Purchase management device, purchase management method, and purchase management program

Abstract

A purchase management device is configured to: receive a switching request for switching on or off a process related to the purchase of a raw material by artificial intelligence (AI); read out, from a blockchain, a physical amount that is recorded in the blockchain, said physical amount being based on changes in the stock of the raw material corresponding to the result of the process performed by the AI; and stop the process performed by the AI in cases in which the physical amount corresponding to the result of the process performed by the AI is equal to or greater than a reference physical amount.

Description

Purchase management device, purchase management method, and purchase management program

[0001] The disclosed technique relates to a purchase management device, a purchase management method, and a purchase management program.

[0002] Japanese Unexamined Patent Application Publication No. 2021-174303 describes an aspect in which information related to ordering such as inventory quantity and order date is centrally managed using a blockchain, the decrease rate of the pseudo inventory quantity is estimated based on the time-dependent transition of the pseudo inventory quantity, and the predicted order date for components is calculated based on the estimated decrease rate.

[0003] Japanese Unexamined Patent Application Publication No. 2022-146784 describes an aspect in a system that provides raw material hedging services to enterprises using distributed technology such as blockchain, in which data for raw material management at small and medium-sized enterprises (annual usage volume, current inventory quantity), raw material price market information and the like are used to automatically analyze hedging needs via AI or the like, and when an analysis result indicating the presence of hedging needs is obtained, raw material hedging proposal information is automatically transmitted as an advertisement or the like to the enterprise that is the customer.

[0004] Japanese Unexamined Patent Application Publication No. 2024-175672 describes an inventory management system capable of recording product-related information on a blockchain.

[0005] As the performance of generative AI improves, the expected role of generative AI is expanding from a copilot that supports human actions and decisions to agent AI that independently takes actions and makes decisions without human intervention. While agent AI can continue to operate nonstop 24 hours a day, 365 days a year, it may take actions and make decisions that differ from expectations due to hallucinations.

[0006] In one aspect, an objective is to provide a purchase management device, a purchase management method, and a purchase management program that can stop processing related to raw material purchasing by AI when the result of the AI processing is not appropriate.

[0007] A first aspect of this disclosure is a purchasing management device equipped with a processor, the processor receiving a switching request to switch on or off processing related to the purchase of raw materials by AI (Artificial Intelligence), reading from the blockchain a physical quantity based on the change in the inventory of the raw materials according to the result of the processing by the AI, and stopping the processing by the AI ​​when the physical quantity according to the result of the processing by the AI ​​becomes equal to or greater than a standard physical quantity.

[0008] A second aspect of this disclosure is a purchasing management method, wherein a computer receives a request to switch on or off an AI (Artificial Intelligence) process related to the purchasing of raw materials, reads from the blockchain a physical quantity based on the inventory status of the raw materials according to the result of the AI ​​process recorded in the blockchain, and stops the AI ​​process if the physical quantity according to the result of the AI ​​process becomes equal to or greater than a standard physical quantity.

[0009] A third aspect of this disclosure is a purchasing management program that receives a request to switch on or off an AI (Artificial Intelligence)-based process for purchasing raw materials, reads from the blockchain a physical quantity based on the inventory status of the raw materials according to the result of the AI-based process recorded in the blockchain, and stops the AI-based process if the physical quantity according to the result of the AI-based process becomes equal to or greater than a standard physical quantity.

[0010] One aspect of this is that if the results of the AI-driven processing are inappropriate, the AI-driven process related to raw material purchasing can be stopped.

[0011] This is an explanatory diagram showing an example configuration of the purchasing management system of this embodiment. This is a schematic block diagram of an example of a computer that functions as a server and user terminal in this embodiment. This is a block diagram showing the configuration of the server in this embodiment. This is a flowchart showing the purchasing process on the server. This is a flowchart showing the switching process on the server.

[0012] An example of an embodiment of the disclosed technology will be described below with reference to the drawings. In each drawing, identical or equivalent components and parts are given the same reference numerals. Furthermore, the dimensional ratios in the drawings are exaggerated for illustrative purposes and may differ from actual ratios.

[0013] <System Configuration> Figure 1 is an explanatory diagram showing an example configuration of the purchasing management system 2. In this embodiment, the purchasing management system 2 that processes the purchasing of raw materials will be described. The purchasing management system 2 includes a server 10 and a user terminal 20. The server 10 and the user terminal 20 are connected by communication via a network N. The server 10 is an example of a purchasing management device.

