Information processor, information processing method, and program

Abstract

To provide an information processor capable of tracing distribution of a raw material, a recycled material, a component, and a product from a material factory to a product factory.SOLUTION: An information processor of the present disclosure includes: an acquisition unit that acquires arrival information and manufacturing information from each of a material factory that manufactures a material from a raw material, a component factory that manufactures a component from the material, and a product factory that manufactures a product from the component; a storage unit that stores the arrival information and the production information acquired by the acquisition unit; and an estimation unit that uses a graph AI to estimate, on the basis of the arrival information and the manufacturing information of each of the material factory, the component factory and the product factory over a specified period, a relationship logic between the material factory, the component factory, and the product factory.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device, an information processing method, and a program. [Background technology]

[0002] In recent years, a system called "Digital Product Passport (DPP)" has been gaining attention from the perspective of moving away from mass production, mass consumption, and mass waste, which assigns information to products such as their durability and ease of recycling. Attention is also being paid to the circular economy, which removes waste and pollution and circulates products and materials within society while maintaining the high value inherent in them.

[0003] For example, when a new product is manufactured using virgin materials, which are raw materials themselves, and recycled materials, it is conceivable to manage information on the mixing ratio and attach it to the manufactured product. Patent Document 1 discloses a system that can recover useful materials contained in products at a high recovery rate in order to improve the recycling rate. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2009-134655 Summary of the Invention [Problem to be solved by the invention]

[0005] In order to realize a circular economy, it is possible that the mixing ratio of recycled materials will become mandatory in the future. Under such circumstances, it will be desirable to issue certificates to prove the amount of recycled material contained in a product. Furthermore, when recycled materials of different qualities are regenerated by each recycler and used as raw materials, it will be necessary for each recycling plant to manage the raw material information of the product.

[0006] However, there is a problem in that it is practically difficult to strictly link the DPP of raw materials, the DPP of materials, the DPP of parts, and the DPP of the product. Furthermore, if the above-mentioned mandatory recycled material mixing ratio is legislated, it is considered necessary to provide evidence information so that the minimum mixing ratio can be proven. On the other hand, users who purchase products are likely to desire information on what raw materials, recycled materials, components, etc. are used to manufacture the product, and the extent to which such raw materials and materials are recycled. The technology described in Patent Document 1 does not anticipate such a problem, and does not disclose any method for solving this problem.

[0007] The present disclosure has been made to solve such problems, and its purpose is to provide an information processing device, an information processing method, and a program that can trace the logistics of raw materials, recycled materials, components, and products from material factories to product factories. [Means for solving the problem]

[0008] An information processing device according to one aspect of the present disclosure includes: an acquisition unit that acquires receipt information and production information from a material factory that manufactures materials from raw materials, a parts factory that manufactures parts from materials, and a product factory that manufactures products from parts; a storage unit that stores the arrival information and the production information acquired by the acquisition unit; an estimation unit that estimates a relationship logic between the material factory, the parts factory, and the product factory using graph AI based on the arrival information and production information of each of the material factory, the parts factory, and the product factory during a predetermined period; It is equipped with the following.

[0009] An information processing method according to one aspect of the present disclosure includes: A step of acquiring receipt information and production information from a material factory that manufactures materials from raw materials, a parts factory that manufactures parts from materials, and a product factory that manufactures products from parts; storing the arrival information and the production information acquired by the acquisition unit; a step of estimating a relationship logic between the material factory, the parts factory, and the product factory using graph AI based on the receipt information and the production information of each of the material factory, the parts factory, and the product factory for a predetermined period; It includes:

[0010] In one aspect of the present disclosure, the program On the computer, A process of acquiring receipt information and production information from a material factory that manufactures materials from raw materials, a parts factory that manufactures parts from materials, and a product factory that manufactures products from parts; a process of storing the arrival information and the production information acquired by the acquisition unit; A process of estimating a relationship logic between the material factory, the parts factory, and the product factory using graph AI based on the arrival information and production information of each of the material factory, the parts factory, and the product factory for a predetermined period; This is what causes the following to be executed. [Effects of the Invention]

[0011] According to the present disclosure, it is possible to provide an information processing device, an information processing method, and a program that can trace the logistics of raw materials, recycled materials, components, and products from material factories to product factories. [Brief explanation of the drawings]

