Shipper clustering-based freight fare management server, system, method, and computer-readable recording medium

Abstract

The present disclosure may comprise: a communication unit for performing communication with a plurality of shipper terminals and a plurality of forwarder terminals; and a processor for controlling an operation related to freight fares based on shipper clustering. The present disclosure enables efficient management of cargo volume and reduction of logistics costs, thereby efficiently lowering freight fares.

Description

Freight rate management server, system, method and computer-readable recording medium based on shipper clustering

[0001] The present disclosure relates to a freight rate management server, system, method and computer-readable recording medium based on shipper clustering.

[0002] Typically, in the case of pricing work, which involves determining freight rates at forwarders and freight forwarders, the person in charge of the work uses qualitative indicators such as freight transport conditions, international situations, and experience.

[0003] Due to these limitations of existing business methods, freight rates not only have a closed nature, but objective evaluation of determined rates is also limited.

[0004] For example, qualitative freight rate indicators such as SCFI, CCFI, BAI, and FAX have been used in the pricing process.

[0005] However, these qualitative freight rate indicators have limitations in that they are defined as a weighted average of the freight rates of a sample of freight transport companies selected from all freight transport companies, and thus do not sufficiently reflect the characteristics of freight transport, which are affected by various variables such as oil prices and exchange rates.

[0006] Therefore, it is necessary to efficiently manage cargo volume and reduce logistics costs by calculating changes in freight rates in real time, providing forwarders with recommended base pricing information that takes into account current price influencing factors, and having forwarders participate in auctions based on the recommended base pricing information, thereby effectively lowering freight rates.

[0007] The purpose of the embodiment disclosed in the present disclosure is to provide a system that efficiently manages cargo volume and reduces logistics costs, thereby efficiently lowering cargo freight rates by clustering multiple cargo owner terminals and transporting each cargo requested by the clustered multiple cargo owner terminals within a single container.

[0008] The problems to be solved by the present disclosure are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

[0009] According to one aspect of the present disclosure for achieving the above-described technical task, a freight rate management server based on shipper clustering comprises: a communication unit for performing communication with a plurality of shipper terminals and a plurality of forwarder terminals; and a processor for controlling operations related to freight rates based on shipper clustering; and the processor, when receiving a request for a freight rate quotation corresponding to export country information for each cargo type from the plurality of shipper terminals through the communication unit, classifies the export country information for each cargo type into export country information for each cargo size and export country information for each similar cargo, and clusters the plurality of shipper terminals using a clustering model based on the export country information for each cargo size, the export country information for each similar cargo, and cargo transportation contract information, and when some or all of the cargo of the plurality of clustered shipper terminals are shipped in one or more containers, and a change in route among freight rate influencing factors related to the export country information for each cargo size or the export country information for each similar cargo is confirmed or predicted, extracts freight rate change information including a changed transportation distance, a changed fuel cost, and the total time required for transportation linked to the change in route, and inputs the freight rate change information into a freight rate prediction model, and outputs recommended reference pricing information learned based on the freight rate prediction model, and allows a freight rate auction to be conducted for each of the cargoes based on the reference pricing information. The freight auction information for each of the above cargoes is displayed on the plurality of forwarder terminals, and when the standard pricing information is output, the metadata among the freight rate fluctuation information, such as macroeconomic variables, freight rates, HS CODE-based freight value indices, container terminal usage fees, and freight rate-related document preparation costs, are additionally input into the freight rate prediction model, thereby outputting recommended standard pricing information.

[0010] In addition, the processor may be characterized in that it clusters the plurality of shipper terminals using the clustering model based on the type of transportation means, contract type, payment method, reservation route, reservation time, contract manager location, and shipper location included in the cargo transportation contract information.

[0011] In addition, the processor may be characterized in further clustering the plurality of shipper terminals using the clustering model based on whether transshipment is included in the cargo transportation contract information and the cargo HS CODE.

[0012] According to another aspect of the present disclosure, a freight rate management system based on shipper clustering comprises: a plurality of shipper terminals requesting freight transport; a plurality of forwarder terminals managing the freight transport; and a freight rate management server communicating with the plurality of shipper terminals and the plurality of forwarder terminals. and the freight rate management server, when receiving a freight rate quotation request corresponding to export country information by cargo type from the plurality of shipper terminals, classifies the export country information by cargo type into export country information by cargo size and export country information by similar cargo, and clusters the plurality of shipper terminals using a clustering model based on the export country information by cargo size, the export country information by similar cargo, and cargo transportation contract information, and when some or all of the cargo of the plurality of clustered shipper terminals are shipped in one or more containers, and a change in route among freight influence factors related to the export country information by cargo size or the export country information by similar cargo is confirmed or predicted, freight rate change information including a changed transportation distance, a changed fuel cost, and the total time required for transportation linked to the change in route is extracted, and the freight rate change information is input into a freight rate prediction model, and recommended reference pricing information learned based on the freight rate prediction model is output, and a freight rate auction is conducted for each of the cargoes based on the reference pricing information. The freight auction information for each of the above cargoes is displayed on the plurality of forwarder terminals, and when the standard pricing information is output, the metadata among the freight rate fluctuation information, such as macroeconomic variables, freight rates, HS CODE-based freight value indices, container terminal usage fees, and freight rate-related document preparation costs, are additionally input into the freight rate prediction model, thereby outputting recommended standard pricing information.

[0013] According to another aspect of the present disclosure, a freight management method based on shipper clustering performed by a freight management server comprises the steps of: receiving, through a communication unit of the freight management server, a freight quotation request request corresponding to export country information for each cargo type from a plurality of shipper terminals; classifying, by a processor of the freight management server, the export country information for each cargo type into export country information for each cargo size and export country information for each similar cargo; clustering, by the processor, the plurality of shipper terminals using a clustering model based on export country information for each cargo size, export country information for each similar cargo, and cargo transportation contract information; A step of extracting freight rate fluctuation information including a changed transportation distance, a changed fuel cost, and a total transportation time linked to the changed transportation route among freight rate influencing factors related to export country information by cargo size or export country information by similar cargo, by the processor, when some or all of the cargo of the clustered plurality of shipper terminals are loaded into one or more containers, and a change in the route is confirmed or predicted; a step of inputting, by the processor, the freight rate fluctuation information into a freight rate prediction model, and outputting recommended reference pricing information learned based on the freight rate prediction model; a step of displaying, by the processor, freight rate auction information for each of the freight on the plurality of forwarder terminals so that a freight rate auction is conducted for each of the freight based on the reference pricing information;However, the step of outputting the standard pricing information may be characterized in that the processor additionally inputs, by the processor, macroeconomic variables, freight indices, HS CODE-based freight value indices, container terminal usage fees, and freight-related document preparation costs, which are metadata among the freight rate fluctuation information, into the freight rate prediction model, thereby outputting recommended standard pricing information.;

[0014] In addition, a computer program stored in a computer-readable recording medium for executing the present disclosure may be further provided.

[0015] In addition, a computer-readable recording medium recording a computer program for executing a method for implementing the present disclosure may be further provided.

[0016] According to the aforementioned problem solving means of the present disclosure, a plurality of shipper terminals can be clustered, and each cargo requested by the clustered plurality of shipper terminals can be loaded and transported within a single container, thereby providing the effect of efficiently managing cargo volume and reducing logistics costs, thereby efficiently lowering cargo freight rates.

[0017] The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

[0018] FIG. 1 is a diagram illustrating a cargo freight management system based on shipper clustering according to the present disclosure.

[0019] Figure 2 is a diagram showing the configuration of the cargo freight management server of Figure 1.

[0020] Figures 3 to 8 are drawings showing examples of a cargo freight management process based on shipper clustering according to the present disclosure.

[0021] Throughout this disclosure, the same reference numerals denote the same components. This disclosure does not describe all elements of the embodiments, and any content that is common in the technical field to which this disclosure pertains or that overlaps between embodiments is omitted. The terms "part, module, element, block" used in the specification may be implemented in software or hardware, and depending on the embodiments, multiple "parts, modules, elements, blocks" may be implemented as a single component, or a single "part, module, element, block" may include multiple components.

[0022] Throughout the specification, when a part is said to be "connected" to another part, this includes not only direct connection but also indirect connection, and indirect connection includes connection via a wireless communication network.

[0023] Additionally, when a part is said to "include" a component, this does not mean that it excludes other components, but rather that it may include other components, unless otherwise specifically stated.

[0024] Throughout the specification, when we say that an element is "on" another element, this includes not only cases where the element is in contact with the other element, but also cases where another element exists between the two elements.

[0025] The terms first, second, etc. are used to distinguish one component from another, and the components are not limited by the aforementioned terms.

[0026] Singular expressions include plural expressions unless the context clearly indicates otherwise.

[0027] The identification codes for each step are used for convenience of explanation and do not describe the order of each step. Each step may be performed in a different order than specified unless the context clearly indicates a specific order.

[0028] The operating principle and embodiments of the present disclosure are described below with reference to the attached drawings.

[0029] The cargo freight management system based on shipper clustering according to the present disclosure may be characterized in that, when a request for a freight freight quotation corresponding to export country information for each cargo type is received from a plurality of shipper terminals, the plurality of shipper terminals are clustered using a clustering model based on export country information and cargo transportation contract information for each cargo type, when each cargo requested by the plurality of clustered shipper terminals is loaded into one container, preset cargo freight fluctuation information linked to the export country information for each cargo type is extracted, the cargo freight fluctuation information is input into a cargo freight prediction model, and reference pricing information learned and recommended based on the cargo freight prediction model is output, and a cargo freight auction is conducted for each cargo based on the reference pricing information, thereby displaying cargo freight auction information for each cargo on a plurality of forwarder terminals.

[0030] This cargo freight management system based on shipper clustering can efficiently manage cargo volume and reduce logistics costs by clustering multiple shipper terminals and transporting each requested cargo within a single container, thereby efficiently lowering cargo freight rates.

[0031] Below, we will examine in detail the freight rate management system based on shipper clustering.

[0032] FIG. 1 is a diagram illustrating a cargo freight management system based on shipper clustering according to the present disclosure.

[0033] Referring to FIG. 1, a cargo freight management system (1000) based on shipper clustering may include a plurality of shipper terminals (100), a plurality of forwarder terminals (200), a cargo freight management server (300), and a cargo freight management terminal (400).

[0034] Multiple shipper terminals (100) may request freight rate quotes from the freight rate management server (300) to request freight transport for each exporting country. Here, the shipper may be the person requesting freight transport. In this case, the freight rate may be the cost incurred when transporting freight using land, sea, or air transportation.

[0035] Multiple forwarder terminals (200) may be provided to transport and manage each consigned cargo to each exporting country. In this case, a forwarder may be a person who transports and manages the cargo.

[0036] Figure 2 is a diagram showing the configuration of the cargo freight management server of Figure 1.

[0037] Referring to FIG. 2, the freight rate management server (300) processes information by communicating with external devices, and may include an application server, a computing server, a database server, a file server, a mail server, a proxy server, and a web server. At this time, a freight rate management terminal (400) may be provided to manage the freight rate management server (300). Here, the freight rate manager can manage data related to freight rates using the freight rate management terminal (400).

[0038] The freight rate management server (300) may include a communication unit (310), a control unit (320), and a display unit (330).

[0039] The communication unit (310) can communicate with a plurality of shipper terminals (110) and a plurality of forwarder terminals (200). Here, the communication unit (310) can include at least one of a wired communication module and a wireless communication module.

[0040] At this time, the wired communication module may include various wired communication modules such as a Local Area Network (LAN) module, a Wide Area Network (WAN) module, or a Value Added Network (VAN) module, as well as various cable communication modules such as a Universal Serial Bus (USB), a High Definition Multimedia Interface (HDMI), a Digital Visual Interface (DVI), RS-232 (recommended standard232), power line communication, or POTS (plain old telephone service).

[0041] In addition, the wireless communication module may include a wireless communication module that supports various wireless communication methods such as GSM (global System for Mobile Communication), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), UMTS (universal mobile telecommunications system), TDMA (Time Division Multiple Access), LTE (Long Term Evolution), 4G, 5G, and 6G, in addition to a WiFi module and a Wireless broadband module.

[0042] The control unit (320) may be implemented with a memory (321) that stores data on an algorithm for controlling the operation of components within the device or a program that reproduces the algorithm, and at least one processor (322) that performs the aforementioned operation using the data stored in the memory (321). Here, the memory (321) and the processor (322) may each be implemented as separate chips. Additionally, the memory (321) and the processor (322) may also be implemented as a single chip.

[0043] The memory (321) can store data supporting various functions of the device, programs for the operation of the control unit, input / output data, and a plurality of application programs (or applications) run on the device, data for the operation of the device, and commands. At least some of these application programs can be downloaded from an external server via wireless communication.

[0044] The memory (321) may include at least one type of storage medium among a flash memory type, a hard disk type, an SSD (Solid State Disk type), an SDD (Silicon Disk Drive type), a multimedia card micro type, a card type memory (e.g., SD or XD memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk. In addition, the memory (321) may be a database that is separate from the device but is connected by wire or wirelessly.

[0045] The memory (321) can store data related to freight rates based on shipper clustering. The processor (322) can control operations related to freight rates based on shipper clustering.

[0046] Figures 3 to 8 are drawings showing examples of a cargo freight management process based on shipper clustering according to the present disclosure.

[0047] As illustrated in FIG. 3, multiple shipper terminals (110) may request freight rate quotations from the freight rate management server (300) to request freight transport for each export country (S112). At this time, shippers may input freight rate quotation request information into the first UI within the multiple shipper terminals (110) (S111).

[0048] When a request for a freight rate quotation corresponding to export country information for each cargo type is received from a plurality of shipper terminals (110) (S112), the processor (322) can cluster the plurality of shipper terminals (110) using a clustering model (M1) based on export country information and cargo transportation contract information for each cargo type (S211). At this time, the clustering model (M1) may be a deep embedded clustering model utilizing an X-shaped variational autoencoder. Since this deep embedded clustering model can cluster the plurality of shipper terminals (110) by closely analyzing export country information and cargo transportation contract information for each cargo type, it is possible to more accurately extract freight rate fluctuation information for each of the clustered plurality of shipper terminals.

[0049] For example, as illustrated in FIG. 4, the clustering model (M1) of the processor (322) can cluster (C1) the first shipper terminal (111), the second shipper terminal (112), and the third shipper terminal (113) according to the first export country information and the first cargo transportation contract information for each first cargo type. As another example, the clustering model (M1) of the processor (322) can additionally cluster (C2) the fourth shipper terminal (114), the fifth shipper terminal (115), the sixth shipper terminal (116), and the seventh shipper terminal (117) according to the second export country information and the second cargo transportation contract information for each second cargo type.

[0050] Here, cargo transportation contract information may include the type of transportation method, contract type, payment method, reservation route, transportation distance along the reservation route, reservation time, contract manager location, shipper location, whether transshipment is involved, and the cargo HS Code. Transshipment may refer to the act of loading cargo onto another transportation method during transit or destination. Furthermore, the cargo HS Code may be a product classification code that comprehensively classifies foreign trade cargo according to the Harmonized System of Product Classification.

[0051] In addition, the processor (322) may further classify each cargo type by cargo size or by similar cargo based on each cargo image data captured by the camera module owned by the cargo freight manager. For example, the processor (322) may classify each cargo type into cargo within a first preset size range, cargo within a second preset size range greater than the first size, and cargo within a third preset size range greater than the second size. As another example, the processor (322) may classify each cargo type into similar cargo having a first preset attribute, similar cargo having a second attribute, and similar cargo having a third attribute. At this time, the camera module may be mounted on the cargo freight management terminal (400) or may be provided as a separate external camera.

[0052] Here, the processor (322) can further cluster multiple shipper terminals (100) using a clustering model (M1) based on export country information for each cargo size or export country information for each similar cargo and cargo transportation contract information. At this time, the export country information may include destination country information, transit country information, and final destination country information.

[0053] For example, the processor (322) can further cluster a plurality of shipper terminals (100) using a clustering model (M1) based on destination country information and cargo transportation contract information for each cargo size. For another example, the processor (322) can further cluster a plurality of shipper terminals (100) using a clustering model (M1) based on transit country information and cargo transportation contract information for each cargo size. For yet another example, the processor (322) can further cluster a plurality of shipper terminals (100) using a clustering model (M1) based on final destination country information and cargo transportation contract information for each cargo size.

[0054] For another example, the processor (322) may further cluster a plurality of shipper terminals (100) using a clustering model (M1) based on destination country information and cargo transportation contract information for each similar cargo. For another example, the processor (322) may further cluster a plurality of shipper terminals (100) using a clustering model (M1) based on transit country information and cargo transportation contract information for each similar cargo. For another example, the processor (322) may further cluster a plurality of shipper terminals (100) using a clustering model (M1) based on final destination country information and cargo transportation contract information for each similar cargo.

[0055] Thereafter, as illustrated in FIGS. 5A to 5C, the processor (322) can extract preset freight rate fluctuation information linked to export country information for each cargo type when each cargo requested by a plurality of clustered shipper terminals (110) is loaded into one container (CT) (S212). At this time, each cargo may be LCL (Less than Container Load) cargo that handles cargo from multiple shippers in one container (CT). In other words, LCL cargo may be cargo that is transported using one of the containers (CT) shared by multiple shippers because the cargo in one container (CT) is not full.

[0056] Here, the processor (322) communicates with the communication unit (310) and can determine whether each cargo is loaded into one container (CT) based on image data captured by a camera installed outside or inside the container (CT).

[0057] At this time, the processor (322) can further extract each cargo freight rate fluctuation information that is preset in connection with each cargo size-specific export country information or each similar cargo-specific export country information.

[0058] For example, as illustrated in FIGS. 6A to 6C, the processor (322) may further extract preset cargo freight fluctuation information linked to destination country information and cargo transportation contract information for each cargo size loaded in the first container (CT1) when the first vessel (S1), the first aircraft (S3), and the first vehicle (S5) transport each cargo to the destination country (A1). In addition, the processor (322) may further extract preset cargo freight fluctuation information linked to destination country information and cargo transportation contract information for each similar cargo loaded in the second container (CT2) when the first vessel (S1), the first aircraft (S3), and the first vehicle (S5) transport each cargo to the destination country (A1).

[0059] For another example, as illustrated in FIGS. 7A to 7C , the processor (322) may further extract preset freight rate fluctuation information linked to the transit country information and freight transport contract information for each cargo size loaded in the third container (CT3) when the second vessel (S2), the second aircraft (S4), and the second vehicle (S6) transport each cargo to the transit country (A2). Thereafter, the processor (322) may further extract preset freight rate fluctuation information linked to the final destination country information and freight transport contract information for each cargo size loaded in addition to the existing one in the third container (CT31) when the second vessel (S2), the second aircraft (S4), and the second vehicle (S6) transport each cargo from the transit country (A2) to the final destination country (A3). At this time, each cargo may be partially unloaded in the transit country (A2) and additionally partially loaded.

[0060] For another example, as illustrated in FIGS. 7A to 7C , the processor (322) may further extract preset freight rate fluctuation information for each similar cargo loaded in the fourth container (CT3) in conjunction with the transit country information and the freight transport contract information when the second vessel (S2), the second aircraft (S4), and the second vehicle (S6) transport their respective cargoes to the transit country (A2). Thereafter, the processor (322) may further extract preset freight rate fluctuation information for each similar cargo loaded in addition to the existing one in the fourth container (CT41) in conjunction with the final destination country information and the freight transport contract information when the second vessel (S2), the second aircraft (S4), and the second vehicle (S6) transport their respective cargoes from the transit country (A2) to the final destination country (A3). At this time, each cargo may be partially unloaded in the transit country (A2) and additionally partially loaded.

[0061] At this time, information on freight rate fluctuations may include changes in transportation distance due to route changes, changes in fuel costs due to route changes, total transportation time due to route changes, macroeconomic variables, freight rate indices, indices related to the value of freight based on HS codes, container terminal usage fees, and freight rate-related document preparation fees. Here, macroeconomic variables may include national GDP, price index, current account balance, dollar index, oil prices, interest rates, and stock market indices. In addition, freight rate indices may include SCFI, CCFI, and BDI, and may include the Baltic Airfreight Index (BAI), Freightos Air Index (FAX), etc. Indices related to the value of freight may include raw material prices and industry indexes.

[0062] Thereafter, as illustrated in FIG. 8, the processor (322) inputs freight rate fluctuation information (Input Data) into the freight rate prediction model (M2), and outputs recommended reference pricing information (Output Data) learned based on the freight rate prediction model (M2) (S213). Here, the freight rate prediction model (M2) may be a multivariate time series forecasting model. For example, the multivariate time series forecasting model may include a VAR (Vector AutoRegressive) model, a Gradient Boosting model, a Transformer-based model, and a Mamba-based model.

[0063] This freight rate prediction model (M2) utilizes various statistical, machine learning, and artificial intelligence models to further refine and closely analyze freight rate fluctuation information (ID), thereby enabling more accurate recommendations of reference pricing information (OD).

[0064] That is, the processor (522) inputs the transportation distance changed by the route change (ID1), the fuel cost changed by the route change (ID2), the total transportation time due to the route change (ID3), the macroeconomic variable (ID4), the freight index (ID5), the index related to the value of the cargo based on the HS CODE (ID6), the container terminal usage fee (ID7), and the freight document preparation fee (ID8) into the freight freight prediction model (M2), and outputs the recommended reference pricing information (OD) learned based on the freight freight prediction model (M2).

[0065] Here, the freight rate prediction model (M2) can be enhanced by using additional learning data sets in addition to various variable transportation distances (ID1), various variable fuel costs (ID2), various total transportation times (ID3), various macroeconomic variables (ID4), various freight rate indices (ID5), various indices related to the value of cargo based on various HS CODES (ID6), various container terminal usage fees (ID7), and various freight rate-related document preparation fees (ID8).

[0066] At this time, the memory (321) can store the recommended reference pricing information (OD) learned based on the freight rate prediction model (M2).

[0067] Thereafter, the processor (322) may transmit a command to display freight auction information to the plurality of forwarder terminals (200) to conduct a freight auction for each cargo based on the reference pricing information (OD) (S214). Here, the plurality of forwarder terminals (200) may display freight auction information for each cargo (S311). At this time, the forwarders may input auction participation information for approval of auction participation into the second UI within the plurality of forwarder terminals (200) so that the forwarders may participate in the auction for freight rates requested by the plurality of clustered shipper terminals using the plurality of forwarder terminals (200) (S312). In addition, the forwarders may each manage auction participation information using the plurality of forwarder terminals (200).

[0068] Meanwhile, in the present disclosure, the processor (322) may transmit a freight rate auction information display command to terminals (500) of multiple freight transport companies communicating via the communication unit (310) to conduct a freight rate auction for each cargo based on the reference pricing information (OD) (S215). In this case, the freight transport companies may be companies that own transportation means such as airplanes, vehicles, and ships.

[0069] Here, terminals (500) of multiple freight transport companies may display freight rate auction information for each cargo (S411). At this time, the freight transport company representatives may input auction participation information for auction participation approval into the third UI within the terminals (500) of multiple freight transport companies, allowing multiple shipper terminals to participate in the auction for freight rates requested by the clustered terminals, using each of the terminals (500) of the multiple freight transport companies (S412). Furthermore, the freight transport company representatives may individually manage auction participation information using each of the terminals (500) of the multiple freight transport companies.

[0070] In the present disclosure, a plurality of shipper terminals (100), a plurality of forwarder terminals (200), a cargo freight management terminal (400), and a plurality of shipping company terminals (500) are wireless communication devices that ensure portability and mobility, for example, and may include all kinds of handheld-based wireless communication devices such as a PCS (Personal Communication System), a GSM (Global System for Mobile communications), a PDC (Personal Digital Cellular), a PHS (Personal Handyphone System), a PDA (Personal Digital Assistant), an IMT (International Mobile Telecommunication)-2000, a CDMA (Code Division Multiple Access)-2000, a W-CDMA (W-Code Division Multiple Access), a WiBro (Wireless Broadband Internet) terminal, a smart phone, and a wearable device such as a watch, a ring, a bracelet, an anklet, a necklace, glasses, a contact lens, or a head-mounted device (HMD).

[0071] The present disclosure performs clustering on each of a plurality of shipper terminals (100), a plurality of forwarder terminals (200), and a plurality of cargo transport company terminals (500), and then makes suggestions for LCL cargo based on the clusters of the plurality of shipper terminals (100). Furthermore, the present disclosure also makes it possible to recommend the optimal forwarder terminal (200) and the optimal cargo transport company terminal (500) based on the cluster distances between the plurality of shipper terminals (100), the plurality of forwarder terminals (200), and the plurality of cargo transport company terminals (500).

[0072] At least one component may be added or deleted to correspond to the performance of the components illustrated in FIGS. 1, 2, and 4 through 8. Furthermore, it will be readily apparent to those skilled in the art that the relative positions of the components may be altered to correspond to the performance or structure of the system.

[0073] Although FIG. 3 describes that multiple steps are executed sequentially, this is merely an example of the technical idea of ​​the present embodiment, and a person having ordinary skill in the technical field to which the present embodiment belongs can modify and apply various modifications and variations by changing the order described in FIG. 3 and executing it or executing one or more steps among the multiple steps in parallel without departing from the essential characteristics of the present embodiment, and therefore FIG. 3 is not limited to a chronological order.

[0074] Meanwhile, the disclosed embodiments may be implemented in the form of a recording medium storing computer-executable instructions. The instructions may be stored in the form of program code, and when executed by a processor, may generate program modules to perform the operations of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

[0075] Computer-readable storage media include all types of storage media that store instructions that can be deciphered by a computer. Examples include read-only memory (ROM), random access memory (RAM), magnetic tape, magnetic disks, flash memory, and optical data storage devices.

[0076] The disclosed embodiments have been described with reference to the attached drawings as described above. Those skilled in the art will understand that the present disclosure can be implemented in forms other than the disclosed embodiments without altering the technical spirit or essential features of the present disclosure. The disclosed embodiments are illustrative and should not be construed as limiting.

Claims

1. A communication unit that performs communication with multiple shipper terminals and multiple forwarder terminals; and A processor for controlling operations related to freight rates based on shipper clustering; The above processor, When a request for a freight quotation corresponding to the export country information for each cargo type is received from the multiple shipper terminals through the above communication unit, The export country information for each cargo type above is classified into export country information for each cargo size and export country information for each similar cargo, The multiple shipper terminals are clustered using a clustering model based on the export country information for each cargo size, the export country information for each similar cargo, and the cargo transportation contract information. When some or all of the cargo of the above-mentioned clustered multiple shipper terminals are loaded into one or more containers, and a change in the route is confirmed or predicted among the freight rate influencing factors related to the export country information by each cargo size or the export country information by each similar cargo, freight rate change information including the changed transportation distance, changed fuel cost, and total transportation time linked to the change in the route is extracted, By inputting the above freight rate fluctuation information into the freight rate prediction model, the recommended standard pricing information learned based on the freight rate prediction model is output. Based on the above standard pricing information, freight auction information for each of the above cargoes is displayed on the plurality of forwarder terminals so that freight auctions are conducted for each of the above cargoes. When printing the above recommended standard pricing information, A cargo freight management server based on shipper clustering, characterized in that among the above cargo freight change information, metadata such as macroeconomic variables, freight indices, HS CODE-based cargo value indices, container terminal usage fees, and freight freight-related document preparation costs are additionally input into the above cargo freight prediction model, thereby outputting recommended standard pricing information.

2. In paragraph 1, The above processor, A cargo freight management server based on shipper clustering, characterized in that it clusters the plurality of shipper terminals using the clustering model based on the type of transportation means, contract type, payment method, reservation route, reservation time, contract manager location, and shipper location included in the above cargo transportation contract information.

3. In paragraph 2, The above processor, A cargo freight management server based on shipper clustering, characterized in that the plurality of shipper terminals are further clustered using the clustering model based on the presence or absence of transshipment and the cargo HS CODE included in the above cargo transportation contract information.

4. Multiple shipper terminals requesting cargo transportation; A plurality of forwarder terminals managing the above cargo transportation; and A cargo freight management server that performs communication with the plurality of shipper terminals and the plurality of forwarder terminals; The above cargo freight management server, When a request for freight quotation corresponding to export country information for each cargo type is received from the multiple shipper terminals above, The export country information for each cargo type above is classified into export country information for each cargo size and export country information for each similar cargo, The multiple shipper terminals are clustered using a clustering model based on the export country information for each cargo size, the export country information for each similar cargo, and the cargo transportation contract information. When some or all of the cargo of the above-mentioned clustered multiple shipper terminals are loaded into one or more containers, and a change in the route is confirmed or predicted among the freight rate influencing factors related to the export country information by each cargo size or the export country information by each similar cargo, freight rate change information including the changed transportation distance, changed fuel cost, and total transportation time linked to the change in the route is extracted, By inputting the above freight rate fluctuation information into the freight rate prediction model, the recommended standard pricing information learned based on the freight rate prediction model is output. Based on the above standard pricing information, freight auction information for each of the above cargoes is displayed on the plurality of forwarder terminals so that freight auctions are conducted for each of the above cargoes. When printing the above recommended standard pricing information, A cargo freight management system based on shipper clustering, characterized in that among the above cargo freight change information, the metadata such as macroeconomic variables, freight index, HS CODE-based cargo value index, container terminal usage fee, and freight freight-related document preparation fee are additionally input into the above cargo freight prediction model, thereby outputting recommended standard pricing information.

5. In a cargo freight management method based on shipper clustering performed by a cargo freight management server, A step of receiving a request for a freight quotation corresponding to export country information for each cargo type from multiple shipper terminals through the communication unit of the above freight rate management server; A step of classifying export country information by each cargo type into export country information by each cargo size and export country information by each similar cargo when a request for a cargo freight quotation request is received by the processor of the cargo freight management server; A step of clustering the plurality of shipper terminals using a clustering model based on export country information for each cargo size, export country information for each similar cargo, and cargo transportation contract information, by the processor; A step of extracting freight rate change information including a changed transport distance, changed fuel cost, and total transport time linked to the change in route, when some or all of the cargo of the clustered plurality of shipper terminals is loaded into one or more containers by the processor, and a change in route is confirmed or predicted among freight rate influence factors related to export country information by each cargo size or export country information by each similar cargo; A step of inputting the freight rate fluctuation information into a freight rate prediction model by the above processor, and outputting recommended reference pricing information learned based on the freight rate prediction model; A step of displaying cargo freight auction information for each cargo on the plurality of forwarder terminals so that a cargo freight auction is conducted for each cargo based on the standard pricing information by the processor; including; The step of outputting the above recommended standard pricing information is: A method characterized in that, by the processor, the metadata of the freight rate fluctuation information, such as macroeconomic variables, freight rate indices, HS CODE-based freight value indices, container terminal usage fees, and freight rate-related document preparation costs, are additionally input into the freight rate prediction model, thereby outputting recommended reference pricing information.

6. A computer-readable recording medium coupled with a computer and storing a program for executing the method of claim 5.

Images