KR20220006728A - Device and method for providing optimal cargo delivery route based on artificial intelligence - Google Patents

Abstract

The present invention relates to a device for providing an optimal delivery route based on artificial intelligence, which optimize costs and time for delivering cargo, and a method thereof. According to the present invention, the device comprises: a milk run order receiving unit receiving a milk run order including cargo dispatch information from a plurality of supplier terminals; a spatial distribution derivation unit using the cargo dispatch information to derive a spatial distribution of a plurality of delivery companies centering on a predetermined delivery destination by; a supplier candidate group determining unit defining a milk run area optimized for cargo transport to a predetermined supplier on the basis of the spatial distribution to determine a supplier candidate group; and a transportation route generation unit generating a milk run transportation route for disembarking cargoes, which are loaded while passing through the delivery companies included in the candidate delivery company group, at at least one delivery point in response to the milk run order.

Description

Apparatus and method for providing an optimal delivery route based on artificial intelligence {DEVICE AND METHOD FOR PROVIDING OPTIMAL CARGO DELIVERY ROUTE BASED ON ARTIFICIAL INTELLIGENCE}

The present invention relates to a technology for providing an optimal delivery route, and more particularly, to an apparatus and method for providing an optimal delivery route based on artificial intelligence capable of optimizing the cost and time for logistics delivery based on the spatial distribution of visited places.

Milkrun is a term originating from the fact that a milk company collects crude oil from livestock farms, and is currently used as a term to refer to the process of circulating products of various suppliers as a pre-logistics, loading vehicles and putting them into distribution centers of distributors. The milk run method has the advantage of being able to calculate reasonable costs through an efficient unit price calculation method according to the consignment of the freight volume of the supplier. is being focused

However, the current milkrun method is being used only in a very limited manner despite its advantages, as the person in charge manually handles the cargo dispatch or uses a simple algorithm to dispatch the cargo.

Therefore, there is a demand for technology development for maximizing the advantages of the milk run method and improving usability.

Korean Patent Publication No. 10-2016-0140035 (2016.12.07)

An embodiment of the present invention is to provide an apparatus and method for providing an artificial intelligence-based optimal delivery route capable of optimizing the cost and time for logistics delivery based on the spatial distribution of visited places.

An embodiment of the present invention is based on artificial intelligence that can improve efficiency in terms of fuel economy/time by determining a delivery route to visit only suppliers existing in a sector-shaped area that forms a predetermined central angle around the location of the delivery destination. We aim to provide an apparatus and method for providing an optimal delivery route.

Among the embodiments, the apparatus for providing an artificial intelligence-based optimal delivery route includes: a milkrun order receiver for receiving a milkrun order including freight dispatch information from a plurality of supplier terminals; a spatial distribution derivation unit for deriving a spatial distribution of a plurality of delivery companies centering on a specific delivery destination using the cargo dispatch information; a supplier candidate group determining unit for determining a supplier candidate group by defining a milkrun region optimized for freight transport to the specific supplier based on the spatial distribution; And in response to the milkrun order, it includes a transportation route generating unit that generates a milkrun transportation route for disembarking the cargoes that have been loaded while passing through the suppliers included in the candidate supplier group at at least one supplier.

The milk run area may be defined as a sector-shaped area forming a central angle of 45 degrees with respect to the location of the specific delivery destination.

The delivery company candidate group determiner may generate at least one milk run candidate area based on the spatial distribution according to the positions of available freight vehicles located in the vicinity of the specific delivery destination.

determining, by the supplier candidate group determining unit, a freight vehicle pair associated with the longest distance between the available freight vehicles; forming first virtual straight lines connecting each of the first and second freight vehicles of the freight vehicle pair at the specific delivery destination, respectively; forming second virtual straight lines forming a predetermined central angle based on the first virtual straight lines; determining a sector-shaped region formed by the first and second virtual straight lines as first and second milkrun candidate regions; and determining candidate milkrun areas formed between the first and second milkrun candidate areas and having different combinations of suppliers existing in each area.

When there are a plurality of specific suppliers, the supplier candidate group determining unit may determine the supplier candidate group by integrating milkrun areas for each of the plurality of suppliers into one.

The supplier candidate group determining unit may determine a supplier corresponding to a final destination of the milkrun transportation route by providing the plurality of suppliers as inputs based on an AI model.