[0012] [Figure 1] FIG. 1 is a block diagram illustrating an example of a system including an information processing device according to the present disclosure. [Figure 2] 2 is a block diagram showing an example of the configuration of the information processing device shown in FIG. 1. FIG. [Figure 3]FIG. 10 is a conceptual diagram showing the flow of data in an information processing device and in each factory when an aggregate graph database is included. [Figure 4] FIG. 10 is a conceptual diagram showing the flow of data in an information processing device and in each factory when an aggregate graph database is not included. [Figure 5] FIG. 1 is a conceptual diagram illustrating a hierarchical structure of a graph database. [Figure 6] FIG. 6 is a diagram for explaining a method of estimating a relation when a factory that is not managed by the system is included in the hierarchical structure of FIG. 5. [Figure 7] FIG. 10 is a diagram illustrating an example of a minimum configuration of relations between nodes in a graph database. [Figure 8] FIG. 10 is a diagram illustrating an example of a specific configuration of relations between nodes in a graph database. [Figure 9] FIG. 2 is a block diagram illustrating an example of a hardware configuration of an information processing device according to the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0013] (Embodiment) Hereinafter, embodiments of the present invention will be described with reference to the drawings. However, the invention according to the claims is not limited to the following embodiments. Furthermore, not all of the configurations described in the present embodiments are necessarily essential means for solving the problems. For clarity of explanation, the following description and drawings have been omitted and simplified as appropriate. In each drawing, the same elements are given the same reference numerals, and duplicate explanations are omitted as necessary.

[0014] <Problem of the present disclosure> As mentioned above, it is thought that there is a demand for linking not only the DPP (product manufacturing information) of a conventionally used product, but also the DPP of this product with the DPP of raw materials and ingredients (i.e., information on incoming shipments, etc.), in order to estimate what raw materials have been used in the product and what kind of products recycled materials have been reborn into.

[0015] When raw materials include virgin materials, which are the raw materials themselves, and recycled materials, it is possible to use the DPP of the virgin material and the DPP of the recycled material to trace the type of product the raw materials were used in, thereby linking the DPP of the product (product ID, e.g., product lot number) with the DPP of the material (material ID, e.g., material lot number).

[0016] It is also anticipated that manufacturers will use this linkage as a certificate to prove the origin of the raw materials used in their products. Such a certificate can also serve as evidence of the extent to which recycled materials were used in the product.

[0017] In particular, when a final product is completed by sending and receiving manufactured goods between multiple material factories, multiple parts factories, and multiple product factories (assembly factories), the above-mentioned linking can serve as evidence proving which raw materials, recycled materials, or materials were used to manufacture the product at which factory.On the other hand, if a discrepancy occurs along the way in tracing such raw materials, recycled materials, or materials from the product, it can also serve as evidence that the factory causing the discrepancy has fraudulently used unauthorized raw materials, recycled materials, or materials, thereby fraudulently manufacturing materials or parts.

[0018] Furthermore, when tracing between multiple factories, if it is not possible to obtain the arrival information or production information of a certain factory, such as a materials factory or parts factory, it is possible to estimate the arrival information and production information of that factory by obtaining the relationships between the multiple factories.

[0019] The present disclosure provides an information processing device for solving such problems. This information processing device is configured to acquire receipt information and production information at each of multiple factories (material factories and parts factories) when a product is manufactured via those factories, and to estimate the relationship logic between the factories based on the acquired information.

[0020] The information processing device of the present disclosure is particularly configured to build a graph database (graph DB) through learning using graph AI (Artificial Intelligence) as a relational logic. The graph database built in this manner makes it possible to estimate the relationships between each raw material, each recycled material, each material, each part, each product, and each factory. The information processing device and information processing method according to this embodiment will be described in detail below.

[0021] <Configuration and operation of information processing device> First, the configuration of an information processing device according to this embodiment will be described. FIG. 1 is a block diagram showing an example of a system including an information processing device according to the present disclosure. As shown in FIG. 1, the system according to the present disclosure includes an information processing device 1 and various factory servers. The information processing device 1 is connected to recycling factory servers 31-3L, raw material vendor servers 41-4M, material factory servers 51-5N, parts factory servers 61-6P, and product factory servers 71-7Q via a network 2 such as the Internet. The factory servers are connected to each other via the network 2 and, although not shown, include databases that store arrival information and production information. Each database may also store warehouse information. Note that each factory server substantially corresponds to each factory node shown in FIG. 8, as will be described later.

