  • E-commerce fulfillment refers to the entire process from the generation of an order to the receipt of the ordered item by the user.
  • Merchants generally set up several distribution centers in or around the area they serve, and each distribution center may set up multiple warehouses to store items for sale.
  • the fulfillment decision is to determine one or more warehouses from the candidate warehouses as the actual fulfillment warehouse for each order, which can also be called a distribution warehouse, and deliver the specified items in the order from the determined distribution warehouse to that warehouse.
  • the delivery address specified in the order The location and inventory levels of different warehouses may vary, and the storage and distribution costs of different warehouses may also vary. Therefore, the result of the fulfillment decision will directly affect the delivery time and delivery cost, thereby affecting the user's shopping experience and the merchant's fulfillment cost.
  • the embodiments of the present disclosure provide an order information processing method and device, computer equipment, and medium to further optimize the e-commerce performance decision plan, and to determine a distribution warehouse that is more in line with actual needs for the order.
  • One aspect of the embodiments of the present disclosure provides an order information processing method, including: acquiring order information, the order information including: information of a designated address and information of at least one designated item.
  • Obtain warehouse information which includes: inventory information of multiple warehouses and delivery information of multiple warehouses. Then, use the pre-built optimization model to process the order information and warehouse information to determine at least one warehouse from the multiple warehouses as the distribution warehouse according to the output result of the optimization model, so that the sum of the first value and the second value Less than or equal to a predetermined value.
  • the first value is used to characterize the delivery time taken to deliver at least one designated item from the above-mentioned distribution warehouse to the designated address
  • the second value is used to characterize the time it takes to deliver at least one designated item from the above-mentioned distribution warehouse to the designated address. The delivery cost.
  • the information of each designated item in the above at least one designated item includes: identification information of each designated item and the required quantity of each designated item.
  • the inventory information of each of the above-mentioned multiple warehouses includes: identification information of the items stored in each warehouse and the storage quantity of each item in each warehouse.
  • the delivery information of each warehouse in the above-mentioned multiple warehouses includes: the expected delivery time length of each warehouse for the multiple addresses and the expected delivery cost of each warehouse.
  • the optimization model includes a first sub-model.
  • the foregoing processing of order information and warehouse information using the pre-built optimization model includes: using a first sub-model to perform the following operations: when at least one item of the first category exists in the at least one specified item, for each item of the first category For items, according to the identification information and the required quantity of the first category items, determine the first candidate warehouse that stores the first category items and the storage quantity is greater than or equal to the required quantity from the above-mentioned multiple warehouses, and select the first candidate warehouse from the first candidate warehouse Determine the first candidate warehouse with the shortest expected delivery time for the designated address as the pending warehouse for the first category of items. Take the respective pending warehouses of the at least one item in the first category as the output result of the first sub-model.
  • the foregoing determining at least one warehouse from a plurality of warehouses as a distribution warehouse according to the output result of the optimization model includes: when the respective pending warehouses of the at least one item of the first category are the same warehouse, determining the at least one warehouse The respective pending warehouses of the items of the first category are the respective distribution warehouses of the at least one item of the first category mentioned above.
  • the optimization model further includes a second sub-model, the second sub-model is an integer programming model, the objective function of the integer programming model represents the sum of the first value and the second value, and the integer programming model includes at least one constraint condition .
  • the foregoing processing of order information and warehouse information using the pre-built optimization model further includes: when the pending warehouses of the at least one item of the first category are not the same warehouse, based on the at least one constraint, the order information and the warehouse information , Determine at least one warehouse distribution method, wherein each warehouse distribution method includes: a distribution relationship between the at least one item of the first category and at least one warehouse in the plurality of warehouses.
  • the value ranges of the first value and the second value are determined. Based on the value range of the first value and the second value, the value of the objective function is calculated. Next, the warehouse allocation method that minimizes the value of the objective function is used as the output result of the second sub-model.
  • the above determining at least one warehouse as a distribution warehouse from a plurality of warehouses according to the output result of the optimization model further includes: determining whether the running time of the second sub-model before obtaining the output result is greater than a predetermined time. If so, it is determined that the respective pending warehouses of the at least one item of the first category are the respective distribution warehouses of the at least one item of the first category. If not, determine the respective distribution warehouse of the at least one item of the first category according to the output result of the second sub-model.
  • each of the foregoing warehouse distribution methods includes: the distribution relationship between the foregoing at least one item of the first category and M warehouses, where M is an integer greater than or equal to 1.
  • the foregoing determination of the value range of the first value and the second value based on at least one warehouse distribution method includes: for each warehouse distribution method, according to the expected delivery time of each warehouse in the M warehouses for the specified address, determine the value range for each warehouse distribution method. The first value of the warehouse allocation method. And, according to the expected distribution cost of each warehouse in the M warehouses, the second value for each warehouse distribution method is determined.
  • the aforementioned at least one constraint condition is used to limit at least one of the following: the number of distribution warehouses for each item of the first category; the storage quantity of the first category of items in the distribution warehouse of each item of the first category ; And, the number of items in the first category delivered by each warehouse.
  • the optimization model further includes a third sub-model.
  • the foregoing processing of order information and warehouse information using the pre-built optimization model further includes: using a third sub-model to perform the following operations: when at least one item of the second category exists in the at least one specified item, for each item of the second category Category items, according to the identification information of the second category items and the required quantity, a second candidate warehouse storing the second category items and the storage quantity is greater than or equal to the required quantity is determined from the above-mentioned multiple warehouses, and the second candidate warehouse is selected from the second candidate warehouse
  • the second candidate warehouse with the shortest expected delivery time for the specified address is determined in, as the delivery warehouse for the second category of items.
  • the respective distribution warehouses of the at least one item of the second category are used as the output result of the third sub-model.
  • the above-mentioned determining at least one warehouse from the plurality of warehouses as a distribution warehouse according to the output result of the optimization model further includes: determining the respective distribution of the at least one item of the second category according to the output result of the third sub-model storehouse.
  • an order information processing device including: a first acquisition module, a second acquisition module, and a model processing module.
  • the first obtaining module is used for obtaining order information, the order information including: information of a designated address and information of at least one designated item.
  • the second acquisition module is used to acquire warehouse information, which includes: inventory information of multiple warehouses and delivery information of multiple warehouses.
  • the model processing module is used to process the above-mentioned order information and warehouse information using a pre-built optimization model, so as to determine at least one warehouse from the above-mentioned multiple warehouses as a distribution warehouse according to the output result of the optimization model, so that the first value is equal to The sum of the second value is less than or equal to the predetermined value.
  • the first value is used to characterize the delivery time taken to deliver at least one designated item from the above-mentioned distribution warehouse to the designated address
  • the second value is used to characterize the time it takes to deliver at least one designated item from the above-mentioned distribution warehouse to the designated address. The delivery cost.
  • the processor executes the program, the above-mentioned method.
  • Another aspect of the embodiments of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the above-mentioned method when executed.
  • Another aspect of the embodiments of the present disclosure provides a computer program that includes computer-executable instructions, which are used to implement the above-mentioned method when executed.
  • a pre-built optimization model is used to make an order fulfillment decision.
  • the order information and warehouse information are used as input features of the optimization model, and the distribution warehouse for at least one specified item indicated by the order information is determined according to the output result of the optimization model.
  • the performance decision result of the optimization model can comprehensively weigh the delivery time and the delivery cost, so that when all the designated items indicated by the order information are delivered from the determined one or more delivery warehouses to the designated instructions, the first value and the first value representing the delivery time
  • the sum of the second numerical value representing the distribution cost is optimized as far as possible to be less than or equal to the predetermined value.
  • Fig. 1 schematically shows an exemplary system architecture of an application order information processing method and device according to an embodiment of the present disclosure
  • Fig. 2 schematically shows a flowchart of an order information processing method according to an embodiment of the present disclosure
  • FIG. 3 schematically shows an exemplary flowchart of an order information processing method according to another embodiment of the present disclosure
  • Fig. 4 schematically shows an exemplary flow chart of an order information processing method according to another embodiment of the present disclosure
  • Fig. 5 schematically shows a block diagram of an order information processing device according to an embodiment of the present disclosure.
  • Fig. 6 schematically shows a block diagram of a computer device according to an embodiment of the present disclosure.
  • At least one of the “systems” shall include, but is not limited to, systems having A alone, B alone, C alone, A and B, A and C, B and C, and/or systems having A, B, C, etc. ).
  • At least one of the “systems” shall include, but is not limited to, systems having A alone, B alone, C alone, A and B, A and C, B and C, and/or systems having A, B, C, etc. ).
  • the order information processing method may include a first acquisition process, a second acquisition process, and a model processing process.
  • first obtaining process order information is obtained, and the order information includes: information of a designated address and information of at least one designated item.
  • second acquisition process warehouse information is acquired, and the warehouse information includes: inventory information of multiple warehouses and delivery information of multiple warehouses.
  • the model processing process is carried out, and the above-mentioned order information and warehouse information are processed using the pre-built optimization model, so as to determine at least one warehouse from the above-mentioned multiple warehouses as the distribution warehouse according to the output result of the optimization model, so that the first value and the first value The sum of the two values is less than or equal to the predetermined value.
  • the first value is used to characterize the delivery time taken to deliver at least one designated item from the above-mentioned distribution warehouse to the designated address
  • the second value is used to characterize the time it takes to deliver at least one designated item from the above-mentioned distribution warehouse to the designated address. The delivery cost.
  • E-commerce fulfillment refers to the entire process from the generation of an order to the receipt of the ordered item by the user.
  • Merchants generally set up several distribution centers in or around the area they serve, and each distribution center may set up multiple warehouses to store items for sale.
  • the fulfillment decision is to determine one or more warehouses from the candidate warehouses as the actual fulfillment warehouse for each order, which can also be called a distribution warehouse, and deliver the specified items in the order from the determined distribution warehouse to that warehouse.
  • the delivery address specified in the order is to determine one or more warehouses from the candidate warehouses as the actual fulfillment warehouse for each order.
  • the choice of a distribution warehouse will directly affect the timeliness of user receipt, that is, the delivery time.
  • the choice of the distribution warehouse will also affect the distribution cost. For example, multiple items shipped from the same warehouse can be combined into one package, thereby reducing logistics costs.
  • the storage and distribution costs of different warehouses will also vary. Therefore, the result of the fulfillment decision will directly affect the delivery time and delivery cost, thereby affecting the user's shopping experience and the merchant's fulfillment cost.
  • the existing performance decision-making scheme is mainly based on preset rules, and the priority of the warehouse is preset according to the user-specified receiving address or the purchased item category.
  • priority is given to the high-priority storehouse.
  • the fulfillment decision will give priority to the warehouse that can satisfy all the items in the order. If a warehouse that meets the above conditions is not found, the order will be split into several sub-orders based on the preset order splitting algorithm, each of which contains part of the original order, and then a performance decision will be made for each sub-order separately.
  • the above scheme cannot comprehensively weigh user experience and contract performance costs.