The transportation route generator may process the operation related to the generation of the milk run transportation route based on an AI model generated by learning learning data including predicted weather and real-time traffic conditions for each day of the week.

Among embodiments, the method for providing an artificial intelligence-based optimal delivery route includes: receiving a milk run order including cargo dispatch information from a plurality of delivery company terminals; deriving a spatial distribution of a plurality of delivery companies around a specific delivery destination using the cargo dispatch information; determining a delivery company candidate group for freight transportation to the specific delivery destination based on the spatial distribution; and generating, as a response to the milkrun order, a milkrun transportation route for disembarking cargoes that have been loaded while passing through the suppliers included in the candidate supplier group at at least one supplier.

The disclosed technology may have the following effects. However, this does not mean that a specific embodiment should include all of the following effects or only the following effects, so the scope of the disclosed technology should not be understood as being limited thereby.

The artificial intelligence-based optimal delivery route providing apparatus and method according to an embodiment of the present invention can optimize the cost and time for logistics delivery based on the spatial distribution of visited places.

The artificial intelligence-based optimal delivery route providing apparatus and method according to an embodiment of the present invention determines the delivery route to visit only the delivery companies that exist within the fan-shaped area forming a predetermined central angle with respect to the location of the delivery destination. /It can improve efficiency in terms of time.

1 is a view for explaining an optimal delivery route providing system according to the present invention.
FIG. 2 is a view for explaining a system configuration of the apparatus for providing an optimal delivery route of FIG. 1 .
FIG. 3 is a view for explaining a functional configuration of the apparatus for providing an optimal delivery route of FIG. 1 .
4 is a flowchart illustrating a process of providing an artificial intelligence-based optimal delivery route according to an embodiment of the present invention.
5 and 6 are diagrams for explaining a process of providing an artificial intelligence-based optimal delivery route according to an embodiment of the present invention.

Since the description of the present invention is merely an embodiment for structural or functional description, the scope of the present invention should not be construed as being limited by the embodiment described in the text. That is, since the embodiment may have various changes and may have various forms, it should be understood that the scope of the present invention includes equivalents capable of realizing the technical idea. In addition, since the object or effect presented in the present invention does not mean that a specific embodiment should include all of them or only such effects, it should not be understood that the scope of the present invention is limited thereby.

On the other hand, the meaning of the terms described in the present application should be understood as follows.

Terms such as “first” and “second” are for distinguishing one component from another, and the scope of rights should not be limited by these terms. For example, a first component may be termed a second component, and similarly, a second component may also be termed a first component.

When a component is referred to as being “connected to” another component, it may be directly connected to the other component, but it should be understood that other components may exist in between. On the other hand, when it is mentioned that a certain element is "directly connected" to another element, it should be understood that the other element does not exist in the middle. Meanwhile, other expressions describing the relationship between elements, that is, "between" and "between" or "neighboring to" and "directly adjacent to", etc., should be interpreted similarly.

The singular expression is to be understood as including the plural expression unless the context clearly dictates otherwise, and terms such as "comprises" or "have" refer to the embodied feature, number, step, action, component, part or these It is intended to indicate that a combination exists, and it should be understood that it does not preclude the possibility of the existence or addition of one or more other features or numbers, steps, operations, components, parts, or combinations thereof.

In each step, identification numbers (eg, a, b, c, etc.) are used for convenience of description, and identification numbers do not describe the order of each step, and each step clearly indicates a specific order in context. Unless otherwise specified, it may occur in a different order from the specified order. That is, each step may occur in the same order as specified, may be performed substantially simultaneously, or may be performed in the reverse order.

The present invention can be embodied as computer-readable codes on a computer-readable recording medium, and the computer-readable recording medium includes all types of recording devices in which data readable by a computer system is stored. . Examples of the computer-readable recording medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, and the like. In addition, the computer-readable recording medium is distributed in a computer system connected to a network, so that the computer-readable code can be stored and executed in a distributed manner.

All terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs, unless otherwise defined. Terms defined in general used in the dictionary should be interpreted as having the meaning consistent with the context of the related art, and cannot be interpreted as having an ideal or excessively formal meaning unless explicitly defined in the present application.

1 is a view for explaining an optimal delivery route providing system according to the present invention.

Referring to FIG. 1 , the optimal delivery route providing system 100 may include a delivery company terminal 110 , a delivery destination terminal 130 , an optimal delivery route providing device 150 , and a database 170 .