[0022] Here, the arrival information includes the product name, lot number, composition, DPP, etc. of the raw materials, recycled materials, or materials arriving at each factory, as well as the quantity or weight of the arrival amount and the arrival date, etc. The arrival information also includes the manufacturer, purchaser, and logistics company of the raw materials, recycled materials, or materials, etc. Note that even if some information is missing, some information can be estimated by AI estimation using the estimation unit 30, which will be described later. Therefore, it is not necessary for all of this arrival information to be registered in each factory server.

[0023] Manufacturing information is information about the items manufactured and shipped by the factory. For example, if the product is a material, the manufacturing information includes the type of raw materials, their ratios, weight, etc. If the product is a part, the manufacturing information includes the type of part, the type of material, their ratios, weight, etc. Furthermore, if the product is a (final) product, the manufacturing information includes the product name, number of products manufactured, lot number, DPP, etc.

[0024] The warehouse information is information about the amount of raw materials, recycled materials, or other materials currently present in the target factory, and includes inventory information obtained through inventory. Each item in the warehouse information is the same as each item in the incoming goods information. The warehouse information may also include equipment information about the equipment in each factory.

[0025] The contents of the arrival information and manufacturing information are not limited to the above examples, but may be anything that contributes to tracing the logistics of raw materials, recycled materials, components, and products from material factories to product factories, as performed by the information processing device 1.

[0026] Fig. 2 is a block diagram showing an example of the configuration of the information processing device 1 shown in Fig. 1. As shown in Fig. 2, the information processing device 1 includes an acquisition unit 10, a storage unit 20, an estimation unit 30, a graph database storage unit 40, and an output unit 50.

[0027] The acquisition unit 10 is configured to acquire, from a plurality of material factory servers 51-5N, a plurality of part factory servers 61-6P, and a plurality of product factory servers 71-7Q, arrival information and production information for each of material factories that manufacture materials from raw materials or recycled materials, part factories that manufacture parts from materials, and product factories that manufacture products from parts. Note that if there is only one material factory, part factory, or product factory, the acquisition unit 10 only needs to acquire arrival information and production information for that factory. Furthermore, the acquisition unit 10 may acquire warehouse information for each factory, if possible.

[0028] The storage unit 20 is configured to store the arrival information and production information of each factory acquired by the acquisition unit 10. In this way, the storage unit 20 may configure a database of the arrival information and production information of each factory. The storage unit 20 may also store warehouse information of each factory acquired by the acquisition unit 10.

[0029] The estimation unit 30 acquires the arrival information and production information of each factory stored in the storage unit 20. The estimation unit 30 is configured to estimate the relationship logic between the material factory, the parts factory, and the product factory using graph AI based on the arrival information and production information of each of the material factory, the parts factory, and the product factory for a predetermined period. Note that the estimation unit 30 may use warehouse information of each factory for such estimation.

[0030] Graph AI refers to AI that learns relationships based on a graph. A graph is composed of a set of nodes and a set of edges between those nodes. This graph is also called a graph database. In the graph database used by the estimation unit 30, in the information stored in the storage unit 20, raw materials, recycled materials, materials, parts, products, material factories, part factories, and product factories each become a node indicating a property, and a line drawn between two nodes becomes an edge indicating the relationship between them.

[0031] 1, the relationship between the databases of each server and the estimation unit 30 of the information processing device 1 will be described. Here, two representative examples will be described of the collaboration between the database 501 of one material factory server 51, the database 601 of one parts factory server 61, and the database 701 of one product factory server 71, and the estimation unit 30. Note that in each of the illustrated systems, servers of multiple factories may be linked together.

[0032] In the first example, information from databases 501, 601, and 701 is aggregated into an aggregate graph database. FIG. 3 is a conceptual diagram showing the flow of data in an information processing device and each factory when the aggregate graph database 100 is included. Database 501 registers and stores arrival information related to the purchase of raw materials, equipment information, and material production information. Database 601 registers and stores arrival information related to the purchase of materials, equipment information, and part production information. Database 701 registers and stores arrival information related to the purchase of parts, equipment information, and product production information.

[0033] 3, databases 501, 601, and 701 are connected to each other and also to aggregate graph database 100 via network 2. Each of databases 501, 601, and 701 is configured to register stored information in aggregate graph database 100 via network 2. Note that aggregate graph database 100 may be stored in a server not shown in FIG. 1, or may be stored directly in information processing device 1. In the latter case, graph database storage unit 40, which will be described later, corresponds to aggregate graph database 100.

