Method for providing unused material transaction service on basis of artificial intelligence algorithm

Abstract

Disclosed are a method and a server for providing an unused material transaction service on the basis of an artificial intelligence algorithm. A method for providing an unused material transaction service provided by a server according to an embodiment of the present disclosure may include the steps of: obtaining an unused material order pattern of a first consumer on the basis of unused material order detail information of the first consumer; obtaining an estimated order amount and an estimated order time of the first consumer on the basis of the unused material order pattern of the first consumer and a cost change monitoring result of the unused material; transmitting a first message inquiring about an intention to order as many unused materials as the estimated order amount to a first terminal device used by the first consumer at the estimated order time; and on the basis of reception of a second message related the order of the unused materials from the first terminal device in response to the first message, transmitting, to the first terminal device, a list of suppliers capable of supplying as many unused materials as the estimated order amount on the basis of the unused material order detail information of the first consumer and an unused material inventory database for each of a plurality of suppliers.

Description

A method for providing a service for trading obsolete materials based on an artificial intelligence algorithm.

[0001] The present disclosure relates to a technology for providing a transaction service for unused materials, and more specifically, to a system for providing a transaction service for unused materials, including a service for predicting the order quantity and order timing of a user based on an artificial intelligence algorithm.

[0002] It's a common business strategy for many companies to purchase raw materials in bulk to lower their purchase costs and to mass-produce plant construction equipment to lower production costs. Meanwhile, when obsolete inventory arises from bulk purchases and production, many companies often try to minimize losses by selling the obsolete inventory to other companies.

[0003] However, the reality is that obsolete inventory is not being traded smoothly within existing, limited offline trading networks. Consequently, many sellers, even with competitive manufacturing technology, are experiencing stagnant performance.

[0004] Moreover, many sellers struggle to manage the obsolete inventory they intend to sell. Typically, significant manpower is invested in managing the type, quantity, and quality of each inventory. This means that when the volume of obsolete inventory to be sold is large, the labor required and the associated costs inevitably increase exponentially.

[0005] In addition, there was a problem in the past where buyers who wanted to purchase materials for plant construction could not efficiently collect information on materials that met the required specifications and could not more efficiently establish material purchasing plans based on the collected information.

[0006] Meanwhile, efforts to apply artificial intelligence algorithms to various industrial fields are increasing. AI technology refers to a technology that learns to mimic human thought processes and controls them to produce various inference results. An algorithm refers to the process of processing input data according to pre-learned methods and procedures to produce results. In other words, an AI algorithm can be a general term for a series of algorithms that learn and infer to produce optimal results.

[0007] The present disclosure has been devised to solve the above-described problems, and the purpose of the present disclosure is to provide a method for providing a waste material transaction service based on an artificial intelligence algorithm.

[0008] In addition, the purpose of the present disclosure is to provide a method for providing a service that identifies a demander's expected order quantity and expected order timing based on the demander's order history, and inquires about the demander's intention to trade unused materials based on the identified expected order quantity and expected order timing.

[0009] In addition, the purpose of the present disclosure is to provide a method for providing a cost fluctuation trend of unused materials to a user and predicting the demand / supply of unused materials based on the cost fluctuation trend.

[0010] 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.

[0011] In one embodiment of the present disclosure, a method for providing a waste material transaction service based on an artificial intelligence algorithm, which is performed by a server, may include: acquiring a waste material ordering pattern of a first user based on waste material ordering history information of the first user; acquiring an expected order quantity and an expected ordering time of the first user based on the waste material ordering pattern of the first user and a result of monitoring a change in the cost of the waste material; transmitting a first message inquiring about an intention to order waste materials in the expected order quantity at the expected ordering time to a first terminal device used by the first user; and transmitting a list of suppliers capable of supplying waste materials in the expected order quantity to the first terminal device based on the waste material ordering history information of the first user and a waste material inventory database for multiple suppliers, based on a second message related to an order of waste materials received from the first terminal device in response to the first message.

[0012] And, the order history information of the first consumer for unused materials includes the purchase cycle of the first consumer for unused materials, the purchase quantity of unused materials per unit order of the first consumer, and information on at least one first supplier from which the first consumer purchased unused materials, and the order pattern of the first consumer for unused materials and the monitoring result of the cost fluctuation of the unused materials are input into a first artificial intelligence (AI) model so that the expected order quantity and expected order time of the first consumer can be obtained.