The supplier terminal 110 may correspond to a computing device operated by a company that provides logistics delivery, and may be implemented as a smartphone, a notebook computer, or a computer, but is not necessarily limited thereto, and may be implemented in various devices such as a tablet PC. can be The delivery company terminal 110 may be connected to the optimal delivery route providing apparatus 150 through a network, and a plurality of delivery company terminals 110 may be simultaneously connected to the optimal delivery route providing apparatus 150 . In addition, the delivery company terminal 110 may provide an integrated system for logistics delivery and management including a dispatch request for cargo transportation through a dedicated program.

In one embodiment, the delivery company terminal 110 generates a transportation request management module for managing a cargo transportation request, a stock management module for managing inventory of cargo according to cargo transportation, and generates transportation information for each day of the week according to the cargo transportation request and based on it It can be implemented including a transport order processing module for transmitting the raw milkrun transport order and a cargo database for storing cargo information.

The delivery destination terminal 130 may correspond to a computing device operated by a company that receives logistics delivery, and may be implemented as a smartphone, a laptop computer, or a computer, and is not necessarily limited thereto, and may be implemented in various devices such as a tablet PC. can The delivery destination terminal 130 may be connected to the optimal delivery route providing apparatus 150 through a network, and a plurality of delivery destination terminals 130 may be simultaneously connected to the optimal delivery route providing apparatus 150 . In addition, the delivery destination terminal 130 may provide an integrated system for logistics warehousing and management, including warehousing inspection and receipt confirmation through a dedicated program.

In one embodiment, the delivery terminal 130 is a transport request management module for managing a cargo transport request, a warehousing cargo management module for managing warehousing cargo according to cargo transport, and generates warehousing information for each day of the week according to the cargo transport request and based on this It can be implemented including a cargo database for storing cargo information and a cargo storage prediction module for predicting the cargo for each day of the week.

The optimal delivery route providing device 150 is a computer or program that can create and provide an optimal delivery route by supplementing the shortcomings of the existing logistics delivery system and applying artificial intelligence built with deep learning based on route big data. It can be implemented as a server. The optimal delivery route providing apparatus 150 may be connected to the delivery company terminal 110 and the delivery destination terminal 130 through a network to exchange data. In addition, the optimal delivery route providing apparatus 150 may provide an integrated system for processing and managing cargo dispatch for logistics delivery and warehousing.

More specifically, the apparatus 150 for providing an optimal delivery route may provide a cargo dispatch system that supplements the existing problems as follows.

1) The problem of specifying the delivery route and vehicle tonnage by automatic routing by a simple algorithm: The optimal delivery route providing device 150 is optimized based on the predicted weather for each day of the week and real-time traffic conditions (time to work and heavy traffic) through AI It is possible to derive the order of visitation, tonnage sorting and vehicle dispatch, and the high-accuracy real-time estimated warehousing time for each supplier and real-time estimated arrival time for the delivery destination (disembarkation point) can be calculated to provide the best service.

2) Problem of not predicting/measuring the amount of orders per supplier/day of the week: The optimal delivery route providing device 150 analyzes the amount of orders by supplier/day of the week through AI and calculates the expected quantity, so that the vehicle can be dispatched in advance. , it is possible to reduce the lead time for vehicle dispatch through this.

3) Difficulty in calculating the quantity (boxes) loaded on the pallet by each supplier: The optimal delivery route providing device 150 calculates the box size and weight for each supplier through AI and calculates the box quantity and loading rate for each vehicle to select the optimal vehicle can proceed. That is, the optimal delivery route providing apparatus 150 can provide a service for automatically calculating and calculating how many pallets are needed according to the box quantity by enabling an order with not only the quantity of pallets but also the quantity of boxes.

4) The problem that the unit price of milk run service fee is measured as a fixed unit price by distance: The optimal delivery route providing device 150 calculates the arrival time of the real-time traffic situation through AI, and can provide the service at a flexible unit price .

5) Problem that cost measurement for various condition values is all done manually: The optimal delivery route providing device 150 links the control system with AI to generate waiting times for each supplier and waiting after arrival for each drop off location Measures can be automatically measured to calculate the total cost.

6) In the case of a type of milk run that is delivered to a single warehouse after pickup from multiple suppliers: The optimal delivery route providing device 150 uses AI to pick up one supplier and deliver to multiple destinations, and after pickup from multiple suppliers Optimal routing can be calculated even for types of delivery to multiple destinations.