[0034] As will be described later with reference to Figures 7 and 8, the aggregate graph database 100 is a database represented by multiple nodes, edges between two nodes, and properties of each node, and is capable of expressing relationships between nodes.

[0035] On the other hand, in the second example, the registered information of each database 501, 601, 701 is not aggregated into the aggregate graph database 100, but data is pooled in a blockchain with the databases 501, 601, 701 as each block. Figure 4 is a conceptual diagram showing the flow of data in an information processing device and each factory when an aggregate graph database is not included. The information registered in each database 501, 601, 701 is the same as the example shown in Figure 3.

[0036] In the data flows shown in FIGS. 3 and 4, the estimation unit 30 is configured to estimate raw materials, recycled materials, or products ultimately manufactured from materials as forward estimation based on the aggregate graph database 100 or the blockchain data pool. FIGS. 3 and 4 show only one database of various factories. However, in reality, there may be multiple factories linked by the aggregate graph database 100 or the blockchain data pool, and in such cases, many products are manufactured. Therefore, for such forward product estimation, it is sufficient to preset a vague answer that answers the most likely product and a precise answer that answers all of the target products.

[0037] Conversely, the estimation unit 30 is configured to estimate raw materials, recycled materials, or materials from a product as backward estimation based on the aggregate graph database 100 or the blockchain data pool. Even in this case, a product may be manufactured from multiple raw materials, recycled materials, or materials. Therefore, for such backward raw material estimation, it is sufficient to set in advance a vague answer that answers one raw material or recycled material with the highest probability, and a precise answer that answers all of the target raw materials or recycled materials.

[0038] As described above, the estimation unit 30 constructs a graph database by estimating a relationship logic using the graph AI. Specifically, the estimation unit 30 is configured to construct the graph database by having the graph AI learn the receiving information and production information of each factory stored in the storage unit 20.

[0039] The estimation unit 30 is configured to estimate the raw materials, recycled materials, or materials of a certain product manufactured at a certain product factory among the multiple product factories based on the constructed graph database. The estimation unit 30 is also configured to estimate the product manufactured from a certain raw material or recycled material received at a certain material factory among the multiple material factories based on the constructed graph database. These two directions of estimation correspond to the reverse raw material estimation and forward product estimation shown in Figures 3 and 4.

[0040] It is possible that the acquisition unit 10 is unable to acquire the receipt information and production information of any of the multiple material factories and multiple parts factories. In such cases, the estimation unit 30 can estimate the receipt information and production information of the target factory based on the graph database and the group of transactions with the factories before and after it. In this way, the estimation unit 30 can use the graph database and graph AI to perform AI estimation using information based on the relationships between nodes as input, thereby complementing missing information and making statistically reliable estimations.

[0041] Here, we will briefly explain the estimation unit 30 and the graph database. This graph database is constructed based on input of variable time-series information (stock information, production information, etc.) and fixed equipment information (facility information) and configuration information input into the database of each factory.

[0042] When a product lot number is input to the graph database as an estimation parameter (query), the estimation unit 30 first outputs the raw material, recycled material, or material mixing ratio along with its basis for proof (evidence). In addition, the estimation unit 30 probabilistically outputs the trace information of the origin product as a vague answer, and outputs all possible raw materials, recycled materials, or materials as a precise answer.

[0043] Furthermore, when estimating the raw material origin ratio of a product, the estimation unit 30 may output the composition of the raw material that is most likely to be derived from the product and the raw material vendor that is most likely to be derived from the product.

[0044] The estimation unit 30 is configured to determine whether there is an estimated contradiction in the receipt information and production information of any factory based on the graph database and the receipt information and production information of multiple material factories and multiple parts factories. If the estimation unit 30 determines that there is an inconsistency, it simply outputs a group of transactions between factories with inconsistencies (a group of transactions with inconsistent results).

[0045] The graph database storage unit 40 is configured to store the graph database constructed by the estimation unit 30. As described above, the aggregate graph database 100 may be stored in the graph database storage unit 40.

[0046] The output unit 50 is configured to output the estimation result estimated by the estimation unit 30 using the graph database stored in the graph database storage unit 40. For example, in response to an inquiry about raw materials based on a product, the output unit 50 may output one or more raw materials or recycled materials. In response to an inquiry about products based on raw materials or recycled materials, the output unit 50 may output one or more products. When such an inquiry is received from a terminal device via the network 2, the output unit 50 may transmit the estimation result to the terminal device.

[0047] Next, the hierarchical structure of a graph database will be described. FIG. 5 is a conceptual diagram for explaining the hierarchical structure of a graph database. In the example shown in FIG. 5, a materials factory receives recycled materials from a recycling factory and also receives virgin materials (e.g., imported materials) and uses them to manufacture materials. This information is then stored in databases 301, 401, and 501, respectively. A parts factory receives materials from a materials factory and uses them to manufacture parts. This information is then stored in database 601. A finished product factory receives parts from a parts factory, assembles the parts into products, and assigns IDs to them. This information is then stored in database 701. Finished products are provided to consumers or users through retailers, etc. Used products and containers such as PET bottles are transported to a recycling factory via a waste collection company. In this type of circulation system, estimations such as those shown in FIGS. 3 and 4 can be made using aggregate graph database 100 or by linking databases 301 to 701 of each factory.

[0048] 5, the aggregate graph database 100 makes it possible to search for what an item discarded by a consumer may have been processed into. Also, by ensuring consistency between factory databases based on the aggregated data, it is possible to estimate the reliability of data such as arrival information and manufacturing information.

[0049] 5, by linking the databases 301 to 701 of each factory, it is possible to estimate raw material lots and material lots from the manufactured products at each factory, as described above. Conversely, it is possible to estimate what a specific raw material lot or material lot was processed into.

[0050] Next, we will explain how to estimate relations when, for example, there is no database of parts factories in the configuration shown in Fig. 5. Fig. 6 is a diagram for explaining a method of estimating relations when the hierarchical structure of Fig. 5 includes factories that are not managed by the system.

[0051] For example, even if a parts factory that is an intermediate processing facility does not participate in the DPP, as long as the total amount of products manufactured at other factories can be proven, a strong inference can be made from the total amount estimate to include raw materials, recycled materials, or materials derived from the product. It is also possible to loosely infer the possibility of parts being manufactured at the parts factory.

[0052] Finally, a specific configuration of a graph database will be described. FIG. 7 is a diagram showing an example of the minimum configuration of relations between nodes in a graph database. The graph database shown in FIG. 7 includes, as factory nodes, a factory A node 5A, which is a materials factory, a factory B node 6B, which is a parts factory, and a factory C node 7C, which is a finished product factory. The graph database shown in FIG. 7 also includes a raw material A node 40A, a material A node 50A, a parts A node 60A, and a finished product A node 70A. The name of each node indicates the properties of the graph database. Examples of semi-fixed relation information, which is information that changes little over time, include the components, physical properties, and recycling methods of products made from raw materials, recycled materials, materials, and parts, as well as the amount of retained raw materials or materials, warehouse capacity, and manufacturing capacity of factories, etc.

[0053] Edges that represent the relationship between two nodes include manufacturing edges, purchasing edges, component edges, and transaction edges. This edge information is time-series information. Note that purchasing edges indicate purchasing information for raw materials, recycled materials, or other materials, manufacturing edges indicate manufacturing information for materials and parts, transaction edges indicate information about business partners, and component edges indicate information about components. For example, in the graph database shown in Figure 7, it can be seen that Factory A node 5A is a materials factory that purchases raw material A and manufactures material A.

[0054] Next, a specific relation configuration will be described. Fig. 8 is a diagram showing an example of a specific configuration of relations between nodes in a graph database. First, graph AI is used to learn the relationship information (received goods information and production information) stored in the databases of each factory, thereby constructing the graph database shown in Fig. 8.

[0055] The graph database shown in Fig. 8 includes, as factory nodes, three material factory nodes 5A-5C, three part factory nodes 6D-6F, and two product factory nodes 7G-7H. The graph database shown in Fig. 8 also includes, as product nodes, three recovered material (recycled material) nodes 30A-30C, four raw material nodes 40A-40D, four material nodes 50A-50D, four part nodes 60A-60D, and two product nodes 70A-70B.

[0056] By constructing such a graph database, it is possible to trace back from a product to estimate its raw materials (backward estimation) and to estimate what was produced from the raw materials (forward estimation). In backward estimation, for example, it can be seen that product A is produced from parts A and C, that part A is produced from material A, and that part C is produced from material C. It can also be seen that material A is produced from raw materials A and B, and that material C is produced from recycled material A and raw material D. From the above, it can be seen that product A is produced from raw materials A, B, D, and recycled material A.

[0057] On the other hand, in forward estimation, for example, it is known that raw material A becomes material A at material factory A, material A becomes part A at part factory D, and part A becomes product A at product factory G. As can be seen from the graph database shown in FIG. 8, these component edges do not include branches, so the possibility that raw material A became product A is a priori 100%.

[0058] It can also be seen that recovered material B becomes raw material D at material factory C, raw material D becomes material C at material factory B, and material C becomes part C at parts factory E and part D at parts factory F. It can also be seen that part C becomes product A at finished product factory G, and part D becomes product B at finished product factory H. In this case, the estimation unit 30 estimates, by AI estimation based on graph AI, based on the arrival information and production information of each factory, that there is a 40% probability that recovered material B becomes product A, and a 60% probability that recovered material B becomes product B, for example.

[0059] It is also understood that raw material C becomes material C at material factory B, and material C becomes part C at parts factory E as described above, and also becomes part D at parts factory F. It is also understood that part C becomes product A at product factory G, and part D becomes product B at product factory H. According to the probability estimation, the estimation unit 30 may estimate that there is a possibility that raw material C becomes product A and product B.

[0060] Here, since the edge information of the graph database is time-series information, the relations between the nodes shown in FIG. 8 indicate the state at a certain time.

[0061] As an example of the application of a graph database, the following effects can be obtained when the relationships between nodes and the distribution and production volumes of each product (including imported virgin materials) are quantitatively rational based on a graph database such as that shown in Figure 8 and AI inference using graph AI. That is, the information processing device 1 disclosed herein can not only provide information that reinforces evidence, but also identify possible fraud at a target factory based on inconsistencies in the timing and quantity of raw materials, recycled materials, and other materials received or shipped. Furthermore, if a product is recalled due to the presence of dangerous compounds in the raw materials, recycled materials, or materials, it can identify products that may have used those raw materials, recycled materials, or materials. Furthermore, even if the receiving and manufacturing information is incomplete or includes factories not managed by the system, a certain degree of tracing can be estimated.

[0062] As described above, the information processing device 1 according to the present embodiment is configured to include an acquisition unit 10 that acquires arrival information and production information for each of a material factory (e.g., corresponding to factory nodes 5A-5C) that produces materials from raw materials, a parts factory (e.g., corresponding to factory nodes 6D-6F) that produces parts from materials, and a finished product factory (e.g., corresponding to factory nodes 7G and 7H) that produces finished products from parts; a storage unit 20 that stores the arrival information and production information acquired by the acquisition unit 10; and an estimation unit 30 that uses graph AI to estimate relationship logic between the material factory, the parts factory, and the finished product factory based on the arrival information and production information for each of the material factory, the parts factory, and the finished product factory over a predetermined period. The estimation unit 30 then constructs a graph database by having the graph AI learn the arrival information and production information stored in the storage unit 20. This configuration of the information processing device 1 according to the present embodiment enables tracing the logistics of raw materials, recycled materials, materials, parts, and finished products from raw material vendors and recycling factories to the finished product factory. Therefore, the information processing device 1 according to the present embodiment can provide evidence that proves what raw materials, recycled materials, components, etc. a certain product is made from.

[0063] The information processing method according to the present embodiment is configured to include the steps of acquiring arrival information and production information for each of a material factory that produces materials from raw materials, a parts factory that produces parts from the materials, and a finished product factory that produces finished products from the parts, storing the arrival information and production information acquired by the acquisition unit, and estimating the relationship logic between the material factory, the parts factory, and the finished product factory using graph AI based on the arrival information and production information for each of the material factory, the parts factory, and the finished product factory for a predetermined period. By configuring the information processing method according to the present embodiment in this way, it is possible to obtain the same effects as the information processing device 1.

[0064] In the above-described embodiment, the present disclosure has been described as a hardware configuration, but the present disclosure is not limited to this. The present disclosure can also be realized by causing a processor in a computer to execute a computer program to perform the processing of the information processing device 1 described in the above-described embodiment.

[0065] Finally, the hardware configuration of the information processing device 1 will be described. FIG. 9 is a block diagram showing an example of the hardware configuration of the information processing device 1 of the present disclosure. As shown in FIG. 9, the information processing device 1 includes a network interface 1010, a processor 1020, and a memory 1030. The network interface 1010 may be used to communicate with not only the network 2 but also network nodes. The network interface 1010 may include, for example, a network interface card (NIC) conforming to the IEEE 802.3 series. IEEE stands for Institute of Electrical and Electronics Engineers.