[0013] In addition, the first AI model can be trained to output a correlation between the purchase amount of unused materials per unit order of the first user and the monitoring result of the cost fluctuation of the unused materials, and to output the cost fluctuation sensitivity of the unused materials of the first user based on the correlation.

[0014] In addition, the first AI model is trained to output the expected ordering time of the first consumer based on the first consumer's purchase cycle of unused materials and the monitoring result of the cost fluctuation of the unused materials, and the sizes of the first weight applied to the first consumer's purchase cycle of unused materials and the second weight applied to the monitoring result of the cost fluctuation of the unused materials can be determined based on the sensitivity of the cost fluctuation of the unused materials of the first consumer.

[0015] And, the first message displayed on the first terminal device includes an icon for accepting an order of unused materials in the expected order amount at the expected order time and an order UI for adjusting the order time and order amount of the unused materials, and based on the order time and order amount of the unused materials being input by the first terminal device through the order UI, the second message including the input order time and order amount of the unused materials can be transmitted to the server.

[0016] And, at least one second supplier holding an unused material inventory at the time of the first demander's unused material order is identified through the unused material inventory database of the plurality of suppliers, and the supplier list may include at least one first supplier from which the first demander purchased unused material and at least one second supplier.

[0017] And, by inputting the evaluation score, the history of sales of unused materials, the delivery schedule, and the expected cost of each of the first at least one supplier and the second at least one supplier into the second AI model, the priorities of each of the first at least one supplier and the second at least one supplier are calculated, and the exposure rankings of the first at least one supplier and the second at least one supplier within the supplier list can be determined based on the calculated priorities.

[0018] And, based on the purchase of the first demander from a specific supplier among the first at least one supplier and the second at least one supplier at a specific time, the accuracy of the first AI model can be calculated through i) a first difference between the order quantity of the first demander at the specific time and the expected order quantity, and ii) a second difference between the specific time and the expected order time.

[0019] And, based on the accuracy of the first AI model being less than a threshold, the method may further include a step of retraining the first AI model based on the first difference and the second difference.

[0020] In addition, the method may further include a step of generating a first block based on a hash value corresponding to the order history information of the first user for unused materials; a step of generating a second block based on a hash value corresponding to the order history information of the first user for unused materials at the specific time; and a step of constructing a database of orders of unused materials of the first user in the form of a blockchain by linking the second block to the first block.

[0021] In addition, a computer-readable recording medium recording a computer program for executing a method for implementing the present disclosure may be further provided.

[0022] According to various embodiments of the present disclosure, a method for providing a waste material transaction service based on an artificial intelligence algorithm can be provided.

[0023] In addition, according to various embodiments of the present disclosure, a method may be provided for providing a service that identifies a demander's expected order quantity and expected order timing based on the demander's order history, and inquires about a willingness to trade unused materials based on the identified expected order quantity and expected order timing.

[0024] In addition, by various embodiments of the present disclosure, a method for providing a cost fluctuation trend of unused materials to a user and predicting the demand / supply of unused materials based on the cost fluctuation trend can be provided.

[0025] The effects of the present disclosure are not limited to those mentioned above, and other effects not mentioned can be clearly understood by those skilled in the art from the description below.

[0026] FIG. 1 is a conceptual diagram schematically illustrating a system for implementing a method for providing a waste material transaction service according to one embodiment of the present disclosure.

[0027] FIG. 2 is a block diagram illustrating the configuration of a server providing a waste material transaction service according to one embodiment of the present disclosure.

[0028] FIG. 3 is a flowchart illustrating a method for providing a waste material transaction service by a server according to one embodiment of the present disclosure.

[0029] FIG. 4 is a diagram illustrating an example of a first message transmitted by a server according to one embodiment of the present disclosure.

[0030] FIG. 5 is a flowchart illustrating a method for outputting a supplier list based on a database of unused material inventory by a server according to one embodiment of the present disclosure.