  • the priority of each warehouse is based on presets, and does not fully reflect the length of the delivery time. Even if a warehouse with a high priority is selected, it is not necessarily the warehouse with the shortest delivery time, and delivery costs are not considered.
  • the warehouse will be selected as the distribution warehouse for all items in the order, and It will not consider whether the delivery time of the warehouse for the delivery address specified by the order is too long. Once the delivery time of the warehouse is too long, the user experience of the order will be extremely poor.
  • the existing order splitting algorithm cannot guarantee the balance and optimization of the delivery time and the delivery cost.
  • an order information processing method and device are provided to make an order fulfillment decision, and determine at least one warehouse from a plurality of warehouses as a distribution warehouse.
  • the order information processing method according to the embodiment of the present disclosure can comprehensively weigh the delivery time and the delivery cost in the fulfillment decision process, which not only improves the user's shopping experience, but also reduces the merchant's fulfillment cost as much as possible.
  • FIG. 1 schematically shows an exemplary system architecture 100 to which an order information processing method and device can be applied according to an embodiment of the present disclosure. It should be noted that FIG. 1 is only an example of the system architecture to which the embodiments of the present disclosure can be applied to help those skilled in the art understand the technical content of the embodiments of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used. For other equipment, systems, environments or scenarios.
  • a system architecture 100 may include terminal devices 101, 102, and 103, a network 104 and a server 105.
  • the network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105.
  • the network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, and so on.
  • the terminal devices 101, 102, and 103 communicate with the server 105 through the network 104 to receive or send messages and the like.
  • Terminal devices 101, 102, 103 can install client applications with various functions, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only examples) .
  • the terminal devices 101, 102, 103 may be various electronic devices, including but not limited to car navigation, smart phones, tablet computers, laptop portable computers, desktop computers, and so on.
  • the server 105 may be a server that provides various services, for example, a background management server that provides support for various client applications in the terminal devices 101, 102, and 103.
  • the background management server can receive the request message sent by the terminal device 101, 102, 103, perform analysis and processing on the received request message, and respond to the response result of the request message (for example, obtaining or processing the generated web page according to the request message, Information, or data, etc.) are fed back to the terminal devices 101, 102, 103, and the terminal devices 101, 102, 103 output these response results to the user.
  • the order information processing method according to the embodiment of the present disclosure can be implemented in the terminal equipment 101, 102, 103, and accordingly, the order information processing apparatus according to the embodiment of the present disclosure can be set in the terminal equipment 101, 102, 103 middle.
  • the order information processing method according to the embodiment of the present disclosure may also be implemented in the server 105, and accordingly, the order information processing apparatus according to the embodiment of the present disclosure may be set in the server 105.
  • the order information processing method according to the embodiment of the present disclosure can also be implemented in other computer equipment capable of communicating with the terminal equipment 101, 102, 103 and/or the server 105. Accordingly, the order information processing apparatus according to the embodiment of the present disclosure It can be set in other computer devices capable of communicating with the terminal devices 101, 102, 103 and/or the server 105.
  • terminal devices, networks, and servers in FIG. 1 are merely illustrative. According to actual needs, there can be any number and any type of terminal devices, networks and servers.
  • an order information processing method is provided.
  • the method will be exemplarily described below with a legend. It should be noted that the sequence number of each operation in the following method is only used as a representation of the operation for description purposes, and should not be regarded as indicating the execution order of each operation. Unless explicitly indicated, the method does not need to be executed exactly in the order shown.
  • Fig. 2 schematically shows a flowchart of an order information processing method according to an embodiment of the present disclosure.
  • the method may include operation S210 to operation S230.
  • the order information includes: information of a designated address and information of at least one designated item.
  • warehouse information is acquired.
  • the warehouse information includes: inventory information of multiple warehouses and delivery information of multiple warehouses.
  • the above-mentioned order information and warehouse information are processed using a pre-built optimization model, so as to determine at least one warehouse from the above-mentioned multiple warehouses as a distribution warehouse according to the output result of the optimization model.
  • the first numerical value is used to characterize the delivery time taken to deliver at least one designated item indicated by the order information from the delivery warehouse to the designated address, and the delivery time can be from the time the order is generated to the order The length of time it takes for all the designated items indicated by the information to be delivered to the designated address, or the delivery time may be the length of time it takes from the start of delivery to when all the designated items indicated by the order information are delivered to the designated address.
  • the second value is used to characterize the delivery cost of delivering at least one designated item indicated by the order information from the delivery warehouse to the designated address.
  • the delivery cost represents the cost that the merchant needs to spend in the delivery process, and may include order information, for example.
  • the foregoing distribution warehouse determined from a plurality of warehouses according to the output result of the optimization model can make the sum of the first value and the second value less than or equal to the predetermined value.
  • the order information processing method utilizes a pre-built optimization model to make an order fulfillment decision.
  • the order information and warehouse information are used as input features of the optimization model, and the distribution warehouse for at least one specified item indicated by the order information is determined according to the output result of the optimization model.
  • the performance decision result of the optimization model can comprehensively weigh the delivery time and the delivery cost, so that when all the designated items indicated by the order information are delivered from the determined one or more delivery warehouses to the designated instructions, the first value and the first value representing the delivery time
  • the sum of the second numerical value representing the distribution cost is optimized as far as possible to be less than or equal to the predetermined value.
  • the information of each designated item in the at least one designated item may include: identification information of each designated item and the required quantity of each designated item.
  • the inventory information of each warehouse in the above-mentioned multiple warehouses may include: identification information of the items stored in each warehouse and the storage quantity of each item in each warehouse.
  • the delivery information of each warehouse in the above-mentioned multiple warehouses may include: the expected delivery time length of each warehouse for the multiple addresses and the expected delivery cost of each warehouse.
  • the designated item or the identification information of the item may be a SKU (Stock Keeping Unit) number.
  • the expected delivery time of a warehouse to an address can represent the expected time it takes to deliver items from the warehouse to the address.
  • the expected delivery cost of a warehouse can represent the expected cost of the warehouse to deliver a package.
  • a package can be packaged by one or more items, and each item can include one or more items.
  • the expected delivery time of each warehouse for any address can be obtained by statistics based on the historical delivery time data of the warehouse for the address, or predicted based on the historical delivery time data of the warehouse for other addresses near the address;
  • the expected distribution cost of a warehouse can also be calculated based on historical distribution cost data.
  • the warehouse information may further include identification information of each of a plurality of warehouses.
  • FIG. 3 schematically shows an exemplary flow chart of an order information processing method according to another embodiment of the present disclosure, and is used to illustrate that operation S230 uses a pre-built optimization model to process the order information and warehouse information according to the optimization model.
  • the output result of at least one warehouse from the above-mentioned multiple warehouses is determined as an example implementation process of a distribution warehouse.
  • the method may include operations S231 to S235.
  • operation S231 it is determined whether there is at least one item of the first category among the at least one specified item indicated by the order information. If yes, perform operation S232. If not, return to the start state.
  • the items of the first category can be set as required.
  • items in the first category can refer to all items that need to be packaged, and can be referred to as "non-original packaged items", that is, items that are not directly delivered according to the original packaging. If there is an item of the first category among the at least one designated item indicated by the order information, the possibility that part or all of the at least one designated item will be combined and packaged needs to be considered in the process of making the performance decision.
  • the order information includes the identification information "A" of the item A of the first category and the required quantity M of the item A of the first category.
  • one or more first candidate warehouses for the item A of the first category are determined from a plurality of warehouses.
  • Each determined first candidate warehouse stores the first category item A, and the storage quantity of the first category item A stored in each first candidate warehouse is greater than or equal to the first category item indicated by the aforementioned order information A's demand quantity M.
  • the foregoing process of determining the first candidate warehouse may be, for example, performing a matching search in the inventory information of multiple warehouses according to the identification information "A", and determining the warehouse with the identification information "A" in the inventory information.
  • the first candidate warehouse with the shortest expected delivery time length for the designated address is determined from the above-mentioned first candidate warehouses as the pending warehouse for the first category of items.
  • this operation S233 determines the expected delivery time length of each of the first candidate warehouses for the designated address indicated by the order information according to the respective delivery information of the first candidate warehouses determined above.
  • the first candidate warehouse with the shortest expected delivery time for the designated address is taken as the pending warehouse for the first category of items.
  • the order information indicates the designated address L and the first category item A, and it is determined through operation S232 that the first candidate warehouse of the first category item A includes warehouses D 1 , D 2, and D 3 .
  • the expected delivery time of warehouse D 1 for the designated address L is t 1
  • the expected delivery time of warehouse D 2 for the designated address L is t2
  • warehouse D 3 is for designated The expected delivery time of address L is t 3 . If t 2 ⁇ t 1 ⁇ t 3 , the warehouse D 2 is determined to be the pending warehouse of the first category of goods A.
  • the order information also indicates other first-category items, the pending warehouse for each first-category item can be determined according to the above logic.
  • the optimization model may include a first sub-model.
  • the foregoing operations S231 to S233 may be performed by using the first sub-model, and the respective pending warehouses of the at least one item of the first category are used as the output result of the first sub-model.
  • operation S234 it is determined whether the pending warehouses of the at least one item of the first category are the same warehouse. If yes, perform operation S235.
  • the output result of the first sub-model indicates that the pending warehouse of at least one item of the first category in the order information is the same warehouse
  • the same warehouse can provide at least one item of the first category at the same time.
  • the same warehouse serves as a distribution warehouse for the at least one item of the first category, and the items of the first category can be packaged into the same package to reduce the delivery cost.
  • this operation S234 may determine the distribution warehouse of at least one item of the first category indicated by the order information according to the output result of the first sub-model, and use the pending warehouse as the distribution warehouse.
  • the optimization model may further include a second sub-model, and the second sub-model is an integer programming model.
  • the objective function of the integer programming model can represent the sum of the first value and the second value, that is, the sum of the delivery time and the delivery cost, and the integer programming model includes at least one constraint condition.
  • the above-mentioned operation S230 uses a pre-built optimization model to process the above-mentioned order information and warehouse information, so as to determine at least one warehouse from the above-mentioned multiple warehouses as a distribution warehouse according to the output result of the optimization model. It may also include operation S236. ⁇ S239.
  • each warehouse distribution method may include: the distribution relationship between the at least one item of the first category and at least one warehouse in the plurality of warehouses.
  • each determined warehouse distribution method may include: the distribution relationship between the first-category item A 1 and one of the multiple warehouses, The distribution relationship between the first category item A 2 and one warehouse in the plurality of warehouses, and the distribution relationship between the first category item A 3 and one warehouse in the plurality of warehouses.
  • the value of the objective function is calculated based on the at least one warehouse allocation method described above.
  • the warehouse allocation method that minimizes the value of the objective function is used as the output result of the second sub-model.
  • the embodiment of the present disclosure may determine the value range of the first numerical value and the second numerical value based on at least one warehouse allocation method described above. Based on the value range of the first value and the second value, the value of the objective function is calculated. Next, the warehouse allocation method that minimizes the value of the objective function is used as the output result of the second sub-model.