In an embodiment, the apparatus 150 for providing an optimal delivery route may store various data necessary for providing an optimal delivery route based on artificial intelligence in conjunction with the database 170 . In addition, the optimal delivery route providing apparatus 150 may be implemented including a processor, a memory, a user input/output unit, and a network input/output unit, which will be described in more detail with reference to FIG. 2 .

The database 170 may correspond to a storage device for storing various pieces of information required in the operation process of the apparatus for providing an optimal delivery route 150 . The database 170 may store information on various freight vehicles, suppliers, and delivery destinations, and may store information on AI models for freight dispatch and optimal delivery route derivation, but is not necessarily limited thereto, and optimal delivery route creation Information collected or processed in various forms during the process can be stored.

FIG. 2 is a view for explaining a system configuration of the apparatus for providing an optimal delivery route of FIG. 1 .

Referring to FIG. 2 , the apparatus for providing an optimal delivery route 150 may be implemented including a processor 210 , a memory 230 , a user input/output unit 250 , and a network input/output unit 270 .

The processor 210 may execute a procedure for processing each step in the process in which the optimal delivery route providing device 150 operates, and manage the memory 230 that is read or written throughout the process, and the memory A synchronization time between the volatile memory and the non-volatile memory in 230 may be scheduled. The processor 210 may control the overall operation of the apparatus for providing an optimal delivery route 150 , and is electrically connected to the memory 230 , the user input/output unit 250 , and the network input/output unit 270 to control the data flow therebetween. can be controlled The processor 210 may be implemented as a central processing unit (CPU) of the apparatus 150 for providing an optimal delivery route.

The memory 230 is implemented as a non-volatile memory, such as a solid state drive (SSD) or a hard disk drive (HDD), and may include an auxiliary storage device used to store overall data required for the apparatus 150 for providing an optimal delivery route. and may include a main memory implemented as a volatile memory such as random access memory (RAM).

The user input/output unit 250 may include an environment for receiving a user input and an environment for outputting specific information to the user. For example, the user input/output unit 250 may include an input device including an adapter such as a touch pad, a touch screen, an on-screen keyboard, or a pointing device, and an output device including an adapter such as a monitor or a touch screen. In an embodiment, the user input/output unit 250 may correspond to a computing device accessed through remote access, and in such a case, the optimal delivery route providing device 150 may be implemented as a server.

The network input/output unit 270 includes an environment for connecting with an external device or system through a network, for example, a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), and a VAN (Wide Area Network) (VAN). It may include an adapter for communication such as Value Added Network).

FIG. 3 is a view for explaining a functional configuration of the apparatus for providing an optimal delivery route of FIG. 1 .

Referring to FIG. 3 , the optimal delivery route providing apparatus 150 includes a milk run order receiver 310 , a spatial distribution derivation part 320 , a delivery company candidate group determiner 330 , a transport route generator 340 , and a controller ( 350) may be included.

The milk run order receiving unit 310 may receive a milk run order including freight dispatch information from a plurality of delivery company terminals 110 . Here, the freight dispatch information may correspond to information necessary for freight transportation and dispatch. For example, cargo dispatch information may include cargo content, loading location, unloading location, loading time, unloading time, cargo cost, cargo capacity, pallet size and number, and the like. In addition, the milk run order may correspond to a freight transport order, and may include pre-approval for the freight transport to be processed in a milk run method. That is, the delivery company terminal 110 may request a milk run order while inputting information necessary for freight transportation, and the optimal delivery route providing device 150 receives it and optimal delivery for processing together with other milk run orders. path can be determined.

In one embodiment, the milk run order receiving unit 310 may automatically receive the milk run order according to the quantity information for each supplier predicted through artificial intelligence. That is, the milk run order receiving unit 310 considers that a virtual milk run order is requested based on the predicted quantity for each supplier predicted by the AI model even when there is no direct receipt of the milk run order from the supplier terminal 110 . Thus, the operation of receiving milk run orders can be automatically processed. To this end, the milk run order receiving unit 310 may receive a prior consent regarding the automatic generation and reception of the milk run order from the corresponding supplier terminal 110 .

The spatial distribution derivation unit 320 may derive the spatial distribution of a plurality of delivery companies centering on a specific delivery destination by using the cargo dispatch information. In the case of milk run transportation, it is processed by visiting a plurality of suppliers sequentially, loading the cargo, and finally visiting the supplier to unload the cargo. Costs may vary. In particular, the location of suppliers who need to visit, that is, spatial distribution may correspond to the factor that has the greatest influence on transportation time or cost.