[0014] Server 10 is, for example, a server computer capable of various information processing and information transmission / reception. Note that the device corresponding to Server 10 is not limited to a server computer; for example, it may be a personal computer. In this embodiment, Server 10 functions as a purchasing management device that records data on a blockchain, reads data from the blockchain, and performs AI-driven processing related to the purchase of raw materials.

[0015] The user terminal 20 is a general-purpose computer such as a personal computer. In this embodiment, the user terminal 20 functions as a device that requests the server 10 to switch the AI-based raw material purchasing process on or off, and also transmits the results of the human-based raw material purchasing process to the server 10.

[0016] In this embodiment, the server 10 records data on the blockchain, reads data from the blockchain, and performs AI-based processing related to the purchase of raw materials. However, the local user terminal 20 may also record data on the blockchain, read data from the blockchain, and perform AI-based processing related to the purchase of raw materials. In other words, the distinction between the two is merely for convenience, and a single computer may perform the entire process.

[0017] <Server Configuration According to This Embodiment> Figure 2 is a block diagram showing the hardware configuration of the server 10 according to this embodiment.

[0018] As shown in Figure 2, the server 10 includes a CPU (Central Processing Unit) 11, ROM (Read Only Memory) 12, RAM (Random Access Memory) 13, storage 14, input unit 15, display unit 16, and communication interface (I / F) 17. Each component is connected to the others via a bus 19 so that they can communicate with each other.

[0019] The CPU 11 is a central processing unit that executes various programs and controls various parts. Specifically, the CPU 11 reads a program from the ROM 12 or storage 14 and executes the program using the RAM 13 as a working area. The CPU 11 controls each of the above components and performs various calculations according to the program stored in the ROM 12 or storage 14. In this embodiment, the ROM 12 or storage 14 stores a purchasing management program for processing related to the purchase of raw materials by AI. The purchasing management program may be a single program or a group of programs composed of multiple programs or modules.

[0020] ROM 12 stores various programs and data. RAM 13 temporarily stores programs or data as a working area. Storage 14 consists of an HDD (Hard Disk Drive) or SSD (Solid State Drive) and stores various programs, including the operating system, and various data.

[0021] The input unit 15 includes a pointing device such as a mouse and a keyboard, and is used for various types of input.

[0022] The display unit 16 is, for example, a liquid crystal display and displays various information. The display unit 16 may also function as an input unit 15 by employing a touch panel system.

[0023] The communication interface 17 is an interface for communicating with other devices, and standards such as Ethernet®, FDDI, and Wi-Fi® can be used.

[0024] Next, the functional configuration of server 10 will be described. Figure 3 is a block diagram showing an example of the functional configuration of server 10.

[0025] Functionally, as shown in Figure 3, the server 10 is configured to include an AI processing unit 21, a first recording unit 23, a second recording unit 25, a reception unit 27, a reading unit 29, a setting unit 31, and an AI control unit 33.

[0026] The AI ​​processing unit 21 performs AI-based processing related to the purchase of raw materials. Specifically, as part of the AI-based processing related to the purchase of raw materials, the AI ​​processing unit 21 places an order for raw materials if the time T that satisfies I + P(T) - S(T) = SI is less than or equal to the procurement lead time L, based on the current raw material inventory I, the total planned amount of raw materials to be used S(T) from the present to a future time T, the total planned amount of raw materials to be received P(T) from the present to a future time T, the raw material procurement lead time L, and the safety stock amount SI. For example, it places an order for raw materials in a predetermined order unit quantity. Here, time T represents the period from the present to that time.

[0027] The first recording unit 23 obtains physical quantities based on the trend of raw material inventory, corresponding to the results of the AI-driven raw material purchasing process, from an external device (not shown) that manages raw material inventory, and writes the obtained physical quantities to block 51 of the blockchain 50. Specifically, the first recording unit 23 obtains the amount of raw material waste per unit period (e.g., quarter) from the external device, corresponding to the results of the AI-driven raw material purchasing process, and writes it to block 51 of the blockchain 50. The amount of raw material waste is an example of a physical quantity based on the trend of raw material inventory.

[0028] Here, the amount of raw materials discarded based on the results of the AI-driven raw material purchasing process during the period when the AI-driven process is active is the actual measured value. Furthermore, the amount of raw materials discarded based on the results of the AI-driven process during the period when the AI ​​process is stopped is an estimated value of the amount of raw materials discarded if the AI ​​process were to be implemented. In cases where periods of active and stopped AI-driven raw material purchasing processes coexist within a single unit period, the amount of raw materials discarded based on the results of the AI ​​process can be determined based on both the actual measured value and the estimated value. For example, the weighted average of the actual measured value and the estimated value can be used as the amount of raw materials discarded based on the results of the AI ​​process.

