CN112308312A - Warehouse-leaving package transferring method, model training method and related equipment - Google Patents
Warehouse-leaving package transferring method, model training method and related equipmentDownload PDFInfo
- Publication number
- CN112308312A CN112308312ACN202011179846.8ACN202011179846ACN112308312ACN 112308312 ACN112308312 ACN 112308312ACN 202011179846 ACN202011179846 ACN 202011179846ACN 112308312 ACN112308312 ACN 112308312A
- Authority
- CN
- China
- Prior art keywords
- logistics
- parcel
- node
- warehouse
- transport vehicle
- 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.)
- Granted
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"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
- 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
- G06Q10/083—Shipping
- G06Q10/08355—Routing methods
- 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
- G06Q10/083—Shipping
- G06Q10/0836—Recipient pick-ups
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0283—Price estimation or determination
- G06Q30/0284—Time or distance, e.g. usage of parking meters or taximeters
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Description
Technical Field
The invention relates to the technical field of logistics, in particular to a warehouse-remaining package transferring method, a model training method and related equipment.
Background
The timely delivery of express packages is the key content concerned by e-commerce platforms, express companies and terminal users, and directly concerns the operation quality and user experience. In the current logistics mode, a part of packages are easily generated in the distribution center, and the packages cannot catch up with the departure time of the current shift, exceed the limit of the residual loading capacity and the like, and are temporarily stored in the distribution center. Parcels stored in the distribution center are usually processed by manual operation and subjective decision.
The manual operation is mainly to perform the warehouse-leaving scanning to track the package track and follow-up processing. This kind of mode not only consumes the manual work, and operating time in the occupation field reduces work efficiency when increasing the cost moreover.
The subjective decision mainly comprises the decision of whether to wait for the next shift to be sent again or newly increase the shift to be sent. However, the former seriously delays the aging of the parcels, and the latter causes waste when the number of the parcels left in the warehouse is insufficient.
It can be seen that, to the processing mode of leaving the storehouse parcel, with high costs, inefficiency, also can't satisfy the requirements such as the ageing of parcel, influence user experience at present.
It is to be noted that the information disclosed in the above background section is only for enhancement of understanding of the background of the invention and therefore may include information that does not constitute prior art that is already known to a person of ordinary skill in the art.
Disclosure of Invention
In view of the above, the present invention provides a leaving warehouse parcel forwarding method, a model training method and related devices, so as to at least partially solve the problems of the prior art.
One aspect of the present invention provides a leaving warehouse parcel forwarding method, including: generating parcel sets with the same logistics nodes according to the warehouse-remaining parcels and the logistics information thereof generated in real time, and determining the forwarding timeliness of each parcel set; obtaining a transport vehicle with a bearing allowance and an allocated logistics node thereof; taking the real-time position of the transport vehicle as a starting point, generating a necessary path node according to each distributed logistics node, and generating a selected path node according to the logistics node of each parcel set; and controlling the transport vehicle to transfer the parcel sets along an optimal path based on a dynamic path planning model taking at least the transfer time as a constraint condition, wherein the optimal path at least maximizes the number of the transferred parcel sets.
In some embodiments, when obtaining a transportation vehicle with a carrying allowance, the unit transportation cost of the transportation vehicle is also obtained; the optimal path also minimizes the overall transportation cost of the transporter.
In some embodiments, said controlling said transporter to forward said set of packages along an optimal path comprises: obtaining the optimal path of the transport vehicle and the time for reaching each path node; and controlling the transport vehicle to transfer the package set along the optimal path, and sending the time of reaching the path node to a logistics node corresponding to the path node at least before the transport vehicle reaches the path node.
In some embodiments, the generating the parcel sets having the same logistics node comprises: obtaining current logistics node and destination information of each warehouse parcel from the logistics information of the warehouse parcels; obtaining the next logistics node of each warehouse remaining package according to the current logistics node and destination information of each warehouse remaining package; and integrating the warehouse-leaving packages with the same current logistics node and the same lower logistics node to generate a package set with the same logistics node.
In some embodiments, said determining a forwarding age for each said parcel set comprises: obtaining the time limit of each warehouse-remaining package in the package set; determining the deadline of each warehouse leaving package for reaching the logistics node of the next station according to the aging limit of each warehouse leaving package; obtaining an earliest deadline from the deadlines of each of the left-behind parcels; and determining the forwarding time limit of the parcel set according to the earliest deadline, so that the time for forwarding the parcel set to the next logistics node is earlier than the earliest deadline.
In some embodiments, after the package sets with the same logistics node are generated, physical parameters of each warehouse-remaining package are obtained from logistics information of the warehouse-remaining packages, and a required bearing capacity of each package set is obtained according to the physical parameters of each warehouse-remaining package; the dynamic path planning model also takes the condition that the required bearing capacity of the transferred parcel set is smaller than the real-time bearing allowance of the transport vehicle as a constraint condition.
In some embodiments, before the warehouse-left package and the logistics information thereof generated in real time, the method further comprises: according to the shift information of each logistics node, obtaining the current shift income and the sent packages of each logistics node in real time, and determining the packages detained in the current shift of each logistics node; screening out packages with abnormal states from the sum of the packages retained in the current shift and the packages retained in the previous shift of each logistics node to obtain the warehouse-retained packages generated in real time; each warehouse-remaining package carries logistics information at least comprising current logistics nodes, destination information, time limit and physical parameters.
In some embodiments, after generating the selected path node according to the logistics node of each parcel set, the method further comprises: and obtaining a first time matrix of the transport vehicle from the starting point to each path node and a second time matrix between every two path nodes based on map service.
Yet another aspect of the present invention provides a model training method, including: obtaining sample data, comprising: generating sample parcel sets with the same logistics nodes according to the sample warehouse-leaving parcels and the logistics information thereof, and determining the forwarding time limit of each sample parcel set; obtaining a transport vehicle with a bearing allowance and an allocated logistics node thereof; generating necessary path nodes according to the distributed logistics nodes, and generating selected path nodes according to the logistics nodes of the sample parcel sets; training a network model, comprising: and taking the sample data as input, at least taking the transfer time effectiveness as a constraint condition, at least taking the number of the sample package sets transferred maximally as an objective function, and training a dynamic path planning model by taking the optimal path for guiding the transport vehicle to transfer the sample package sets as output until the model converges.
In some embodiments, the obtaining sample data further comprises: obtaining a unit transportation cost of the transport vehicle; the training network model further comprises: to minimize the total transportation cost of the vehicle as an objective function.