[0066] The processor 1020 reads and executes software (computer programs) from the memory 1030 to perform various processes of the information processing device 1 described above. The processor 1020 may be, for example, a microprocessor, an MPU (Micro-Processing Unit), or a CPU (Central Processing Unit). The processor 1020 may include multiple processors.

[0067] The memory 1030 is configured by a combination of volatile memory and non-volatile memory. The memory 1030 may include storage located remotely from the processor 1020. In this case, the processor 1020 may access the memory 1030 via an I / O (Input / Output) interface (not shown).

[0068] 9, the memory 1030 is used to store a group of software modules. The processor 1020 reads and executes these software modules from the memory 1030, thereby performing various processes of the information processing device 1 described in the above embodiment.

[0069] As explained using Figure 9, each of the processors possessed by the information processing device 1 in the above-mentioned embodiment executes one or more programs including a group of instructions for causing a computer to perform the algorithm explained using the drawings.

[0070] Some or all of the processes in the information processing device 1 described above can be realized as a computer program. Such a program can be stored in various types of non-transitory computer-readable media and supplied to a computer. Non-transitory computer-readable media include various types of tangible recording media. Examples of non-transitory computer-readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-R / Ws, and semiconductor memories (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs (Random Access Memory)). The program may also be supplied to a computer by various types of temporary computer-readable media. Examples of temporary computer-readable media include electrical signals, optical signals, and electromagnetic waves. The temporary computer-readable media can supply the program to a computer via a wired communication path such as an electric wire or optical fiber, or via a wireless communication path.

[0071] Although the present invention has been described with reference to the embodiments, the present invention is not limited to the above-described embodiments and can be modified as appropriate within the scope of the invention.

[0072] A part or all of the above-described embodiments can be described as, but not limited to, the following supplementary notes. (Appendix 1) an acquisition unit that acquires receipt information and production information from a material factory that manufactures materials from raw materials, a parts factory that manufactures parts from materials, and a product factory that manufactures products from parts; a storage unit that stores the arrival information and the production information acquired by the acquisition unit; an estimation unit that estimates a relationship logic between the material factory, the parts factory, and the product factory using graph AI based on the arrival information and production information of each of the material factory, the parts factory, and the product factory during a predetermined period; An information processing device comprising: (Appendix 2) The estimation unit constructs a graph database by having the graph AI learn the arrival information and the production information stored in the storage unit. 2. The information processing device according to claim 1. (Appendix 3) In the graph database, the raw materials, the materials, the parts, the products, the material factories, the parts factories, and the product factories each serve as a node indicating a property, and a line drawn between two nodes serves as an edge indicating a relationship between them. 3. The information processing device according to claim 2. (Appendix 4) the acquisition unit acquires receipt information and production information for each of the material factories, the parts factories, and the product factories; The estimation unit constructs a graph database by having the graph AI learn the arrival information and the production information acquired by the acquisition unit. 3. The information processing device according to claim 2. (Appendix 5) the estimation unit estimates raw materials or ingredients of a certain product manufactured in a certain product factory among the plurality of product factories based on the constructed graph database; 5. The information processing device according to claim 4. (Appendix 6) the estimation unit estimates a product manufactured from a certain raw material received at a certain material factory among the plurality of material factories based on the constructed graph database; 5. The information processing device according to claim 4. (Appendix 7) When the acquisition unit is unable to acquire the arrival information and the production information of any of the plurality of material factories and the plurality of part factories, the estimation unit estimates the arrival information and the production information of any of the factories based on the graph database. 5. The information processing device according to claim 4. (Appendix 8) The plurality of material factories includes a material factory that receives recycled materials as the raw materials. 8. The information processing device according to any one of Supplementary Notes 4 to 7. (Appendix 9) the estimation unit determines whether there is any inconsistency in the arrival information and the production information of any of the factories based on the graph database and the arrival information and the production information of the plurality of material factories and the plurality of parts factories; 9. The information processing device according to claim 8. (Appendix 10) A step of acquiring receipt information and production information from a material factory that manufactures materials from raw materials, a parts factory that manufactures parts from materials, and a product factory that manufactures products from parts; storing the arrival information and the production information acquired by the acquisition unit; a step of estimating a relationship logic between the material factory, the parts factory, and the product factory using graph AI based on the receipt information and the production information of each of the material factory, the parts factory, and the product factory for a predetermined period; An information processing method, including: (Appendix 11) On the computer, A process of acquiring receipt information and production information from a material factory that manufactures materials from raw materials, a parts factory that manufactures parts from materials, and a product factory that manufactures products from parts; a process of storing the arrival information and the production information acquired by the acquisition unit; A process of estimating a relationship logic between the material factory, the parts factory, and the product factory using graph AI based on the arrival information and production information of each of the material factory, the parts factory, and the product factory for a predetermined period; A program that executes.

[0073] Some or all of the elements (e.g., configurations and functions) described in Supplementary Notes 2 to 9 that are dependent on Supplementary Note 1 may also be dependent on Supplementary Notes 10 and 11 in the same dependency relationship as Supplementary Notes 2 to 9. Some or all of the elements described in any Supplementary Note may be applied to various hardware, software, recording means for recording software, systems, and methods. [Explanation of symbols]

[0074] 1. Information processing equipment 10 Acquisition Department 20 Memory section 30 Estimation part 40 Graph database storage 50 Output section 2 Network 31~3L Recycle Factory Server 41~4M Raw material vendor server 51~5N Material factory server 61~6P Parts factory server 71~7Q Product factory server 30A~30C Recycled Material Nodes 40A~40D Raw material nodes 50A~50D Material Node 60A~60D Part Node 70A, 70B product nodes 5A-5C, 6B, 6D-6F, 7C, 7G, 7H Factory Node 100 Aggregated Graph Databases 501, 601, 701 databases 1010 Network Interface 1020 processor 1030 memory

Claims

1. an acquisition unit that acquires receipt information and production information from a material factory that manufactures materials from raw materials, a parts factory that manufactures parts from materials, and a product factory that manufactures products from parts; a storage unit that stores the arrival information and the production information acquired by the acquisition unit; an estimation unit that estimates a relationship logic between the material factory, the parts factory, and the product factory using graph AI based on the arrival information and production information of each of the material factory, the parts factory, and the product factory during a predetermined period; An information processing device comprising:

2. The estimation unit constructs a graph database by having the graph AI learn the arrival information and the production information stored in the storage unit. The information processing device according to claim 1 .

3. In the graph database, the raw materials, the materials, the parts, the products, the material factories, the parts factories, and the product factories each serve as a node indicating a property, and a line drawn between two nodes serves as an edge indicating a relationship therebetween. The information processing device according to claim 2 .

4. the acquisition unit acquires arrival information and production information for each of the material factories, the parts factories, and the product factories; The estimation unit constructs a graph database by having the graph AI learn the arrival information and the production information acquired by the acquisition unit. The information processing device according to claim 2 .

5. the estimation unit estimates raw materials or ingredients of a certain product manufactured in a certain product factory among the plurality of product factories based on the constructed graph database; The information processing device according to claim 4 .

6. When the acquisition unit is unable to acquire the arrival information and the production information of any of the plurality of material factories and the plurality of part factories, the estimation unit estimates the arrival information and the production information of any of the factories based on the graph database. The information processing device according to claim 4 .

7. The plurality of material factories includes a material factory that receives recycled materials as the raw materials. The information processing device according to claim 4 .

8. the estimation unit determines whether there is any inconsistency in the arrival information and the production information of any of the factories based on the graph database and the arrival information and the production information of the plurality of material factories and the plurality of parts factories. The information processing device according to claim 7 .

9. A step of acquiring receipt information and production information from a material factory that manufactures materials from raw materials, a parts factory that manufactures parts from materials, and a product factory that manufactures products from parts; storing the arrival information and the production information acquired by the acquisition unit; a step of estimating a relationship logic between the material factory, the parts factory, and the product factory using graph AI based on the receipt information and the production information of each of the material factory, the parts factory, and the product factory for a predetermined period; An information processing method, including:

10. On the computer, A process of acquiring receipt information and production information from a material factory that manufactures materials from raw materials, a parts factory that manufactures parts from materials, and a product factory that manufactures products from parts; a process of storing the arrival information and the production information acquired by the acquisition unit; a process of estimating a relationship logic between the material factory, the parts factory, and the product factory using graph AI based on the receipt information and the production information of each of the material factory, the parts factory, and the product factory for a predetermined period; A program that executes.

Images