  • each of the foregoing warehouse distribution methods may include: the distribution relationship between the foregoing at least one item of the first category and M warehouses, where M is an integer greater than or equal to 1.
  • the foregoing determination of the value range of the first value and the second value based on at least one warehouse distribution method includes: for each warehouse distribution method, according to the expected delivery time of each warehouse in the M warehouses for the specified address, determine the value range for each warehouse distribution method. The first value of the warehouse allocation method. And, according to the expected distribution cost of each warehouse in the M warehouses, the second value for each warehouse distribution method is determined.
  • an integer programming model can be set as shown in formulas (1) to (7).
  • formula (1) expresses that the goal of the integer programming model is to minimize the objective function.
  • Formulas (2) to (7) show the constraint conditions of the integer programming model.
  • i represents the SKU number of the item
  • I is the set of SKU numbers of all specified items in the order information.
  • j represents the number of the warehouse
  • J is a collection of multiple warehouses.
  • t j represents the expected delivery time of warehouse j.
  • n i represents the required quantity of the specified item i indicated by the order information.
  • n represents the total quantity of all specified items indicated by the order information.
  • w is a weight.
  • the weight can, for example, represent the expected delivery cost of a package delivered by any warehouse, and the same or different weights can be set for different warehouses.
  • the value of Y j is used to characterize whether there is a designated item delivered by warehouse j in the order information.
  • the formula (1) characterizes the minimization of the average expected delivery time and the average expected delivery cost.
  • the average expected delivery cost is equal to the weighted sum of the number of orders.
  • the constraint condition of formula (2) restricts that each item (for example, uniquely identified by SKU number) can only be delivered by a warehouse capable of satisfying all the required quantities of the item.
  • the constraint of formula (3) restricts each item to be delivered by only one warehouse.
  • the constraints of formulas (4) and (5) restrict a warehouse to deliver at least one item before it can become an actual delivery warehouse.
  • the constraints of formulas (6) and (7) restrict X ij and Y j to be variables in the interval [0-1].
  • the above at least one constraint condition is used to limit at least one of the following: the number of distribution warehouses for each item of the first category; the distribution warehouse of each item of the first category in the first category The number of storage; and, the number of items of the first category delivered by each warehouse.
  • the integer programming model several warehouse distribution methods can be limited. Within this limited range, the optimal output result can be determined according to the objective function.
  • operation S238 it is determined whether the running duration of the second sub-model before obtaining the output result is greater than the predetermined duration. If yes, return to perform operation S235. If not, perform operation S239.
  • the respective distribution warehouses of the at least one item of the first category are determined according to the output result of the second sub-model.
  • operation S239 may be performed as follows: In operation S2391, it is determined whether the output result of the second sub-model is better than the output result of the first sub-model. If yes, perform operation S2392. If not, return to perform operation S235. In operation S2392, the warehouse allocation mode for which the output result of the second sub-model is targeted is used to determine the respective distribution warehouses of the at least one item of the first category.
  • FIG. 4 schematically shows an exemplary flow chart of an order information processing method according to another embodiment of the present disclosure, which is used to illustrate that operation S230 uses a pre-built optimization model to process the order information and warehouse information according to the optimization model.
  • the output result is another example implementation process of determining at least one warehouse as a distribution warehouse from the above-mentioned multiple warehouses.
  • the method may include operations S2310 to S2312.
  • operation S2310 it is determined whether there is at least one item of the second category among the at least one specified item. If yes, perform operation S2311. If not, return to the start state.
  • the second category of items can be set as needed.
  • the second category items can refer to all items that do not need to be packaged, and can be called "original package items", that is, items that can be directly distributed according to the original packaging. If there are items of the second category in at least one designated item indicated by the order information, the possibility that these items of the second category are combined and packaged may not be considered in the process of making the performance decision.
  • the second candidate warehouse with the shortest expected delivery time for the designated address is determined from the second candidate warehouses as the delivery warehouse for the second category of items.
  • the foregoing operations S2311 to S2312 have the same implementation principles as the foregoing operations S232 to S233, and will not be repeated here. After determining the second candidate warehouse with the shortest expected delivery time for an item of the second category, it can be directly used as the distribution warehouse for the item of the second category.
  • the optimization model may further include a third sub-model.
  • the above operations S2310 to S2312 may be performed by using the third sub-model, and the respective distribution warehouses of at least one item of the second category determined above are used as the output result of the third sub-model. Therefore, the respective distribution warehouses of at least one item of the second category can be determined according to the output result of the third sub-model.
  • Fig. 5 schematically shows a block diagram of an order information processing device according to an embodiment of the present disclosure.
  • the order information processing apparatus 500 may include: a first acquisition module 510, a second acquisition module 520, and a model processing module 530.
  • the first obtaining module 510 is configured to obtain order information, and the order information includes: information of a designated address and information of at least one designated item.
  • the second acquisition module 520 is used to acquire warehouse information, which includes: inventory information of multiple warehouses and delivery information of multiple warehouses.
  • the model processing module 530 is used to process the above-mentioned order information and warehouse information by using a pre-built optimization model to determine at least one warehouse from the above-mentioned multiple warehouses as a distribution warehouse according to the output result of the optimization model, so that the first value and the first value The sum of the two values is less than or equal to the predetermined value.
  • the first value is used to characterize the delivery time taken to deliver at least one designated item from the above-mentioned distribution warehouse to the designated address
  • the second value is used to characterize the time it takes to deliver at least one designated item from the above-mentioned distribution warehouse to the designated address.
  • the delivery cost is used to process the above-mentioned order information and warehouse information by using a pre-built optimization model to determine at least one warehouse from the above-mentioned multiple warehouses as a distribution warehouse according to the output result of the optimization model, so that the first value and the first value The sum of the two values is less than or equal to the predetermined value.
  • the first value is
  • any number of the modules, sub-modules, units, and sub-units, or at least part of the functions of any number of them may be implemented in one module. Any one or more of the modules, sub-modules, units, and sub-units according to the embodiments of the present disclosure may be split into multiple modules for implementation.
  • any one or more of the modules, sub-modules, units, and sub-units according to the embodiments of the present disclosure may be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), System-on-chip, system-on-substrate, system-on-package, application-specific integrated circuit (ASIC), or can be implemented by hardware or firmware in any other reasonable way that integrates or encapsulates the circuit, or by software, hardware, and firmware. Any one of these implementations or an appropriate combination of any of them can be implemented.
  • one or more of the modules, sub-modules, units, and sub-units according to the embodiments of the present disclosure may be at least partially implemented as a computer program module, and when the computer program module is executed, the corresponding function may be performed.
  • any number of the first acquisition module 510, the second acquisition module 520, and the model processing module 530 can be combined into one module for implementation, or any one of them can be split into multiple modules. Or, at least part of the functions of one or more of these modules may be combined with at least part of the functions of other modules and implemented in one module.
  • At least one of the first acquisition module 510, the second acquisition module 520, and the model processing module 530 may be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), programmable logic Array (PLA), system on chip, system on substrate, system on package, application specific integrated circuit (ASIC), or any other reasonable way to integrate or package the circuit, or other hardware or firmware, or by software , Hardware, and firmware, or any combination of any of them.
  • FPGA field programmable gate array
  • PLA programmable logic Array
  • ASIC application specific integrated circuit
  • at least one of the first acquisition module 510, the second acquisition module 520, and the model processing module 530 may be at least partially implemented as a computer program module, and when the computer program module is run, it may perform a corresponding function.
  • Fig. 6 schematically shows a block diagram of a computer device suitable for implementing the above-described model training method and/or mapping method according to an embodiment of the present disclosure.
  • the computer device shown in FIG. 6 is only an example, and should not bring any limitation to the function and scope of use of the embodiments of the present disclosure.
  • a computer device 600 includes a processor 601, which can be loaded into a random access memory (RAM) 603 according to a program stored in a read only memory (ROM) 602 or from a storage part 608 The program executes various appropriate actions and processing.
  • the processor 601 may include, for example, a general-purpose microprocessor (for example, a CPU), an instruction set processor and/or a related chipset and/or a special-purpose microprocessor (for example, an application specific integrated circuit (ASIC)), and so on.
  • the processor 601 may also include on-board memory for caching purposes.
  • the processor 601 may include a single processing unit or multiple processing units for executing different actions of a method flow according to an embodiment of the present disclosure.
  • the processor 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604.
  • the processor 601 executes various operations of the method flow according to the embodiments of the present disclosure by executing programs in the ROM 602 and/or RAM 603. It should be noted that the program can also be stored in one or more memories other than ROM 602 and RAM 603.
  • the processor 601 may also execute various operations of the method flow according to the embodiments of the present disclosure by executing programs stored in the one or more memories.
  • the device 600 may further include an input/output (I/O) interface 605, and the input/output (I/O) interface 605 is also connected to the bus 604.
  • the device 600 may also include one or more of the following components connected to the I/O interface 605: an input part 606 including a keyboard, a mouse, etc.; including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker
  • the output section 607 including the hard disk and the like; the storage section 608 including the hard disk and the like; and the communication section 609 including the network interface card such as a LAN card, a modem, and the like.
  • the communication section 609 performs communication processing via a network such as the Internet.
  • the driver 610 is also connected to the 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, etc., is installed on the drive 610 as needed, so that the computer program read from it is installed into the storage part 608 as needed.
  • the method flow according to the embodiment of the present disclosure may be implemented as a computer software program.
  • an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program contains program code for executing the method shown in the flowchart.
  • the computer program may be downloaded and installed from the network through the communication part 609, and/or installed from the removable medium 611.
  • the computer program is executed by the processor 601
  • the above-mentioned functions defined in the system of the embodiment of the present disclosure are executed.
  • the systems, devices, devices, modules, units, etc. described above may be implemented by computer program modules.
  • the embodiments of the present disclosure also provide a computer-readable storage medium.
  • the computer-readable storage medium may be included in the device/device/system described in the above-mentioned embodiments; or it may exist alone without being assembled into the Equipment/device/system.
  • the foregoing computer-readable storage medium carries one or more programs, and when the foregoing one or more programs are executed, the model training method and/or the map drawing method according to the embodiments of the present disclosure are implemented.
  • the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but not limited to: portable computer disk, hard disk, random access memory (RAM), read-only memory (ROM) , Erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • the computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.
  • the computer-readable storage medium may include one or more memories other than the ROM 602 and/or RAM 603 and/or ROM 602 and RAM 603 described above.
  • each block in the flowchart or block diagram may represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more for realizing the specified logic function.
  • Executable instructions may also occur in a different order from the order marked in the drawings. For example, two blocks shown one after another can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved.
  • each block in the block diagram or flowchart, and the combination of blocks in the block diagram or flowchart can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by It is realized by a combination of dedicated hardware and computer instructions.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Theoretical Computer Science (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Game Theory and Decision Science (AREA)
  • Educational Administration (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本公开提供了一种订单信息处理方法，包括：获取订单信息，该订单信息包括：指定地址的信息和至少一项指定物品的信息。获取仓库信息，该仓库信息包括：多个仓库的库存信息和多个仓库的配送信息。然后，利用预先构建的优化模型对上述订单信息和仓库信息进行处理，以根据优化模型的输出结果从上述多个仓库中确定至少一个仓库作为配送仓库，从而使得第一数值与第二数值之和小于等于预定值。其中，第一数值用于表征将至少一项指定物品从上述配送仓库配送至指定地址所花费的配送时长，第二数值用于表征将至少一项指定物品从上述配送仓库配送至指定地址所花费的配送费用。本公开还提供了订单信息处理装置、计算机设备和介质。