In some embodiments, the obtaining sample data further comprises: obtaining a desired load capacity for each of the sample package sets; the training network model further comprises: and taking the condition that the required bearing capacity of the transferred sample package set is less than the bearing allowance of the transport vehicle as a constraint condition.
Yet another aspect of the present invention provides a left-out package transfer apparatus comprising: the parcel set acquisition module is configured to generate parcel sets with the same logistics nodes according to the warehouse-remaining parcels and the logistics information thereof generated in real time, and determine the forwarding timeliness of each parcel set; the transport vehicle acquisition module is configured to acquire a transport vehicle with a bearing allowance and the distributed logistics nodes thereof; a path node determination module configured to generate a necessary path node according to each allocated logistics node and generate a selected path node according to the logistics node of each parcel set, with a real-time position of the transport vehicle as a starting point; and the transfer path planning module is configured to control the transport vehicle to transfer the parcel sets along an optimal path based on a dynamic path planning model taking at least the transfer time as a constraint condition, wherein the optimal path at least maximizes the number of the transferred parcel sets.
Yet another aspect of the present invention provides a left-out package transfer system comprising: a plurality of logistics nodes; the warehouse-remaining package transfer device is communicated with each logistics node.
Yet another aspect of the present invention provides a model training apparatus comprising: a sample data acquisition module configured to: generating sample parcel sets with the same logistics nodes according to the sample warehouse-leaving parcels and the logistics information thereof, and determining the forwarding time limit of each sample parcel set; obtaining a transport vehicle with a bearing allowance and an allocated logistics node thereof; generating necessary path nodes according to the distributed logistics nodes, and generating selected path nodes according to the logistics nodes of the sample parcel sets; a network model training module configured to: and taking the sample data as input, at least taking the transfer time effectiveness as a constraint condition, at least taking the number of the sample package sets transferred maximally as an objective function, and training a dynamic path planning model by taking the optimal path for guiding the transport vehicle to transfer the sample package sets as output until the model converges.
Yet another aspect of the invention provides a computer apparatus comprising: a processor; a memory storing executable instructions; wherein the executable instructions, when executed by the processor, implement the leave-in-store parcel forwarding method and/or the model training method of any of the above embodiments.
Yet another aspect of the present invention provides a computer readable storage medium storing a computer program which, when executed, implements the method for transferring a warehoused package and/or the method for training a model according to any of the embodiments described above.
Compared with the prior art, the invention has the beneficial effects that:
the parcel sets are generated through integration, so that unified processing of the left-warehouse parcels with the same logistics nodes is realized; according to the related information of the parcel sets and the related information of the transport vehicles, the optimal path for the transport vehicles to transfer the parcel sets to the maximum is obtained through dynamic path planning and based on real-time statistics and aging constraints, efficient processing of the parcel left in the warehouse is achieved, and user experience is improved;
furthermore, when the optimal path for the transport vehicle to transfer the parcel sets is planned, the transportation cost is minimized, so that the processing cost is saved while the efficient processing of the parcel leaving the warehouse is realized.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention. It is obvious that the drawings described below are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.
FIG. 1 is a schematic diagram illustrating the steps of a method for transferring a parked parcel in an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating the steps of automated extraction of package information in an embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating steps of obtaining parcel set information and carrier information and performing dynamic path planning according to an embodiment of the present invention;
FIG. 4 is a schematic block diagram of a reservoired parcel transfer apparatus in an embodiment of the present invention;
FIG. 5 is a block diagram of a warehouse parcel forwarding system according to an embodiment of the present invention;
FIG. 6 is a schematic diagram illustrating steps of a model training method according to an embodiment of the present invention;
FIG. 7 is a block diagram of a model training apparatus according to an embodiment of the present invention;
FIG. 8 is a schematic diagram showing the structure of a computer device in the embodiment of the present invention;
fig. 9 shows a schematic structural diagram of a computer-readable storage medium in an embodiment of the present invention.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art.
Furthermore, the drawings are merely schematic illustrations of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.
The step numbers in the following embodiments are only used to indicate different execution contents, and do not limit the execution sequence between the steps. The use of "first," "second," and similar terms in the detailed description is not intended to imply any order, quantity, or importance, but rather is used to distinguish one element from another. It should be noted that features of the embodiments of the invention and of the different embodiments may be combined with each other without conflict.
Fig. 1 shows the main steps of the leaving warehouse parcel forwarding method in the embodiment, and referring to fig. 1, the leaving warehouse parcel forwarding method in the embodiment includes: in step S110, package sets having the same logistics node are generated according to the warehouse-remaining packages and the logistics information thereof generated in real time, and the forwarding timeliness of each package set is determined; in step S120, obtaining a transport vehicle with a carrying margin and its allocated logistics node; in step S130, a necessary path node is generated according to each distributed logistics node with the real-time position of the transport vehicle as a starting point, and a selected path node is generated according to the logistics node of each parcel set; in step S140, the transport vehicle is controlled to transfer the parcel sets along the optimal path based on the dynamic path planning model with at least the transfer time as a constraint condition, wherein the optimal path at least maximizes the number of the parcel sets transferred.
The warehouse-remaining package transferring method can be executed by a control center of a target area, and the control center can monitor the package information of each logistics node and transfer the warehouse-remaining packages of each logistics node; or the control center can be used for combining the control units of all the logistics nodes to execute the processing, the control units of all the logistics nodes feed back the package information, and the control center is used for allocating the forwarding processing of the warehouse-remaining packages of all the logistics nodes. Depending on the size of the stream, the target area may cover several adjacent cities, or several areas in a city, etc.
The logistics nodes specifically refer to logistics data points with distributed functions, such as distribution centers and sorting centers. Every logistics node is equipped with the operation shift that carries out the distributed processing to the parcel, stays storehouse parcel and specifically means after every operation shift, stays the parcel that has not transported away at the logistics node temporarily. For a logistics node, the transport vehicle is a freight vehicle of an additional supplementary shift between two operation shifts of the logistics node, and the transport vehicle may be a freight vehicle of a normal operation shift of other logistics nodes, as long as the transport vehicle has a carrying margin and can realize package transfer, so as to maximize the package processing efficiency of a target area.