[0029] Blockchain 50 is constructed from a blockchain network consisting of multiple computer terminals, and is a chronological link of blocks 51 containing data and an ID to identify the data. The first recording unit 23 prevents data tampering by writing the amount of waste raw materials to block 51 on blockchain 50 each time it acquires the amount of waste raw materials.

[0030] The second recording unit 25 obtains physical quantities based on the changes in raw material inventory, corresponding to the results of processing related to the purchase of raw materials by humans, from the user terminal 20, and writes the obtained physical quantities to block 51 of the blockchain 50. Specifically, the second recording unit 25 obtains the amount of raw material waste per unit period (e.g., quarter), corresponding to the results of processing related to the purchase of raw materials by humans, from the user terminal 20, and writes it to block 51 of the blockchain 50. In addition, in the processing related to the purchase of raw materials by humans, for example, humans place orders for raw materials by referring to the processing related to the purchase of raw materials by AI.

[0031] Here, the amount of raw material waste resulting from human-based raw material purchasing processes during periods when AI processing is active is an estimate of the amount of raw material waste that would occur if human-based raw material purchasing processes were performed. Conversely, the amount of raw material waste resulting from human-based raw material purchasing processes during periods when AI processing is suspended is an actual measured value. Furthermore, periods when AI-based raw material purchasing processes are active and periods when they are suspended may be mixed within a single unit period. In such cases, the amount of raw material waste resulting from human-based raw material purchasing processes can be determined based on both the actual measured value and the estimated value. For example, the weighted average of the actual measured value and the estimated value can be used as the amount of raw material waste resulting from human-based raw material purchasing processes.

[0032] The reception unit 27 receives a request from the user terminal 20 to switch the AI-based raw material purchasing process on or off.

[0033] The reading unit 29 reads from the blockchain 50 the amount of raw materials to be discarded, which is recorded in the blockchain 50 and corresponds to the results of processing by the AI.

[0034] Furthermore, the reading unit 29 reads from the blockchain 50 the amount of raw materials that have been discarded, based on the results of the processing related to the purchase of raw materials by humans, which is recorded in the blockchain 50.

[0035] The setting unit 31 sets the amount of raw material to be discarded as a standard physical quantity, according to the results of processing by humans.

[0036] The AI ​​control unit 33 stops the AI-based processing if the amount of raw materials to be discarded, based on the results of the AI-based processing related to the purchase of raw materials, exceeds a standard physical quantity.

[0037] <Configuration of the user terminal according to this embodiment> Figure 2 above is a block diagram showing the hardware configuration of the user terminal 20 according to this embodiment.

[0038] As shown in Figure 2 above, the user terminal 20, like the server 10, has a CPU 11, ROM 12, RAM 13, storage 14, input unit 15, display unit 16, and communication interface (I / F) 17. Each component is connected to the others via a bus 19 so that they can communicate with each other.

[0039] ROM 12 or storage 14 stores a program for requesting the server 10 to switch the AI-based raw material purchasing process on or off. This program may be a single program, or it may be a group of programs consisting of multiple programs or modules.

[0040] The input unit 15 receives a switching request to toggle the AI-based raw material purchasing process on or off. The input unit 15 also receives the amount of raw materials that would be wasted if the raw material purchasing process were performed manually by a human.

[0041] When CPU 11 receives a switchover request, it sends the switchover request to server 10. Also, when CPU 11 receives the amount of raw material waste in the hypothetical case where processing related to the purchase of raw materials by humans is performed, it requests server 10 to write the data.

[0042] <Operation of Server 10 According to This Embodiment> Next, the operation of Server 10 According to this Embodiment will be described.

[0043] First, the server 10 periodically performs the purchasing process shown in Figure 4 by having the CPU 11 read the purchasing management program from the ROM 12 or storage 14, load it into the RAM 13, and execute it. Here, we assume that the AI-based processing related to the purchasing of raw materials is enabled.

[0044] In the purchasing process, first, in step S100, the AI processing unit 21 performs processing related to the purchase of raw materials by AI.

[0045] In step S102, the first recording unit 23 acquires the discard amount of the raw material corresponding to the result of the processing related to the purchase of the raw material by AI from an external device (not shown) that manages the inventory of the raw material, and writes the acquired discard amount of the raw material into the block 51 of the blockchain 50.