Description

订单信息处理方法、装置、计算机设备和介质 技术领域
本公开实施例涉及计算机技术领域，更具体地，涉及一种订单信息处理方法、装置、计算机设备和介质。
背景技术
随着互联网技术的快速发展，电子商务迅速兴起，各种电商平台提供了多种多样的线上商品交易渠道，极大地方便了人们的工作和生活。
电商履约，是指从订单生成开始，到用户收到订购的物品为止的全过程。商家一般会在所服务的区域内或周围设置若干个配送中心，每个配送中心下可能设置多个仓库，用来存储待售卖的物品。履约决策是指对每一订单，从候选的多个仓库中，确定一个或多个仓库作为实际履约仓库，也可称为配送仓库，将订单中的指定物品从所确定的配送仓库配送至该订单所指定的收货地址。不同仓库的位置和库存水平等均可能有所差异，并且，不同仓库的仓储和配送成本也会存在差异。因此，履约决策的结果，会直接影响配送时长和配送费用，从而影响用户的购物体验和商家的履约成本。
发明内容
有鉴于此，本公开实施例提供了一种订单信息处理方法及装置、计算机设备和介质，以进一步优化电商履约决策方案，针对订单确定更符合实际需求的配送仓库。
本公开实施例的一个方面提供了一种订单信息处理方法，包括：获取订单信息，该订单信息包括：指定地址的信息和至少一项指定物品的信息。获取仓库信息，该仓库信息包括：多个仓库的库存信息和多个仓库的配送信息。然后，利用预先构建的优化模型对上述订单信息和仓库信息进行处理，以根据优化模型的输出结果从上述多个仓库中确定至少一个仓库作为配送仓库，从而使得第一数值与第二数值之和小于等于预定值。其中，第一数值用于表征将至少一项指定物品从上述配送仓库配送至指定地址所花费的配送时长，第二数值用于表征将至少一项指定物品从上述配送仓库配送至指定地址所花费的配送费用。
根据本公开的实施例，上述至少一项指定物品中每项指定物品的信息 包括：每项指定物品的标识信息和每项指定物品的需求数量。上述多个仓库中每个仓库的库存信息包括：每个仓库中存储的物品的标识信息和每个仓库中每项物品的存储数量。以及，上述多个仓库中每个仓库的配送信息包括：每个仓库针对多个地址的期望配送时长和每个仓库的期望配送费用。
根据本公开的实施例，优化模型包括第一子模型。上述利用预先构建的优化模型对订单信息和仓库信息进行处理包括：利用第一子模型执行如下操作：当上述至少一项指定物品中存在至少一项第一类别物品时，针对每项第一类别物品，根据该第一类别物品的标识信息和需求数量，从上述多个仓库中确定存储有该第一类别物品、且存储数量大于等于需求数量的第一候选仓库，并从第一候选仓库中确定针对指定地址的期望配送时长最短的第一候选仓库，以作为该第一类别物品的待定仓库。将上述至少一项第一类别物品各自的待定仓库作为第一子模型的输出结果。
根据本公开的实施例，上述根据优化模型的输出结果从多个仓库中确定至少一个仓库作为配送仓库包括：当上述至少一项第一类别物品各自的待定仓库为同一仓库时，确定上述至少一项第一类别物品各自的待定仓库为上述至少一项第一类别物品各自的配送仓库。
根据本公开的实施例，优化模型还包括第二子模型，第二子模型为整数规划模型，整数规划模型的目标函数表征第一数值和第二数值之和，整数规划模型包括至少一个约束条件。上述利用预先构建的优化模型对订单信息和仓库信息进行处理还包括：当上述至少一项第一类别物品各自的待定仓库不是同一仓库时，基于上述至少一个约束条件、上述订单信息和上述仓库信息，确定至少一种仓库分配方式，其中每种仓库分配方式包括：上述至少一项第一类别物品与上述多个仓库中的至少一个仓库之间的配送关系。基于上述至少一种仓库分配方式，确定第一数值和第二数值的取值范围。再基于第一数值和第二数值的取值范围，计算目标函数的取值。接着，将使得目标函数的取值最小的仓库分配方式，作为第二子模型的输出结果。
根据本公开的实施例，上述根据优化模型的输出结果从多个仓库中确定至少一个仓库作为配送仓库还包括：确定第二子模型在得到输出结果之前的运行时长是否大于预定时长。如果是，则确定上述至少一项第一类别 物品各自的待定仓库为上述至少一项第一类别物品各自的配送仓库。如果否，则根据第二子模型的输出结果确定上述至少一项第一类别物品各自的配送仓库。
根据本公开的实施例，上述每种仓库分配方式包括：上述至少一项第一类别物品与M个仓库之间的配送关系，M为大于等于1的整数。上述基于至少一种仓库分配方式，确定第一数值和第二数值的取值范围包括：针对每种仓库分配方式，根据M个仓库中每个仓库针对指定地址的期望配送时长，确定针对每种仓库分配方式的第一数值。并且，根据M个仓库中每个仓库的期望配送费用，确定针对每种仓库分配方式的第二数值。
根据本公开的实施例，上述至少一个约束条件用于限制如下至少一项：每项第一类别物品的配送仓库的数量；每项第一类别物品的配送仓库中该第一类别物品的存储数量；以及，每个仓库所配送的第一类别物品的项数。
根据本公开的实施例，优化模型还包括第三子模型。上述利用预先构建的优化模型对订单信息和仓库信息进行处理还包括：利用第三子模型执行如下操作：当上述至少一项指定物品中存在至少一项第二类别物品时，针对每项第二类别物品，根据该第二类别物品的标识信息和需求数量，从上述多个仓库中确定存储有该第二类别物品、且存储数量大于等于需求数量的第二候选仓库，并从第二候选仓库中确定针对指定地址的期望配送时长最短的第二候选仓库，以作为该第二类别物品的配送仓库。将上述至少一项第二类别物品各自的配送仓库作为所述第三子模型的输出结果。
根据本公开的实施例，上述根据优化模型的输出结果从多个仓库中确定至少一个仓库作为配送仓库还包括：根据第三子模型的输出结果，确定上述至少一项第二类别物品各自的配送仓库。
本公开实施例的另一方面提供了一种订单信息处理装置，包括：第一获取模块、第二获取模块和模型处理模块。第一获取模块用于获取订单信息，该订单信息包括：指定地址的信息和至少一项指定物品的信息。第二获取模块用于获取仓库信息，该仓库信息包括：多个仓库的库存信息和多个仓库的配送信息。然后，模型处理模块用于利用预先构建的优化模型对上述订单信息和仓库信息进行处理，以根据优化模型的输出结果从上述多个仓库中确定至少一个仓库作为配送仓库，从而使得第一数值与第二数值 之和小于等于预定值。其中，第一数值用于表征将至少一项指定物品从上述配送仓库配送至指定地址所花费的配送时长，第二数值用于表征将至少一项指定物品从上述配送仓库配送至指定地址所花费的配送费用。
本公开实施例的另一方面提供了一种计算机设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述程序时实现如上所述的方法。
本公开实施例的另一方面提供了一种计算机可读存储介质，存储有计算机可执行指令，所述指令在被执行时用于实现如上所述的方法。
本公开实施例的另一方面提供了一种计算机程序，所述计算机程序包括计算机可执行指令，所述指令在被执行时用于实现如上所述的方法。
根据本公开的实施例，利用预先构建的优化模型来进行订单的履约决策。以订单信息和仓库信息作为优化模型的输入特征，根据优化模型的输出结果来确定针对订单信息所指示的至少一项指定物品的配送仓库。优化模型的履约决策结果能够综合权衡配送时长和配送费用，使得在将订单信息所指示的全部指定物品从所确定的一个或多个配送仓库配送至指定指示时，表征配送时长的第一数值和表征配送费用的第二数值的总和尽量优化至小于等于预定值。从而提高用户体验和履约成本，满足用户和商家双方的需求。
附图说明
通过以下参照附图对本公开实施例的描述，本公开实施例的上述以及其他目的、特征和优点将更为清楚，在附图中：
图1示意性示出了根据本公开实施例的应用订单信息处理方法及装置的示例性系统架构；
图2示意性示出了根据本公开实施例的订单信息处理方法的流程图；
图3示意性示出了根据本公开另一实施例的订单信息处理方法的示例流程图；
图4示意性示出了根据本公开另一实施例的订单信息处理方法的示例流程图；
图5示意性示出了根据本公开实施例的订单信息处理装置的框图；以及
图6示意性示出了根据本公开实施例的计算机设备的框图。
具体实施方式
以下，将参照附图来描述本公开的实施例。但是应该理解，这些描述只是示例性的，而并非要限制本公开实施例的范围。在下面的详细描述中，为便于解释，阐述了许多具体的细节以提供对本公开实施例的全面理解。然而，明显地，一个或多个实施例在没有这些具体细节的情况下也可以被实施。此外，在以下说明中，省略了对公知结构和技术的描述，以避免不必要地混淆本公开实施例的概念。
在此使用的术语仅仅是为了描述具体实施例，而并非意在限制本公开实施例。在此使用的术语“包括”、“包含”等表明了所述特征、步骤、操作和/或部件的存在，但是并不排除存在或添加一个或多个其他特征、步骤、操作或部件。
在此使用的所有术语(包括技术和科学术语)具有本领域技术人员通常所理解的含义，除非另外定义。应注意，这里使用的术语应解释为具有与本说明书的上下文相一致的含义，而不应以理想化或过于刻板的方式来解释。
在使用类似于“A、B和C等中至少一个”这样的表述的情况下，一般来说应该按照本领域技术人员通常理解该表述的含义来予以解释(例如，“具有A、B和C中至少一个的系统”应包括但不限于单独具有A、单独具有B、单独具有C、具有A和B、具有A和C、具有B和C、和/或具有A、B、C的系统等)。在使用类似于“A、B或C等中至少一个”这样的表述的情况下，一般来说应该按照本领域技术人员通常理解该表述的含义来予以解释(例如，“具有A、B或C中至少一个的系统”应包括但不限于单独具有A、单独具有B、单独具有C、具有A和B、具有A和C、具有B和C、和/或具有A、B、C的系统等)。
本公开的实施例提供了一种订单信息处理方法、装置、计算机设备以及介质。其中，订单信息处理方法可以包括第一获取过程、第二获取过程和模型处理过程。在第一获取过程，获取订单信息，该订单信息包括：指定地址的信息和至少一项指定物品的信息。在第二获取过程，获取仓库信息，该仓库信息包括：多个仓库的库存信息和多个仓库的配送信息。然后 进行模型处理过程，利用预先构建的优化模型对上述订单信息和仓库信息进行处理，以根据优化模型的输出结果从上述多个仓库中确定至少一个仓库作为配送仓库，从而使得第一数值与第二数值之和小于等于预定值。其中，第一数值用于表征将至少一项指定物品从上述配送仓库配送至指定地址所花费的配送时长，第二数值用于表征将至少一项指定物品从上述配送仓库配送至指定地址所花费的配送费用。
随着互联网技术的快速发展，电子商务迅速兴起，各种电商平台提供了多种多样的线上商品交易渠道，极大地方便了人们的工作和生活。电商履约，是指从订单生成开始，到用户收到订购的物品为止的全过程。商家一般会在所服务的区域内或周围设置若干个配送中心，每个配送中心下可能设置多个仓库，用来存储待售卖的物品。履约决策是指对每一订单，从候选的多个仓库中，确定一个或多个仓库作为实际履约仓库，也可称为配送仓库，将订单中的指定物品从所确定的配送仓库配送至该订单所指定的收货地址。一方面，由于不同仓库的位置和库存水平等均可能有所差异，针对配送仓库的选择会直接影响用户收货时效，即影响配送时长。另一方面，对于同一订单，针对配送仓库的选择也会影响配送成本。例如，从同一仓库发货的多个物品可以合并为一个包裹，从而减少物流费用。此外，不同仓库的仓储和配送成本也会存在差异。因此，履约决策的结果，会直接影响配送时长和配送费用，从而影响用户的购物体验和商家的履约成本。
现有履约决策方案主要基于预设规则，根据用户指定的收货地址或所购买物品品类预先设置好仓库的优先级，在对某一订单中的物品进行履约决策时，优先考虑高优先级的仓库。当一个订单包含多项物品时，履约决策时会优先考虑能满足订单中全部物品的仓库。如果未找到满足上述条件的仓库，则基于预设的拆单算法，将订单拆分为若干子单，每个子单分别包含原订单的一部分商品，再对每个子单分别进行履约决策。
以上方案无法综合权衡用户体验和履约成本。各个仓库的优先级是基于预设得到的，并不完全反映配送时长的长短。即便选择了优先级高的仓库，并不一定是配送时长最短的仓库，且并未对配送费用加以考虑。例如，在目前的履约决策方法下，对于包含多个物品的一个订单，当有且只有一个仓库能够提供订单中的所有物品时，该仓库会被选中，作为该订单所有 物品的配送仓库，而不会考虑该仓库针对该订单所指定的收货地址的费送时长是否过长。一旦该仓库的配送时长过长，会导致该订单的用户体验极差。并且，在未找到能够提供订单中所有物品的仓库时，现有的拆单算法不能保证配送时长和配送费用的平衡与优化。