The warehouse-remaining package forwarding method of the embodiment realizes the uniform processing of warehouse-remaining packages with the same logistics nodes by integrating and generating the package set; according to the related information of the parcel sets and the related information of the transport vehicle, the optimal path of the transport vehicle for transferring the parcel sets to the maximum is obtained through dynamic path planning and based on real-time statistics and aging constraints, efficient processing of the parcel left in the warehouse is achieved, and user experience is improved.
Further, in one embodiment, when obtaining a transporter with a carrying margin, a unit transportation cost of the transporter is also obtained; and, the optimal path planned by the dynamic path planning model also minimizes the total transportation cost of the vehicle. Therefore, the processing cost is saved while the efficient processing of the reserved package is realized.
The steps of the leave-in package forwarding method will be described in detail with reference to specific examples.
In step S110, before the warehouse-remaining package and the logistics information thereof generated in real time, the method further includes a step of obtaining the warehouse-remaining package and the logistics information thereof, and specifically includes: according to the shift information of each logistics node, obtaining the current shift income and the sent packages of each logistics node in real time, and determining the packages detained in the current shift of each logistics node; screening out packages with abnormal states from the sum of the packages retained in the current shift and the packages retained in the previous shift of each logistics node to obtain the warehouse-retained packages generated in real time; each warehouse-leaving package carries logistics information at least comprising current logistics nodes, destination information, time limit and physical parameters.
The current logistics node is the logistics node where the warehouse leaving package is located currently, the destination information is the destination address of the warehouse leaving package which is appointed to be sent, and the aging limit is the aging requirement of the warehouse leaving package, for example, a certain warehouse leaving package needs to be sent before a preset date; the physical parameters comprise weight, volume and other parameters of the warehouse parcel. In a specific example, the parcel leaving warehouse and the logistics information of each logistics node which is insufficient in transportation capacity or cannot catch up with the operation shift in time can be obtained through automatic extraction of the parcel information.
Fig. 2 shows the main steps of automatic extraction of package information in the embodiment, and referring to fig. 2, the process of automatically extracting package information and obtaining warehouse-remaining packages and logistics information thereof includes: s210, acquiring operation shift information of each logistics node; s220, acquiring the information of the parcel list number subjected to income scanning operation in each shift time, and determining the income parcels; s230, acquiring the information of the parcel single number subjected to the scanning operation within each shift time, and determining the sent parcel; s240, calculating the package of the current warehouse, wherein the package of the current warehouse is the income package, the issued package and the package of the previous warehouse; s250, removing packages in abnormal states from the packages in the current warehouse to form warehouse-remaining packages of each logistics node, wherein the abnormal states comprise wanted, required to return, serious damage and the like; and S260, correlating and obtaining logistics information such as weight, volume, aging requirement, destination information and the like of the warehouse-remaining package of each logistics node through the package single number.
After obtaining the warehouse-remaining packages and the logistics information thereof, the step of generating the package sets with the same logistics nodes specifically comprises the following steps: acquiring current logistics node and destination information of each warehouse parcel in logistics information of the warehouse parcels; obtaining the next logistics node of each warehouse parcel according to the current logistics node and destination information of each warehouse parcel; and integrating the warehouse-leaving packages with the same current logistics node and the same lower logistics node to generate a package set with the same logistics node.
In one particular example, a routing service may be invoked to automatically obtain a next-stop logistics node of a warehouse-leaving package based on current logistics node and destination information of the warehouse-leaving package, such that warehouse-leaving packages that are the same as one current logistics node and are going to the same next-stop logistics node are integrated into a package set based on a calculation result of the routing service.
For example, when the next logistics node can be obtained according to the common path from the current logistics node to the destination information, the routing service can also adopt the existing technology, and the existing technology is not specifically developed here. After the integration is the parcel set, the current logistics node is used as the starting point of the parcel set, and the next logistics node is used as the destination of the parcel set.
After the package set is generated, the method further comprises the following steps: acquiring physical parameters of each reserved warehouse parcel from logistics information of the reserved warehouse parcels, and acquiring the required bearing capacity of each parcel set according to the physical parameters of each reserved warehouse parcel; and the dynamic path planning model also takes the required bearing capacity of the transferred parcel set smaller than the real-time bearing allowance of the transport vehicle as a constraint condition. Thus, when dynamically planning the optimal path for the transport vehicle to transfer the parcel sets, it is ensured that the transport vehicle can carry the parcel sets to be transferred.
Further, after the package sets are generated by integration, the step of determining the forwarding time limit of each package set specifically includes: obtaining the time limit of each reserved cabin package in a package set; determining the deadline of each warehouse leaving package for reaching the logistics node of the next station according to the aging limit of each warehouse leaving package; obtaining an earliest deadline from the deadlines of each remaining bin parcel; and determining the transfer aging of the parcel sets according to the earliest deadline, so that the transfer time of the parcel sets to the logistics nodes at the lower stations is earlier than the earliest deadline.
In one particular example, a time-of-use prediction service may be invoked to obtain the latest time for a parcel set to arrive at a next-stop logistics node based on the current logistics node of the parcel set, the next-stop logistics node, and the time-of-use limits of each warehouse parcel. For example, the remaining delivery time is obtained according to the time limit of the parcel leaving the warehouse, then the deadline of the parcel leaving the warehouse to reach the next logistics node is obtained according to the ratio of the delivery route from the current logistics node to the next logistics node in the delivery route from the current logistics node to the destination information, and the forwarding time of the parcel set is determined according to the deadline of each parcel leaving the warehouse. The aging prediction service may also employ existing techniques and is not specifically developed here.
In the above embodiments, after the parcel set is generated according to the warehouse-remaining parcel generated in real time, a forwarding request carrying the parcel set and related information may be sent out in a quantitative, timing or emergency processing manner, and the step of obtaining the transport vehicle may be further performed. Specifically, quantification refers to performing the step of obtaining a transporter when the number of parcel sets exceeds a predetermined amount; timing refers to executing the step of obtaining the transport vehicle at preset time intervals; emergency processing refers to performing the step of obtaining a carrier when the time of delivery of a package set is imminent, e.g., less than a set time. Therefore, the transport vehicle can be flexibly dispatched based on the condition that the parcel is left in the warehouse, and the parcel forwarding cost is reduced while the timeliness constraint is met. Of course, the forwarding request may also be issued in real-time after the package set is generated to maximize the processing efficiency of the package set.
Further, the forwarding request can be sent by each logistics node according to the respective parcel warehouse-leaving condition, and can also be scheduled by the control center in a unified way.
