JP7779280B2 - Information processing device and information processing method - Google Patents

Description

The present invention relates to an information processing device and an information processing method.

Conventionally, a known method for managing products filled in containers as they circulate in the distribution market involves using container identification codes attached to the containers to manage inventory, sales forecasts, marketing, tracing, and more. For example, Patent Document 1 discloses a technology for managing products by reading barcodes printed on containers with a barcode reader. Furthermore, Patent Document 2 discloses a technology for managing products by reading IC tags attached to containers with a reader/writer.

Japanese Patent Application Laid-Open No. 2003-256765 JP 2018-188199 A

In Patent Documents 1 and 2, product distribution and inventory are managed using container identification codes attached to containers. For example, when adopting a production model such as high-mix, low-volume production, in which containers of the same specifications are used for multiple types of contents, the distribution status of each product filled with each content will differ depending on the type of content. Therefore, if consumer information such as what type of content a consumer wants to purchase next could be known in advance, this information could be extremely useful in realizing the above-mentioned production model.

The present invention was made in consideration of the above-mentioned problems, and aims to provide an information processing device and information processing method that enable the stable distribution of containers.

In order to achieve the above object, an information processing device according to one aspect of the present invention comprises:
an information acquisition unit that acquires purchase information indicating the type of content that a consumer of the product wishes to purchase from among the contents that can be filled into a container of the same specifications as the container, based on web access information contained in an information storage carrier attached to the container that is filled with the content to constitute the product;
The purchasing information acquisition unit includes a storage processing unit that stores the purchasing information acquired by the information acquisition unit in a storage device.

In an information processing device according to one aspect of the present invention, purchasing information indicating the type of content that a consumer of the product wishes to purchase from among the contents that can be filled into a container with the same specifications as the container is obtained based on information contained in an information storage carrier attached to the container that constitutes the product, and stored in a storage device. Therefore, by utilizing the purchasing information, it is possible to ensure a stable distribution of containers. For example, in the case of high-mix, low-volume production where containers with the same specifications are used for multiple types of content, it is possible to accurately forecast consumer demand and formulate supply plans for distributors based on the purchasing information, thereby ensuring a stable distribution of containers.

Other issues, configurations, and advantages will be clarified in the detailed description of the invention described below.

1 is an overall view showing an example of a container distribution system 1 according to an embodiment of the present invention. 1A to 1C are explanatory diagrams showing an example of each distribution stage of the container 10. FIG. 2 is a block diagram showing an example of an information processing device 2 according to the present embodiment. FIG. 2 is a functional explanatory diagram showing a container investment management function 200 and an example of information flow. FIG. 2 is a data configuration diagram showing an example of a distribution management database 210. FIG. 2 is a data configuration diagram showing an example of a container investment management database 211. FIG. 2 is a functional explanatory diagram showing a container purchasing management function 201 and an example of information flow. FIG. 2 is a data configuration diagram showing an example of a web management database 212. FIG. 2 is a data structure diagram showing an example of a container purchase management database 213. 1 is a functional explanatory diagram showing a learning function 202 and an example of information flow. FIG. FIG. 2 is a functional explanatory diagram showing a demand and supply management function 203 and an example of information flow. FIG. 9 is a hardware configuration diagram showing an example of a computer 900 that constitutes each device. 10 is a flowchart showing an example of a container purchase management method by the container purchase management function 201. 10 is a flowchart illustrating an example of a machine learning method performed by the learning function 202. 10 is a flowchart showing an example of a demand and supply management method performed by the demand and supply management function 203.

The following describes an embodiment of the present invention with reference to the drawings. The following provides a schematic illustration of the scope necessary for the explanation of achieving the objectives of the present invention, and focuses on the scope necessary for explaining the relevant parts of the present invention. Any parts that are omitted from the explanation are based on publicly known technology.

(Configuration of container distribution system 1)
Fig. 1 is an overall view showing an example of a container distribution system 1 according to this embodiment. Fig. 2 is an explanatory view showing an example of each distribution stage of a container 10.

The container distribution system 1 includes, as its main component, an information processing device 2. The information processing device 2 manages various information acquired as containers 10, which are filled with contents 11 to form products 12, are distributed through the distribution market, and performs multiple functions (described in detail below).

The information processing device 2 is composed of a general-purpose or dedicated computer (see Figure 12 below). Connected to the information processing device 2 via a wired or wireless network 8 are an investor terminal device 3 used by an investor U1, an information user terminal device 4 used by an information user U2, a management company terminal device 5 used by a management company U3 of the information processing device 2, distributor terminal devices 6A-6C used by a container manufacturer U4, a content manufacturer U5, and a container washer U6, respectively, and a consumer terminal device 7 used by a consumer U7. Note that the number of devices 2-7 and the configuration of the network 8 are not limited to the example in Figure 1.

The investor terminal device 3, information user terminal device 4, management company terminal device 5, distribution company terminal devices 6A-6C, and consumer terminal device 7 are general-purpose or dedicated computers (see Figure 12 below), and are composed of, for example, stationary or portable computers. Programs such as browsers and apps are installed on them, and they accept various input operations and output various information via display screens and audio.

Container 10 is manufactured using raw materials such as plastic, metal, glass, paper, etc., and can have any shape or size. The specifications of container 10 are determined by the type of container 10, raw materials, capacity, shape, size, etc. Examples of types of container 10 include plastic bottles made of polyethylene terephthalate (PET), metal cans made of steel, aluminum, etc., glass bottles, paper cartons, laminated pouches, etc. Container 10 may be a returnable container or a one-way container.

Here, the condition for multiple containers 10 to have the same specifications is met if the numerical value of at least one of the multiple specification items is the same or falls within a specific approximate range, or if the contents are the same or fall within a specific similar range. For example, for one specification item, the capacity of the container 10, two containers 10 may be considered to have the same specifications if both have a capacity of 200 ml, or if the capacities of the two containers 10 are within an approximate range of, for example, 200 ml and 180 ml. For one specification item, the type of container 10, two containers 10 may be considered to have the same specifications if, for example, both are glass bottles, or if the types of the two containers 10 are within an approximate range of, for example, a steel can and an aluminum can.

As shown in FIG. 2, the container 10 is attached with an information storage carrier 100 capable of storing container identification information D7 and web access information D8. The container identification information D7 is information for identifying the container 10 and specifying the specifications of the container 10. The container identification information D7 is, for example, a container ID (container identification code) for identifying the container 10 individually or by lot. Note that the container identification information D7 may be omitted and not stored in the information storage carrier 100. The web access information D8 is information required for the consumer U7 to access, for example, a web service operated by the management company U3. The web access information D8 includes, for example, a web address (URL) for accessing a web page provided by the web service and link information for launching an app provided by the web service.

