Device and method for managing logistics, and recording medium for recording instructions

Abstract

The present disclosure provides a device comprising one or more processors, and one or more memories in which instructions to be executed by the one or more processors are stored, wherein, upon execution of the instructions, the one or more processors are configured to: receive, from a camera, first information on an image of a target parcel in which a product is packaged; receive, from a scanner, second information acquired by scanning one or more identification codes for the target parcel; on the basis of the first information and the second information, determine a target area to which the target parcel needs to be transported for delivery; and control a sorter to transport the target parcel to the target area, and the one or more processors are configured to: in determining the target area, determine, on the basis of the first information, whether the target parcel is packaged in a predetermined first packaging type; according to a determination that the target parcel is packaged in the first packaging type, determine, on the basis of the second information, whether a packaging identification code for the target parcel has been scanned; and according to a determination that the packing identification code has not been scanned, determine the target area as a predetermined holding area.

Description

A recording medium that records devices, methods, and commands for managing logistics

[0001] The present disclosure relates to technology for managing logistics.

[0002] Due to the development of communication technology, e-commerce services for trading goods online are being widely used. The range of products covered by e-commerce services is expanding to include even fresh foods such as food.

[0003] As the range of products covered by e-commerce services diversifies in this way, various types of goods can be packaged using suitable packaging materials. For the packaged parcels, a dispatch operation is performed to ship them to customers.

[0004] At least one embodiment of the present disclosure can manage a parcel of a product that has been packaged.

[0005] The technical problems of the present disclosure are not limited to those mentioned above, and other unmentioned technical problems will be clearly understood by a person skilled in the art from the description in the specification.

[0006] An apparatus according to one embodiment of the present disclosure comprises one or more processors and one or more memories in which instructions to be executed by the one or more processors are stored. When the instructions are executed, the one or more processors receive first information regarding an image of a target parcel containing a product from a camera, and receive second information obtained by scanning one or more identification codes for the target parcel from a scanner. Based on the first information and the second information, the processor determines a target area to which the target parcel is to be transported for delivery, and controls a sorter to transport the target parcel to the target area. In determining the target area, the processor determines whether the target parcel is packaged in a predetermined first packaging type based on the first information, and based on the determination that the target parcel is packaged in the first packaging type, determines whether a packaging identification code for the target parcel has been scanned based on the second information, and based on the determination that the packaging identification code has not been scanned, the processor determines the target area as a predetermined hold area.

[0007] In one embodiment, the second information may be information obtained by scanning the outside of the target parcel passing through the classifier from the scanner.

[0008] In one embodiment, the one or more processors may be configured to determine whether the target parcel is packaged in the first packaging type by inputting the first information to an artificial neural network trained to identify a packaging type from an image of the parcel, obtaining a predicted packaging type for the target parcel as the output of the artificial neural network, determining whether the predicted packaging type is the same as the first packaging type, and determining that the target parcel is packaged according to the first packaging type in response to the determination that the predicted packaging type is the same as the first packaging type.

[0009] In one embodiment, the one or more processors may be configured to acquire third information indicating whether the target parcel is packaged in the first packaging type from a worker terminal of a worker on the side of the holding area, in accordance with the determination of the target area as the holding area, and in response to acquiring the third information indicating that the target parcel is not packaged in the first packaging type, generate learning information by labeling the first information to indicate that it is not the first packaging type, and further train the artificial neural network based on the learning information.

[0010] In one embodiment, the one or more processors may be configured to determine whether a packaging identification code for the target parcel has been scanned based on the second information in accordance with the determination that the target parcel has not been packaged in the first packaging type, generate learning information by labeling the first information to indicate the first packaging type in accordance with the determination that the packaging identification code has been scanned, and further train the artificial neural network based on the learning information.

[0011] In one embodiment, the first packaging type may be a packaging type that requires retrieval after the target parcel has been delivered.

[0012] In one embodiment, the one or more processors may be configured to determine the target area as a predetermined delivery area rather than the holding area, based on the determination that the target parcel is not packaged in the first packaging type when determining the target area.

[0013] In one embodiment, the one or more processors may be configured to determine the target area as the delivery area corresponding to the delivery destination in response to obtaining the second information by scanning an invoice identification code for the target parcel in determining the target area—wherein the invoice identification code includes information regarding the delivery destination of the target parcel.

[0014] In one embodiment, the one or more processors may be configured to acquire fourth information indicating a packaging type to be used for packaging of the product, and in determining the target area, determine whether the fourth information indicates the first packaging type, and in response to the determination that the fourth information indicates the first packaging type, determine the target area based on the first information and the second information.

[0015] In one embodiment, the one or more processors may be configured to determine the target area as a predetermined delivery area rather than the hold area in response to a decision that the first packaging type is not indicated in the fourth information when determining the target area.

[0016] A method according to one embodiment of the present disclosure is performed in a device comprising one or more processors and one or more memories in which instructions to be executed by the one or more processors are stored, wherein the one or more processors include the steps of: receiving first information regarding an image of a target parcel containing a product from a camera; receiving second information obtained by scanning one or more identification codes for the target parcel from a scanner; determining a target area to which the target parcel is to be transported for delivery based on the first information and the second information; and controlling a sorter to transport the target parcel to the target area. The step of determining the target area may include the steps of: determining whether the target parcel is packaged in a predetermined first packaging type based on the first information; determining whether a packaging identification code for the target parcel has been scanned based on the second information based on the determination that the target parcel is packaged in the first packaging type; and determining the target area as a predetermined hold area based on the determination that the packaging identification code has not been scanned.