In step S120, the allocated logistics node of the transport vehicle is the destination point where the transport vehicle has shipped the package. The packages shipped by the terminal may be the package collections that were warehoused by the first few logistics nodes, or the packages of a normal transportation shift.
In step S130, after determining the starting point of the path planning, the inevitable path node, and the selected path force node, the method further includes: based on map service, a first time matrix of the transport vehicle from a starting point to each path node and a second time matrix between every two path nodes are obtained.
Specifically, based on map service, the longitude and latitude of the current position of the transport vehicle can be obtained as a starting point; and acquiring the longitude and latitude of each logistics node, and respectively generating a necessary path node and a selected path node. Further, the running time of the transport vehicle from the current position to each path node is obtained in real time, and a first time matrix is generated; and obtaining the running time between every two path nodes in real time, and generating a second time matrix for the dynamic path planning model to plan the path. The real-time acquired driving time takes into account road conditions and other factors, and can be realized based on the existing map service, and the description is not repeated here. In addition, considering that each path node needs to reserve loading and unloading time, a certain margin can be added to the calculated running time for loading and unloading.
Fig. 3 shows the main steps of acquiring package set information and transport vehicle information and performing dynamic path planning in the embodiment. Based on the description of the foregoing embodiments, in a specific example, the obtaining of the relevant information of the parcel sets and the relevant information of the transportation vehicles and the inputting of the relevant information into the dynamic path planning model to obtain the optimal path specifically includes: s310, acquiring logistics information such as weight/volume (package _ volume), destination, aging limit and the like of the parcel left in the automatic extraction of the parcel information; s320, calling a routing service, and acquiring a next _ hub _ code of the warehouse-left package based on the current hub _ code and the destination of the warehouse-left package; s330, integrating the warehouse-remaining packages, starting the same current logistics node, and integrating the warehouse-remaining packages arriving at the same next-station logistics node into a package set (package _ id); s340, a logistics node or a control center sends a package set forwarding request; s350, invoking an aging prediction service, and acquiring the latest time (package _ arrival _ time) when the parcel set reaches a logistics node of a next station based on the current logistics node of the parcel set, the logistics node of the next station and the aging limit of the parcel left in the warehouse; s360, acquiring a currently available transport vehicle (truck _ id), and residual carrying capacity (truck _ capacity), cost per kilometer per hour (truck _ cost), longitude and latitude of a current position, and a currently scheduled transfer task (truck _ current _ route) of the transport vehicle; s370, calling map service, acquiring a driving time matrix (o-d _ matrix) based on the longitude and latitude of every two logistics nodes in the target area, and acquiring the driving time (truck _ travel _ time) of the transport vehicle reaching each logistics node in real time based on the longitude and latitude of the current position of the transport vehicle and the longitude and latitude of each logistics node; s380, calling a dynamic path planning model, and acquiring the optimal path for transferring the parcel set and the time for reaching each path logistics node based on the acquired information related to the parcel set and the information related to the transport vehicle; and S390, controlling the transport vehicle to transfer the parcel sets along the optimal path, and enabling the corresponding logistics nodes to prepare the parcel sets to wait for the transport vehicle to transfer.
Based on the above process, the obtained related information of the parcel sets and the related information of the transportation vehicles input into the dynamic path planning model include:
hub _ code: the code of the current logistics node, string type, is used for uniquely marking the current logistics node of the package set and is used as the starting point of package set forwarding;
package _ id: the label and string type of the package set are used for uniquely marking the package set as a forwarded object;
package _ volume: weight or volume, double (double precision floating point) type, for marking the weight or volume of a parcel set;
package _ arrival _ time: a time of transfer, time (time) type, for marking the latest time at which the parcel set was transferred to the next logistics node;
next _ hub _ code: the coding and string type of the lower station logistics node are used for uniquely marking the lower station logistics node of the package set as a destination for forwarding the package set;
o-d _ matrix: a driving distance/time matrix between every two path nodes, and an array type;
truck _ id: the identification of the transport vehicle, the string type, is used for uniquely marking the transport vehicle;
truck _ capacity: the residual bearing capacity of the transport vehicle, double type, is used for marking the residual maximum tonnage of the transport vehicle;
truck _ cost, the transportation cost of the transport vehicle, double type, used for marking the transportation cost of the transport vehicle per kilometer per hour;
truck _ travel _ time: the travel time, set (set) type, when the current position of the transport vehicle reaches each path node;
truck _ current _ route: the existing mission schedule, string type, of the transport vehicle includes the identification of the assigned logistics node.
In this embodiment, the dynamic path planning model takes the constraint conditions that the weight of the newly added package set is smaller than the real-time remaining bearing capacity of the transport vehicle, and the latest time when the package set reaches the next logistics node is earlier than the aging requirement, and takes the maximization of the number of package sets that can be transferred and the minimization of the transportation cost of the transport vehicle as an objective function, and the output obtained by path planning includes:
truck _ optimized _ route: the optimized task arrangement and string type of the transport vehicle comprise the code and time of arriving at each passing logistics node;
transmitted _ package _ id _ set: the identification set and the set type of the package set which can be transferred maximally;
optimized _ cost: minimized transport vehicle cost, double type.
In this embodiment, the listed input, output, constraint conditions and objective function are also basic data for training the dynamic path planning model in the model training phase. Of course, the above list should not be construed as limiting the invention. In other embodiments, the dynamic path planning model may be adjusted as long as it can implement the basic scheme of the present invention, i.e., plan to obtain the optimal path for controlling the transport vehicle to maximally forward the parcel set based on real-time statistics and aging constraints.
And further, after the optimal path and the time for reaching each path node are obtained, when the transport vehicle is controlled to transfer the package set along the optimal path, at least before the transport vehicle reaches one path node, the time for reaching the path node is sent to the logistics node corresponding to the path node, so that the logistics node prepares the package set and waits for the transfer before the transport vehicle.
In other embodiments, after the optimal path is obtained, the time to reach each route path node may be sent to the logistics node corresponding to each route path node. Considering that the optimal path of the transport vehicle may change at any time along with the warehouse-remaining package generated in real time, the time for reaching a path node is sent to the corresponding logistics node before reaching the path node, and the transport vehicle can be ensured to be accurately butted with the logistics node corresponding to each path node.