The information storage carrier 100 is configured with a code image such as a one-dimensional code or two-dimensional code. In this case, a label with the printed code image may be attached to or wrapped around the container 10, or may be embedded inside the molded body of the container 10. The information storage carrier 100 may also be configured with an electronic tag (IC tag) known as an RFID. In this case, the electronic tag is embedded inside the molded body of the container 10. Note that multiple information storage carriers 100 may be attached to the container 10; for example, an information storage carrier 100 containing container identification information D7 and an information storage carrier 100 containing web access information D8 may be attached.

Contents 11 may be liquid, solid, powder, granules, etc. Examples of types of contents 11 include beverages such as water, juice, and milk, food, medicines, cosmetics, and detergents. Contents 11 may be at room temperature, chilled (refrigerated), or frozen. Furthermore, contents 11 may be heated or unheated during the manufacturing process, and in the case of beverages and foods, they may be fresh or processed.

For example, the container 10 is manufactured by a container manufacturer U4 (container manufacturing stage), and the contents 11 are manufactured by a contents manufacturer U5 (content manufacturing stage). The contents 11 are then filled into the container 10 by the contents manufacturer U5 (filling stage), resulting in the product 12. The contents manufacturer U5 is, for example, a beverage manufacturer or a food manufacturer, and orders the containers 10 from the container manufacturer U4 or the container washer U6, specifying the specifications and quantity of the containers 10. The containers 10 corresponding to the order are delivered by the container manufacturer U4 or the container washer U6, and payment is made to the container manufacturer U4 or the container washer U6. If the information storage carrier 100 is composed of a code image, for example, a label with the code image printed thereon is attached to the container 10 by the contents manufacturer U5 during the filling stage. Furthermore, when the information storage carrier 100 is composed of an electronic tag, the electronic tag is embedded in the container 10 by the container manufacturer U4 during the container manufacturing stage, and the container identification information D7 and web access information D8 are written to the electronic tag by the contents manufacturer U5 during the filling stage.

Product 12 is shipped from content manufacturer U5 (shipping stage) and transported to, for example, a retailer or warehouse (transportation stage). Product 12 is then sold to consumer U7 via, for example, a wholesaler, retailer, trading company, etc. (sales stage), and content 11 is consumed by consumer U7 (consumption stage). Consumer U7 includes not only general consumers but also businesses, etc. If container 10 is a returnable container, once content 11 is consumed by consumer U7 (consumption stage), container 10 is collected from consumer U7 (collection stage) and cleaned by container washer U6 (cleaning stage). Content 11 is then filled into cleaned container 10 by content manufacturer U5 (filling stage), thereby producing product 12.

As described above, the container 10 is distributed through multiple distribution stages in the distribution market. These include, but are not limited to, a container manufacturing stage, a contents manufacturing stage, a filling stage, a shipping stage, a transportation stage, a sales stage, a consumption stage, a collection stage, and a cleaning stage. If the container 10 is a returnable container, the multiple distribution stages include at least a cleaning stage, a filling stage, and a consumption stage, and the container 10 is reused by repeating these distribution stages. In this embodiment, the container 10 is a glass bottle manufactured as a returnable container, and the type of contents 11 is mainly a beverage such as water, juice, or milk.

(Configuration of information processing device 2)
3 is a block diagram showing an example of an information processing device 2 according to this embodiment. The information processing device 2 includes a control unit 20 configured with a processor or the like, a storage unit 21 configured with an HDD, an SSD, a memory or the like, a communication unit 22 that is a communication interface with the network 8, an input unit 23 configured with a keyboard, a mouse or the like, and a display unit 24 configured with a display or the like. Note that the input unit 23 and the display unit 24 may be omitted.

The storage unit 21 stores various databases (DBs) 210-215 and an information processing program 216, as well as the operating system, other programs, data, etc.

The control unit 20 executes the information processing program 216 stored in the memory unit 21 to implement the container investment management function 200, container purchasing management function 201, learning function 202, and demand/supply management function 203. The control unit 20 includes an information acquisition unit 201A and a storage processing unit 201B as the units that implement the container purchasing management function 201. The control unit 20 includes a learning data acquisition unit 202A and a machine learning unit 202B as the units that implement the learning function 202. The control unit 20 includes an information acquisition unit 203A, a generation processing unit 203B, and an output processing unit 203C as the units that implement the demand/supply management function 203.

The following describes the contents of each function 200-203 and each database 210-215.

(Container investment management function 200)
4 is a functional explanatory diagram showing the container investment management function 200 and an example of information flow. The control unit 20 of the information processing device 2 mainly uses a distribution management database 210 (see FIG. 5 described later) and a container investment management database 211 (see FIG. 6 described later) to manage the container investment management function 200.
Achieve this.

The information processing device 2 receives investment information D1 from the investor U1 via the investor terminal device 3 (arrow (1a) in FIG. 4), registers the investment information D1 in the container investment management database 211, and generates distribution container setting information D2 based on the investment information D1, which sets the container quantity, specifications, and type of contents 11 of the container 10 to be invested in, and invests in the container 10 (arrow (1b)). When the container 10 to be invested in is distributed in the distribution market, the information processing device 2, upon reading the information storage carrier 100 attached to the container 10 with a reading device (not shown), registers container status data indicating the status of the container 10 at each distribution stage in the distribution management database 210 in association with the container identification information D7 included in the information storage carrier 100, and stores the collected data D3 in the container investment management database 211 as a dataset of container status data for multiple containers 10 (arrow (1c)). The reading device may be, for example, a code reader, camera, or electronic tag reader, and may be a fixed or handheld type, or may be an embedded type built into a portable computer (such as a smartphone). Reading devices are used at each stage of distribution in the distribution market, and are installed in various locations such as manufacturing plants, logistics centers, transportation means, sales stores, and refrigerators in consumer U7's homes.

Furthermore, the information processing device 2 generates container distribution information D4 based on the collected data D3 (arrow (1d)), and converts the container distribution information D4 into a value medium 13 by providing it to the information user U2 via the information user terminal device 4 (arrow (1e)). The information processing device 2 then distributes the value medium 13 based on the investment information D1 to generate dividend information D6 (arrow (1f)), registers the dividend information D6 in the container investment management database 211, and distributes dividends to the investor U1 based on the dividend information D6 (arrow (1g)).

Examples of contributions to containers 10 include contributions to part or all of the purchase cost of containers 10 when content manufacturer U5 places an order for the containers 10, and contributions to part or all of the manufacturing and cleaning costs of containers 10 when container manufacturer U4 or container washer U6 manufactures or cleans the containers 10. The containers 10 to be contributed are provided to content manufacturer U5 in response to an order from content manufacturer U5, and content manufacturer U5 can receive the contributed containers 10 without having to pay the contributed costs. On the other hand, in exchange for receiving the contribution, content manufacturer U5 consents to the collection of collected data D3 using the contributed containers 10 without retaining ownership of the contributed containers 10, and is required to cooperate in the collection of collected data D3 as necessary.