根据本公开实施例，提供了一种订单信息处理方法及装置，以进行订单的履约决策，从多个仓库中确定至少一个仓库作为配送仓库。根据本公开实施例的订单信息处理方法在履约决策过程中能够综合权衡配送时长和配送费用，不仅提高用户的购物体验，同时尽量降低商家的履约成本。
图1示意性示出了根据本公开实施例的可以应用订单信息处理方法及装置的示例性系统架构100。需要注意的是，图1所示仅为可以应用本公开实施例的系统架构的示例，以帮助本领域技术人员理解本公开实施例的技术内容，但并不意味着本公开实施例不可以用于其他设备、系统、环境或场景。
如图1所示，根据本公开实施例的系统架构100可以包括终端设备101、102、103，网络104和服务器105。网络104用以在终端设备101、102、103和服务器105之间提供通信链路的介质。网络104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。
终端设备101、102、103通过网络104与服务器105进行通信，以接收或发送消息等。终端设备101、102、103上可以安装具有各种功能的客户端应用，例如购物类应用、网页浏览器应用、搜索类应用、即时通信工具、邮箱客户端、社交平台软件等(仅为示例)。
终端设备101、102、103可以是各种电子设备，包括但不限于车载导航、智能手机、平板电脑、膝上型便携计算机和台式计算机等等。
服务器105可以是提供各种服务的服务器，例如对终端设备101、102、103中的各种客户端应用提供支持的后台管理服务器。后台管理服务器可以接收终端设备101、102、103发送的请求消息，对接收到的请求消息进行分析处理等响应，并将针对该请求消息的响应结果(例如根据请求消息获取或处理生成的网页、信息、或数据等)反馈给终端设备101、102、103，终端设备101、102、103将这些响应结果输出给用户。
需要说明的是，根据本公开实施例的订单信息处理方法可以在终端设 备101、102、103中实施，相应地，根据本公开实施例的订单信息处理装置可以设置于终端设备101、102、103中。或者，根据本公开实施例的订单信息处理方法也可以在服务器105中实施，相应地，根据本公开实施例的订单信息处理装置可以设置于服务器105中。或者，根据本公开实施例的订单信息处理方法也可以在能够与终端设备101、102、103和/或服务器105通信的其它计算机设备中实施，相应地，根据本公开实施例的订单信息处理装置可以设置于能够与终端设备101、102、103和/或服务器105通信的其它计算机设备中。
应该理解，图1中的终端设备、网络和服务器的数目和类型仅仅是示意性的。根据实际需要，可以具有任意数目、任意类型的终端设备、网络和服务器。
根据本公开实施例，提供了一种订单信息处理方法。下面通过图例对该方法进行示例性说明。应注意，以下方法中各个操作的序号仅作为该操作的表示以便描述，而不应被看作表示该各个操作的执行顺序。除非明确指出，否则该方法不需要完全按照所示顺序来执行。
图2示意性示出了根据本公开实施例的订单信息处理方法的流程图。
如图2所示，该方法可以包括操作S210～操作S230。
在操作S210，获取订单信息。
其中，该订单信息包括：指定地址的信息和至少一项指定物品的信息。
在操作S220，获取仓库信息。
其中，该仓库信息包括：多个仓库的库存信息和多个仓库的配送信息。
然后，在操作S230，利用预先构建的优化模型对上述订单信息和仓库信息进行处理，以根据优化模型的输出结果从上述多个仓库中确定至少一个仓库作为配送仓库。
根据本公开的实施例，例如通过第一数值来表征将上述订单信息所指示的至少一项指定物品从上述配送仓库配送至指定地址所花费的配送时长，该配送时长可以为从订单生成至订单信息所指示的指定物品全部配送至指定地址所花费的时间长度，或者，该配送时长可以为从开始配送至订单信息所指示的指定物品全部配送至指定地址所花费的时间长度。通过第二数值来表征将上述订单信息所指示的至少一项指定物品从上述配送仓 库配送至指定地址所花费的配送费用，配送费用表示商家在配送过程中需要花费的成本，例如可以包括订单信息所指示的全部指定物品在配送过程所花费的交通费用、包裹打包费送、配送过程人工费用等一种或多种。上述根据优化模型的输出结果从多个仓库中所确定的配送仓库能够使得第一数值与第二数值之和小于等于预定值。
本领域技术人员可以理解，根据本公开实施例的订单信息处理方法利用预先构建的优化模型来进行订单的履约决策。以订单信息和仓库信息作为优化模型的输入特征，根据优化模型的输出结果来确定针对订单信息所指示的至少一项指定物品的配送仓库。优化模型的履约决策结果能够综合权衡配送时长和配送费用，使得在将订单信息所指示的全部指定物品从所确定的一个或多个配送仓库配送至指定指示时，表征配送时长的第一数值和表征配送费用的第二数值的总和尽量优化至小于等于预定值。从而提高用户体验和履约成本，满足用户和商家双方的需求。
根据本公开的实施例，上述至少一项指定物品中每项指定物品的信息可以包括：每项指定物品的标识信息和每项指定物品的需求数量。上述多个仓库中每个仓库的库存信息可以包括：每个仓库中存储的物品的标识信息和每个仓库中每项物品的存储数量。以及，上述多个仓库中每个仓库的配送信息可以包括：每个仓库针对多个地址的期望配送时长和每个仓库的期望配送费用。
例如，指定物品或物品的标识信息可以是SKU(Stock Keeping Unit，库存单位)编号。一个仓库对于一个地址的期望配送时长可以表征将物品从该仓库配送至该地址需要花费的预期时长。一个仓库的期望配送费用可以表征该仓库配送一个包裹需要花费的预期费用，一个包裹可由一项或多项物品打包得到，每项物品可以包括一件或多件。示例性地，每个仓库针对任一地址的期望配送时长可以根据该仓库针对该地址的历史配送时长数据统计得到，或者根据该仓库针对该地址附近的其他地址的历史配送时长数据预测得到；每个仓库的期望配送费用也可以根据历史配送费用数据统计得到。根据本公开的另一实施例，仓库信息还可以包括多个仓库各自的标识信息。
图3示意性示出了根据本公开另一实施例的订单信息处理方法的示例 流程图，用于说明上述操作S230利用预先构建的优化模型对上述订单信息和仓库信息进行处理，以根据优化模型的输出结果从上述多个仓库中确定至少一个仓库作为配送仓库的示例实施过程。
如图3所示，在开始执行后，该方法可以包括操作S231～S235。
在操作S231，确定订单信息所指示的至少一项指定物品中是否存在至少一项第一类别物品。如果是，则执行操作S232。如果否，则返回开始状态。
示例性地，第一类别物品可以根据需要进行设置。例如第一类别物品可以指所有需要进行打包的物品，可称为“非原包物品”，即不按照原始包装直接进行配送的物品。订单信息所指示的至少一项指定物品中如果存在第一类别物品，则在进行履约决策的过程中需要考虑到该至少一项指定物品的部分或全部被合并打包的可能性。
在操作S232，针对每项第一类别物品，根据该第一类别物品的标识信息和需求数量，从上述多个仓库中确定存储有该第一类别物品、且存储数量大于等于需求数量的第一候选仓库。
下面以任一项第一类别物品A为例进行示例性说明。订单信息中包括该第一类别物品A的标识信息“A”和该第一类别物品A的需求数量M件。针对该第一类别物品A，从多个仓库中确定一个或多个针对第一类别物品A的第一候选仓库。所确定的每个第一候选仓库均存储有该第一类别物品A，且每个第一候选仓库中所存储的第一类别物品A的存储数量大于等于上述订单信息所指示的第一类别物品A的需求数量M。上述确定第一候选仓库的过程例如可以是，根据标识信息“A”在多个仓库的库存信息中进行匹配查找，确定库存信息中包含标识信息“A”的仓库。再根据需求数量M在包含标识信息“A”的库存信息中进行匹配查找，确定库存信息中与标识信息“A”对应的存储数量大于等于M的仓库，以作为针对第一类别物品A的第一候选仓库。
在操作S233，从上述第一候选仓库中确定针对指定地址的期望配送时长最短的第一候选仓库，以作为该第一类别物品的待定仓库。
示例性地，本操作S233根据上述所确定的第一候选仓库各自的配送信息来确定第一候选仓库各自针对订单信息所指示的指定地址的期望配 送时长。将其中针对指定地址的期望配送时长最短的第一候选仓库作为第一类别物品的待定仓库。例如，订单信息指示指定地址L和第一类别物品A，通过操作S232确定第一类别物品A的第一候选仓库包括仓库D 1、D 2和D 3。根据仓库D 1、D 2和D 3各自的配送信息可知：仓库D 1针对指定地址L的期望配送时长为t 1，仓库D 2针对指定地址L的期望配送时长为t2，仓库D 3针对指定地址L的期望配送时长为t 3。如果t 2＜t 1＜t 3，则确定仓库D 2为第一类别物品A的待定仓库。同理地，当订单信息还指示其他第一类别物品时，可以按照上述逻辑确定每项第一类别物品的待定仓库。
根据本公开的实施例，优化模型可以包括第一子模型。上述操作S231～S233均可以利用第一子模型执行，并将上述至少一项第一类别物品各自的待定仓库作为第一子模型的输出结果。
在操作S234，确定上述至少一项第一类别物品各自的待定仓库是否为同一仓库。如果是，则执行操作S235。
在操作S235，确定上述至少一项第一类别物品各自的待定仓库为上述至少一项第一类别物品各自的配送仓库。
示例性地，当第一子模型的输出结果表征订单信息中的至少一项第一类别物品的待定仓库为同一仓库时，说明该同一仓库可以同时提供上述至少一项第一类别物品，如果将该同一仓库作为上述至少一项第一类别物品的配送仓库，可以将上述第一类别物品打包为同一包裹，降低配送成本。并且由于该同一仓库对于每项第一类别物品来说的期望配送时长均较短，以该同一仓库作为上述至少一项第一类别物品的配送仓库不会导致配送时长的增加。因此，本操作S234可以根据第一子模型的输出结果来确定订单信息所指示的至少一项第一类别物品的配送仓库，将待定仓库作为配送仓库。
根据本公开的实施例，优化模型还可以包括第二子模型，第二子模型为整数规划(integer programming)模型。该整数规划模型的目标函数可以表征第一数值和第二数值之和，即表征配送时长和配送费用的总和，该整数规划模型包括至少一个约束条件。如图3所示，上述操作S230利用预先构建的优化模型对上述订单信息和仓库信息进行处理，以根据优化模型的输出结果从上述多个仓库中确定至少一个仓库作为配送仓库还可以 包括操作S236～S239。
当在上述操作S234确定至少一项第一类别物品各自的待定仓库不是同一仓库时，执行操作S236：基于上述至少一个约束条件、上述订单信息和上述仓库信息，确定至少一种仓库分配方式。其中，每种仓库分配方式可以包括：上述至少一项第一类别物品与上述多个仓库中的至少一个仓库之间的配送关系。例如，订单信息指示有第一类别物品A 1、A 2和A 3，所确定的每种仓库分配方式可以包括：第一类别物品A 1与多个仓库中的一个仓库之间的配送关系，第一类别物品A 2与多个仓库中的一个仓库之间的配送关系，第一类别物品A 3与多个仓库中的一个仓库之间的配送关系。
在操作S237，基于上述至少一种仓库分配方式，计算目标函数的取值。将使得目标函数的取值最小的仓库分配方式，作为第二子模型的输出结果。
示例性地，本公开实施例可以基于上述至少一种仓库分配方式，确定第一数值和第二数值的取值范围。再基于第一数值和第二数值的取值范围，计算目标函数的取值。接着，将使得目标函数的取值最小的仓库分配方式，作为第二子模型的输出结果。
例如，上述每种仓库分配方式可以包括：上述至少一项第一类别物品与M个仓库之间的配送关系，M为大于等于1的整数。上述基于至少一种仓库分配方式，确定第一数值和第二数值的取值范围包括：针对每种仓库分配方式，根据M个仓库中每个仓库针对指定地址的期望配送时长，确定针对每种仓库分配方式的第一数值。并且，根据M个仓库中每个仓库的期望配送费用，确定针对每种仓库分配方式的第二数值。