[0046] In step S104, the second recording unit 25 acquires, from the user terminal 20, the discard amount of the raw material in a case where processing related to the purchase of the raw material by a human is tentatively performed, writes the acquired discard amount of the raw material into the block 51 of the blockchain 50, and ends the purchasing process.

[0047] Next, when the server 10 receives a switching request for switching on / off of the processing related to the purchase of raw materials by AI from the user terminal 20, the CPU 11 reads out a purchase management program from the ROM 12 or the storage 14, develops the program in the RAM 13, and executes the program. As a result, the switching process shown in FIG. 5 is performed. Note that the switching process may be implemented as a smart contract and executed on the blockchain 50.

[0048] In the switching process, first, in step S110, the reading unit 29 reads out, from the blockchain 50, the discard amount of the raw material corresponding to the result of the processing related to the purchase of the raw material by AI, which is most recently recorded in the blockchain 50.

[0049] In step S112, the reading unit 29 reads out, from the blockchain 50, the discard amount of the raw material corresponding to the result of the processing related to the purchase of the raw material by a human, which is most recently recorded in the blockchain 50. Then, the setting unit 31 sets the discard amount of the raw material corresponding to the result of the processing related to the purchase of the raw material by a human as a reference physical quantity.

[0050] In step S114, the AI ​​control unit 33 determines whether the amount of raw material waste resulting from the AI ​​processing is less than a standard physical amount. If the amount of raw material waste resulting from the AI ​​processing is less than a standard physical amount, the process proceeds to step S116. On the other hand, if the amount of raw material waste resulting from the AI ​​processing is equal to or greater than the standard physical amount, the process proceeds to step S118.

[0051] In step S116, the AI ​​control unit 33 enables the AI-based processing related to the purchase of raw materials and terminates the switching process.

[0052] In step S118, the AI ​​control unit 33 disables the AI-based processing related to raw material purchasing and terminates the switching process.

[0053] Based on the above, the purchasing management system 2 according to this embodiment receives a switching request to switch the AI-based raw material purchasing process on or off. The purchasing management system 2 reads from the blockchain a physical quantity based on the inventory changes of raw materials, corresponding to the results of the AI-based processing, which is recorded on the blockchain. If the physical quantity corresponding to the results of the AI-based processing becomes equal to or greater than a standard physical quantity, the purchasing management system 2 stops the AI-based processing. This makes it possible to stop the AI-based raw material purchasing process if the results of the AI-based processing are inappropriate.

[0054] Furthermore, in the process of purchasing raw materials by AI, if hallucination causes the AI ​​to take actions or make decisions that differ from expectations beyond an acceptable range, the process of purchasing raw materials by AI can be stopped.

[0055] <Modifications> It should be noted that the present invention is not limited to the embodiments described above, and various modifications and applications are possible without departing from the spirit of the invention.

[0056] For example, in the above embodiment, the case in which the amount of raw material waste is used as a physical quantity based on the trend of raw material inventory was explained, but it is not limited to this. As a physical quantity based on the trend of raw material inventory, the degree of raw material inventory stinginess, which indicates how close the current inventory level is to the safety stock level, may also be used. In this case, in the above embodiment, "amount of raw material waste" can be read as "degree of raw material inventory stinginess," and the various processes can be carried out in the same manner.

[0057] Furthermore, the various processes that the CPU reads and executes in each of the above embodiments may be executed by various processors other than the CPU. Examples of such processors include dedicated electrical circuits, which are processors with circuit configurations specifically designed to execute particular processes, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices) whose circuit configurations can be changed after manufacturing, and ASICs (Application Specific Integrated Circuits). In addition, the purchasing process and switching process may be executed by one of these various processors, or by a combination of two or more processors of the same or different types (for example, multiple FPGAs, and a combination of a CPU and an FPGA). More specifically, the hardware structure of these various processors is an electrical circuit that combines circuit elements such as semiconductor elements.

[0058] Furthermore, although the above embodiments describe a configuration in which the purchasing management program is pre-stored (installed) on the storage 14, the program is not limited to this. The program may be provided in a form stored on a non-transitor storage medium such as a CD-ROM (Compact Disk Read Only Memory), DVD-ROM (Digital Versatile Disk Read Only Memory), or USB (Universal Serial Bus) memory. Alternatively, the program may be provided in a form that is downloaded from an external device via a network.

[0059] The program of this application can be provided as a program product. A program product includes all forms of products for providing a program. For example, a program product includes a program provided via a network such as the Internet, and non-temporary computer-readable recording media such as CD-ROMs and DVDs on which the program is stored.