Figure 5 is a data structure diagram showing an example of the distribution management database 210. The distribution management database 210 has a record for each container identification information D7 (container ID). Each record has fields for registering container status data. In the example of Figure 5, the database has fields for registering container specifications, manufacturing date and time (cleaning date and time), manufacturing location (cleaning location), filling date and time, filling location, type of filled content, shipping date and time, transportation time, transportation temperature, sales date and time, sales location, consumption date and time, consumption location, storage temperature, etc. Note that while the container status data is registered when the container identification information D7 is read by a reading device, some of the container status data may be acquired by a status detection device (such as a temperature sensor) installed in various locations similar to the reading device. Furthermore, the container status data may be acquired by the information processing device 2 linking with an external system (such as a manufacturing management system, transportation management system, or sales management system) or an external app (such as an online shopping app or refrigerator management app).

The manufacturing location, cleaning location, filling location, sales location, consumption location, etc. correspond to distribution location information regarding the location of the container 10 as it is distributed through each distribution stage. Furthermore, when the container 10 is temporarily stored at each distribution stage (for example, when it is stored during the period from the filling date and time to the shipping date and time) or when it is stored in a storage location such as a warehouse, the manufacturing location, cleaning location, filling location, sales location, storage location, etc. correspond to inventory location information regarding the location of the container 10 when it is stocked. The distribution location information and inventory location information may be recorded, for example, using coordinates such as latitude and longitude indicating each location, or may be recorded by region or area such as an administrative district or mesh division.

Figure 6 is a data structure diagram showing an example of the container investment management database 211. The container investment management database 211 has a record for each investment ID used to associate various information handled by the container investment management function 200. Each record has fields in which investment information D1, circulation container setting information D2, collected data D3, container circulation information D4, value medium information D5, dividend information D6, etc. can be registered. The container investment management database 211 can be referenced from the management business operator terminal device 5, and editing operations such as adding, deleting, and modifying each piece of data may be performed on the display screen of the management business operator terminal device 5.

The investment information D1 includes at least the investor U1 and the amount of investment by that investor U1. If there are multiple investors U1, the investment amount for each investor U1 is included. The investment information D1 may also include at least one of the specifications of the container 10 to be invested in and the type of contents 11 to be filled into the container 10 to be invested in.

The distribution container setting information D2 includes at least the number of containers 10 to be contributed and a contribution container ID that identifies each of the contribution containers 10 using container identification information D7. The distribution container setting information D2 may also include at least one of the specifications of the contribution containers 10 and the type of contents 11 to be filled into the contribution containers 10.

Collected data D3 consists of container status data for each container 10 acquired as the invested containers 10 are circulated in the secondary market. For example, in a record identified by the investment ID "I001," if the circulating container setting information D2 is set to "1000" for the container quantity and "A0001-A1000" for the invested container ID, collected data D3 will consist of container status data for 1000 containers 10, as shown in Figure 5.

Container distribution information D4 includes, for example, data analysis results generated by performing data analysis processes such as aggregation, statistical processing, and analytical processing on collected data D3. Note that container distribution information D4 may also include collected data D3 itself instead of or in addition to the data analysis results.

The value medium information D5 includes at least the unit of the value medium 13 and the quantity of that value medium 13. The value medium 13 is the consideration that the information user U2 hands over in exchange for the provision of the container distribution information D4. For example, when paying in any currency (including digital currency), the quantity of the value medium 13 corresponds to the payment amount.

Dividend information D6 includes at least the investor U1 and the dividend amount for that investor U1. If there are multiple investors U1, it includes the dividend amount for each investor U1.

(Container purchasing management function 201)
7 is a functional diagram illustrating an example of the container purchasing management function 201 and the flow of information. The information acquisition unit 201A and the storage processing unit 201B of the information processing device 2 mainly use a web management database 212 (see FIG. 8 described later) and a container purchasing management database 213 (see FIG. 9 described later) to realize the container purchasing management function 201.

The information acquisition unit 201A acquires purchase information D12 indicating the type of contents 11 (hereinafter referred to as the "type of contents desired to be purchased") that a consumer U7 of the product 12 wishes to purchase from among the contents 11 that can be filled into a container with the same specifications as the container 10 (hereinafter referred to as the "same-specification container"), based on the container identification information D7 and web access information D8 included in the information storage carrier 100 attached to the container 10 constituting the product 12. Note that the conditions for the same-specification container may be set by the management business operator U3, the container manufacturer U4, or the like, and stored in the storage unit 21. In that case, for example, editing operations for the conditions for the same-specification container may be performed on the display screen of the management business operator terminal device 5 or the distribution business operator terminal device 6A.

Specifically, the information acquisition unit 201A accesses a web service based on web access information D8 read from the information storage carrier 100 using the consumer terminal device 7, and acquires purchasing information D12 via the web service. At that time, the information acquisition unit 201A may further acquire consumer information D13 about consumer U7 from the consumer terminal device 7 when the web service is accessed.

For example, consumer U7 who purchased product 12 uses consumer terminal device 7 to read the information storage carrier 100 attached to container 10, similar to the reading device described above (arrow (2a) in Figure 7), and accesses a web service based on web access information D8 contained in information storage carrier 100 (arrow (2b)). Consumer terminal device 7 then displays a display screen provided by the web service in a browser or app (arrow (2c)), and accepts input of purchase request data D9 from consumer U7 on the display screen, including the type of contents and quantity desired to be purchased (arrow (2d)). Information acquisition unit 201A then associates the purchase request data D9 with container identification information D7 contained in information storage carrier 100 and registers it in web management database 212 (arrow (2e)). Purchase information D12 is then acquired as a dataset of purchase request data D9 for multiple containers 10 (consumer U7). The web service may accept the purchase request data D9 as an actual order for the product 12, or as a reservation for the product 12 or the result of a questionnaire.

Furthermore, if persona data D10 such as consumer U7's gender, age, preferences, and location is stored in the memory of the consumer terminal device 7, the information acquisition unit 201A references that memory, accepts input of persona data D10 from consumer U7 on the display screen of the consumer terminal device 7, and receives location information detected by the location detection function of the consumer terminal device 7 (arrows (2f) and (2g)). As a result, the information acquisition unit 201A associates the persona data D10 with container identification information D7 contained in the information storage carrier 100 and registers it in the web management database 212 (arrow (2e)). Then, consumer information D13 is acquired as a dataset of persona data D10 for multiple containers 10 (consumer U7).