下面结合具体例子对上述利用整数规划模型处理订单数据和仓库数据的过程进行示例性说明。
例如，可以设置整数规划模型如公式(1)～(7)所示。
Figure PCTCN2021087173-appb-000001
Figure PCTCN2021087173-appb-000002
Figure PCTCN2021087173-appb-000003
Figure PCTCN2021087173-appb-000004
Figure PCTCN2021087173-appb-000005
Figure PCTCN2021087173-appb-000006
Figure PCTCN2021087173-appb-000007
其中，公式(1)表示整数规划模型的目标为使得目标函数最小化。公式(2)～(7)示出了该整数规划模型的约束条件。示例性地，i表示物品的SKU编号，I为订单信息中所有指定物品的SKU编号的集合。j表示仓库的编号，J为多个仓库的集合。s ij的取值用于表征仓库j能否满足订单信息所指示的指定物品i的全部需求，当s ij＝1时表示能满足，当s ij＝0时表示不能满足。t j表示仓库j的期望配送时长。n i表示订单信息所指示的指定物品i的需求数量。n表示订单信息所指示的全部指定物品的总数量。w为权重，该权重例如可以表征任一仓库配送一次包裹的期望配送费用，针对不同的仓库可设置相同或不同的权重。X ij的取值用于表征指定物品i是否由仓库j进行配送，即指定物品i是否与仓库j具有配送关系。当X ij＝1时表示指定物品i由仓库j进行配送，当X ij＝0时表示指定物品i不由仓库j进行配送。Y j的取值用于表征订单信息中是否存在由仓库j进行配送的指定物品，当Y j＝1时表示存在，当Y j＝0时表示不存在。公式(1)表征最小化平均期望配送时长和平均期望配送费用，本例中平均期望配送费用等于拆单数的加权求和结果。公式(2)的约束条件限制每一物品(例如通过SKU编号唯一标识)只能由有能力满足该物品全部需求数量的仓库进行配送。公式(3)的约束条件限制每一物品只由一个仓库进行配送。公式(4)和(5)的约束条件限制某个仓库至少配送一个物品才有可能成为实际配送仓库。公式(6)和(7)的约束条件限制X ij和Y j是[0-1]区间的变量。
可以理解，根据本公开的实施例，上述至少一个约束条件用于限制如下至少一项：每项第一类别物品的配送仓库的数量；每项第一类别物品的 配送仓库中该第一类别物品的存储数量；以及，每个仓库所配送的第一类别物品的项数。通过整数规划模型，可以限定若干仓库配送方式。在该限定范围内，可以根据目标函数来确定最优化的输出结果。
继续参阅图3，在操作S238，确定第二子模型在得到输出结果之前的运行时长是否大于预定时长。如果是，则返回执行操作S235。如果否，则执行操作S239。
在操作S239，根据第二子模型的输出结果确定上述至少一项第一类别物品各自的配送仓库。
根据本公开的实施例，操作S239可以按照如下方式执行：在操作S2391，确定第二子模型的输出结果是否优于第一子模型的输出结果。如果是，则执行操作S2392。如果否，返回执行操作S235。在操作S2392，将第二子模型的输出结果所针对的仓库分配方式确定上述至少一项第一类别物品各自的配送仓库。
图4示意性示出了根据本公开另一实施例的订单信息处理方法的示例流程图，用于说明上述操作S230利用预先构建的优化模型对上述订单信息和仓库信息进行处理，以根据优化模型的输出结果从上述多个仓库中确定至少一个仓库作为配送仓库的另一种示例实施过程。
如图4所示，在开始执行后，该方法可以包括操作S2310～S2312。
在操作S2310，确定上述至少一项指定物品中是否存在至少一项第二类别物品。如果是，则执行操作S2311。如果否，则返回开始状态。
示例性地，第二类别物品可以根据需要进行设置。例如第二类别物品可以指所有不需要进行打包的物品，可称为“原包物品”，即可以按照原始包装直接进行配送的物品。订单信息所指示的至少一项指定物品中如果存在第二类别物品，则在进行履约决策的过程中可以不考虑这些第二类别物品被合并打包的可能性。
在操作S2311，针对每项第二类别物品，根据该第二类别物品的标识信息和需求数量，从上述多个仓库中确定存储有该第二类别物品、且存储数量大于等于需求数量的第二候选仓库。
在操作S2312，从第二候选仓库中确定针对指定地址的期望配送时长最短的第二候选仓库，以作为该第二类别物品的配送仓库。
上述操作S2311～S2312与上文中的操作S232～S233的实施原理相同，在此不再赘述。在确定一项第二类别物品的期望配送时间最短的第二候选仓库后，可以直接作为该第二类别物品的配送仓库。
根据本公开的实施例，优化模型还可以包括第三子模型。上述操作S2310～S2312均可以利用第三子模型执行，并将上述所确定的至少一项第二类别物品各自的配送仓库作为所述第三子模型的输出结果。从而可以根据第三子模型的输出结果，确定至少一项第二类别物品各自的配送仓库。
图5示意性示出了根据本公开实施例的订单信息处理装置的框图。
如图5所示，订单信息处理装置500可以包括：第一获取模块510、第二获取模块520和模型处理模块530。
第一获取模块510用于获取订单信息，该订单信息包括：指定地址的信息和至少一项指定物品的信息。
第二获取模块520用于获取仓库信息，该仓库信息包括：多个仓库的库存信息和多个仓库的配送信息。
模型处理模块530用于利用预先构建的优化模型对上述订单信息和仓库信息进行处理，以根据优化模型的输出结果从上述多个仓库中确定至少一个仓库作为配送仓库，从而使得第一数值与第二数值之和小于等于预定值。其中，第一数值用于表征将至少一项指定物品从上述配送仓库配送至指定地址所花费的配送时长，第二数值用于表征将至少一项指定物品从上述配送仓库配送至指定地址所花费的配送费用。
需要说明的是，装置部分实施例中各模块/单元/子单元等的实施方式、解决的技术问题、实现的功能、以及达到的技术效果分别与方法部分实施例中各对应的步骤的实施方式、解决的技术问题、实现的功能、以及达到的技术效果相同或类似，在此不再赘述。
根据本公开的实施例的模块、子模块、单元、子单元中的任意多个、或其中任意多个的至少部分功能可以在一个模块中实现。根据本公开实施例的模块、子模块、单元、子单元中的任意一个或多个可以被拆分成多个模块来实现。根据本公开实施例的模块、子模块、单元、子单元中的任意一个或多个可以至少被部分地实现为硬件电路，例如现场可编程门阵列(FPGA)、可编程逻辑阵列(PLA)、片上系统、基板上的系统、封装上 的系统、专用集成电路(ASIC)，或可以通过对电路进行集成或封装的任何其他的合理方式的硬件或固件来实现，或以软件、硬件以及固件三种实现方式中任意一种或以其中任意几种的适当组合来实现。或者，根据本公开实施例的模块、子模块、单元、子单元中的一个或多个可以至少被部分地实现为计算机程序模块，当该计算机程序模块被运行时，可以执行相应的功能。
例如，第一获取模块510、第二获取模块520和模型处理模块530中的任意多个可以合并在一个模块中实现，或者其中的任意一个模块可以被拆分成多个模块。或者，这些模块中的一个或多个模块的至少部分功能可以与其他模块的至少部分功能相结合，并在一个模块中实现。根据本公开的实施例，第一获取模块510、第二获取模块520和模型处理模块530中的至少一个可以至少被部分地实现为硬件电路，例如现场可编程门阵列(FPGA)、可编程逻辑阵列(PLA)、片上系统、基板上的系统、封装上的系统、专用集成电路(ASIC)，或可以通过对电路进行集成或封装的任何其他的合理方式等硬件或固件来实现，或以软件、硬件以及固件三种实现方式中任意一种或以其中任意几种的适当组合来实现。或者，第一获取模块510、第二获取模块520和模型处理模块530中的至少一个可以至少被部分地实现为计算机程序模块，当该计算机程序模块被运行时，可以执行相应的功能。
图6示意性示出了根据本公开实施例的适于实现上文描述的模型训练方法和/或地图绘制方法的计算机设备的框图。图6示出的计算机设备仅仅是一个示例，不应对本公开实施例的功能和使用范围带来任何限制。
如图6所示，根据本公开实施例的计算机设备600包括处理器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。处理器601例如可以包括通用微处理器(例如CPU)、指令集处理器和/或相关芯片组和/或专用微处理器(例如，专用集成电路(ASIC))，等等。处理器601还可以包括用于缓存用途的板载存储器。处理器601可以包括用于执行根据本公开实施例的方法流程的不同动作的单一处理单元或者是多个处理单元。
在RAM 603中，存储有设备600操作所需的各种程序和数据。处理器601、ROM 602以及RAM 603通过总线604彼此相连。处理器601通过执行ROM 602和/或RAM 603中的程序来执行根据本公开实施例的方法流程的各种操作。需要注意，所述程序也可以存储在除ROM 602和RAM 603以外的一个或多个存储器中。处理器601也可以通过执行存储在所述一个或多个存储器中的程序来执行根据本公开实施例的方法流程的各种操作。
根据本公开的实施例，设备600还可以包括输入/输出(I/O)接口605，输入/输出(I/O)接口605也连接至总线604。设备600还可以包括连接至I/O接口605的以下部件中的一项或多项：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。
根据本公开的实施例，根据本公开实施例的方法流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存储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。在该计算机程序被处理器601执行时，执行本公开实施例的系统中限定的上述功能。根据本公开的实施例，上文描述的系统、设备、装置、模块、单元等可以通过计算机程序模块来实现。
本公开实施例还提供了一种计算机可读存储介质，该计算机可读存储介质可以是上述实施例中描述的设备/装置/系统中所包含的；也可以是单独存在，而未装配入该设备/装置/系统中。上述计算机可读存储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执行时，实现根据本公开实施例的模型训练方法和/或地图绘制方法。
根据本公开的实施例，计算机可读存储介质可以是非易失性的计算机可读存储介质，例如可以包括但不限于：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)、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。在本公开实施例中，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。例如，根据本公开的实施例，计算机可读存储介质可以包括上文描述的ROM 602和/或RAM 603和/或ROM 602和RAM 603以外的一个或多个存储器。
附图中的流程图和框图，图示了按照本公开实施例各种实施例的系统、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，上述模块、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，框图或流程图中的每个方框、以及框图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。
本领域技术人员可以理解，本公开实施例的各个实施例和/或权利要求中记载的特征可以进行多种组合和/或结合，即使这样的组合或结合没有明确记载于本公开实施例中。特别地，在不脱离本公开实施例精神和教导的情况下，本公开实施例的各个实施例和/或权利要求中记载的特征可以进行多种组合和/或结合。所有这些组合和/或结合均落入本公开实施例的范围。