In summary, the warehouse-remaining package forwarding method described in each of the above embodiments generates a package set by integration, so as to implement uniform processing on warehouse-remaining packages having the same logistics node; according to the method, the time efficiency constraint and the bearing constraint are determined according to the relevant information of the parcel set and the relevant information of the transport vehicle, the optimal path of the transport vehicle for maximally transferring the parcel set and minimizing the transport cost is obtained in real time by utilizing dynamic path planning, the efficient processing of the parcel left in the warehouse is realized, the user experience is improved, and the processing cost is saved.
The embodiment of the present invention further provides a remaining warehouse parcel forwarding device, fig. 4 shows main modules of the remaining warehouse parcel forwarding device, and referring to fig. 4, the remaining warehouseparcel forwarding device 400 in this embodiment includes: a parcel setacquisition module 410 configured to generate parcel sets with the same logistics node according to the warehouse-remaining parcels and the logistics information thereof generated in real time, and determine the forwarding timeliness of each parcel set; thecarrier acquiring module 420 is configured to acquire a carrier with a carrying allowance and the distributed logistics nodes thereof; a pathnode determining module 430 configured to generate a necessary path node according to each allocated logistics node and a selected path node according to the logistics node of each parcel set, with the real-time position of the transport vehicle as a starting point; and the transferpath planning module 440 is configured to control the transport vehicle to transfer the parcel sets along the optimal path based on a dynamic path planning model taking at least the transfer time as a constraint condition, wherein the optimal path at least maximizes the number of the transferred parcel sets.
Further, the left-behindparcel forwarding apparatus 400 may further include modules for executing other process steps of the left-behind parcel forwarding methods, and specific principles of the modules may refer to the left-behind parcel forwarding method embodiments, which are not repeated herein.
The leaving warehouseparcel forwarding device 400 of the embodiment generates a parcel set by integration, and realizes unified processing of leaving warehouse parcels with the same logistics node; according to the related information of the parcel sets and the related information of the transport vehicles, the optimal path for the transport vehicles to transfer the parcel sets to the maximum is obtained through dynamic path planning and based on real-time statistics and aging constraints, efficient processing of the parcel left in the warehouse is achieved, and user experience is improved; and, can also further save the treatment cost.
An embodiment of the present invention further provides a remaining warehouse parcel forwarding system, fig. 5 shows a main architecture of the remaining warehouse parcel forwarding system, and referring to fig. 5, the remaining warehouse parcel forwarding system in this embodiment includes: the warehouseparcel forwarding apparatus 400 described in the above embodiment specifically includes a dynamic path planning algorithm engine, and interface services such as map service, routing service, and aging service for the dynamic path planning algorithm engine to call. The dynamic path planning algorithm engine may invoke the MySQLrelational database 510 to implement the invocation of the basic data for path planning. Thelogistics node 520 and thetransport vehicle 530 may communicate with the warehouseparcel forwarding device 400, specifically the dynamic path planning algorithm engine, through theRedis cache database 540. Eachlogistics node 520 can send a transfer request, and the dynamic path planning algorithm engine can plan the dispatchingtransport vehicle 530, so that efficient and low-cost transfer of the warehouse-remaining packages is realized. The specific planning process may refer to the above embodiments of the warehouse-leaving parcel forwarding method, and the description thereof is not repeated here.
The embodiment of the invention also provides a model training method, which is used for training the dynamic path planning model of the arbitrary warehouse-remaining package transferring method embodiment. Fig. 6 shows the main steps of the model training method, and referring to fig. 6, the model training method in this embodiment includes: in step S610, obtaining sample data specifically includes: s610-2, generating sample package sets with the same logistics nodes according to the sample warehouse-leaving packages and the logistics information thereof, and determining the forwarding timeliness of each sample package set; s610-4, obtaining a transport vehicle with a bearing allowance and distributed logistics nodes thereof; s610-6, generating necessary path nodes according to the distributed logistics nodes, and generating selected path nodes according to the logistics nodes of the sample parcel sets; in step S620, training the network model specifically includes: s620-2, taking the sample data as input, at least taking the transfer time effectiveness as a constraint condition, at least taking the maximum transferred sample package set quantity as an objective function, taking the optimal path of the sample package set transferred by the transport vehicle as output, and training a dynamic path planning model until the model converges.
Therefore, the dynamic path planning model obtained by training can guide the transport vehicle to maximally transfer the optimal path of the sample parcel set based on the time-effect constraint dynamic planning according to the relevant information of the sample parcel set and the relevant information of the transport vehicle.
Further, when the sample data is obtained, the unit transportation cost of the transport vehicle is also obtained, and when the network model is trained, the total transportation cost of the transport vehicle is also minimized as an objective function. Thus, the trained dynamic path planning model is able to output an optimal path that maximizes the number of sample parcel sets forwarded and minimizes transportation costs.
Further, when sample data is obtained, the required bearing capacity of each sample package set is also obtained, and when the network model is trained, the required bearing capacity of the transferred sample package sets is smaller than the bearing allowance of the transport vehicle as a constraint condition, so that the transport vehicle can bear the sample package sets to be transferred.
The dynamic path planning model can specifically adopt heuristic algorithms based on a simulated annealing method and the like. The specific input, output, constraint conditions and objective functions of the dynamic path planning model in the training phase may refer to the above embodiments of the leave-bin parcel forwarding method, and a description thereof is not repeated here.
The embodiment of the invention further provides a model training device, which is used for training the dynamic path planning model described in the embodiment. Fig. 7 shows the main blocks of the model training apparatus, and referring to fig. 7, themodel training apparatus 700 in this embodiment includes: a sampledata acquisition module 710 configured to: generating sample parcel sets with the same logistics nodes according to the sample warehouse-leaving parcels and the logistics information thereof, and determining the forwarding timeliness of each sample parcel set; obtaining a transport vehicle with a bearing allowance and an allocated logistics node thereof; generating necessary path nodes according to the distributed logistics nodes, and generating selected path nodes according to the logistics nodes of the sample parcel sets; a networkmodel training module 720 configured to: and training a dynamic path planning model by taking the sample data as input, at least taking the forwarding time limit as a constraint condition, at least taking the number of the sample package sets which are maximally forwarded as an objective function, and guiding the transport vehicle to forward the optimal path of the sample package sets as output until the model converges.
Themodel training device 700 of this embodiment can train and obtain the related information based on the sample package set and the related information of the transport vehicle, and dynamically plan and guide the transport vehicle to maximally transfer the optimal path of the sample package set; and the transportation cost of the transport vehicle can be further minimized, so that the high-efficiency and low-cost transfer of the left warehouse parcel is realized when the dynamic path planning model obtained by training is applied to the transfer processing of the left warehouse parcel.