The information acquisition unit 201A may further acquire container management information D14 (arrow (2h)) that includes at least one of distribution information when containers with the same specifications are distributed through multiple distribution stages and inventory information when they are stocked at multiple distribution stages. The container management information D14 may be acquired, for example, from the distributor terminal devices 6A-6C, or by referencing information registered in each field of the distribution management database 210 (e.g., distribution location information, inventory location information, etc.), or by the information processing device 2 linking with an external system (e.g., a manufacturing management system, a transportation management system, a sales management system, etc.).

The storage processing unit 201B stores the purchasing information D12 acquired by the information acquisition unit 201A in the container purchasing management database 213 (arrow (2i)). If the information acquisition unit 201A acquires consumer information D13 and container management information D14 in addition to the purchasing information D12, the storage processing unit 201B stores the consumer information D13 and container management information D14 in the container purchasing management database 213 (arrow (2i)). The storage processing unit 201B may also store the purchasing information D12, etc. acquired by the information acquisition unit 201A in the container investment management database 211. In this case, the purchasing information D12, etc. may be provided to the information user U2 as part of the container distribution information D4 in exchange for the value medium 13.

Figure 8 is a data structure diagram showing an example of the web management database 212. The web management database 212 has a record for each container identification information D7 (container ID). Each record has fields for registering purchase request data D9 and persona data D10 obtained via the web service. In the example of Figure 8, there are fields for registering the acquisition date and time, type of content desired to be purchased, desired purchase quantity, gender, age, preferences, location, etc. of consumer U7.

The location included in persona data D10 corresponds to consumer location information regarding the location of consumer U7. Consumer location information is recorded, for example, as coordinates such as latitude and longitude that indicate consumer U7's location at a specific time (for example, at the time of accessing a web service). Note that consumer location information may also indicate a location such as an address or range of activity, in which case it may be recorded in terms of a region or area such as an administrative district or mesh division.

The web management database 212 can also be associated with the distribution management database 210 via the container identification information D7. In this case, by referencing the distribution management database 210 via the container identification information D7, information registered in each field of the distribution management database 210 (e.g., distribution location information, inventory location information, etc.) can be obtained for each container 10.

Figure 9 is a data structure diagram showing an example of the container purchasing management database 213. The container purchasing management database 213 has a record for each management ID used to associate various information handled by the container purchasing management function 201. Each record has fields in which management information D11, purchasing information D12, consumer information D13, container management information D14, etc. can be registered. The container purchasing management database 213 can be referenced from the management company terminal device 5 and the distribution company terminal devices 6A-6C, and editing operations such as adding, deleting, and modifying each piece of data can be performed on the display screen of the management company terminal device 5 and the distribution company terminal devices 6A-6C.

Management information D11 includes at least the specifications of the managed containers 10 and managed container IDs that identify each managed container 10 using container identification information D7. Multiple containers 10 identified by managed container IDs are containers with the same specifications.

Purchase information D12 is composed of purchase request data D9 for each container 10 obtained via a web service from a consumer U7 of a product 12, which is a container 10 to be managed and filled with contents 11. For example, in a record identified by container management ID "J001," if management information D11 specifies the container 10 specifications as "200 ml glass bottle" and the managed container IDs are "B0001-B1000," purchase information D12 is composed of purchase request data D9 for 1,000 containers 10 (200 ml glass bottles) with the same specifications, as shown in FIG. 9. Note that purchase information D12 may include the purchase request data D9 for each container 10 itself, or alternatively or additionally, may include data analysis results generated by performing data analysis processes such as aggregation, statistical processing, and analysis on the purchase request data D9 for each container 10.

The consumer information D13 is composed of persona data D10 (gender, age, preferences, location, etc.) for each container 10 acquired via a web service from a consumer U7 of a product 12 in which the contents 11 are filled in the container 10 to be managed. In the example of FIG. 9 , the consumer information D13 is composed of persona data D10 for 1,000 containers 10 (200 ml glass bottles) of the same specifications. The consumer information D13 may include the persona data D10 itself for each container 10, or may instead or in addition include data analysis results generated by performing data analysis processes such as aggregation, statistical processing, and analysis on the persona data D10 for each container 10.

Container management information D14 includes at least one of distribution information when containers with the same specifications as the managed container 10 are distributed through multiple distribution stages, and inventory information when the container is stocked at multiple distribution stages. Distribution information includes, for example, the number of items in circulation, the distribution rate, the distribution time, and the distribution cost at each distribution stage. Inventory information includes, for example, the number of items in circulation, the inventory rate, the inventory time, and the inventory cost at each distribution stage.

The distribution information may also include distribution location information. Distribution location information includes, for example, information on each location (manufacturing location, cleaning location, filling location, sales location, consumption location, etc.) where the container 10 is distributed through each distribution stage. In this case, the distribution information may include the number of items distributed at each location, distribution rate, distribution time, distribution cost, etc.

The inventory information may also include inventory location information. For example, inventory location information may include information on each location (manufacturing location, cleaning location, filling location, sales location, storage location, etc.) where the container 10 is stored at each distribution stage. In this case, the inventory information may include the number of items in stock, the inventory rate, the inventory time, the inventory cost, etc. at each location.

(Learning function 202)
10 is a functional explanatory diagram showing an example of the learning function 202 and the flow of information. The learning data acquisition unit 202A and the machine learning unit 202B of the information processing device 2 mainly use a container purchase management database 213, a learning data management database 214 (learning data storage unit), and a trained model management database 215 (trained model storage unit) to realize the learning function 202.

The learning data acquisition unit 202A acquires learning data D17 consisting of market information D15 for the container 10 being learned and supply and demand information D16 for that container 10. The learning data D17 is data used as teacher data (training data), verification data, and test data in supervised learning. In addition, the supply and demand information D16 is data used as the correct answer label in supervised learning.

The market information D15 that constitutes the input data for the learning data D17 includes purchasing information D12 that indicates the type of contents 11 that a consumer U7 of the product 12 made up of the container 10 wishes to purchase from among the contents 11 that can be filled into a container with the same specifications as the container 10, as information obtained based on the container identification information D7 and web access information D8 contained in the information storage carrier 100 attached to the container 10 being learned.

The purchasing information D12 is preferably the result of data analysis based on the purchase request data D9 from multiple containers 10 (consumer U7), taking into account the input to the learning model D18. For example, as shown in FIG. 10, the purchasing information D12 indicates the percentage of each type of content desired to be purchased, and is expressed as the percentage of those wishing to purchase "water," "juice," and "milk." The purchasing information D12 may also be for a single type of content 11, and may be expressed, for example, as the percentage of those wishing to purchase "water."

The market information D15 may further include consumer information D13 about a consumer U7 of the product 12 configured with the container 10 of the learning target. The market information D15 may also include container management information D14 including at least one of distribution information when a container having the same specifications as the container 10 of the learning target is distributed through multiple distribution stages and inventory information when the container is stocked at multiple distribution stages.
It may further include:

Demand and supply information D16, which constitutes the output data of learning data D17, is information regarding the demand or supply of product 12, which is a container with the same specifications as the container 10 being learned and filled with contents 11. Demand and supply information D16 includes, for example, at least one of demand forecast information regarding the demand forecast for product 12 as information regarding the demand for product 12, and supply plan information regarding the supply plan for product 12 as information regarding the supply of product 12.

The demand forecast information takes into account the output from the learning model D18 and is expressed, for example, as a numerical value indicating the degree of demand for each type of content 11 (a numerical value normalized in the range of 0 to 1 as shown in FIG. 10) or a score for each demand classification (such as "low," "normal," or "high") for each type of content 11. Note that the demand forecast information may also be for a single type of content 11, and may be expressed as a numerical value or score indicating the degree of demand for "water," for example.

The supply plan information takes into account the output from the learning model D18 and is expressed, for example, as a numerical value indicating the supply level for each type of content 11 (a numerical value normalized in the range of 0 to 1 as shown in FIG. 10) or a score for each demand classification (such as "low," "normal," or "high") for each type of content 11. Note that the supply plan information may be for a single type of content 11, and may be expressed as a numerical value or classification value indicating the supply level for "water," for example.

For example, the learning data acquisition unit 202A acquires market information D15, which constitutes the learning data D17, by referencing the purchasing information D12, consumer information D13, and container management information D14 registered in the container purchasing management database 213, and by accepting input operations from the management company terminal device 5 and the distribution company terminal devices 6A-6C. The learning data acquisition unit 202A also acquires demand and supply information D16, which constitutes the learning data D17, by referencing demand and supply information D16 registered as actual values, planned values, simulation values, etc. in external systems (production management systems, transportation management systems, sales management systems, etc.), and by accepting input operations from the management company terminal device 5 and the distribution company terminal devices 6A-6C.

The learning data management database 214 stores multiple sets of learning data D17 acquired by the learning data acquisition unit 202A.

The machine learning unit 202B performs machine learning using multiple sets of training data D17 stored in the training data management database 214. That is, the machine learning unit 202B inputs multiple sets of training data D17 into the training model D18 and generates a trained training model D18 by having the training model D18 learn the correlation between the market information D15 and the supply and demand information D16 contained in the training data D17. When performing machine learning, the machine learning unit 202B can employ any method, such as online learning, batch learning, or mini-batch learning. Note that the machine learning unit 202B may perform predetermined pre-processing on the input data (market information D15) input to the training model D18, or may perform predetermined post-processing on the output data (supply and demand information D16) output from the training model D18.

Learning model D18, for example, employs a neural network structure and includes an input layer 110, an intermediate layer 111, and an output layer 112. Synapses (not shown) that connect each neuron are established between each layer, and each synapse is assigned a weight. A group of weight parameters consisting of the weights of each synapse is adjusted by machine learning.

The input layer 110 has neurons corresponding in number to the market information D15 as input data, and each value of the market information D15 is input to each neuron. The output layer 112 has neurons corresponding in number to the demand and supply information D16 as output data, and prediction results (inference results) of the demand and supply information D16 for the market information D15 are output as output data. When the learning model D18 is configured as a regression model, the demand and supply information D16 is output, for example, as shown in FIG. 11 , as a numerical value (normalized in the range of 0 to 1) indicating the demand level for each type of content 11 and a numerical value (normalized in the range of 0 to 1) indicating the supply level for each type of content 11. When the learning model D18 is configured as a classification model, the demand and supply information D16 is output, for example, as a score for each demand classification for each type of content 11 and a score for each supply classification for each type of content 11.

The trained model management database 215 stores the trained learning model D18 (specifically, the adjusted weight parameter group) generated by the machine learning unit 202B. The trained learning model D18 stored in the trained model management database 215 may be provided to other systems via the network 8, a recording medium, etc. The trained learning model D18 may also be stored in the container investment management database 211, in which case the trained learning model D18 may be provided to the information user U2 as part of the container distribution information D4 in exchange for the value medium 13.

In this embodiment, the data configuration of the learning data D17 and learning model D18 is described as being configured as shown in FIG. 10, but multiple data configurations with different conditions, such as machine learning techniques, specifications of the container 10, types of data included in market information D15, and types of data included in supply and demand information D16, may also be adopted. In this case, the learning data acquisition unit 202A acquires multiple types of learning data D17 corresponding to the multiple data configurations with different conditions, and the machine learning unit 202B performs machine learning using each of these learning data D17, and stores the trained learning model D18 in the trained model management database 215.

(Demand supply management function 203)
11 is a functional diagram illustrating an example of the flow of information and the demand and supply management function 203. The information acquisition unit 203A, the generation processing unit 203B, and the output processing unit 203C of the information processing device 2 mainly use the container purchase management database 213 and the trained model management database 215 to realize the demand and supply management function 203.

The information acquisition unit 203A acquires market information D15 for the container 10 to be predicted. For example, the information acquisition unit 203A references the container purchasing management database 213 and acquires the purchasing information D12 registered in the container purchasing management database 213 as the market information D15 for the container 10 to be predicted. Note that the market information D15 for the container 10 to be predicted may further include at least one of consumer information D13 and container management information D14 in addition to the purchasing information D12, as shown in FIG. 11.

The generation processing unit 203B generates supply and demand information D16 for the market information D15 of the container 10 to be predicted, based on the supply and demand information D16 output by inputting the market information D15 of the container 10 to be predicted acquired by the information acquisition unit 203A as input data into the learning model D18. The generation processing unit 203B may perform predetermined pre-processing on the input data (market information D15) to be input into the learning model D18, or may perform predetermined post-processing on the output data (supply and demand information D16) output from the learning model D18.

The learning model D18 used by the generation processing unit 203B is a trained learning model D18 stored in the trained model management database 215. When multiple learning models D18 with different conditions are stored in the trained model management database 215, the generation processing unit 203B may use the multiple learning models D18 selectively or in parallel according to the type of data included in the market information D15 and the demand and supply information D16, for example.

The output processing unit 203C performs output processing to output the demand and supply information D16 generated by the generation processing unit 203B. For example, the output processing unit 203C may transmit the demand and supply information D16 to the management company terminal device 5 or the distribution company terminal devices 6A-6C. The output processing unit 203C may also store the demand and supply information D16 in the container purchasing management database 213 or the container investment management database 211. In this case, the demand and supply information D16 stored in the container investment management database 211 may be provided to the information user U2 as part of the container distribution information D4 in exchange for the value medium 13.

Figure 12 is a hardware configuration diagram showing an example of a computer 900 that constitutes each device.