[0017] In one embodiment, the second information may be information obtained by scanning the outside of the target parcel passing through the classifier from the scanner.

[0018] In one embodiment, the step of determining whether the target parcel is packaged in the first packaging type may include: inputting the first information into an artificial neural network trained to identify a packaging type from an image of the parcel, thereby obtaining a predicted packaging type for the target parcel as the output of the artificial neural network; determining whether the predicted packaging type is the same as the first packaging type; and determining that the target parcel is packaged according to the first packaging type in response to the determination that the predicted packaging type is the same as the first packaging type.

[0019] In one embodiment, the method may further include the steps of: the one or more processors determining the target area as the hold area, obtaining third information from a worker terminal of a worker on the hold area side indicating whether the target parcel is packaged in the first packaging type; generating learning information by labeling the first information to indicate that it is not the first packaging type in response to obtaining the third information indicating that the target parcel is not packaged in the first packaging type; and additionally training the artificial neural network based on the learning information.

[0020] In one embodiment, the one or more processors may further include the steps of: determining whether a packaging identification code for the target parcel has been scanned based on the second information, in accordance with the determination that the target parcel has not been packaged in the first packaging type; generating learning information by labeling the first information to indicate the first packaging type, in accordance with the determination that the packaging identification code has been scanned; and further training the artificial neural network based on the learning information.

[0021] In one embodiment, the first packaging type may be a packaging type that requires retrieval after the target parcel has been delivered.

[0022] In one embodiment, the step of determining the target area may include determining the target area as a predetermined delivery area rather than the holding area, based on the determination that the target parcel is not packaged in the first packaging type.

[0023] In one embodiment, the step of determining the target area may include, in response to obtaining the second information by scanning an invoice identification code for the target parcel—wherein the invoice identification code includes information regarding the delivery destination of the target parcel—determining the target area as the delivery area corresponding to the delivery destination.

[0024] In one embodiment, the step of determining the target area may include: obtaining fourth information indicating a packaging type to be used for packaging of the product; determining whether the fourth information indicates the first packaging type; and determining the target area based on the first information and the second information in response to the determination that the fourth information indicates the first packaging type.

[0025] A recording medium according to one embodiment of the present disclosure is a non-transient computer-readable recording medium that records instructions for one or more processors to perform operations when executed by one or more processors, wherein the instructions are configured such that the one or more processors receive first information regarding an image of a target parcel containing a product from a camera, receive second information obtained by scanning one or more identification codes for the target parcel from a scanner, determine a target area to which the target parcel is to be transported for delivery based on the first information and the second information, and control a sorter to transport the target parcel to the target area, wherein in determining the target area, the processor determines whether the target parcel is packaged in a predetermined first packaging type based on the first information, determines whether a packaging identification code for the target parcel has been scanned based on the second information based on the determination that the target parcel is packaged in the first packaging type, and determines the target area as a predetermined hold area based on the determination that the packaging identification code has not been scanned.

[0026] According to one embodiment of the present disclosure, a parcel of a product with completed packaging can be managed.

[0027] The effects according to the technical concept of the present disclosure are not limited to those mentioned above, and other unmentioned effects will be clearly understood by a person skilled in the art of the present disclosure from the description in the specification.

[0028] FIG. 1 illustrates an environment in which a device according to one embodiment of the present disclosure can be applied.

[0029] FIG. 2 illustrates an example in which an environment according to one embodiment of the present disclosure is implemented.

[0030] FIG. 3 illustrates an example in which a device according to one embodiment of the present disclosure is implemented.

[0031] FIG. 4 illustrates a flowchart showing a method according to one embodiment of the present disclosure.

[0032] FIG. 5 illustrates an example of a method for determining a target area in one embodiment according to the present disclosure.

[0033] FIG. 6 illustrates an example of additionally training an artificial neural network in one embodiment according to the present disclosure.

[0034] FIG. 7 illustrates an example of additionally training an artificial neural network in one embodiment according to the present disclosure.

[0035] FIG. 8 illustrates a flowchart showing a method according to one embodiment of the present disclosure.

[0036] The various embodiments described in this disclosure are illustrative for the purpose of clearly explaining the technical concept of this disclosure and are not intended to limit it to specific embodiments. The technical concept of this disclosure includes various modifications, equivalents, alternatives, and embodiments selectively combined from all or part of each embodiment described in this disclosure. Furthermore, the scope of the technical concept of this disclosure is not limited to the various embodiments presented below or the specific descriptions thereof.

[0037] Terms used in this disclosure, including technical or scientific terms, may have the meaning generally understood by those skilled in the art to which this disclosure pertains, unless otherwise defined.

[0038] Expressions used in this disclosure, such as “comprising,” “may compose,” “possessing,” “possessing,” “having,” and “possessing,” mean that the subject feature (e.g., function, operation, or component, etc.) exists and do not exclude the existence of other additional features. That is, such expressions should be understood as open-ended terms implying the possibility of including other embodiments.

[0039] Singular expressions used in this disclosure may include the meaning of the plural form unless otherwise indicated by the context, and this applies likewise to singular expressions described in the claims.

[0040] Expressions such as "first," "second," or "first," "second," etc., used in this disclosure are used to distinguish one object from another when referring to a plurality of objects of the same kind, unless otherwise indicated in the context, and do not limit the order or importance of the objects.

[0041] Expressions used in the present disclosure, such as “A, B and C,” “A, B or C,” “at least one of A, B and C,” or “at least one of A, B or C,” may mean each of the listed items or all possible combinations of the listed items. For example, “at least one of A or B” may refer to (1) at least one A, (2) at least one B, and (3) at least one A and at least one B.

[0042] The expression “based on” as used in this disclosure is used to describe one or more factors affecting an act or action of a decision or judgment described in the phrase or sentence containing this expression, and this expression does not exclude additional factors affecting said act or action of a decision or judgment.

[0043] As used in the present disclosure, the expression that a certain component (e.g., a first component) is "connected" or "connected" to another component (e.g., a second component) may mean that the said certain component is not only directly connected or connected to the said other component, but is also connected or connected through a new other component (e.g., a third component).

[0044] As used in this disclosure, the expression "configured to" may have meanings such as "set to," "capable of," "modified to," "made to," or "capable of." This expression is not limited to the meaning of "specifically designed in hardware." For example, a processor configured to perform a specific operation may mean a generic-purpose processor capable of performing that specific operation by executing software, or a special-purpose computer structured through programming to perform that specific operation.

[0045] Hereinafter, various embodiments described in this disclosure will be explained with reference to the attached drawings. In the attached drawings and the description thereof, identical or substantially equivalent components may be given the same reference numerals. Furthermore, in the description of the various embodiments below, the description of identical or corresponding components may be omitted, but this does not mean that such components are not included in the embodiments.

[0046] FIG. 1 illustrates an environment (100) to which a device (110) according to one embodiment of the present disclosure may be applied. Such an environment (100) may include a device (110), a camera (121), a scanner (122), and / or a classifier (123). FIG. 1 illustrates only one embodiment for achieving the purpose of the present disclosure, and some components may be added as needed. For example, an operator terminal used by an operator who is the entity managing the device (110), a delivery terminal of a delivery person delivering a parcel being shipped out under the management of the device (110), and / or a worker terminal of a worker managing a parcel whose shipment is withheld under the management of the device (110) may be added to the environment (100). In this specification, a parcel may mean a unit in which packaging of goods is completed so that goods can be shipped. A single parcel may include one or more goods being shipped to a single delivery destination.

[0047] The device (110) may be a server device for managing logistics, such as packaging goods, sorting parcels containing packaged goods, and initiating delivery to parcels. This device (110) may be a device for performing operations to manage the processing of logistics.

[0048] However, the device (110) may be a general-purpose type of server device, not limited to the examples described above. Such a device (110) may perform operations such as controlling a sorter (123) to transport a parcel to a target area (delivery area or holding area) by executing the method, etc. according to the present disclosure. Various embodiments of the present disclosure to be specified below may, for example, relate to the shipment of goods (or parcels containing goods).

[0049] The device (110) may be implemented as one or more computing devices. For example, all functions of the device (110) may be implemented in a single computing device. As another example, the first function of the device (110) may be implemented in the first computing device, and the second function may be implemented in the second computing device. As a specific example, if the device (110) is a server device for managing logistics, the first function for managing logistics may be implemented in the first computing device, and the second function, which is distinct from the first function, may be implemented in the second computing device. Even if the first computing device and the second computing device exist physically separated, the first computing device and the second computing device may be referred to as the device (110) as an abstract concept that integrates them.

[0050] The aforementioned computing device may be, for example, a desktop computer, a laptop computer, an application server, a proxy server, or a cloud server, but is not limited thereto, and any type of device equipped with computing functions may be a computing device.

[0051] The camera (121) can photograph the parcel being shipped. For example, the camera (121) can photograph the outside of the parcel so that an image regarding the packaging of the parcel is obtained. The camera (121) can obtain first information by photographing the image of the parcel and transmit the first information to the device (110).

[0052] The scanner (122) can identify various identification codes (e.g., packaging identification code, invoice identification code, etc.) attached to the outside of the parcel being shipped. The scanner (122) can obtain second information by scanning one or more identification codes on the outside of the parcel and transmit the second information to the device (110). For example, if one identification code is scanned, the second information may indicate information corresponding to one identification code. As another example, if an identification code is not scanned, the second information may indicate that an identification code was not scanned.

[0053] The sorter (123) may be a device that sorts packaged parcels according to their delivery destination. The sorter (123) may be configured to transport packaged parcels to a target area (delivery area or hold area) under the control of the device (110). The delivery area may be an area for delivering parcels to a delivery person who performs the delivery so that the parcels can be delivered. The hold area may be an area where parcels are transported for which their dispatch is temporarily withheld.

[0054] The device (110), camera (121), scanner (122) and / or classifier (123) can communicate through a network. This network can be implemented as any kind of wired or wireless network, such as, for example, a Local Area Network (LAN), a Wide Area Network (WAN), a Mobile Radio Communication Network (MRCN), or WiBro (Wireless Broadband).

[0055] FIG. 2 illustrates an example in which an environment (100) according to one embodiment of the present disclosure is implemented. A parcel (210) that has completed packaging can be moved via a conveyor belt (220).

[0056] In one embodiment, the camera (121), scanner (122), and / or classifier (123) may be installed on the conveyor belt (220). For example, the camera (121), scanner (122), and / or classifier (123) may be positioned along the path where the parcel (210) travels on the conveyor belt (220). In one example, the scanner (122) may be positioned within the classifier (123). However, this is not limited thereto, and the camera (121), scanner (122), and classifier (123) may each be positioned separately from one another.

[0057] A camera (121) can photograph the parcel (210) to generate first information regarding an image of the parcel (210). A scanner (122) can scan one or more identification codes attached to the parcel (210) to generate second information.

[0058] The classifier (123) obtains information from the device (110) indicating a target area to which each parcel (210) is to be moved, and can classify the parcels (210) accordingly. The target area may be any one of one or more delivery areas (230a, 230b, 230c) or a holding area (230d). For example, the classifier (123) can physically classify the movement path of each parcel entering the classifier (123) and move it to one or more lanes (220a, 220b, 220c, 220d) on the conveyor belt. The classifier (123) may be controlled by the device (110).

[0059] The conveyor belt (220) may be connected to a lane corresponding to each of one or more delivery areas (230a, 230b, 230c) or holding area (230d). A first parcel (210a) on the first lane (220a) may be moved to the first delivery area (230a). A second parcel (210b) on the second lane (220b) may be moved to the second delivery area (230b). A third parcel (210c) on the third lane (220c) may be moved to the third delivery area (230c). A fourth parcel (210d) on the fourth lane (220d) may be moved to the holding area (230d). A classifier (123) may perform a sorting operation for each parcel so that the parcel is moved to the lane corresponding to the target area.

[0060] The holding area (230d) may be an area where the fourth parcel (210d), for which shipment is temporarily withheld, is transported. The fourth parcel (210d) transported to the holding area (230d) may be transported directly to the delivery area corresponding to the second parcel (210d) by a worker (240) on the holding area side.

[0061] The packaging type used for the parcel may require management. For example, a specific packaging type (hereinafter referred to as "first packaging type") may be a type that requires the retrieval of the packaging after the delivery of the parcel is completed. In the case of such first packaging type, a corresponding packaging identification code may be attached to the outside of the packaging, and the parcel may be processed as released upon scanning the packaging identification code. However, if the packaging identification code is not scanned, the parcel moves to a holding area (230d), and the worker (240) on the holding area side may have to perform additional tasks, such as directly scanning the packaging identification code. As the number of parcels transported to the holding area (230d) increases, the workload of the worker (240) increases, and a problem may arise in which the time required for the release of the parcel increases.

[0062] One embodiment of the present disclosure can identify the packaging type of a parcel to reduce the number of parcels transported to a holding area and reduce the amount of work required during the shipping process.

[0063] FIG. 3 illustrates an example in which a device (100) according to one embodiment of the present disclosure is implemented. The device may include one or more processors (310) and one or more memories (320). The device may further include a communication circuit (330). In one embodiment, some components of the device may be omitted, or other components (e.g., a display or an input device, etc.) may be added to the device. Additionally, some components may be implemented by being integrated or by being implemented as a single or multiple entities. In the present disclosure, one or more processors (310) may be referred to as processors (310). Unless the context clearly indicates otherwise, the term processor may mean a set of one or more processors. Also, in the present disclosure, one or more memories (320) may be referred to as memories (320). Unless the context clearly indicates otherwise, the term memory may mean a set of one or more memories.

[0064] The processor (310) can perform operations or information processing regarding the control or communication of each component of the device. Specifically, the processor (310) can control at least one component of the device connected to the processor (310) by running software (or computer program) received from another component. As an example, the processor (310) can load instructions (e.g., instructions, code, or code segments) or information into memory (320), process the instructions or information stored in memory (320), and store result information resulting from the processing in memory (320). Additionally, the processor (310) can be operatively connected to the components of the device to perform various operations such as operations, processing, generation, or processing related to the present disclosure.

[0065] The memory (320) may store various information. The information stored in the memory (320) may include software, which is information acquired, processed, or used by at least one component of the device. The software may include one or more instructions that cause the processor (310) to perform operations according to various embodiments of the present disclosure when loaded into the memory (320). That is, the processor (310) may perform operations according to various embodiments of the present disclosure by executing the one or more instructions mentioned above. The memory (320) may include, for example, volatile or non-volatile memory. In one embodiment, the program may be software stored in the memory (320) and may include an operating system for controlling the resources of the device, an application, or middleware that provides various functions to the application so that the application can utilize the resources of the device.

[0066] A communication circuit (330) can establish a wired or wireless communication channel with another device and transmit and receive various information with that other device. In one embodiment, the communication circuit (330) may include at least one port for connecting to another device via a wired cable in order to communicate with another device via a wire. In this case, the communication circuit (330) can perform communication with another device that is wired through at least one port. In one embodiment, the communication circuit (330) may include a cellular communication module and be configured to be connected to a cellular network (e.g., 3G, LTE, 5G, Wibro, or Wimax). In one embodiment, the communication circuit (330) may include a short-range communication module and transmit and receive information with another device using short-range communication (e.g., Wi-Fi, Bluetooth, Bluetooth Low Energy (BLE), UWB). In one embodiment, the communication circuit (330) may include a contactless communication module for contactless communication. Contactless communication may include at least one contactless proximity communication technology, such as, for example, Near Field Communication (NFC) communication, Radio Frequency Identification (RFID) communication, or Magnetic Secure Transmission (MST) communication. In addition to the various examples described above, the device may be implemented in various known ways for communicating with other devices, and the scope of the present disclosure is not limited by the examples described above.

[0067] The processor (310), memory (320), and communication circuit (330) are connected to each other via a bus, GPIO (General Purpose Input / Output), SPI (Serial Peripheral Interface), or MIPI (Mobile Industry Processor Interface), etc., so that they can give or receive information or signals.

[0068] In one embodiment, the device may further include a display. The display may display various screens based on the control of the processor (310). For example, a web browser or a dedicated application may be installed on the device to display screens with various interfaces applied to them. Additionally, the display may be configured to interact with a user and may receive input from the user. Such a display may be implemented in the form of a touch sensor panel (TSP) capable of recognizing contact or proximity of various external objects (e.g., a finger or a stylus).

[0069] In one embodiment, the device may further include an input device (e.g., a mouse or keyboard). The input device may receive information to be used by a component of the device from outside the device.

[0070] Hereinafter, methods according to various embodiments of the present disclosure will be described in detail. It should be noted that although operations are illustrated in a specific order in the drawings below, the operations must not necessarily be executed in the specific order illustrated or in a sequential order, or all illustrated operations must be executed to obtain the desired result.

[0071] Additionally, the operation of the method described below with reference to the drawings may be performed by a computing device. In other words, the operation of the method may be implemented by one or more instructions executed by the processor (310) of the computing device. All operations included in this method may be performed by a single physical computing device, but the first operation of the method may be performed by the first computing device and the second operation of the method may be performed by the second computing device.

[0072] In the following, the explanation will continue assuming that the operation of the aforementioned method is performed by the device (110). Additionally, for the convenience of explanation, the subject of the operation included in the method may be omitted, but unless otherwise indicated by the context, it should be interpreted that the operation is performed by the device (110).

[0073] FIG. 4 illustrates a flowchart illustrating a method according to one embodiment of the present disclosure. The method may include a series of operations performed by a device (110) in conjunction with a camera (121), a scanner (122) and / or a classifier (123).

[0074] In step S410, the processor (310) may receive first information regarding an image of a target parcel containing a product from the camera (121). For example, the processor (310) may include an image file obtained by photographing the exterior of the target parcel as the first information.

[0075] In step S420, the processor (310) may receive second information obtained by scanning one or more identification codes for a target parcel from the scanner (122). In one embodiment, one or more identification codes may include a packaging identification code for identifying a first packaging type.

[0076] In one example, as a package identification code attached to a target parcel is exposed to a scanner (122), second information indicating that the package identification code has been scanned may be obtained. At this time, the second information may further include information regarding the package type corresponding to the package identification code.

[0077] In another example, as the packaging identification code attached to the target parcel is not exposed to the scanner (122), second information indicating that the packaging identification code has not been scanned may be obtained. For example, during the process of scanning the target parcel, if the side to which the packaging identification code is attached is in contact with the bottom surface, the packaging identification code may not be exposed to the scanner (122). In another example, even if the packaging identification code itself is not attached to the target parcel, the second information indicating that the packaging identification code has not been scanned may be obtained because the packaging identification code is not scanned by the scanner (122).

[0078] In another embodiment, one or more identification codes may include an invoice identification code containing information regarding the delivery of a target parcel. The invoice identification code may include information regarding the delivery destination of the target parcel, information regarding the recipient, etc.

[0079] In step S430, the processor (310) can determine the target area to which the target parcel should be transported for delivery based on the first information and the second information.

[0080] In step S440, the processor (310) can control the classifier (123) to transport the target parcel to the target area. The processor (310) can transmit information indicating the target area to the classifier (123), and in response, the classifier (123) can be configured to transport the target parcel to the target area.

[0081] FIG. 5 illustrates an example of a method for determining a target area in one embodiment according to the present disclosure. FIG. 5 can be understood as a specific method for determining a target area in step S430 of FIG. 4.

[0082] In step S510, the processor (310) can determine whether the target parcel is packaged in a predetermined first packaging type based on the first information. The processor (310) can determine in advance a first packaging type that is a packaging type requiring special management. In one embodiment, the processor (310) can determine the first packaging type as a packaging type to which a packaging identification code is attached. For example, the first packaging type is a packaging type that requires retrieval after delivery and may be a cooling box for packaging fresh food. However, it is not limited thereto, and the first packaging type may mean any packaging type to which a packaging identification code is attached.

[0083] In one embodiment, the processor (310) may use an artificial neural network to determine whether the target parsel is packaged in a first packaging type. The artificial neural network may be a supervised learning-based classification model. The artificial neural network may be generated by learning from images of one or more parsels and may be generated to identify packaging types from images of parsels. Such an artificial neural network model may be stored in memory (320) in a state where learning is complete.

[0084] For training an artificial neural network model, a label indicating a class and an input image may be used as training data as a pair. Additionally, evaluation data for evaluating the training of the artificial neural network model may be provided separately from the training data. For example, "Image A," which is a first-type insulated box, and the label "Insulated Box" may be used as a pair of first training data; "Image B," which is a paper box, and the label "Paper Box" may be used as a pair of second training data; and "Image C," which is a plastic box, and the label "Plastic Box" may be used as a pair of third training data. During the training process, the artificial neural network model can derive regularities from such multiple training data and classify a new image into a corresponding label when it is input. Various known technologies may be referenced in this disclosure for the implementation of such an artificial neural network model.

[0085] The processor (310) can input first information into an artificial neural network to obtain a predicted packing type for a target parse as the output of the artificial neural network. The predicted packing type may indicate any one of one or more classes labeled in the artificial neural network. The processor (310) can determine whether the predicted packing type is the same as the first packing type.

[0086] For example, in response to a determination that the predicted packaging type is the same as the first packaging type, the processor (310) may determine that the target parcel is packaged according to the first packaging type. In this case, step S520 may be performed.

[0087] As another example, in response to a determination that the predicted packaging type is not the same as the first packaging type, the processor (310) may determine that the target parcel is not packaged according to the first packaging type. In this case, step S530 may be performed. Thus, in various embodiments according to the present disclosure, if the packaging of the target parcel is not determined to be the first packaging type based on the first information, it may not be transported to the holding area. Accordingly, since a parcel packaged with a second packaging type different from the first packaging type may not be transported to the holding area, the number of parcels transported to the holding area may be reduced.

[0088] In step S520, the processor (310) may determine whether a packaging identification code for the target parcel has been scanned based on the second information, depending on the determination that the target parcel has been packaged in a first packaging type. Depending on the determination that the packaging identification code has been scanned, step S530 may be performed. Depending on the determination that the packaging identification code has not been scanned, step S540 may be performed.

[0089] In step S530, the target area may be determined as a predetermined delivery area rather than a holding area for the target parcel. In one embodiment, the processor (310) may receive second information obtained by scanning an invoice identification code containing information regarding the delivery of the target parcel from the scanner (122). The invoice identification code may contain information regarding the delivery destination of the target parcel, and the processor (310) may determine the target area as a delivery area corresponding to the delivery destination.

[0090] In step S540, the processor (310) may determine the target area as a predetermined hold area based on the determination that the package identification code has not been scanned. That is, the parcel in which the target area is determined as a hold area may be a parcel that was determined as a first package type in step S510 but for which the package identification code was not obtained in step S520.

[0091] FIG. 6 illustrates an example of additionally training an artificial neural network in an embodiment according to the present disclosure. For example, in step S510 of FIG. 5, when the predicted packaging type obtained by inputting first information into the artificial neural network indicates the first packaging type, the processor (310) determines that the target parcel is packaged in the first packaging type; however, if the target parcel is actually packaged in the second packaging type without a packaging identification code attached, a situation may occur where the target parcel packaged in the second packaging type is transported to a holding area. To reduce the occurrence of such a situation, the artificial neural network may be additionally trained.

[0092] In step S610, the processor (310) may obtain third information from the worker terminal of the worker on the hold area side. The third information may indicate whether the target parcel is packaged in a first packaging type. For example, depending on the determination of the target area as a hold area, the processor (310) may transmit a request to the worker terminal instructing verification of the packaging of the target parcel, the worker may verify the actual packaging type of the target parcel and input user input into the worker terminal, and the worker terminal may generate third information based on the user input and transmit it to the device.

[0093] In step S620, in response to obtaining third information indicating that the target parcel is not packaged in a first packaging type, the processor (310) may generate learning information by labeling an image of the first information to indicate that it is not a first packaging type. For example, the third information may further include information indicating a second packaging type in which the target parcel is actually packaged. The processor (310) may generate learning information by labeling the first information with the second packaging type.

[0094] In step S630, based on the learning information, the processor (310) can further train the artificial neural network. The processor (310) can store the artificial neural network that has been further trained based on the learning information in memory (320).

[0095] FIG. 7 illustrates an example of additionally training an artificial neural network in an embodiment according to the present disclosure. For example, in step S510 of FIG. 5, the processor (310) determines that the target parcel is not packed with the first packing type because the predicted packing type obtained by inputting the first information into the artificial neural network does not indicate the first packing type, but in reality, a case may occur where the target parcel is packed with the first packing type. FIG. 7 can be understood as a method to further improve the performance of the artificial neural network when such a situation occurs.

[0096] In step S710, depending on the determination that the target parcel is not packaged in the first packaging type, the processor (310) may determine whether a packaging identification code for the target parcel has been scanned based on the second information. In one embodiment, even if the processor (310) determines that the target parcel is not packaged in the first packaging type, the scanner (122) may still scan one or more identification codes for the target parcel to generate the second information and transmit it to the device.

[0097] In step S720, upon determining that a packaging identification code has been scanned, the processor (310) can generate learning information by labeling the first information to indicate the first packaging type.

[0098] In step S730, based on the learning information, the processor (310) can further train the artificial neural network. The processor (310) can store the artificial neural network that has been further trained based on the learning information in memory (320).

[0099] FIG. 8 illustrates a flowchart illustrating a method according to one embodiment of the present disclosure. In step S810, the processor (310) may obtain fourth information indicating a packaging type to be used for packaging a product. For example, the fourth information may indicate that the product be packaged with a first packaging type or a second packaging type.

[0100] The fourth information may be information transmitted to the terminal of a packaging worker who packages the product. The packaging worker can complete the parcel by packaging the product by referring to the fourth information displayed on the packaging worker's terminal. For example, when the fourth information indicates a second packaging type, the packaging worker may be highly likely to package the product using the second packaging type. However, when the fourth information indicates a first packaging type, the packaging worker may not package the product using the first packaging type. For instance, this situation may occur when using the second packaging type is easier than using the first packaging type. Therefore, when the fourth information indicates a first packaging type, there is a need to intensively monitor whether the target parcel has actually been packaged using the first packaging type. On the other hand, if the fourth information indicates a second packaging type instead of the first, the target parcel may not be transported to the holding area, thereby reducing the workload of the worker on the holding area side.

[0101] In step S820, the processor (310) can determine whether the first packaging type is indicated in the fourth information.

[0102] In step S830, in response to the decision that the first packaging type is indicated in the fourth information, the processor (310) may determine a target area based on the first information and the second information. The method for determining the target area in step S830 may employ the method described in FIG. 5.

[0103] In step S840, in response to the decision that the first packaging type is not indicated in the fourth information, the processor (310) may determine the target area as the delivery area. That is, when the first packaging type is not indicated in the fourth information, the target parcel is not transported to the holding area, thereby reducing the workload of the worker on the holding area side.

[0104] In the flowcharts of the present disclosure, the operations of the method or algorithm are described in a sequential order, but may be performed in any combination other than sequentially. The description of the flowcharts of the present disclosure does not exclude changes or modifications to the method or algorithm and does not imply that any operation is essential or desirable. In one embodiment, at least some operations may be performed in parallel, iteratively, or heuristically. In another embodiment, at least some operations may be omitted or other operations may be added.

[0105] Various embodiments of the present disclosure may be implemented as software on a machine-readable storage medium (MRSM). The software may be software for implementing various embodiments of the present disclosure. The software may be inferred from the various embodiments of the present disclosure by programmers in the art to which the present disclosure belongs. For example, the software may be a computer program containing instructions that can be read by a computing device. A computing device is a device capable of operating according to instructions called from a storage medium, and may be referred to interchangeably with, for example, an electronic device. In one embodiment, a processor (310) of a computing device may execute a called instruction to cause components of the computing device to perform functions corresponding to the instruction. A storage medium may refer to any type of recording medium in which information is stored that can be read by a device. A storage medium may include, for example, ROM, RAM, CD-ROM, magnetic tape, floppy disk, or optical information storage device. In one embodiment, the storage medium may be implemented in a distributed form in a computer system connected by a network, etc. In this case, the software may be stored and executed in a distributed manner in a computer system, etc. In another embodiment, the storage medium may be a non-transitory storage medium. A non-transitory storage medium refers to a medium that exists regardless of whether information is stored semi-permanently or temporarily, and does not include signals that are transmitted transitorily.

[0106] Although the technical concept according to the present disclosure has been described by various embodiments above, the technical concept according to the present disclosure includes various substitutions, modifications, and changes that can be made within the scope of understanding of a person skilled in the art to which the present disclosure pertains. Furthermore, it should be understood that such substitutions, modifications, and changes may be included within the scope of the appended claims.

Claims

1. One or more processors; and It includes one or more memories in which instructions to be executed by the above one or more processors are stored, and When executing the above instructions, the one or more processors, Receive first information regarding an image of a target parcel containing a packaged product from a camera, and Receiving second information obtained by scanning one or more identification codes for the target parcel from the scanner, and Based on the above first information and the above second information, determine the target area where the target parcel must be transported for delivery, and It is configured to control a classifier to transport the target parcel to the target area, and In determining the above target area, Based on the above first information, determine whether the target parcel is packaged in a predetermined first packaging type, and Based on the determination that the target parcel is packaged in the first packaging type, it is determined whether a packaging identification code for the target parcel has been scanned based on the second information, and A device configured to determine the target area as a predetermined hold area based on the determination that the above packaging identification code was not scanned.

2. In Paragraph 1, A device in which the above second information is information obtained by scanning the outside of the target parcel passing through the classifier from the scanner.

3. In Paragraph 1, The above one or more processors, in determining whether the target parcel is packaged in the first packaging type, The first information is input into an artificial neural network trained to identify a packaging type from an image of a parcel, and a predicted packaging type for the target parcel is obtained as the output of the artificial neural network. Determining whether the above predicted packaging type is the same as the above first packaging type, A device configured to determine that the target parcel is packaged according to the first packaging type in response to a determination that the predicted packaging type is identical to the first packaging type.

4. In Paragraph 3, The above one or more processors, Based on determining the above target area as the above hold area, third information indicating whether the above target parcel is packaged in the first packaging type is obtained from the worker terminal of the worker on the side of the above hold area, and In response to obtaining the third information indicating that the target parcel is not packaged in the first packaging type, learning information is generated by labeling the first information to indicate that it is not the first packaging type. A device configured to further train the artificial neural network based on the above learning information.

5. In Paragraph 3, The above one or more processors, Based on the determination that the target parcel is not packaged in the first packaging type, it is determined whether the packaging identification code for the target parcel has been scanned based on the second information, and Based on the determination that the above packaging identification code has been scanned, learning information is generated by labeling the above first information to indicate the above first packaging type, and A device configured to further train the artificial neural network based on the above learning information.

6. In Paragraph 1, The above first packaging type is a device that is a packaging type requiring retrieval after the above target parcel has been delivered.

7. In Paragraph 1, The above one or more processors, in determining the target area, Based on the determination that the above target parcel was not packaged in the above first packaging type, A device configured to determine the above target area as a predetermined delivery area rather than the above holding area for the above target parcel.

8. In Paragraph 7, The above one or more processors, in determining the target area, In response to obtaining the second information by scanning the invoice identification code for the above-mentioned target parcel - the invoice identification code includes information regarding the delivery destination of the above-mentioned target parcel - , A device configured to determine the above target area as the above delivery area corresponding to the above delivery destination.

9. In Paragraph 1, The above one or more processors, Obtaining fourth information indicating the packaging type to be used for the packaging of the above product, In determining the above target area, Determining whether the above fourth information indicates the above first packaging type, and A device configured to determine the target area based on the first information and the second information in response to a decision indicating the first packaging type in the fourth information.

10. In Paragraph 9, The above one or more processors, in determining the target area, A device configured to determine the target area as a predetermined delivery area rather than the holding area, in response to a decision that the first packaging type is not indicated in the fourth information above.

11. A method performed in a device comprising one or more processors and one or more memories storing instructions to be executed by said one or more processors, wherein One or more of the above processors, A step of receiving first information regarding an image of a target parcel containing a packaged product from a camera; A step of receiving second information obtained by scanning one or more identification codes for the target parcel from a scanner; Based on the first information and the second information, a step of determining a target area to which the target parcel is to be transported for delivery; and The method includes the step of controlling a classifier to transport the target parcel to the target area. In the step of determining the above target area, A step of determining whether the target parcel is packaged in a predetermined first packaging type based on the first information above; A step of determining whether a packaging identification code for the target parcel has been scanned based on the second information, in accordance with the determination that the target parcel has been packaged in the first packaging type; and A method comprising the step of determining the target area as a predetermined hold area based on the determination that the above packaging identification code was not scanned.

12. In Paragraph 11, A method in which the second information is information obtained by scanning the outside of the target parcel passing through the classifier from the scanner.

13. In Paragraph 11, In the step of determining whether the target parcel is packaged in the first packaging type, the above one or more processors A step of inputting the first information into an artificial neural network trained to identify a packaging type from an image of a parcel, and obtaining a predicted packaging type for the target parcel as the output of the artificial neural network; A step of determining whether the predicted packaging type is the same as the first packaging type; and A method comprising the step of determining that the target parcel is packaged according to the first packaging type in response to a determination that the predicted packaging type is the same as the first packaging type.

14. In Paragraph 13, One or more of the above processors, A step of obtaining third information indicating whether the target parcel is packaged in the first packaging type from a worker terminal of a worker on the side of the holding area, based on the determination of the target area as the holding area; In response to obtaining the third information indicating that the target parcel is not packaged in the first packaging type, a step of generating learning information by labeling the first information to indicate that it is not the first packaging type; and A method comprising the step of additionally training the artificial neural network based on the above learning information.

15. In Paragraph 13, One or more of the above processors, A step of determining whether a packaging identification code for the target parcel has been scanned based on the second information, in accordance with the determination that the target parcel is not packaged in the first packaging type; A step of generating learning information by labeling the first information to indicate the first packaging type, based on the determination that the above packaging identification code has been scanned; and A method comprising the step of additionally training the artificial neural network based on the above learning information.

16. In Paragraph 11, The above first packaging type is a packaging type that requires retrieval after the above target parcel has been delivered.

17. In Paragraph 11, In the step of determining the target region, the above one or more processors, Based on the determination that the above target parcel was not packaged in the above first packaging type, A method comprising the step of determining the target area as a predetermined delivery area rather than the holding area for the target parcel.

18. In Paragraph 17, In the step of determining the target region, the above one or more processors, In response to obtaining the second information by scanning the invoice identification code for the above-mentioned target parcel - the invoice identification code includes information regarding the delivery destination of the above-mentioned target parcel - , A method comprising the step of determining the above target area as the above delivery area corresponding to the above delivery destination.

19. In Paragraph 11, One or more of the above processors, It further includes the step of obtaining a fourth piece of information indicating a packaging type to be used for the packaging of the above-mentioned product, and In the step of determining the above target area, Determining whether the above fourth information indicates the above first packaging type, and A method comprising the step of determining the target area based on the first information and the second information in response to a decision indicating the first packaging type in the fourth information.

20. A non-transient computer-readable recording medium having recorded instructions that cause one or more processors to perform an operation when executed by one or more processors, The above instructions cause the one or more processors, Receive first information regarding an image of a target parcel containing a packaged product from a camera, and Receiving second information obtained by scanning one or more identification codes for the target parcel from the scanner, and Based on the above first information and the above second information, determine the target area where the target parcel must be transported for delivery, and It is configured to control a classifier to transport the target parcel to the target area, and In determining the above target area, Based on the above first information, determine whether the target parcel is packaged in a predetermined first packaging type, and Based on the determination that the target parcel is packaged in the first packaging type, it is determined whether a packaging identification code for the target parcel has been scanned based on the second information, and A computer-readable recording medium configured to determine the target area as a predetermined hold area based on the determination that the above-mentioned packaging identification code was not scanned.

Images