The embodiment of the present invention further provides a computer device, which includes a processor and a memory, where the memory stores executable instructions, and the executable instructions, when executed by the processor, implement the leave-bin parcel forwarding method/model training method described in any of the above embodiments.
As described above, the computer device of the present invention can generate the parcel set by integration, thereby realizing the uniform processing of the warehouse-remaining parcels having the same logistics node; according to the related information of the parcel sets and the related information of the transport vehicles, the optimal path for the transport vehicles to transfer the parcel sets to the maximum is obtained through dynamic path planning and based on real-time statistics and aging constraints, efficient processing of the parcel left in the warehouse is achieved, and user experience is improved; furthermore, when the optimal path for the transport vehicle to transfer the parcel sets is planned, the transportation cost is minimized, so that the processing cost is saved while the efficient processing of the parcel leaving the warehouse is realized.
While fig. 8 shows the main structure of the computer device in the embodiment, it should be understood that fig. 8 only schematically shows the modules, which may be virtual software modules or actual hardware modules, and the combination, the splitting and the addition of the rest of the modules are within the protection scope of the present invention.
As shown in fig. 8,computer device 800 is in the form of a general purpose computing device. The components ofcomputer device 800 may include, but are not limited to: at least oneprocessing unit 810, at least onememory unit 820, abus 830 connecting different platform components (includingmemory unit 820 and processing unit 810), adisplay unit 840, etc.
The storage unit stores program code, which can be executed by theprocessing unit 810, so that theprocessing unit 810 executes the warehouse parcel forwarding method/model training method described in any of the above embodiments. For example, theprocessing unit 810 may perform the steps shown in fig. 1-3, and 6.
Thestorage unit 820 may include readable media in the form of volatile memory units such as a random access memory unit (RAM)8201 and/or acache memory unit 8202, and may further include a read only memory unit (ROM) 8203.
Thecomputer device 800 may also communicate with one or moreexternal devices 8000, which may be one or more of a keyboard, pointing device, Bluetooth device, etc. Theseexternal devices 8000 enable a user to interactively communicate with thecomputer device 800. Thecomputer device 800 can also communicate with one or more other computing devices, including routers, modems. Such communication may occur via input/output (I/O) interfaces 850. Also,computer device 800 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet) vianetwork adapter 860. Thenetwork adapter 860 may communicate with other modules of thecomputer device 800 via thebus 830. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with thecomputer device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms, to name a few.
An embodiment of the present invention further provides a computer-readable storage medium, which is used for storing a program, and when the program is executed, the method for forwarding a left-in-store parcel/training a model described in any of the above embodiments is implemented. In some possible embodiments, the various aspects of the invention may also be implemented in the form of a program product comprising program code for causing a terminal device to perform the method for warehouse parcel forwarding/model training described in any of the above embodiments, when the program product is run on the terminal device.
As described above, the computer-readable storage medium of the present invention can realize the uniform processing of the warehouse-remaining packages having the same logistics node by integrating to generate the package set; according to the related information of the parcel sets and the related information of the transport vehicles, the optimal path for the transport vehicles to transfer the parcel sets to the maximum is obtained through dynamic path planning and based on real-time statistics and aging constraints, efficient processing of the parcel left in the warehouse is achieved, and user experience is improved; furthermore, when the optimal path for the transport vehicle to transfer the parcel sets is planned, the transportation cost is minimized, so that the processing cost is saved while the efficient processing of the parcel leaving the warehouse is realized.
Fig. 9 is a schematic structural diagram of a computer-readable storage medium of the present invention. Referring to fig. 9, aprogram product 900 may employ a portable compact disc read only memory (CD-ROM) and include program code and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited in this respect, and a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of readable storage media include, but are not limited to: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
A computer readable storage medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable storage medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device, such as through the internet using an internet service provider.
The foregoing is a more detailed description of the invention in connection with specific preferred embodiments and it is not intended that the invention be limited to these specific details. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.
Claims (16)
1. A method of leaving a warehouse for transferring parcels, comprising:
generating parcel sets with the same logistics nodes according to the warehouse-remaining parcels and the logistics information thereof generated in real time, and determining the forwarding timeliness of each parcel set;
obtaining a transport vehicle with a bearing allowance and an allocated logistics node thereof;
taking the real-time position of the transport vehicle as a starting point, generating a necessary path node according to each distributed logistics node, and generating a selected path node according to the logistics node of each parcel set;
and controlling the transport vehicle to transfer the parcel sets along an optimal path based on a dynamic path planning model taking at least the transfer time as a constraint condition, wherein the optimal path at least maximizes the number of the transferred parcel sets.
2. The method of claim 1, wherein obtaining a transporter with a carrying margin also obtains a unit transportation cost of the transporter;
the optimal path also minimizes the overall transportation cost of the transporter.
3. The method of claim 1, wherein said controlling said transporter to forward said package set along an optimal path comprises:
obtaining the optimal path of the transport vehicle and the time for reaching each path node;
and controlling the transport vehicle to transfer the package set along the optimal path, and sending the time of reaching the path node to a logistics node corresponding to the path node at least before the transport vehicle reaches the path node.
4. The method of claim 1, wherein generating the parcel sets having the same logistics node comprises:
obtaining current logistics node and destination information of each warehouse parcel from the logistics information of the warehouse parcels;
obtaining the next logistics node of each warehouse remaining package according to the current logistics node and destination information of each warehouse remaining package;
and integrating the warehouse-leaving packages with the same current logistics node and the same lower logistics node to generate a package set with the same logistics node.
5. The method of claim 4, wherein said determining a forwarding age for each of said parcel sets comprises:
obtaining the time limit of each warehouse-remaining package in the package set;
determining the deadline of each warehouse leaving package for reaching the logistics node of the next station according to the aging limit of each warehouse leaving package;
obtaining an earliest deadline from the deadlines of each of the left-behind parcels;
and determining the forwarding time limit of the parcel set according to the earliest deadline, so that the time for forwarding the parcel set to the next logistics node is earlier than the earliest deadline.
6. The method of claim 1, wherein after generating parcel sets having the same logistics node, obtaining physical parameters of each of the parcel sets from the logistics information of the parcel sets, and obtaining the required carrying capacity of each of the parcel sets according to the physical parameters of each of the parcel sets;
the dynamic path planning model also takes the condition that the required bearing capacity of the transferred parcel set is smaller than the real-time bearing allowance of the transport vehicle as a constraint condition.