Each of the devices 2-7 in the container distribution system 1 is configured as a general-purpose or dedicated computer 900. As shown in FIG. 12, the computer 900 includes, as its main components, a bus 910, a processor 912, a memory 914, an input device 916, an output device 917, a display device 918, a storage device 920, a communication I/F (interface) unit 922, an external device I/F unit 924, an I/O (input/output) device I/F unit 926, and a media input/output unit 928. Note that the above components may be omitted as appropriate depending on the application for which the computer 900 is used.

The processor 912 is composed of one or more arithmetic processing devices (such as a CPU (Central Processing Unit), MPU (Micro-processing unit), DSP (Digital Signal Processor), GPU (Graphics Processing Unit)), and operates as a control unit that oversees the entire computer 900. The memory 914 stores various data and programs 930, and is composed of, for example, volatile memory (DRAM, SRAM, etc.) that functions as main memory, non-volatile memory (ROM), flash memory, etc.

The input device 916 is composed of, for example, a keyboard, mouse, numeric keypad, electronic pen, etc., and functions as an input unit. The output device 917 is composed of, for example, a sound (audio) output device, vibration device, etc., and functions as an output unit. The display device 918 is composed of, for example, an LCD display, an organic EL display, electronic paper, a projector, etc., and functions as an output unit. The input device 916 and display device 918 may be integrated, such as a touch panel display. The storage device 920 is composed of, for example, an HDD, SSD, etc., and functions as a memory unit. The storage device 920 stores various data necessary for executing the operating system and program 930.

The communication I/F unit 922 is connected by wire or wireless to a network 940 such as the Internet or an intranet (which may be the same as the network 8 in FIG. 1 ), and functions as a communication unit that transmits and receives data to and from other computers in accordance with a predetermined communication standard. The external device I/F unit 924 is connected by wire or wireless to an external device 950 such as a camera, printer, scanner, or reader/writer, and functions as a communication unit that transmits and receives data to and from the external device 950 in accordance with a predetermined communication standard. The I/O device I/F unit 926 is connected to I/O devices 960 such as various sensors and actuators, and functions as a communication unit that transmits and receives various signals and data, such as detection signals from sensors and control signals to actuators, to and from the I/O devices 960. The media input/output unit 928 is connected by wire or wireless to a media such as a DVD (Digital Versatile Disc) drive, a CD (Compact Disc), or the like.
The storage device 970 is made up of a drive device such as an ISC drive, a memory card slot, and a USB connector, and reads and writes data from and to media (non-transitory storage media) 970 such as DVDs, CDs, memory cards, and USB memories.

In the computer 900 having the above configuration, the processor 912 loads the program 930 stored in the storage device 920 into the memory 914, executes it, and controls each component of the computer 900 via the bus 910. The program 930 may also be stored in the memory 914 instead of the storage device 920. The program 930 may be recorded on the media 970 in an installable file format or an executable file format, and provided to the computer 900 via the media input/output unit 928. The program 930 may also be provided to the computer 900 by downloading it via the communication I/F unit 922 over the network 940. Furthermore, the computer 900 may implement the various functions achieved by the processor 912 executing the program 930 using hardware such as an FPGA (field-programmable gate array) or an ASIC (application specific integrated circuit).

The computer 900 may be, for example, a desktop computer or a portable computer, and may be any type of electronic device. The computer 900 may be a client computer, a server computer, or a cloud computer.

(Operation of container distribution system 1)
Below, we will explain the functions 201 to 203 realized by the information processing device 2 as the operation of the container distribution system 1. Note that the information processing device 2 accesses the databases 210 to 215 to register and refer to the information D1 to D16, but in the following explanation, the access operation will be omitted as appropriate.

(Container purchasing management method)
FIG. 13 is a flowchart showing an example of a container purchase management method by the container purchase management function 201.

First, in step S100, a consumer U7 who has purchased product 12 uses a consumer terminal device 7 to read the information storage carrier 100 attached to the container 10 that constitutes product 12. As a result, the consumer terminal device 7 accesses the web service based on the web access information D8 contained in the information storage carrier 100 and displays a display screen based on the web service.

Next, in step S110, when the consumer terminal device 7 receives input of purchase request data D9, including the type of content desired to be purchased and the desired quantity, from the consumer U7 on its display screen, the consumer terminal device 7 transmits the purchase request data D9 to the information processing device 2 along with the container identification information D7 contained in the information storage carrier 100.

Then, in step S120, the information acquisition unit 201A of the information processing device 2 receives the purchase request data D9 and container identification information D7 from the consumer terminal device 7, and associates the purchase request data D9 with the container identification information D7 and registers it in the web management database 212. Note that if persona data D10 is acquired along with the purchase request data D9, the persona data D10 is also registered in the web management database 212.

By performing the above steps S100 to S120 for each of the multiple consumers U7 who purchase the product 12, purchase preference data D9 for multiple containers 10 (consumers U7) is accumulated in the web management database 212.

Next, in step S130, the information acquisition unit 201A references the web management database 212 and acquires purchase information D12 as a data set of purchase request data D9 for multiple containers 10 (consumer U7). If persona data D10 is also registered in the web management database 212, the information acquisition unit 201A acquires consumer information D13 as a data set of persona data D10 for multiple containers 10 (consumer U7). Furthermore, the information acquisition unit 201A may acquire container management information D14.

Next, in step S140, the storage processing unit 201B stores the purchasing information D12 acquired by the information acquisition unit 201A in the container purchasing management database 213. If the information acquisition unit 201A has acquired consumer information D13 or container management information D14, the information acquisition unit 201A stores the consumer information D13 and container management information D14 in the container purchasing management database 213.

As described above, the series of steps in the container purchasing management method shown in Figure 13 is completed. In the container purchasing management method, steps S100 to S130 correspond to the information acquisition process, and step S140 corresponds to the storage processing process.

As described above, the container purchasing management function 201 and container purchasing management method (information processing method) of the information processing device 2 according to this embodiment obtains purchasing information D12 indicating the type of contents 11 that a consumer U7 of the product 12 wishes to purchase from among contents 11 that can be filled into a container with the same specifications as the container 10, based on web access information D8 contained in the information storage carrier 100 attached to the container 10 that constitutes the product 12, and the purchasing information D12 is stored in the container purchasing management database 213 (storage device). Therefore, by utilizing the purchasing information D12, the containers 10 can be distributed stably.

For example, in the case of high-mix, low-volume production where containers of the same specifications are used for multiple types of contents 11, it is possible to accurately predict consumer U7 demand and create supply plans for distributors (such as container manufacturers U4, content manufacturers U5, and container cleaners U6) based on the purchasing information D12, thereby ensuring stable distribution of containers 10. In particular, by obtaining the above-described purchasing information D12 for the target containers 10, it is possible to accurately predict demand and create supply plans for products 12 using the target containers 10, promoting the distribution of the target containers 10 in the distribution market, and thereby quickly and reliably collecting collected data D3 from the target containers 10. This ensures that dividends on investments can be reliably paid, thereby improving the added value of the container investment management function 200.