[0031] The present disclosure may be modified in various ways and encompasses numerous embodiments. Specific embodiments are illustrated in the drawings and described in detail herein. However, this is not intended to limit the present disclosure to specific embodiments, and it should be understood that the present disclosure encompasses all modifications, equivalents, and alternatives falling within the spirit and technical scope of the present disclosure.

[0032] In describing the present disclosure, detailed descriptions of related known technologies will be omitted if they are deemed to unnecessarily obscure the gist of the present invention. Furthermore, numbers (e.g., "first," "second," etc.) used throughout the description of this specification are merely identifiers used to distinguish one component from another.

[0033] Additionally, when a component of this specification is referred to as being "connected" or "connected" to another component, it should be understood that the component may be directly connected or connected to the other component, but may also be connected or connected via another component in between, unless otherwise specifically stated.

[0034] In addition, components expressed as 'unit', 'module', etc. in this specification may be two or more components combined into one component, or one component may be divided into two or more components with more detailed functions. In addition, each component described below may additionally perform some or all of the functions performed by other components in addition to its own main function, and of course, some of the main functions performed by each component may be performed exclusively by other components.

[0035] In describing the present disclosure, “demander” may collectively refer to an entity (e.g., a company, an individual, etc.) that purchases unused materials, and “supplier” may collectively refer to an entity (e.g., a company, an individual, etc.) that supplies unused materials.

[0036] Hereinafter, a method for providing a waste material transaction service based on an artificial intelligence algorithm according to the present disclosure will be specifically described with reference to drawings.

[0037] FIG. 1 is a conceptual diagram schematically illustrating a system for implementing a method for providing a waste material transaction service according to one embodiment of the present disclosure.

[0038] As illustrated in FIG. 1, a system (1000) for implementing a method for providing a waste material transaction service according to one embodiment of the present disclosure may include a server (100), a terminal device (200) used by a user, and terminal devices (300-1, 300-2, ... 300-N) used by multiple suppliers.

[0039] Here, the terminal device (200) used by the user is implemented as a smart phone, and the terminal devices (300-1, 300-2, ... 300-N) (N is a natural number greater than or equal to 1) used by multiple suppliers are implemented as desktops, but the present invention is not limited thereto.

[0040] The terminal device (200) used by the user and the terminal devices (300-1, 300-2, ... 300-N) used by multiple suppliers can be implemented as various types of electronic devices (e.g., notebook, desktop, laptop, tablet PC, slate PC device, server device, etc.), and can also be implemented as a device group in which one or more types of devices are connected.

[0041] The server (100) may also be implemented as a device group to which one or more types of devices are connected. For example, the server (100) may be implemented as one or more devices that manage an application / website providing a waste material transaction service and a cloud server that stores data related to the application / website.

[0042] In the following, it is assumed that each demander and supplier has registered with an application / website that provides a waste material transaction service (i.e., a waste material transaction platform created and managed by the server (100).

[0043] Also, while FIG. 1 illustrates a case where there is only one user, the present invention is not limited thereto. The number of users registered on an application / website providing a service for trading unused materials on the system (1000) may vary.

[0044] In the system (1000), a server (100), a terminal device (200) used by a user, and terminal devices (300-1, 300-2, ... 300-N) used by multiple suppliers can communicate via a network (W).

[0045] Here, the network (W) may include wired networks and wireless networks. For example, the network may include various networks such as a local area network (LAN), a metropolitan area network (MAN), and a wide area network (WAN).

[0046] Additionally, the network (W) may include the well-known World Wide Web (WWW). However, the network (W) according to the embodiment of the present disclosure is not limited to the networks listed above, and may include at least a portion of a well-known wireless data network, a well-known telephone network, or a well-known wired / wireless television network.

[0047] The server (100) can create and provide an application / website that provides a service for trading waste materials. Terminal devices (200) used by users and terminal devices (300-1, 300-2, ... 300-N) used by multiple suppliers can register with the application / website that provides a service for trading waste materials created / managed by the server (100).

[0048] The server (100) can obtain information about unused materials purchased by the user on the application / website (i.e., unused material order history). Based on the user's unused material order history, the server (100) can obtain the user's unused material ordering pattern.

[0049] Furthermore, the server (100) can obtain the expected order quantity and expected order timing of the customer based on the customer's ordering pattern of unused materials and the monitoring results of fluctuations in the cost of unused materials. The server (100) can then inquire of the customer's intention to order an amount of unused materials equivalent to the expected order quantity at the expected order timing through the relevant application / website.