7. The method of any one of claims 1-6, wherein the generating of the warehouse parcel and the logistics information thereof in real time is preceded by:
according to the shift information of each logistics node, obtaining the current shift income and the sent packages of each logistics node in real time, and determining the packages detained in the current shift of each logistics node;
screening out packages with abnormal states from the sum of the packages retained in the current shift and the packages retained in the previous shift of each logistics node to obtain the warehouse-retained packages generated in real time;
each warehouse-remaining package carries logistics information at least comprising current logistics nodes, destination information, time limit and physical parameters.
8. The method of claim 1, wherein after generating the elected path nodes from the logistics nodes of each of the parcel sets, further comprising:
and obtaining a first time matrix of the transport vehicle from the starting point to each path node and a second time matrix between every two path nodes based on map service.
9. A method of model training, comprising:
obtaining sample data, comprising:
generating sample parcel sets with the same logistics nodes according to the sample warehouse-leaving parcels and the logistics information thereof, and determining the forwarding time limit of each sample parcel set;
obtaining a transport vehicle with a bearing allowance and an allocated logistics node thereof;
generating necessary path nodes according to the distributed logistics nodes, and generating selected path nodes according to the logistics nodes of the sample parcel sets;
training a network model, comprising:
and taking the sample data as input, at least taking the transfer time effectiveness as a constraint condition, at least taking the number of the sample package sets transferred maximally as an objective function, and training a dynamic path planning model by taking the optimal path for guiding the transport vehicle to transfer the sample package sets as output until the model converges.
10. The method of claim 9, wherein said obtaining sample data, further comprises: obtaining a unit transportation cost of the transport vehicle;
the training network model further comprises: to minimize the total transportation cost of the vehicle as an objective function.
11. The method of claim 9, wherein said obtaining sample data, further comprises: obtaining a desired load capacity for each of the sample package sets;
the training network model further comprises: and taking the condition that the required bearing capacity of the transferred sample package set is less than the bearing allowance of the transport vehicle as a constraint condition.
12. A leave bin parcel transfer apparatus comprising:
the parcel set acquisition module is configured to generate parcel sets with the same logistics nodes according to the warehouse-remaining parcels and the logistics information thereof generated in real time, and determine the forwarding timeliness of each parcel set;
the transport vehicle acquisition module is configured to acquire a transport vehicle with a bearing allowance and the distributed logistics nodes thereof;
a path node determination module configured to generate a necessary path node according to each allocated logistics node and generate a selected path node according to the logistics node of each parcel set, with a real-time position of the transport vehicle as a starting point;
and the transfer path planning module is configured to control the transport vehicle to transfer the parcel sets along an optimal path based on a dynamic path planning model taking at least the transfer time as a constraint condition, wherein the optimal path at least maximizes the number of the transferred parcel sets.
13. A leave bin parcel forwarding system, comprising:
a plurality of logistics nodes;
the invention according to claim 12 wherein said warehouse parcel transfer device is in communication with each of said logistics nodes.
14. A model training apparatus, comprising:
a sample data acquisition module configured to:
generating sample parcel sets with the same logistics nodes according to the sample warehouse-leaving parcels and the logistics information thereof, and determining the forwarding time limit of each sample parcel set;
obtaining a transport vehicle with a bearing allowance and an allocated logistics node thereof;
generating necessary path nodes according to the distributed logistics nodes, and generating selected path nodes according to the logistics nodes of the sample parcel sets;
a network model training module configured to:
and taking the sample data as input, at least taking the transfer time effectiveness as a constraint condition, at least taking the number of the sample package sets transferred maximally as an objective function, and training a dynamic path planning model by taking the optimal path for guiding the transport vehicle to transfer the sample package sets as output until the model converges.
15. A computer device, comprising:
a processor;
a memory storing executable instructions;
wherein the executable instructions, when executed by the processor, implement the method of any of claims 1-11.
16. A computer-readable storage medium storing a computer program, wherein the computer program when executed implements the method of any one of claims 1-11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011179846.8ACN112308312B (en) | 2020-10-29 | 2020-10-29 | Warehouse-leaving package transfer method, model training method and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011179846.8ACN112308312B (en) | 2020-10-29 | 2020-10-29 | Warehouse-leaving package transfer method, model training method and related equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112308312Atrue CN112308312A (en) | 2021-02-02 |
| CN112308312B CN112308312B (en) | 2024-05-03 |
Family
ID=74331983
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011179846.8AActiveCN112308312B (en) | 2020-10-29 | 2020-10-29 | Warehouse-leaving package transfer method, model training method and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112308312B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113469417A (en)* | 2021-06-10 | 2021-10-01 | 哈尔滨工业大学 | Express vehicle transportation scheduling method, system and equipment |
| CN115007483A (en)* | 2021-03-05 | 2022-09-06 | 法麦凯尼柯数据股份公司 | Method for dynamically analyzing packages |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002193450A (en)* | 2000-12-27 | 2002-07-10 | Toyota Motor Corp | Transport freight logistics control method and logistics control system |
| JP2004001975A (en)* | 2002-06-03 | 2004-01-08 | Hitachi Ltd | How to create a two-way transportation schedule |
| JP2015000781A (en)* | 2013-06-14 | 2015-01-05 | 鍵和田 芳光 | Logistics support method, system and program |