Claims (13)

  1. 一种订单信息处理方法，包括：
    获取订单信息，所述订单信息包括：指定地址的信息和至少一项指定物品的信息；
    获取仓库信息，所述仓库信息包括：多个仓库的库存信息和所述多个仓库的配送信息；以及
    利用预先构建的优化模型对所述订单信息和所述仓库信息进行处理，以根据所述优化模型的输出结果从所述多个仓库中确定至少一个仓库作为配送仓库，从而使得第一数值与第二数值之和小于等于预定值，
    其中，所述第一数值用于表征将所述至少一项指定物品从所述配送仓库配送至所述指定地址所花费的配送时长，所述第二数值用于表征将所述至少一项指定物品从所述配送仓库配送至所述指定地址所花费的配送费用。
  2. 根据权利要求1所述的方法，其中，
    所述至少一项指定物品中每项指定物品的信息包括：所述每项指定物品的标识信息和所述每项指定物品的需求数量；
    所述多个仓库中每个仓库的库存信息包括：所述每个仓库中存储的物品的标识信息和所述每个仓库中每项物品的存储数量；以及
    所述多个仓库中每个仓库的配送信息包括：所述每个仓库针对多个地址的期望配送时长和所述每个仓库的期望配送费用。
  3. 根据权利要求2所述的方法，其中，所述优化模型包括第一子模型；
    所述利用预先构建的优化模型对所述订单信息和所述仓库信息进行处理包括：利用所述第一子模型执行如下操作：
    当所述至少一项指定物品中存在至少一项第一类别物品时，针对每项第一类别物品，根据所述第一类别物品的标识信息和需求数量，从所述多个仓库中确定存储有所述第一类别物品、且存 储数量大于等于所述需求数量的第一候选仓库，并从所述第一候选仓库中确定针对所述指定地址的期望配送时长最短的第一候选仓库，以作为所述第一类别物品的待定仓库；以及
    将所述至少一项第一类别物品各自的待定仓库作为所述第一子模型的输出结果。
  4. 根据权利要求3所述的方法，其中，所述根据所述优化模型的输出结果从所述多个仓库中确定至少一个仓库作为配送仓库包括：
    当所述至少一项第一类别物品各自的待定仓库为同一仓库时，确定所述至少一项第一类别物品各自的待定仓库为所述至少一项第一类别物品各自的配送仓库。
  5. 根据权利要求3或4所述的方法，其中，所述优化模型还包括第二子模型，所述第二子模型为整数规划模型，所述整数规划模型的目标函数表征所述第一数值和所述第二数值之和，所述整数规划模型包括至少一个约束条件；
    所述利用预先构建的优化模型对所述订单信息和所述仓库信息进行处理还包括：
    当所述至少一项第一类别物品各自的待定仓库不是同一仓库时，基于所述至少一个约束条件、所述订单信息和所述仓库信息，确定至少一种仓库分配方式，其中每种仓库分配方式包括：所述至少一项第一类别物品与所述多个仓库中的至少一个仓库之间的配送关系；
    基于所述至少一种仓库分配方式，确定所述第一数值和所述第二数值的取值范围；
    基于所述第一数值和所述第二数值的取值范围，计算所述目标函数的取值；以及
    将使得所述目标函数的取值最小的仓库分配方式，作为所述第二子模型的输出结果。
  6. 根据权利要求5所述的方法，其中，所述根据所述优化模型的输出结果从所述多个仓库中确定至少一个仓库作为配送仓库还包括：
    确定所述第二子模型在得到所述输出结果之前的运行时长是否 大于预定时长；
    如果是，则确定所述至少一项第一类别物品各自的待定仓库为所述至少一项第一类别物品各自的配送仓库；以及
    如果否，则根据所述第二子模型的输出结果确定所述至少一项第一类别物品各自的配送仓库。
  7. 根据权利要求5所述的方法，其中，所述每种仓库分配方式包括：所述至少一项第一类别物品与M个仓库之间的配送关系，M为大于等于1的整数；
    所述基于所述至少一种仓库分配方式，确定所述第一数值和所述第二数值的取值范围包括：
    针对所述每种仓库分配方式，
    根据所述M个仓库中每个仓库针对所述指定地址的期望配送时长，确定针对所述每种仓库分配方式的所述第一数值；以及
    根据所述M个仓库中每个仓库的期望配送费用，确定针对所述每种仓库分配方式的所述第二数值。
  8. 根据权利要求5所述的方法，其中，所述至少一个约束条件用于限制如下至少一项：
    每项第一类别物品的配送仓库的数量；
    每项第一类别物品的配送仓库中所述第一类别物品的存储数量；以及
    每个仓库所配送的第一类别物品的项数。
  9. 根据权利要求3所述的方法，其中，所述优化模型还包括第三子模型；
    所述利用预先构建的优化模型对所述订单信息和所述仓库信息进行处理还包括：利用所述第三子模型执行如下操作：
    当所述至少一项指定物品中存在至少一项第二类别物品时，针对每项所述第二类别物品，根据所述第二类别物品的标识信息和需求数量，从所述多个仓库中确定存储有所述第二类别物品、且存储数量大于等于所述需求数量的第二候选仓库，并从所述第二候选仓库中确定针对所述指定地址的期望配送时长最短的第二 候选仓库，以作为所述第二类别物品的配送仓库；
    将所述至少一项第二类别物品各自的配送仓库作为所述第三子模型的输出结果。
  10. 根据权利要求9所述的方法，其中，所述根据所述优化模型的输出结果从所述多个仓库中确定至少一个仓库作为配送仓库还包括：
    根据所述第三子模型的输出结果，确定所述至少一项第二类别物品各自的配送仓库。
  11. 一种订单信息处理装置，包括：
    第一获取模块，用于获取订单信息，所述订单信息包括：指定地址的信息和至少一项指定物品的信息；
    第二获取模块，用于获取仓库信息，所述仓库信息包括：多个仓库的库存信息和所述多个仓库的配送信息；以及
    模型处理模块，用于利用预先构建的优化模型对所述订单信息和所述仓库信息进行处理，以根据所述优化模型的输出结果从所述多个仓库中确定至少一个仓库作为配送仓库，从而使得第一数值与第二数值之和小于等于预定值，
    其中，所述第一数值用于表征将所述至少一项指定物品从所述配送仓库配送至所述指定地址所花费的配送时长，所述第二数值用于表征将所述至少一项指定物品从所述配送仓库配送至所述指定地址所花费的配送费用。
  12. 一种计算机设备，包括：
    存储器，其上存储有计算机指令；以及
    至少一个处理器；
    其中，所述处理器执行所述计算机指令时实现根据权利要求1～10中任一项所述的方法。
  13. 一种计算机可读存储介质，其上存储有计算机指令，所述计算机指令被处理器执行时实现根据权利要求1～10中任一项所述的方法。
PCT/CN2021/087173 2020-04-14 2021-04-14 订单信息处理方法、装置、计算机设备和介质 WO2021208950A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
US17/995,084 US20230245055A1 (en) 2020-04-14 2021-04-14 Method and apparatus of processing order information, computer device and medium
JP2022559325A JP7423816B2 (ja) 2020-04-14 2021-04-14 注文情報処理方法、装置、コンピュータ機器及び媒体
KR1020227038193A KR20230019076A (ko) 2020-04-14 2021-04-14 주문 정보 처리 방법, 장치, 컴퓨터 기기 및 매체