[0050] The method by which the server (100) performs the various operations described above will be described in detail with reference to FIGS. 2 to 5.

[0051] Terminal devices (300-1, 300-2, ... 300-N) used by multiple suppliers can update their own unused material inventory database on the server (100). Updating their own unused material inventory database on the server (100) by terminal devices (300-1, 300-2, ... 300-N) used by multiple suppliers may mean that terminal devices (300-1, 300-2, ... 300-N) used by multiple suppliers upload update information of the unused material inventory database on the corresponding application / website. Through this, the server (100) can check the unused material inventory status of each supplier.

[0052] FIG. 2 is a block diagram illustrating the configuration of a server providing a waste material transaction service according to one embodiment of the present disclosure.

[0053] As illustrated in FIG. 2, the server (100) may include a memory (110), a communication module (120), a display (130), and a processor (140).

[0054] However, the configuration illustrated in FIG. 2 is an example for implementing embodiments of the present disclosure, and appropriate hardware and software configurations that are obvious to a person skilled in the art may be additionally included in the server (100).

[0055] The memory (110) can store one or more instructions for the processor (140) to perform various operations. The memory (110) can store data supporting various functions of the server (100), programs for the operation of the processor (140), and input / output data.

[0056] The memory (110) can store data related to a user and multiple suppliers. For example, the memory (110) can store information related to the user (e.g., the user's order history for unused materials, the user's personal information, the user's expected order quantity / expected order timing, etc.) and information related to the supplier (e.g., the supplier's unused materials inventory database, etc.). Furthermore, the memory (110) can store information on cost fluctuation trends for unused materials.

[0057] The memory (110) 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.

[0058] The communication module (120) may include one or more components including circuitry that enables communication with external devices (e.g., terminal devices used by demanders / suppliers). For example, the communication module (120) may include at least one of a broadcast reception module, a wired communication module, a wireless communication module, a short-range communication module, and a location information module.

[0059] The display (130) displays (outputs) information processed by the server (100). For example, the display (130) may display execution screen information of an application program (e.g., a program providing a waste material transaction service) running on the server (100), or UI (User Interface) or GUI (Graphical User Interface) information according to such execution screen information.

[0060] The processor (140) may provide a method for providing a waste material transaction service based on an artificial intelligence algorithm by executing one or more instructions stored in the memory (110). That is, the processor (140) may control the overall operation and function using each component of the server (100).

[0061] Specifically, the processor (140) may be implemented as a memory that stores data regarding an algorithm for controlling the operation of components within the server (100) or a program that reproduces the algorithm, and at least one processor that performs the aforementioned operations using the data stored in the memory. In this case, the memory and the processor may each be implemented as separate chips. Alternatively, the memory and the processor may be implemented as a single chip.

[0062] In addition, the processor (140) can control any one or a combination of the components discussed above to implement various embodiments according to the present disclosure described in FIGS. 3 and 5 below on the server (100).

[0063] FIG. 3 is a flowchart illustrating a method for providing a waste material transaction service according to one embodiment of the present disclosure.

[0064] The server can obtain the order pattern of the first demander's unused materials based on the order history information of the first demander's unused materials (S310).

[0065] Specifically, the server can collect information on the order history of unused materials on an application / website that provides unused material transaction services to the first demander.

[0066] For example, the order history information of the first demander's unused materials may include the first demander's unused materials purchase cycle, the unused materials purchase quantity per unit order of the first demander, and information about at least one first supplier from which the first demander purchased unused materials.

[0067] The server can classify and analyze the order history information of the first demander's unused material, the unused material purchase cycle of the first demander, the unused material purchase quantity per unit order of the first demander, and information about at least one first supplier from which the first demander purchased unused material, thereby obtaining the order pattern of the first demander.

[0068] The server can obtain the expected order quantity and expected order timing of the first demander based on the first demander's order pattern of unused materials and the result of monitoring the cost fluctuation of unused materials (S320).

[0069] Specifically, the server can monitor the cost of unused materials in real time. For example, the server can monitor raw material prices related to unused materials and the cost of unused materials within another platform that provides unused materials trading services.

[0070] For example, the server may apply a first predefined weight to the raw material price associated with the obsolete material and a second predefined weight to the cost of the obsolete material within another platform that provides obsolete material trading services. The server may identify the average of the first predefined weight applied to the raw material price associated with the obsolete material and the second predefined weight applied to the cost of the obsolete material within another platform that provides obsolete material trading services as the result of monitoring the cost fluctuations of the obsolete material.

[0071] The server can input the first demander's order pattern of unused materials and the monitoring results of the cost fluctuation of unused materials into the first artificial intelligence (AI) model to obtain the first demander's expected order quantity and expected order timing.

[0072] For example, the first AI model can be trained to output a correlation between the purchase quantity of unused materials per unit order of the first demander and the monitoring result of the cost fluctuation of the unused materials, and output the cost fluctuation sensitivity of the unused materials of the first demander based on the correlation.

[0073] Here, the correlation between the purchase quantity of unused materials by unit order of the first demander and the monitoring result of the change in the cost of unused materials means a relationship indicating whether the purchase quantity of unused materials by the first demander changes when the cost of unused materials changes.

[0074] For example, the server can set a standard scenario where the cost of unused materials increases by a first value and the quantity purchased of unused materials decreases by a second value. If the cost of unused materials increases by the first value and the quantity purchased of unused materials decreases by a third value greater than the second value, the first AI model can be trained to output information indicating a strong correlation between the quantity purchased and the results of monitoring the cost fluctuations of unused materials.

[0075] In addition, the first AI model can be trained to output information indicating that the higher the correlation between the quantity of material purchased and the monitoring result of the change in the cost of unused materials, the higher the sensitivity of the first demander to the change in the cost of unused materials.

[0076] Additionally, the first AI model can be trained to output the expected order timing of the first demander based on the monitoring results of the purchase cycle of the first demander's unused materials and the cost fluctuation of the unused materials.

[0077] Here, the size of each of the first weight applied to the purchase cycle of the first demander's unused materials and the second weight applied to the result of monitoring the cost fluctuation of the unused materials can be determined based on the sensitivity of the cost fluctuation of the first demander's unused materials.

[0078] For example, the greater the sensitivity to cost fluctuations of unused materials for the first demander, the greater the impact of monitoring the cost fluctuations of unused materials on the first demander's anticipated order timing. Accordingly, the greater the sensitivity to cost fluctuations of unused materials for the first demander, the more likely the first AI model can be trained to determine the second weight value as a value (i.e., determine that the second weight value is greater than the first weight value).

[0079] For example, the lower the sensitivity of the primary demander to changes in the cost of unused materials, the more likely the primary demander is to conduct purchasing activities in accordance with their own unused materials purchase cycle, regardless of cost fluctuation trends. The lower the sensitivity of the primary demander to changes in the cost of unused materials, the more likely the primary AI model can be trained to determine the first weight value to be greater than the second weight value (i.e., determine the first weight value to be greater than the second weight value).

[0080] The server can transmit a first message to the first terminal device used by the first user, asking for the intention to order the amount of unused materials equivalent to the expected order quantity at the expected order time (S330).

[0081] The server can transmit a first message to the first demander via the application / website, requesting the first demander's intent to order the expected order quantity of unused materials at the expected order time. Accordingly, the terminal device used by the first demander can display the first message.

[0082] For example, as illustrated in FIG. 4, a first message (210) displayed on a first terminal device (200) used by a first user may include a UI (220) indicating the expected order quantity and price of the first user, an icon (230-1) for accepting / agreeing to an order of unused materials equivalent to the expected order quantity calculated at the expected order time, and an order UI (240) for adjusting the order time and order quantity of unused materials.

[0083] For example, when an icon (230-2) for changing an order quantity is selected, the second terminal device can display an order UI (240) on the first message (210).

[0084] Based on the order timing and order quantity of the unusable material being input by the first terminal device through the order UI (240), the first terminal device (200) can transmit a second message including the input order timing and order quantity of the unusable material to the server.

[0085] Based on the second message related to the order of unused materials being received from the first terminal device in response to the first message, the server can transmit to the first terminal device a list of suppliers capable of supplying the expected order quantity of unused materials based on the unused materials order history information of the first demander and the unused materials inventory database of multiple suppliers (S330).