| EA201300710A1 (en)* | 2013-07-15 | 2015-01-30 | Открытое акционерное общество "Российские железные дороги" (ОАО "РЖД") | METHOD OF MANAGING THE TRAFFIC TRAFFIC BY TIMETABLE |
| CN107145971A (en)* | 2017-04-18 | 2017-09-08 | 苏州工业职业技术学院 | A Dynamically Adjusted Express Delivery Optimization Method |
| CN107292565A (en)* | 2017-06-29 | 2017-10-24 | 浙江优展信息科技有限公司 | A kind of fresh shopping dis-tribution model in preposition storehouse |
| CN109784820A (en)* | 2019-03-28 | 2019-05-21 | 上海中通吉网络技术有限公司 | A kind of express delivery routing intelligence solution, device, terminal device and storage medium |
| CN110046749A (en)* | 2019-03-22 | 2019-07-23 | 杭州师范大学 | It is a kind of based on real-time road electric business package with city o2o wrap up Common Distribution system |
| CN110580546A (en)* | 2019-08-26 | 2019-12-17 | 安徽师范大学 | Method and system for route planning based on the same type of vehicle carrying people and goods |
| CN111325371A (en)* | 2018-12-13 | 2020-06-23 | 顺丰科技有限公司 | Transportation route planning method and system |
| CN111507497A (en)* | 2019-01-31 | 2020-08-07 | 顺丰科技有限公司 | Site selection system and method for distributed point and transit point |
| CN111553626A (en)* | 2020-04-09 | 2020-08-18 | 北京顺达同行科技有限公司 | Path planning method and device, electronic equipment and storage medium thereof |
| CN111563709A (en)* | 2020-03-31 | 2020-08-21 | 深圳市跨越新科技有限公司 | Intelligent logistics cargo link cargo collection method and system |
- 2020
- 2020-10-29CNCN202011179846.8Apatent/CN112308312B/enactiveActive
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002193450A (en)* | 2000-12-27 | 2002-07-10 | Toyota Motor Corp | Transport freight logistics control method and logistics control system |
| JP2004001975A (en)* | 2002-06-03 | 2004-01-08 | Hitachi Ltd | How to create a two-way transportation schedule |
| JP2015000781A (en)* | 2013-06-14 | 2015-01-05 | 鍵和田 芳光 | Logistics support method, system and program |
| EA201300710A1 (en)* | 2013-07-15 | 2015-01-30 | Открытое акционерное общество "Российские железные дороги" (ОАО "РЖД") | METHOD OF MANAGING THE TRAFFIC TRAFFIC BY TIMETABLE |
| CN107145971A (en)* | 2017-04-18 | 2017-09-08 | 苏州工业职业技术学院 | A Dynamically Adjusted Express Delivery Optimization Method |
| CN107292565A (en)* | 2017-06-29 | 2017-10-24 | 浙江优展信息科技有限公司 | A kind of fresh shopping dis-tribution model in preposition storehouse |
| CN111325371A (en)* | 2018-12-13 | 2020-06-23 | 顺丰科技有限公司 | Transportation route planning method and system |
| CN111507497A (en)* | 2019-01-31 | 2020-08-07 | 顺丰科技有限公司 | Site selection system and method for distributed point and transit point |
| CN110046749A (en)* | 2019-03-22 | 2019-07-23 | 杭州师范大学 | It is a kind of based on real-time road electric business package with city o2o wrap up Common Distribution system |
| CN109784820A (en)* | 2019-03-28 | 2019-05-21 | 上海中通吉网络技术有限公司 | A kind of express delivery routing intelligence solution, device, terminal device and storage medium |
| CN110580546A (en)* | 2019-08-26 | 2019-12-17 | 安徽师范大学 | Method and system for route planning based on the same type of vehicle carrying people and goods |
| CN111563709A (en)* | 2020-03-31 | 2020-08-21 | 深圳市跨越新科技有限公司 | Intelligent logistics cargo link cargo collection method and system |
| CN111553626A (en)* | 2020-04-09 | 2020-08-18 | 北京顺达同行科技有限公司 | Path planning method and device, electronic equipment and storage medium thereof |
Non-Patent Citations (3)
| Title |
|---|
| 杨埙 等: "《物联网技术概论》", 西安电子科技大学出版社, pages: 197* |
| 杨忠振;邹汶倩;: "基于蚁群算法的公路客运快递网络优化", 交通运输系统工程与信息, no. 01, 15 February 2011 (2011-02-15), pages 197 - 99* |
| 王蕾;蔡翠;裴爱晖;肖荣娜;叶静;: "基于改进蚁群算法的物流配送中多取货车辆的最优路径研究", 公路交通科技(应用技术版), no. 05, 15 May 2018 (2018-05-15), pages 328 - 331* |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115007483A (en)* | 2021-03-05 | 2022-09-06 | 法麦凯尼柯数据股份公司 | Method for dynamically analyzing packages |
| CN113469417A (en)* | 2021-06-10 | 2021-10-01 | 哈尔滨工业大学 | Express vehicle transportation scheduling method, system and equipment |
| CN113469417B (en)* | 2021-06-10 | 2022-08-05 | 哈尔滨工业大学 | Express vehicle transportation scheduling method, system and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112308312B (en) | 2024-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6668493B2 (en) | System and method for handling simultaneous carpool requests | |
| CN111868654B (en) | Route planning method and device | |
| CN111950803A (en) | Logistics object delivery time prediction method and device, electronic equipment and storage medium | |
| CN113172625A (en) | A robot scheduling method, device, equipment and storage medium | |
| KR20210008581A (en) | System for providing logistics transportation service for multi pick up and delivery with imporved navigation algorithm | |
| CN114529236B (en) | A storage management method, device, electronic device and storage medium for shelves | |
| CN112308312B (en) | Warehouse-leaving package transfer method, model training method and related equipment | |
| KR20220006726A (en) | Device and method for providing automatic distribution of milk run cargo based on route big data | |
| Ninikas et al. | Reoptimization strategies for a dynamic vehicle routing problem with mixed backhauls | |
| CN115310777A (en) | Vehicle scheduling method, device, equipment and storage medium | |
| CN113762830A (en) | Order splitting processing method, device and equipment and readable storage medium | |
| CN116415787A (en) | Logistics transportation vehicle dispatching method, system and device | |
| CN113988615A (en) | Distribution method, system, equipment and storage medium based on intercity logistics continuation | |
| CN118917766A (en) | Intelligent automatic dispatch and path planning method for running leg distribution | |
| Hassan et al. | Daily load planning under different autonomous truck deployment scenarios | |
| CN114386903B (en) | Method and device for managing and controlling waybill, electronic equipment and storage medium | |
| CN114462948A (en) | Freight scheduling processing method, device, equipment and medium | |
| CN116090689B (en) | Freight resource optimization method and system based on transfer connection | |
| CN113762689B (en) | Scheduling method, device, equipment and storage medium | |
| CN115730807A (en) | Transportation vehicle scheduling method, system, device and storage medium | |
| CN115860608A (en) | Method, device, equipment and storage medium for distributing logistics orders to freight orders | |
| CN116957463A (en) | Method, system and device for processing waybill based on transportation route | |
| CN113177661A (en) | Freight order recommendation method, device, equipment and storage medium | |
| KR102447123B1 (en) | Apparatus and method for providing box truck dispatch service based on artificial intelligence | |
| CN111738895B (en) | Multi-station passenger transport line generation method, device, medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |