Apparatus and method for generating per-unit-time virtual logistics data for data generalization using generative adversarial model

Abstract

The present invention relates to an apparatus and method for generating per-unit-time virtual logistics data for data generalization using a generative adversarial model and, more particularly, to an apparatus and method capable of predicting future logistics on the basis of data on a current situation and past logistics data. The method for generating per-unit-time virtual logistics data for data generalization using a generative adversarial model, according to the present invention, may comprise the steps of: receiving at least one of transaction information for each dealership and existing logistics supply records; dividing input data into past data and current data; training an artificial intelligence model using the past data and validating the trained artificial intelligence model using the current data; and predicting future logistics data on the basis of the current data after training the artificial intelligence model.

Description

Device and method for generating virtual data per unit time of logistics data for adversarial generative model-based data generalization

[0001] The present invention relates to an apparatus and method for generating virtual data per unit time of logistics data for adversarial generative model-based data generalization, and specifically, to an apparatus and method capable of predicting future logistics based on data regarding the current situation and past logistics data.

[0002]

[0003] Because existing logistics forecasting models predict inventory flow based only on current situations, they fail to reflect inventory conditions in various environments, or their prediction accuracy decreases for situations not included in their training.

[0004] Most prediction models learn by adding randomness to the data to address this phenomenon, but this results in a lack of diversity in situations where the trend itself is altered, such as periodicity.

[0005] Therefore, it is necessary to diversify instances of data change through generative models and secure data on whether they can become the current trend in various situations.

[0006]

[0007] The present invention aims to provide an apparatus and method capable of improving the accuracy of logistics forecasting by analyzing and verifying how the inventory situation reached the current state based on data regarding the current situation and past logistics data, using logistics time series data, which is representative time series data, as an example.

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

[0009]

[0010] According to one embodiment of the present invention for solving the problem described above, a method for generating virtual data per unit time of logistics data for adversarial generative model-based data generalization may include the steps of receiving at least one of each agency transaction information and existing logistics supply records, classifying the input data into past data and present data, training an artificial intelligence model with past data and verifying the artificial intelligence model trained with present data, and predicting future logistics data through the present data after training the artificial intelligence model.

[0011] In an alternative embodiment, the step of training an artificial intelligence model with the past data may include the step of the artificial intelligence model generating amplified data using the past data as input data, and the step of training the artificial intelligence model based on the past data and the amplified data.

[0012] In an alternative embodiment, the step of verifying an artificial intelligence model trained with current data may include the step of the artificial intelligence model generating prediction data using the past data as input data and the step of evaluating the accuracy of the artificial intelligence model by comparing the prediction data with the current data.

[0013] In an alternative embodiment, the step of separating input data into past data and current data may involve arranging the input data in chronological order according to a preset criterion and separating them into past data and current data.

[0014] In addition, the present invention may provide a server that performs the method described above by including a memory for storing one or more instructions and a processor for executing the one or more instructions stored in the memory, wherein the processor executes the one or more instructions.

[0015] In addition, the present invention may provide a computer program stored on a recording medium readable by a computer, which is combined with hardware such as a computer, to perform the above method.

[0016] Other specific details of the present invention are included in the detailed description and drawings.

[0017]

[0018] The present invention can increase the reliability of a prediction model by ensuring diversity of cases in the predicted model.

[0019] The effects of the present invention are not limited to those mentioned above, and other unmentioned effects will be clearly understood by a person skilled in the art from the description below.

[0020]

[0021] FIG. 1 is a drawing illustrating a system according to one embodiment of the present invention.

[0022] FIG. 2 is a hardware configuration diagram of a server according to one embodiment of the present invention.

[0023] FIG. 3 is a hardware configuration diagram of a terminal according to one embodiment of the present invention.

[0024] FIG. 4 is a flowchart illustrating a data generation method according to an embodiment of the present invention.

[0025] FIG. 5 is a conceptual diagram showing the basic data configuration according to the present invention.

[0026] FIG. 6 is a flowchart of a method for generating and verifying amplified data according to one embodiment of the present invention.

[0027] FIG. 7 is a flowchart of a circular evaluation / verification method of data generated by a generative AI model, including a model learning process according to one embodiment of the present invention.

[0028]

[0029] Various embodiments are now described with reference to the drawings. In this specification, various descriptions are provided to facilitate an understanding of the invention. However, it is evident that these embodiments can be practiced without such specific descriptions.