[0086] That is, if the first demander's intent to order unused materials is confirmed, the server can provide the first terminal device with a list of suppliers from whom the first demander can purchase unused materials. The related operations are described in detail with reference to FIG. 5.

[0087] Additionally or alternatively, based on a purchase by a first demander from a specific supplier among the first at least one supplier and the second at least one supplier at a specific time, the server may calculate the accuracy of the first AI model based on i) a first difference between the order quantity of the first demander at the specific time and the expected order quantity, and ii) a second difference between the specific time and the expected order quantity.

[0088] That is, the smaller the first and second differences, the higher the accuracy of the first AI model can be set by the server.

[0089] Based on the accuracy of the first AI model being below a threshold, the server can retrain the first AI model based on the first and second differences. That is, if the accuracy of the first AI model is determined to be below a certain level, the server can retrain the first AI model.

[0090] Additionally or alternatively, the server may generate a first block based on a hash value corresponding to the first demander's unusable material order history information. Here, a block refers to a bundle of valid information, and may include a block hash value that serves as the block identifier, a previous block hash value, a Merkle root, and transaction information.

[0091] The server can generate a second block based on a hash value corresponding to the first demander's unused material order information at a specific time.

[0092] The server can build a database of unused material orders for the first customer in blockchain form by linking a second block to the first block. This allows the server to efficiently build a record of unused material orders for the first customer.

[0093] FIG. 5 is a flowchart illustrating a method for outputting a supplier list based on a database of unused material inventory by a server according to one embodiment of the present disclosure.

[0094] The server can identify at least one second supplier that holds inventory of unused materials at the time of the first demander's order for unused materials through a database of unused materials inventory by multiple suppliers (S510).

[0095] The server can generate a supplier list based on at least one first supplier from which the first demander purchased the unused material and at least one second supplier that holds unused material inventory at the time the first demander ordered the unused material.

[0096] As described above, multiple suppliers can update their obsolete inventory databases on a server-generated application / website.

[0097] The server can calculate the priorities of each of the first at least one supplier and the second at least one supplier (S520).

[0098] Specifically, the server can input the evaluation scores, the history of sales of unused materials, the delivery schedule, and the expected cost of each of the first at least one supplier and the second at least one supplier into the second AI model to calculate the priorities of each of the first at least one supplier and the second at least one supplier.

[0099] A supplier's evaluation score may be calculated based on a numerical value corresponding to the evaluation score and / or review text data assigned to the supplier on the application and / or website.

[0100] For example, a server can input a supplier's review text data into a third-party AI model to obtain a numerical value corresponding to the review text data. The numerical value corresponds to the supplier's evaluation value contained in the review text data. If the review text contains positive content about the supplier, the third-party AI model can be trained to produce a high numerical value.

[0101] For example, the third AI model may include a natural language understanding (NLU) module. The NLU module of the third AI model may be trained to output intents corresponding to review text data. If the intent corresponding to the review text data is a positive evaluation of the supplier, the third AI model may be trained to output a high value.

[0102] For example, if a particular supplier has a history of selling unused materials, the third AI model may assign a high value to the value used to prioritize that particular supplier.

[0103] For example, the shorter the material delivery schedule for a particular supplier, the lower the expected cost, and the higher the value a third AI model can assign to prioritizing a particular supplier.

[0104] The server can determine the exposure order of at least one first supplier and at least one second supplier within the supplier list based on priority (S530).

[0105] The server can transmit a list of suppliers capable of supplying the unused materials of the expected order quantity of the user to the first terminal device based on priority (S540).

[0106] That is, the server can place the highest priority provider at the top of the provider list.

[0107] Meanwhile, the embodiments of the present invention described above can be written as a program that can be executed on a computer, and the written program can be stored in a medium.

[0108] A medium may permanently store a computer-executable program, or may temporarily store it for execution or download. Furthermore, a medium may be a variety of recording or storage devices, including a single or multiple hardware devices. It is not limited to media directly connected to a computer system, but may also be distributed across a network.

[0109] Examples of media may include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and ROM, RAM, flash memory, and the like, configured to store program instructions. Furthermore, examples of other media may include recording or storage media managed by app stores that distribute applications, sites that supply or distribute various software, servers, etc.