That is, the spatial distribution derivation unit 320 may extract information on delivery places that need to be visited based on the freight dispatch information, and may derive the spatial distribution based on this information. Here, the spatial distribution may be defined including location information on the electronic map, and may be expressed as two-dimensional or three-dimensional information according to a space defined on the electronic map.

The supplier candidate group determining unit 330 may determine the supplier candidate group by defining a milkrun region optimized for freight transportation to a specific supplier based on the spatial distribution. In this case, the milk run region may be defined as a sector-shaped region forming a predetermined central angle with respect to the location of a specific delivery destination. The milk run area may correspond to an area with a high probability of deriving an optimized delivery route in milk run transport. In other words, if only suppliers located within the Milkrun area can visit and load cargo and then transport the cargo to a specific delivery location, it is possible to achieve optimized cargo transportation in terms of cost/time.

Meanwhile, the candidate supplier group may correspond to a set of suppliers located in the milkrun area, and the milkrun transportation route may correspond to a movement route for visiting only suppliers included in the candidate supplier group. When the milk run area is determined, the supplier candidate group determiner 330 may create a supplier candidate group by grouping suppliers existing in the milk run area into one.

In one embodiment, the milk run area may be defined as a sector-shaped area forming a central angle of 45 degrees with respect to the location of a specific delivery destination. As a result of analyzing the delivery information collected during the milkrun method of freight transportation, when visiting a supplier that is outside the area within a radius of about 45 degrees centered on the location of the delivery destination corresponding to the final destination, fuel economy/time, etc. Inefficiencies may occur.

Accordingly, the supplier candidate group determining unit 330 defines a sector-shaped region forming a central angle of 45 degrees centered on the location of a specific supplier as the milk run area, and selects the supplier candidate group consisting of only suppliers existing in the milk run area. By determining it, it is possible to increase the probability that the milk run transportation route generated based on this will become the optimal delivery route. On the other hand, the milk run area is a sector-shaped area centered on a specific delivery destination, and may be extended from the center to the outside, and may be limitedly determined within a specific radius from the center if necessary.

In an embodiment, the delivery company candidate group determiner 330 may generate at least one milk run candidate area according to the locations of available freight vehicles located in the vicinity of a specific delivery destination based on the spatial distribution. The available freight vehicle may correspond to a freight vehicle that is not currently delivering freight and can handle freight dispatch normally. The supplier candidate group determining unit 330 may determine freight vehicles located in the vicinity of a specific delivery destination as available freight vehicles, and may determine a milk run candidate area based on the location of the available freight vehicle. The milk run candidate area may correspond to a candidate area that is likely to be determined as the milk run area.

On the other hand, the supplier candidate group determining unit 330 determines the available freight vehicle based on the condition of the freight vehicle located in the vicinity of the specific delivery destination, but is not limited thereto, and the available freight according to the conditions related to the milk run method freight transportation. Of course, you can also decide on a vehicle.

In one embodiment, the supplier candidate group determining unit 330 determines a freight vehicle pair associated with the longest distance between available freight vehicles, the first and second freight vehicles of the freight vehicle pair at a specific delivery destination Forming first virtual straight lines connecting each, forming virtual second straight lines forming a predetermined central angle based on the virtual first straight lines, respectively, on the virtual first and second straight lines Determining the sector-shaped region formed by It may operate through the step of determining the milkrun candidate regions.

More specifically, the supplier candidate group determining unit 330 may determine a freight vehicle pair associated with the longest distance between available freight vehicles. That is, the supplier candidate group determining unit 330 may determine a freight vehicle pair by grouping available freight vehicles that exist at the farthest distance among available freight vehicles.

In addition, the supplier candidate group determining unit 330 may form first virtual straight lines connecting each of the first and second freight vehicles of the freight vehicle pair at a specific delivery destination, respectively. That is, the supplier candidate group determining unit 330 may form a first virtual straight line passing through the first freight vehicle constituting the freight vehicle pair at the location of the specific delivery destination, and configuring the freight vehicle pair at the location of the specific delivery destination. Another virtual first straight line passing through the second freight vehicle may be formed.

Also, the supplier candidate group determining unit 330 may form second virtual straight lines forming a predetermined central angle based on the first virtual straight lines. That is, the supplier candidate group determining unit 330 may form a first virtual straight line passing through the first freight vehicle and a second virtual straight line forming a predetermined central angle, and another virtual second line passing through the second freight vehicle. Another imaginary second straight line forming a predetermined central angle with the first straight line may be formed.

Also, the supplier candidate group determiner 330 may determine the sector-shaped region formed by the first and second virtual straight lines as the first and second milkrun candidate regions. That is, the first milk run candidate area may correspond to an area formed based on a straight line passing through the first freight vehicle, and the second milk run candidate area may correspond to an area formed based on a straight line passing through the second freight vehicle. have.

Also, the supplier candidate group determiner 330 may determine the milkrun candidate regions that are formed between the first and second milkrun candidate regions and have different combinations of suppliers existing in each region. That is, different milkrun candidate areas may be formed even between the first and second milkrun candidate areas formed based on each of the first and second freight vehicles, and suppliers included in each of the milkrun candidate areas may be different from each other.

As a result, the supplier candidate group determining unit 330 may determine virtual areas capable of handling milkrun freight transportation using available freight vehicles as milkrun candidate areas, and among them, The milkrun area to be used can be finally determined.

In an embodiment, when there are a plurality of specific suppliers, the supplier candidate group determiner 330 may determine the supplier candidate group by integrating milkrun areas for each of the plurality of suppliers into one. The milkrun method of freight transportation can basically be performed by sequentially visiting a plurality of suppliers to load and unload the freight, and finally visit one supplier to unload the freight. You can also unload cargo. The supplier candidate group determining unit 330 may determine milkrun areas for each of the suppliers when there are two or more suppliers that provide disembarkation of cargo on the milkrun transportation route, and finally determine the milkrun areas for each of the suppliers. By integrating them into one, the final milk run area can be determined, and based on this, the candidate group can be determined.

In an embodiment, the supplier candidate group determiner 330 may determine a supplier corresponding to the final destination of the milkrun transportation route by providing a plurality of suppliers as inputs based on the AI model. In the milkrun method, freight can be unloaded by sequentially visiting a plurality of suppliers and loading and unloading freight by sequentially visiting a plurality of suppliers. can be used to determine the last delivery destination along the Milkrun transport route.

To this end, the optimal delivery route providing device 150 may generate various AI models by learning variously collected cargo delivery information. The delivery destination can be determined as the final destination. That is, the AI model can learn big data about the delivery route where the cargo is delivered and the delivery unit price according to it based on the dispatch information on which the cargo has been dispatched. In particular, the AI model may provide information on the probability of corresponding to the final destination for each delivery point existing on the delivery route as an output.

As a response to the milk run order, the transport route generating unit 340 may generate a milk run transport route for disembarking cargoes that have been loaded while passing through the suppliers included in the supplier candidate group at at least one supplier. That is, the transportation route generator 340 may derive an optimal visiting route by considering the milk run orders received from various suppliers in an integrated manner. The milkrun transportation route derived through the transportation route generator 340 is basically a method of loading and unloading cargo while sequentially visiting a plurality of delivery companies, arriving at the final destination, and disembarking the cargo. It may correspond to the optimal path.

In addition, the transportation route generator 340 may generate a milk run transportation route by using various route generation algorithms as needed, and may generate a milk run transportation route using a pre-established AI model. The transport route generating unit 340 may generate a preliminary set of suppliers included on the milk run transport route as a candidate supplier group in a previous stage of generation of the milk run transport route. As a result, the transportation route generating unit 340 may generate a milk run transportation route for the candidate delivery company, and in this case, the delivery company candidate group is a condition for creating an optimal delivery route, and includes delivery companies existing in a specific area. can consist of only

In an embodiment, the transportation route generator 340 may process an operation related to generation of a milk run transportation route based on an AI model generated by learning learning data including predicted weather and real-time traffic conditions for each day of the week. To this end, the apparatus 150 for providing an optimal delivery route may build an AI model by collecting various pieces of information regarding cargo dispatch in a cargo transportation process. In particular, the AI model can be used for real-time route optimization in the process of cargo dispatch, information utilization between cargo vehicles, distribution and logistics demand forecasting, and resource utilization. The transportation route generator 340 generates an optimal delivery route according to the supplier location, cargo volume, visit order, traffic conditions and weather for milk run-type cargo transportation through an AI model built by learning route big data. can

In one embodiment, the transport route generating unit 340 applies the freight transport conditions including the number of pallets per truck size, the total weight, the distance for each bundle of visits, and the time required to warehouse warehousing, based on the AI model, for milkrun transport You can create a route. In this case, the milk run transportation route may be separately generated for each priority regarding the minimum cost, the minimum time, and the minimum distance.

More specifically, the transportation route generator 340 may generate a milk run transportation route in consideration of various cargo transportation conditions, and for this purpose, it is possible to perform learning of the AI model in advance. At this time, the AI model can be built to learn the training data including various freight transport conditions and output the optimal transport route suitable for it as a result.

The control unit 350 controls the overall operation of the optimal delivery route providing device 150, the milk run order receiver 310, the spatial distribution derivation unit 320, the delivery company candidate group determiner 330, and the transportation route generator ( 340) may manage a control flow or data flow between the 340).

4 is a flowchart illustrating a process of providing an artificial intelligence-based optimal delivery route according to an embodiment of the present invention.

Referring to FIG. 4 , the optimal delivery route providing apparatus 150 may receive a milk run order including freight dispatch information from a plurality of delivery company terminals 110 through the milk run order receiving unit 310 (step S410). The optimal delivery route providing apparatus 150 may derive the spatial distribution of a plurality of delivery companies centering on a specific delivery destination by using the cargo dispatch information through the spatial distribution derivation unit 320 (step S430).

In addition, the optimal delivery route providing apparatus 150 may determine the delivery company candidate group by defining a milkrun region optimized for freight transportation to a specific delivery destination based on the spatial distribution through the delivery company candidate group determining unit 330 (step S450). As a response to the milk run order through the transportation route generating unit 340, the optimal delivery route providing device 150 provides milk for disembarking cargoes that have been loaded while passing through the delivery companies included in the delivery company candidate group at at least one delivery location. A run transportation route may be created (step S470).

5 and 6 are diagrams for explaining a process of providing an artificial intelligence-based optimal delivery route according to an embodiment of the present invention.

5 and 6 , the optimal delivery route providing apparatus 150 visits a plurality of delivery companies 520 to load and unload cargo, and visits one delivery point 510 to unload cargo. It is possible to create an optimal delivery route for

In particular, the optimal delivery route providing apparatus 150 may generate a milk run transportation route through an AI model built through artificial intelligence learning. The optimal delivery route providing apparatus 150 may determine a milkrun area in which an optimal delivery route can be derived in terms of cost/fuel efficiency in the stage before generating the milkrun transportation route, and based on the milkrun area, the milkrun transportation route can create

In FIG. 5 , the milkrun area may be determined as any one of the milkrun candidate areas 550a and 550b, and the milkrun area may be defined as a sector-shaped area that extends radially around the location of the delivery destination 510. have. In one embodiment, the optimal delivery route providing apparatus 150 may determine the available freight vehicles 530 based on the location of the delivery destination 510, and the distance between the available freight vehicles 530 is associated with the longest distance. A pair of freight vehicles can be determined. In this case, the available freight vehicles 530 may correspond to freight vehicles existing within the dispatch area 540 defined as an area within a specific radius r around the location of the delivery destination 510 , and the freight vehicle pair is the available freight. It may consist of vehicles (a) and (b).

In addition, the optimal delivery route providing apparatus 150 may generate first virtual straight lines (a') and (b') connecting each of the available freight vehicles (a) and (b) at the delivery destination 510, respectively, and , virtual second straight lines (a'') and (b'') that form a predetermined central angle α based on the first virtual straight lines (a') and (b') may be generated, respectively. The optimal delivery route providing apparatus 150 may determine the sector-shaped area formed by the first and second virtual straight lines as the first and second milkrun candidate areas 550a and 550b.

On the other hand, the optimal delivery route providing apparatus 150 is formed between the first and second milkrun candidate areas 550a and 550b and selects milkrun candidate areas in which the combination of the delivery companies 520 present in each area is different from each other. You can also create additional ones.

As a result, the optimal delivery route providing apparatus 150 may determine any one of the milkrun candidate areas 550a and 550b as the milkrun area, and may generate a milkrun transportation route based on the milkrun area. , in this case, an AI model can be utilized.

In FIG. 6 , one 550a of the milkrun candidate areas of FIG. 5 may be determined as a milkrun area, and the optimal delivery route providing apparatus 150 generates a milkrun transportation route 610 based on the corresponding milkrun area. can do. That is, the milk run transport route 610 may correspond to a delivery route that sequentially visits only the delivery companies 520 existing in the milk run area formed in a sectoral shape with a central angle of α centered on the location of the delivery destination 510. In addition, it may correspond to a movement route of sequentially visiting the delivery companies 520 using the location of the available freight vehicle 530 as a starting point and finally visiting the delivery destination 510 .

Although the above has been described with reference to the preferred embodiment of the present invention, those skilled in the art can variously modify and change the present invention within the scope without departing from the spirit and scope of the present invention as described in the claims below. You will understand that it can be done.

100: Optimal delivery route providing system
110: supplier terminal 130: supplier terminal
150: device for providing an optimal delivery route 170: database
210: processor 230: memory
250: user input/output unit 270: network input/output unit
310: milk run order receiving unit 320: spatial distribution derivation unit
330: delivery company candidate group determination unit 340: transportation route generation unit
350: control unit
510: delivery company 520: delivery company
530: available freight vehicle 540: dispatch area
550a, 550b: milkrun candidate regions
610: milk run transport route

Claims (8)

a milk run order receiving unit for receiving a milk run order including freight dispatch information from a plurality of supplier terminals;
a spatial distribution derivation unit for deriving a spatial distribution of a plurality of delivery companies centering on a specific delivery destination using the cargo dispatch information;
a supplier candidate group determining unit for determining a supplier candidate group by defining a milk run area optimized for freight transport to the specific supplier based on the spatial distribution; and
In response to the milkrun order, a transportation route generating unit for generating a milkrun transportation route for disembarking cargoes that have been loaded while passing through the delivery companies included in the candidate delivery company group at at least one delivery point,
The milkrun area is an artificial intelligence-based optimal delivery route providing apparatus defined as a sector-shaped area forming a predetermined central angle around the location of the specific delivery destination.
According to claim 1, wherein the milk run region
Artificial intelligence-based optimal delivery route providing apparatus, characterized in that it is defined as a sector-shaped area forming a central angle of 45 degrees around the location of the specific delivery destination.
According to claim 1, wherein the supplier candidate group determining unit
The apparatus for providing an optimal delivery route based on artificial intelligence, characterized in that based on the spatial distribution, at least one milk run candidate area is generated according to the positions of available freight vehicles located in the vicinity of the specific delivery destination.
According to claim 3, wherein the supplier candidate group determining unit
determining a freight vehicle pair associated with the longest distance between the available freight vehicles;
forming first virtual straight lines connecting each of the first and second freight vehicles of the freight vehicle pair at the specific delivery destination, respectively;
forming second virtual straight lines forming a predetermined central angle based on the first virtual straight lines;
determining a sector-shaped region formed by the first and second virtual straight lines as first and second milkrun candidate regions; and
An artificial intelligence-based optimal delivery route, characterized in that it operates through the step of determining candidate milkrun areas formed between the first and second milkrun candidate areas and having different combinations of suppliers existing in each area provided device.
According to claim 1, wherein the supplier candidate group determining unit
When there are a plurality of specific delivery points, the apparatus for providing the optimal delivery route based on artificial intelligence, characterized in that the milk run areas for each of the plurality of delivery points are integrated into one to determine the delivery company candidate group.
The method of claim 5, wherein the supplier candidate group determining unit
An apparatus for providing an optimal delivery route based on artificial intelligence, characterized in that by providing the plurality of delivery points as inputs based on an AI model, a delivery location corresponding to the final destination of the milkrun transportation route is determined.
According to claim 1, wherein the transport route generating unit
An apparatus for providing an optimal delivery route based on artificial intelligence, characterized in that the operation related to the generation of the milk run transportation route is processed based on the AI model generated by learning the learning data including the predicted weather and real-time traffic conditions for each day of the week.
Receiving a milk run order including cargo dispatch information from a plurality of delivery company terminals;
deriving a spatial distribution of a plurality of delivery companies around a specific delivery destination using the cargo dispatch information;
determining a delivery company candidate group by defining a milkrun region optimized for freight transportation to the specific delivery destination based on the spatial distribution; and
In response to the milkrun order, generating a milkrun transportation route for disembarking cargoes that have been loaded while passing through the suppliers included in the candidate supplier group at at least one supplier,
The milkrun area is an artificial intelligence-based optimal delivery route providing method defined as a sector-shaped area forming a predetermined central angle around the location of the specific delivery destination.

Images