[0060] The embodiments disclosed herein should be considered in all respects to be illustrative and not restrictive. The scope of the present invention is indicated by the claims, not in the sense described above, and all modifications within the sense and scope equivalent to the claims are intended.

[0061] The following additional information is disclosed regarding the embodiments described above.

[0062] (Note 1) A purchasing management device including a processor, wherein the processor receives a switching request to switch on or off processing related to the purchase of raw materials by AI (Artificial Intelligence), reads from the blockchain a physical quantity based on the inventory change of the raw materials according to the result of the processing by the AI, and stops the processing by the AI ​​when the physical quantity according to the result of the processing by the AI ​​becomes equal to or greater than a standard physical quantity.

[0063] (Note 2) The purchasing management device according to Note 1, wherein the processor further reads from the blockchain the physical quantity corresponding to the result of processing related to the purchase of the raw materials by a person, and sets the physical quantity corresponding to the result of the processing by a person as the reference physical quantity.

[0064] (Note 3) The processor is a purchasing management device according to Note 1 or 2, which, as the processing by the AI, places an order for the raw materials when T satisfies I + P(T) - S(T) = SI, based on the current inventory amount I, the total planned amount S(T) of the raw materials to be used from the present to a future point in time T, the total planned amount P(T) of the raw materials to be received from the present to a future point in time T, the procurement lead time L for the raw materials, and the safety stock amount SI, and T is less than or equal to L.

[0065] (Note 4) The purchasing management device described in any one of Notes 1 to 3, wherein the physical quantity is the amount of waste of the raw materials or the degree of inventory shortage of the raw materials.

[0066] (Note 5) A purchasing management method in which a computer receives a request to switch on or off the process of purchasing raw materials by AI (Artificial Intelligence), reads from the blockchain a physical quantity based on the inventory change of the raw materials according to the result of the process by the AI, and stops the process by the AI ​​if the physical quantity according to the result of the process by the AI ​​becomes equal to or greater than a standard physical quantity.

[0067] (Note 6) A purchasing management program that receives a request to switch on or off the process of purchasing raw materials by AI (Artificial Intelligence), reads from the blockchain a physical quantity based on the inventory status of the raw materials according to the result of the process by the AI, and stops the process by the AI ​​if the physical quantity according to the result of the process by the AI ​​exceeds a standard physical quantity.

[0068] The disclosure of Japanese Patent Application No. 2025-066432 is incorporated herein by reference in its entirety.

[0069] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually described as being incorporated by reference.

Claims

1. A purchasing management device equipped with a processor, wherein the processor receives a switching request to switch on or off processing related to the purchase of raw materials by AI (Artificial Intelligence), reads from the blockchain a physical quantity based on the inventory change of the raw materials according to the result of the processing by the AI, and stops the processing by the AI ​​when the physical quantity according to the result of the processing by the AI ​​becomes equal to or greater than a standard physical quantity.

2. The purchasing management device according to claim 1, wherein the processor further reads from the blockchain the physical quantity corresponding to the result of processing related to the purchase of the raw materials by a human, which is recorded in the blockchain, and sets the physical quantity corresponding to the result of the processing by a human as the reference physical quantity.

3. The purchasing management device according to claim 1, wherein the processor, as the processing by the AI, places an order for the raw materials when T satisfies I + P(T) - S(T) = SI, based on the current inventory amount I, the total planned amount S(T) of the raw materials to be used from the present to a future point in time T, the total planned amount P(T) of the raw materials to be received from the present to a future point in time T, the procurement lead time L for the raw materials, and the safety stock amount SI, and T is less than or equal to L.

4. The purchasing management device according to claim 1, wherein the physical quantity is the amount of waste of the raw materials or the degree of inventory shortage of the raw materials.

5. A purchasing management method in which a computer receives a request to switch on or off the process of purchasing raw materials by AI (Artificial Intelligence), reads from the blockchain a physical quantity based on the inventory change of the raw materials according to the result of the process by the AI, and stops the process by the AI ​​if the physical quantity according to the result of the process by the AI ​​becomes equal to or greater than a standard physical quantity.

6. A purchasing management program that receives a request to switch on or off the process of purchasing raw materials by AI (Artificial Intelligence), reads from the blockchain a physical quantity based on the inventory status of the raw materials according to the result of the AI ​​process recorded in the blockchain, and stops the AI ​​process if the physical quantity according to the result of the AI ​​process exceeds a standard physical quantity.

Images