[0110] The embodiments described in this disclosure and the accompanying drawings merely exemplify some of the technical concepts encompassed by this disclosure. Therefore, the embodiments disclosed in this specification are intended to illustrate, rather than limit, the technical concepts of this disclosure. Therefore, it is clear that the scope of the technical concepts of the present invention is not limited by these embodiments.

[0111] All modifications and specific embodiments that can be easily inferred by a person skilled in the art within the scope of the technical idea included in the specification and drawings of the present disclosure should be interpreted as being included within the scope of the rights of the present disclosure.

Claims

1. A method for providing a waste material transaction service based on an artificial intelligence algorithm performed by a server, A step of obtaining an order pattern of unused materials of a first demander based on the order history information of unused materials of the first demander; A step of obtaining the expected order quantity and expected order time of the first demander based on the monitoring result of the order pattern of the unused materials and the cost fluctuation of the unused materials of the first demander; A step of transmitting a first message to the first terminal device used by the first demander, inquiring about the intention to order the amount of unused materials equivalent to the expected order quantity at the expected order time; and A method comprising the step of transmitting, to the first terminal device, a list of suppliers capable of supplying the expected order quantity of unused materials based on unused material order history information of the first demander and an unused material inventory database of multiple suppliers, based on a second message related to an order for unused materials received from the first terminal device in response to the first message.

2. In paragraph 1, The information on the order history of the first demander's unused materials includes the unused materials purchase cycle of the first demander, the unused materials purchase quantity per unit order of the first demander, and information on at least one first supplier from which the first demander purchased the unused materials. A method in which the first demander's order pattern for unused materials and the monitoring results of the cost fluctuation of unused materials are input into a first artificial intelligence (AI) model to obtain the first demander's expected order quantity and expected order timing.

3. In paragraph 1, The above first AI model: Output the correlation between the purchase quantity of unused materials by unit order of the above first demander and the monitoring result of the change in cost of the unused materials, A method that learns to output the cost fluctuation sensitivity of the unused material of the first demander based on the above correlation.

4. In paragraph 3, The above first AI model is, It is learned to output the expected order time of the first demander based on the purchase cycle of the unused materials of the first demander and the monitoring result of the cost change of the unused materials, A method wherein the sizes of the first weight applied to the purchase cycle of the first demander's unused materials and the second weight applied to the result of monitoring the cost fluctuation of the unused materials are determined based on the cost fluctuation sensitivity of the unused materials of the first demander.

5. In paragraph 1, The first message displayed on the first terminal device includes an icon for accepting an order of unused materials in the amount of the expected order at the expected order time and an order UI for adjusting the order time and amount of the unused materials. A method in which the second message including the order time and order quantity of the unused material entered by the first terminal device through the order UI is transmitted to the server.

6. In paragraph 2, At least one second supplier holding an unused material inventory is identified through the above multiple supplier-specific unused material inventory database at the time of the first demander's unused material order, A method wherein the above supplier list includes at least one first supplier and at least one second supplier from which the first demander purchased the unused material.

7. In paragraph 6, The evaluation scores, sales history of unused materials, delivery schedules and expected costs of each of the first at least one supplier and the second at least one supplier are input into the second AI model, and the priorities of each of the first at least one supplier and the second at least one supplier are calculated. A method in which the exposure order of the first at least one supplier and the second at least one supplier within the supplier list is determined based on the calculated priorities.

8. In paragraph 7, A method wherein the accuracy of the first AI model is calculated based on i) a first difference between the order quantity of the first demander at the specific time and the expected order quantity, and ii) a second difference between the specific time and the expected order time, based on a purchase by the first demander from a specific supplier among the first at least one supplier and the second at least one supplier at a specific time.

9. In paragraph 8, A method further comprising the step of retraining the first AI model based on the first difference and the second difference, based on the accuracy of the first AI model being less than a threshold value.

10. In paragraph 8, A step of generating a first block based on a hash value corresponding to the information on the order history of the first demander's unused materials; A step of generating a second block based on a hash value corresponding to the unused material order information of the first demander at the specific time; and A method further comprising the step of constructing a database of unused material orders of the first demander in the form of a blockchain by connecting the second block to the first block.

Images