[0030] As used herein, terms such as “component,” “module,” “system,” etc. refer to computer-related entities, hardware, firmware, software, combinations of software and hardware, or executions of software. For example, a component may be, but is not limited to, a procedure executed on a processor, a processor, an object, an execution thread, a program, and / or a computer. For example, both an application executed on a computing device and the computing device itself may be a component. One or more components may reside within a processor and / or an execution thread. A component may be localized within a single computer. A component may be distributed among two or more computers. Additionally, these components may be executed from various computer-readable media having various data structures stored therein. Components may communicate through local and / or remote processes, for example, according to signals having one or more data packets (e.g., data from a component interacting with another component in a local system or distributed system, and / or data transmitted through signals to other systems and networks such as the Internet).

[0031] Furthermore, the term "or" is intended to mean an implicit "or" rather than an exclusive "or." That is, unless otherwise specified or evident from the context, "X uses A or B" is intended to mean one of the natural implicit substitutions. In other words, if X uses A; if X uses B; or if X uses both A and B, "X uses A or B" may apply to any of these cases. Additionally, the term "and / or" as used herein should be understood to refer to and include all possible combinations of one or more of the enumerated related items.

[0032] Additionally, the terms “comprising” and / or “comprising” should be understood to mean that such features and / or components are present. However, the terms “comprising” and / or “comprising” should be understood not to exclude the presence or addition of one or more other features, components and / or groups thereof. Furthermore, unless otherwise specified or clearly evident from the context to indicate a singular form, the singular in this specification and claims should generally be interpreted to mean “one or more.”

[0033] Those skilled in the art should recognize that the various exemplary logical blocks, configurations, modules, circuits, means, logics, and algorithmic steps described in connection with the embodiments disclosed herein may be implemented in electronic hardware, computer software, or a combination of both. To clearly exemplify the interchangeability of hardware and software, various exemplary components, blocks, configurations, means, logics, modules, circuits, and steps have been generally described above in terms of their functionality. Whether such functionality is implemented in hardware or software depends on the specific application and design constraints imposed on the overall system. Skilled technicians may implement the described functionality in various ways for each specific application. However, such decisions regarding implementation should not be interpreted as moving out of the scope of the invention.

[0034] The description of the presented embodiments is provided to enable those skilled in the art to use or practice the present invention. Various modifications to these embodiments will be apparent to those skilled in the art. The general principles defined herein may be applied to other embodiments without departing from the scope of the present invention. Thus, the present invention is not limited to the embodiments presented herein. The present invention should be interpreted in the broadest possible scope consistent with the principles and novel features presented herein.

[0035] In this specification, the term "computer" refers to any type of hardware device comprising at least one processor, and may be understood to include software configurations operating on said hardware device according to the embodiments. For example, the term "computer" may be understood to include smartphones, tablet PCs, desktops, laptops, and user clients and applications running on each of these devices, but is not limited thereto.

[0036] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings.

[0037] Each step described in this specification is described as being performed by a computer, but the subject of each step is not limited thereto, and depending on the embodiment, at least some of each step may be performed on different devices.

[0038]

[0039] FIG. 1 is a drawing illustrating a system according to one embodiment of the present invention.

[0040] Referring to FIG. 1, a device according to one embodiment of the present invention may include a server (100) and a terminal (200). The server (100) and the terminal may transmit and receive data through a network (300). The device (or system) illustrated in FIG. 1 is according to one embodiment, and its components are not limited to the embodiment illustrated in FIG. 1 and may be added, changed, or deleted as needed.

[0041] Data generation according to the present invention may be performed solely by a server (100) or a terminal (200), or implemented through data transmission and reception between the server (100) and the terminal (200). Even if the data generation method described below is described with the performing entity limited to either the server (100) or the terminal (200), it is obvious that the method may be performed by other performing entities or through data transmission and reception between the server (100) and the terminal (200).

[0042] In one embodiment, the server (100) may receive transaction information of each agency or existing logistics supply records as input.

[0043] In one embodiment, the server (100) can perform analysis on the input data.

[0044] In one embodiment, the server (100) can distinguish between past data and current data, excluding a current portion of the input data.

[0045] In one embodiment, the server (100) can diversify past data through GAN and predict the present with a prediction model to verify with current data.

[0046] In one embodiment, the server can calculate a loss value according to a separate loss function by comparing past logistics changes generated by the model with the current product inventory status of the agency.

[0047] In one embodiment, the server can predict future data through current data after the model training is completed.

[0048] Hereinafter, an example of a method for generating data according to the present invention will be described with reference to FIGS. 4 to 7.

[0049] In various embodiments, the server (100) may provide Web or Application-based services. However, it is not limited thereto.

[0050] The server (100) may include any type of computer system or computer device, such as, for example, a microprocessor, a mainframe computer, a digital processor, a portable device, and a device controller. However, it is not limited thereto.

[0051] Hereinafter, the hardware configuration of the server (100) will be described with reference to FIG. 2.

[0052] FIG. 2 is a hardware configuration diagram of a server according to one embodiment of the present invention.

[0053] Referring to FIG. 2, a server (100) according to one embodiment of the present invention may include one or more processors (110), a memory (120) for loading a computer program (151) executed by the processor (110), a bus (130), a communication interface (140), and a storage (150) for storing the computer program (151). Here, FIG. 2 illustrates only the components related to the embodiment of the present invention. Therefore, a person skilled in the art to which the present invention pertains will understand that other general-purpose components may be included in addition to the components illustrated in FIG. 2.

[0054] The processor (110) controls the overall operation of each component of the server (100). The processor (110) may be composed of one or more cores and may include processors for data analysis and deep learning, such as a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), or a tensor processing unit (TPU) of a computing device. Alternatively, it may be configured to include any type of processor well known in the art of the present invention.

[0055] Additionally, the processor (110) may perform operations for at least one application or program for executing the method according to embodiments of the present invention, and the server (100) may have one or more processors.

[0056] In various embodiments, the processor (110) may further include RAM (Random Access Memory, not shown) and ROM (Read-Only Memory, not shown) for temporarily and / or permanently storing signals (or data) processed within the processor (110). Additionally, the processor (110) may be implemented in the form of a system-on-chip (SoC) comprising at least one of a graphics processing unit, RAM, and ROM.

[0057] Memory (120) stores various data, instructions and / or information. Memory (120) may load a computer program (151) from storage (150) to execute a method / operation according to various embodiments of the present invention. When the computer program (151) is loaded into memory (120), the processor (110) may perform the method / operation by executing one or more instructions constituting the computer program (151). Memory (120) may be implemented as volatile memory such as RAM, but the technical scope of the present invention is not limited thereto.

[0058] The bus (130) provides communication functions between components of the server (100). The bus (130) can be implemented as various types of buses, such as an address bus, a data bus, and a control bus.

[0059] The communication interface (140) supports wired and wireless internet communication of the server (100). Additionally, the communication interface (140) may support various communication methods other than internet communication. To this end, the communication interface (140) may be configured to include a communication module well known in the art of the present invention. In some embodiments, the communication interface (140) may be omitted.

[0060] Storage (150) can store a computer program (151) non-temporarily. When performing a process according to an embodiment of the present invention through a server (100), storage (150) can store various information necessary to perform a method according to the disclosed embodiment or to provide a service.

[0061] The storage (150) may be configured to include non-volatile memory such as ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), flash memory, a hard disk, a removable disk, or any form of computer-readable recording medium well known in the art to which the present invention belongs.

[0062] A computer program (151) may include one or more instructions that cause a processor (110) to perform a method / operation according to various embodiments of the present invention when loaded into memory (120). That is, the processor (110) may perform the method / operation according to various embodiments of the present invention by executing the one or more instructions.

[0063] In one embodiment, the computer program (151) may include one or more instructions to perform various methods related to various tasks related to learning a neural network model.

[0064] The steps of the method or algorithm described in connection with embodiments of the present invention may be implemented directly in hardware, implemented as a software module executed by hardware, or implemented by a combination thereof. The software module may reside in RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), Flash Memory, a hard disk, a removable disk, a CD-ROM, or any form of computer-readable recording medium well known in the art to which the present invention belongs.

[0065] The components of the present invention may be implemented as a program (or application) and stored on a medium to be executed in combination with a computer, which is hardware. The components of the present invention may be implemented as software programming or software elements, and similarly, embodiments may be implemented in programming or scripting languages ​​such as C, C++, Java, assembler, etc., including various algorithms implemented as combinations of data structures, processes, routines, or other programming configurations. Functional aspects may be implemented as algorithms executed on one or more processors.

[0066] Hereinafter, the hardware configuration of the terminal (100) will be described with reference to FIG. 2.

[0067] FIG. 3 is a hardware configuration diagram of a terminal according to one embodiment of the present invention.

[0068] The terminal (200) may include, for example, various types of computer devices. Specifically, for example, the user terminal may refer to various terminal devices such as smartphones, tablet PCs, desktops, and laptops.

[0069] The terminal (200) may have one or more processors (210) that perform operations for at least one application or program for executing a method according to embodiments of the present invention.

[0070] The memory (220) can store a computer program (221) non-temporarily. When performing a process according to an embodiment of the present invention through a device (100), the memory (220) can store various information necessary to perform a method according to the disclosed embodiment or to provide a service.

[0071] The memory (220) may be configured to include non-volatile memory such as ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), flash memory, a hard disk, a removable disk, or any form of computer-readable recording medium well known in the art to which the present invention belongs.

[0072] A computer program (221) may include one or more instructions that cause a processor (210) to perform a method / operation according to various embodiments of the present invention when loaded into memory (220). That is, the processor (210) may perform the method / operation according to various embodiments of the present invention by executing the one or more instructions.

[0073] In one embodiment, the computer program (221) may include one or more instructions to perform various methods related to various tasks related to learning a neural network model.

[0074] The communication interface (230) supports wired and wireless internet communication of the terminal (200). Additionally, the communication interface (230) may support various communication methods other than internet communication. To this end, the communication interface (230) may be configured to include a communication module well known in the art of the present invention. In some embodiments, the communication interface (230) may be omitted.

[0075] The input interface (230) supports the user in inputting various information into the terminal (200). For example, the input interface (230) may include a keyboard, mouse, microphone, USB port, etc., and may be configured to include an input module well known in the technical field.

[0076] The terminal (200) includes a display (250) and may include an operating system for running services based on applications or extension programs provided by the server (100). For example, the user terminal may be a smartphone, but is not limited thereto. The user terminal may be a wireless communication device that ensures portability and mobility, and may include all kinds of handheld-based wireless communication devices such as navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) terminal, smartpad, tablet PC, etc.

[0077] The server (100) and the terminal (200) can be connected via a network.

[0078] Referring again to FIG. 1, the network (300) may refer to a connection structure capable of exchanging information between each node, such as a computing device, a plurality of terminals, and servers. For example, the network (300) includes a Local Area Network (LAN), a Wide Area Network (WAN), the World Wide Web (WWW), a wired and wireless data network, a telephone network, a wired and wireless television network, etc.

[0079] Wireless data communication networks include, but are not limited to, 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), 5GPP (5th Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), Wi-Fi, Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth network, NFC (Near-Field Communication) network, satellite broadcasting network, analog broadcasting network, DMB (Digital Multimedia Broadcasting) network, etc.

[0080] Below, a method for generating data using the aforementioned hardware is described in detail.

[0081] FIG. 4 is a flowchart illustrating a data generation method according to an embodiment of the present invention, and FIG. 5 is a conceptual diagram illustrating a basic data configuration according to the present invention.

[0082] Referring to FIG. 4, a step of receiving at least one of each agency transaction information and existing logistics supply records is performed (S110).

[0083] The server (100) can receive transaction information and existing logistics supply records of the agency through terminals (200) placed at each agency.

[0084] Next, a step of separating the input data into past data and current data is performed (S120).

[0085] Referring to FIG. 5, the input data (11) can be broadly divided into two types. Specifically, the input data can be divided into prediction model training data (510) and prediction model validation data (520).

[0086] The prediction model training data (510) includes past data (511) that is in the past in time series order among the data classified according to the pre-set criteria of the input data (11).

[0087] The prediction model validation data includes current data (521), which is the remaining data excluding past data in time series order among the data classified according to pre-set criteria.

[0088] The server (100) can arrange input data in chronological order according to a preset standard and distinguish between past data and current data.

[0089] Next, a step is performed to train an artificial intelligence model with past data and to verify the trained artificial intelligence model with current data (S130).

[0090] Referring to FIG. 5, the server (100) can generate logistics data (512) for various situations by utilizing past data (511) as a generative model. Additionally, the server (100) can train an artificial intelligence model by utilizing the past data (511) and the logistics data (512).

[0091] Here, learning can refer to the process of updating the model's weights by indicating the optimal logistics transaction volume (change amount) considering the loss value from the previous step.

[0092] Meanwhile, the server (100) can generate predicted data (522) that predicts the future using past data (511) as input data after training the artificial intelligence model. Afterward, the server (100) can verify the performance of the artificial intelligence model by comparing the predicted data (522) with the current data (521).

[0093] After training an artificial intelligence model in the manner described above, a step of predicting future logistics data using current data is performed (S140).

[0094] Below, the learning method of the artificial intelligence model described in Fig. 5 will be explained in more detail.

[0095] FIG. 6 is a flowchart of a method for generating and verifying amplified data according to one embodiment of the present invention.

[0096] Referring to FIG. 6, the server (100) reduces and preprocesses (21) only the parts necessary for learning from the original data.

[0097] The input data (11) generated through the above preprocessing is classified (22) according to the pre-set data classification criteria.

[0098] Past data (611) is input into a generative artificial intelligence model (23), and the generative artificial intelligence model (23) generates amplified data (612). Past data (611) and amplified data (612) are used as training data (610) for the artificial intelligence model.

[0099] Afterwards, the future is predicted (622) using past data (611).

[0100] Meanwhile, the server (100) evaluates the accuracy (24) by comparing the current data (621) with the prediction data predicted by the artificial intelligence model using past data (611). Afterward, it performs verification (25) on the amplified data based on the evaluation results.

[0101] The above verification can be utilized in the future process of improving the prediction model.

[0102] Next, a cyclic evaluation / verification method according to one embodiment of the present invention will be described.

[0103] FIG. 7 is a flowchart of a circular evaluation / verification method of data generated by a generative AI model, including a model learning process according to one embodiment of the present invention.

[0104] Referring to FIG. 7, the generative model (711) is a generative part of a generative AI model that distinguishes between past data and current data.

[0105] The generated data (712) is data generated through the generation model (before verification).

[0106] The classification model (713) is a part of the classification model of a generative AI model that performs the operation of distinguishing between past data and current data.

[0107] The (classified) generated data (714) is data classified as data generated through a classification model.

[0108] The (classified) past data (715) is data classified as past data through a classification model. A prediction model is trained using this data.

[0109] Unlike the accuracy evaluation (23) in Fig. 6, the current data (721) is an accuracy evaluation during the learning process, so when the target value is not achieved, the loss value of the artificial intelligence model's future prediction data (generated in S140) is passed to each model, and a cyclic learning process is performed that includes a comprehensive score on how the classification model classifies and predicts, rather than repeated learning on the same data.

[0110] In the prediction data (722) of the cyclic learning, the prediction model is evaluated for both data and prediction performance through a comparative evaluation with the current data.

[0111] Although embodiments of the present invention have been described above with reference to the attached drawings, those skilled in the art will understand that the present invention may be implemented in other specific forms without altering its technical concept or essential features. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive.

[0112]

[0113] The relevant details have been described in the best mode for carrying out the invention as described above.

Claims

1. A method performed by a computing device comprising at least one processor, A step of receiving at least one of each agency transaction information and existing logistics supply records; A step of separating input data into past data and current data; A step of training an artificial intelligence model with historical data and verifying the trained artificial intelligence model with current data; and The stage of predicting future logistics data using current data after training an artificial intelligence model; including, Method for generating virtual data per unit time of logistics data for adversarial generative model-based data generalization.

2. In Paragraph 1, The step of training an artificial intelligence model with the aforementioned historical data is, A step in which the artificial intelligence model generates amplified data using the past data as input data; Characterized by including the step of training the artificial intelligence model based on the past data and the amplified data. Method for generating virtual data per unit time of logistics data for adversarial generative model-based data generalization.

3. In Paragraph 2, The step of verifying an artificial intelligence model trained with current data is, A step in which the artificial intelligence model generates prediction data using the past data as input data; and Characterized by including a step of evaluating the accuracy of the artificial intelligence model by comparing the above prediction data with the above current data. Method for generating virtual data per unit time of logistics data for adversarial generative model-based data generalization.

4. In Paragraph 3, The step of separating input data into past data and current data is, Characterized by arranging input data in chronological order according to preset criteria and distinguishing between past data and present data, Method for generating virtual data per unit time of logistics data for adversarial generative model-based data generalization.

5. Memory for storing one or more instructions; and A processor that executes one or more instructions stored in the memory. Including, The above processor executes the above one or more instructions, A server that performs the method of claim 1.

6. A computer program stored on a computer-readable recording medium that is combined with a computer, which is hardware, to perform the method of claim 1.

Images