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010293111.1 2020-04-14
CN202010293111.1A CN112329970A (zh) 2020-04-14 2020-04-14 订单信息处理方法、装置、计算机设备和介质

Publications (1)

Publication Number Publication Date
WO2021208950A1 true WO2021208950A1 (zh) 2021-10-21

Family

ID=74302994

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/087173 WO2021208950A1 (zh) 2020-04-14 2021-04-14 订单信息处理方法、装置、计算机设备和介质

Country Status (5)

Country Link
US (1) US20230245055A1 (zh)
JP (1) JP7423816B2 (zh)
KR (1) KR20230019076A (zh)
CN (1) CN112329970A (zh)
WO (1) WO2021208950A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115423417A (zh) * 2022-11-03 2022-12-02 图林科技(深圳)有限公司 一种跨境电商数字化的智能风控系统及方法
CN117910707A (zh) * 2024-03-15 2024-04-19 浙江口碑网络技术有限公司 负载评估方法、装置、电子设备和计算机可读存储介质

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112329970A (zh) * 2020-04-14 2021-02-05 北京沃东天骏信息技术有限公司 订单信息处理方法、装置、计算机设备和介质
CN112884408A (zh) * 2021-02-20 2021-06-01 北京每日优鲜电子商务有限公司 物品出库方法、装置、电子设备和计算机可读介质
CN113239317B (zh) * 2021-05-11 2024-02-13 北京沃东天骏信息技术有限公司 确定订单履约仓库的方法和装置
CN113487259B (zh) * 2021-07-06 2022-02-18 深圳市通拓信息技术网络有限公司 一种用于电商智能仓储的出库配送方法
CN114348585B (zh) * 2021-12-30 2024-04-09 重庆特斯联智慧科技股份有限公司 一种基于平台调度的物流机器人系统及其控制方法
CN114819840A (zh) * 2022-05-10 2022-07-29 北京沃东天骏信息技术有限公司 一种仓库信息处理方法及装置、存储介质
CN115082125A (zh) * 2022-07-07 2022-09-20 北京京东振世信息技术有限公司 配送费用的确定方法和装置
CN117094626A (zh) * 2022-09-02 2023-11-21 深圳小狮快送科技有限公司 一种基于大数据的第四方汽配物流平台及管理方法
CN117078150B (zh) * 2023-10-17 2024-02-09 深圳市中农易讯信息技术有限公司 一种农产品运送的路径优化方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108399464A (zh) * 2017-09-27 2018-08-14 圆通速递有限公司 一种多式联运路径优化方法和系统
CN109447355A (zh) * 2018-10-31 2019-03-08 网易无尾熊（杭州）科技有限公司 仓库货物的配送优化方法、装置、介质和计算设备
CN110390498A (zh) * 2018-04-17 2019-10-29 北京京东尚科信息技术有限公司 订单分配方法和装置
CN110874700A (zh) * 2018-09-03 2020-03-10 菜鸟智能物流控股有限公司 物流订单匹配方法、装置以及电子设备
CN112329970A (zh) * 2020-04-14 2021-02-05 北京沃东天骏信息技术有限公司 订单信息处理方法、装置、计算机设备和介质

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003208549A (ja) 2002-01-17 2003-07-25 Takakazu Shimazu 商品配送手段選択システム、商品配送手段の選択方法、商品配送システム

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108399464A (zh) * 2017-09-27 2018-08-14 圆通速递有限公司 一种多式联运路径优化方法和系统
CN110390498A (zh) * 2018-04-17 2019-10-29 北京京东尚科信息技术有限公司 订单分配方法和装置
CN110874700A (zh) * 2018-09-03 2020-03-10 菜鸟智能物流控股有限公司 物流订单匹配方法、装置以及电子设备
CN109447355A (zh) * 2018-10-31 2019-03-08 网易无尾熊（杭州）科技有限公司 仓库货物的配送优化方法、装置、介质和计算设备
CN112329970A (zh) * 2020-04-14 2021-02-05 北京沃东天骏信息技术有限公司 订单信息处理方法、装置、计算机设备和介质

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115423417A (zh) * 2022-11-03 2022-12-02 图林科技(深圳)有限公司 一种跨境电商数字化的智能风控系统及方法
CN117910707A (zh) * 2024-03-15 2024-04-19 浙江口碑网络技术有限公司 负载评估方法、装置、电子设备和计算机可读存储介质

Also Published As

Publication number Publication date
KR20230019076A (ko) 2023-02-07
JP2023523530A (ja) 2023-06-06
JP7423816B2 (ja) 2024-01-29
CN112329970A (zh) 2021-02-05
US20230245055A1 (en) 2023-08-03

Similar Documents

Publication Publication Date Title
WO2021208950A1 (zh) 订单信息处理方法、装置、计算机设备和介质
US11093986B2 (en) Personalized delivery time estimate system
US10636008B2 (en) Data processing system and method
CN111523977B (zh) 波次订单集合的创建方法、装置、计算设备和介质
WO2022237667A1 (zh) 确定订单履约仓库的方法和装置
US11715147B2 (en) Online platform for processing merchandise shipping
US10373117B1 (en) Inventory optimization based on leftover demand distribution function
CN113762858B (zh) 一种库存管理方法和装置
CN111861639B (zh) 金融交易撮合匹配方法及系统
CN111626652A (zh) 订单处理方法、装置、系统及介质
CN112184348B (zh) 订单数据处理方法、装置、电子设备及介质
CN109345166B (zh) 用于生成信息的方法和装置
CN110503528B (zh) 一种线路推荐方法、装置、设备和存储介质
CN112070423B (zh) 库存预占方法、装置、电子设备及存储介质
US20150106224A1 (en) Determining picking costs for a set of candidate products for a product order
US11978072B2 (en) Systems for management of location-aware market data
WO2023005653A1 (zh) 物品分配方法和装置
CN114254845A (zh) 仓库选址方法、装置、计算机设备和存储介质
US20240104490A1 (en) Systems and methods for electronically analyzing and normalizing a shipping parameter based on user preference data
US10929805B2 (en) Adjusting simulation times for cost simulation analysis of transportation lane proposals based on space and time granularities
CN113159877A (zh) 数据处理方法、装置、系统、计算机可读存储介质
CN113780923A (zh) 派件方法、装置、电子设备及介质
US8875136B2 (en) Methods of personalizing services via identification of common components
CN113554380A (zh) 一种物品出库定位方法和装置
CN113538080A (zh) 一种任务单拆分方法和装置

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: 21788218

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2022559325

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21788218

Country of ref document: EP

Kind code of ref document: A1