(machine learning method)
FIG. 14 is a flowchart showing an example of a machine learning method performed by the learning function 202.

First, in step S200, the learning data acquisition unit 202A of the information processing device 2 acquires a desired number of pieces of learning data D17 as a preliminary preparation for starting machine learning, and stores the acquired learning data D17 in the learning data management database 214. The number of pieces of learning data D17 to be prepared here may be set taking into consideration the inference accuracy required for the learning model D18 that is ultimately obtained.

Next, in step S210, the machine learning unit 202B prepares a pre-learning learning model D18 in order to begin machine learning. The pre-learning learning model D18 prepared here is configured using the neural network model shown in Figure 10, with the weights of each synapse set to their initial values.

Next, in step S220, the machine learning unit 202B, for example, randomly acquires one set of training data D17 from the multiple sets of training data D17 stored in the training data management database 214.

Next, in step S230, the machine learning unit 202B inputs market information D15 (input data) contained in a set of training data D17 to the input layer 110 of the prepared pre-training (or training) training model D18. As a result, demand and supply information D16 (output data) is output as an inference result from the output layer 112 of the training model D18, but this output data was generated by the pre-training (or training) training model D18. Therefore, in the pre-training (or training) state, the output data output as an inference result indicates information that differs from the demand and supply information D16 (correct label) contained in the training data D17.

Next, in step S240, the machine learning unit 202B compares the supply and demand information D16 (correct label) included in the set of learning data D17 acquired in step S220 with the supply and demand information D16 (output data) output as an inference result from the output layer 112 in step S230, and performs a process of adjusting the weights of each synapse (backpropagation), thereby performing machine learning. In this way, the machine learning unit 202B causes the learning model D18 to learn the correlation between the market information D15 and the supply and demand information D16.

Next, in step S250, the machine learning unit 202B determines whether a predetermined learning termination condition has been met, for example, based on the evaluation value of an error function based on the demand and supply information D16 (correct label) included in the learning data D17 and the demand and supply information D16 (output data) output as an inference result, or the remaining number of unlearned learning data D17 stored in the learning data management database 214.

If, in step S250, the machine learning unit 202B determines that the learning termination condition has not been met and that machine learning should continue (No in step S250), the process returns to step S220, and steps S220 to S240 are performed multiple times on the learning model D18 being trained using untrained learning data D17. On the other hand, if, in step S250, the machine learning unit 202B determines that the learning termination condition has been met and that machine learning should be terminated (Yes in step S250), the process proceeds to step S260.

Then, in step S260, the machine learning unit 202B stores the trained learning model D18 (adjusted weight parameter group) generated by adjusting the weights associated with each synapse in the trained model management database 215.

As described above, the series of steps in the machine learning method shown in Figure 14 is completed. In the machine learning method, step S200 corresponds to the learning data storage process, steps S210 to S250 correspond to the machine learning process, and step S260 corresponds to the trained model storage process.

As described above, the learning function 202 and machine learning method of the information processing device 2 according to this embodiment allow the learning model D18 to learn the correlation between market information D15 for the container 10 to be learned, which includes at least purchasing information D12 as information obtained based on web access information D8 contained in the information storage carrier 100 attached to the container 10 constituting the product 12, and demand/supply information D16, which includes information regarding the demand or supply of products 12 in which contents 11 are filled in containers with the same specifications as the container 10, for each type of content 11. This makes it possible to provide a learning model D18 that can generate (infer) demand/supply information D16 for the container 10 to be predicted from the market information D15 for the container 10.

(Demand and supply management method)
FIG. 15 is a flowchart showing an example of a demand and supply management method performed by the demand and supply management function 203.

First, in step S300, the information acquisition unit 203A of the information processing device 2 receives, for example, from the management business terminal device 5, a prediction target container ID that identifies the prediction target container 10 using container identification information D7. The information acquisition unit 203A then references the container purchasing management database 213 to identify the management ID that includes the prediction target container ID. The information acquisition unit 203A then acquires the purchasing information D12, consumer information D13, and container management information D14 associated with the management ID as market information D15 for the prediction target container 10. Note that the information acquisition unit 203A may acquire market information D15 for the prediction target container 10 by receiving other information, such as the specifications of the container 10, instead of the container identification information D7.

Next, in step S310, the generation processing unit 203B inputs the market information D15 for the container 10 to be predicted, acquired in step S300, into the learning model D18, thereby generating demand and supply information D16 for the market information D15 as output data.

Next, in step S320, the output processing unit 203C transmits the demand and supply information D16 for the container 10 to be predicted, which was generated in step S310, to the management company terminal device 5. The management company terminal device 5 then displays a display screen based on the demand and supply information D16, thereby presenting the demand and supply information D16 for the container 10 to the management company U3. Note that the destination of the demand and supply information D16 may be a distribution company terminal device 6A-6C in addition to or instead of the management company terminal device 5.

As described above, the series of steps in the demand and supply management method shown in Figure 15 is completed. In the above demand and supply management method, step S300 corresponds to the information acquisition process, step S310 corresponds to the generation processing process, and step S320 corresponds to the output processing process.

As described above, the demand and supply management function 203 and demand and supply management method (information processing method) of the information processing device 2 according to this embodiment are used to obtain, as market information D15 for the container 10 being predicted, purchase information D12 indicating the type of contents 11 that a consumer U7 of the product 12 wishes to purchase from among the contents 11 that can be filled into a container with the same specifications as the container 10, based on web access information D8 contained in the information storage carrier 100 attached to the container 10 constituting the product 12. By inputting this market information D15 into a learning model D18, demand and supply information D16 is generated, which includes information regarding the demand or supply of the product 12, in which the contents 11 are filled into containers with the same specifications as the container 10, for each type of content 11. Therefore, by utilizing demand and supply information D16, the stable distribution of containers 10 can be ensured.

For example, by treating the container 10 that is the subject of investment as the container 10 that is the subject of prediction, the above-described supply and demand information D16 is generated for the market information D15 of the container 10 that is the subject of investment. Then, by using this supply and demand information D16 to stimulate the circulation of the container 10 that is the subject of investment in the secondary market, collected data D3 from the container 10 that is the subject of investment can be collected quickly and reliably. This allows dividends on investment to be reliably paid, thereby improving the added value of the container investment management function 200.

Furthermore, if the container management information D14 included in the market information D15 includes distribution location information and inventory location information, the demand and supply information D16 described above is generated taking into account the location of the containers 10 at each distribution stage, i.e., the distribution status of the containers 10 along the distribution flow line, such as their status as they are being held up. This makes it possible to realize more accurate demand forecasts and supply plans according to the distribution status of the containers 10.

(Other embodiments)
The present invention is not limited to the above-described embodiment, and various modifications can be made without departing from the spirit and scope of the present invention, all of which are included in the technical concept of the present invention.

In the above embodiment, the multiple functions 200-203 provided in the information processing device 2 were described as being realized by a single device, but each of the functions 200-203 may be distributed across multiple devices (computers) and realized by multiple devices. In this case, each of the four functions 200-203 may be realized by a single device, or any two or three of the four functions 200-203 may be realized by a single device.

In the above embodiment, the information processing device 2 operates according to the flowcharts shown in Figures 13 to 15, but some of the processes (units) may be omitted, or other processes may be added. In this case, the omitted processes (units) may be executed by an external system (such as a manufacturing management system, a transportation management system, a sales management system, or a data analysis system).

In the above embodiment, a case has been described in which a neural network is employed as the learning model D18 that realizes machine learning by the learning function 202, but other machine learning models may also be employed. Examples of other machine learning models include tree types such as decision trees and regression trees, ensemble learning such as bagging and boosting, neural network types (including deep learning) such as recurrent neural networks, convolutional neural networks, and LSTM, clustering types such as hierarchical clustering, non-hierarchical clustering, k-nearest neighbors, and k-means, multivariate analyses such as principal component analysis, factor analysis, and logistic regression, and support vector machines.

(Inference device, inference method, and inference program)
The present invention can be provided not only in the form of the information processing device 2 (method or program) according to the above embodiment, but also in the form of an inference device (inference method or inference program). In this case, the inference device (inference method or inference program) can include a memory and a processor, and the processor executes a series of processes. The series of processes includes an information acquisition process (information acquisition step) that acquires at least purchase information as market information for the container to be inferred based on web access information included in an information storage carrier attached to the container, and an inference process (inference step) that infers demand and supply information for the container to be inferred once the market information for the container to be inferred is acquired in the information acquisition process.

By providing it in the form of an inference device (inference method or inference program), it can be more easily applied to a variety of devices than when implemented in an information processing device. It will be obvious to those skilled in the art that when the inference device (inference method or inference program) infers supply and demand information, it may also apply the inference method implemented by the generation processing unit using a trained learning model generated by the machine learning device and machine learning method according to the above embodiments.

1...container distribution system, 2...information processing device, 3...investor terminal device,
4... Information user terminal device, 5... Management company terminal device, 6A to 6C... Distribution company terminal devices, 7... Consumer terminal device, 8... Network, 10... Container, 11... Contents, 12... Product,
20...control unit, 21...storage unit, 22...communication unit, 23...input unit, 24...display unit,
100...information storage carrier, 200...container investment management function,
201...container purchase management function, 201A...information acquisition unit, 201B...storage processing unit,
202... learning function, 202A... learning data acquisition unit, 202B... machine learning unit,
203...demand and supply management function, 203A...information acquisition unit, 203B...generation processing unit,
203C...output processing unit, 210...distribution management database,
211...container investment management database, 212...web management database,
213...container purchase management database, 214...learning data management database,
215...model management database, 216...information processing program,
D1... investment information, D2... distribution container setting information, D3... collected data,
D4...container distribution information, D5...value medium information, D6...dividend information, D7...container identification information,
D8...Web access information, D9...Purchase preference data, D10...Persona data,
D11...management information, D12...purchasing information, D13...consumer information,
D14...Container management information, D15...Market information, D16...Demand and supply information,
D17...Learning data, D18...Learning model,
U1...Investor, U2...Information user, U3...Manager, U4...Container manufacturer,
U5...Contents manufacturer, U6...Container cleaner, U7...Consumer

Claims (8)

an information acquisition unit that acquires, for each container, purchase desire data indicating the type of contents that a consumer of the product desires to purchase from among the contents that can be filled into a container of the same specifications as the container, based on web access information contained in an information storage carrier attached to the container that is filled with the contents to constitute the product, and container identification information contained in the information storage carrier;
a storage processing unit that associates the purchase request data and the container identification information acquired by the information acquisition unit and stores them in a storage device,
The storage device includes:
The specifications of the container are associated with a plurality of pieces of container identification information each identifying a container of the same specifications, and are stored as management information;
The information acquisition unit
performing a data analysis process on the purchase request data for each of the containers associated with the plurality of container identification information stored as the management information, thereby acquiring purchase information including a data analysis result;
The storage processing unit
storing the purchase information acquired by the information acquisition unit in the storage device ;
Information processing device. The information acquisition unit
Further acquiring container management information including at least one of distribution information when the containers of the same specifications are distributed through a plurality of distribution stages and inventory information when the containers are stocked at the plurality of distribution stages;
The storage processing unit
storing the container management information acquired by the information acquisition unit in the storage device;
The information processing device according to claim 1 . the distribution information includes distribution location information regarding a location of the container when it is distributed,
the inventory information includes inventory location information regarding the location where the container is stored;
The information processing device according to claim 2 . The plurality of distribution stages include:
a cleaning step of cleaning the container;
a filling step of filling the container with the contents;
and a consumption step in which the content filled in the container is consumed by the consumer.
The information processing device according to claim 2 . The information acquisition unit
a web service is accessed based on the web access information read from the information storage carrier using a terminal device used by the consumer, and the purchase request data and the container identification information read from the information storage carrier are acquired via the web service.
The information processing device according to claim 1 . The information acquisition unit
Further acquiring persona data relating to the consumer for each of the containers from the terminal device when the web service is accessed;
The storage processing unit
The persona data and the container identification information acquired by the information acquisition unit are stored in the storage device in association with each other ,
The information acquisition unit
performing a data analysis process on the persona data for each of the containers associated with the plurality of container identification information stored as the management information, thereby obtaining consumer information including a data analysis result;
The storage processing unit
storing the consumer information acquired by the information acquisition unit in the storage device;
The information processing device according to claim 5 . the persona data includes consumer location information regarding the location of the consumer;
The information processing device according to claim 6 . 1. A computer-implemented information processing method, comprising:
an information acquisition step of acquiring, for each container, purchase desire data indicating the type of contents that a consumer of the product desires to purchase from among contents that can be filled into a container of the same specifications as the container, based on web access information contained in an information storage carrier attached to the container that is filled with the contents to constitute the product, and container identification information contained in the information storage carrier ;
a storage processing step of storing the purchase request data and the container identification information acquired in the information acquisition step in a storage device in association with each other ,
The storage device includes:
The specifications of the container are associated with a plurality of pieces of container identification information each identifying a container of the same specifications, and are stored as management information;
The information acquisition step includes:
performing a data analysis process on the purchase request data for each of the containers associated with the plurality of container identification information stored as the management information, thereby acquiring purchase information including a data analysis result;
The storage processing step includes:
storing the purchase information acquired in the information acquisition step in the storage device;
Information processing methods.