JP2020154936A - Inventory management device, inventory management method, and computer program - Google Patents

Abstract

To take inventory of various types of goods without much time and labor.SOLUTION: An inventory management device (1) includes: extraction means (110) for extracting a feature quantity specific to an article from image data of the article to be inventoried; identifying means (120) for identifying the article based on the feature quantity extracted by the extraction means; generation means (130) for generating inventory data for managing the article identified by the identifying unit; and registration means (140) for registering the data generated by the generation means with an inventory ledger (300) capable of registering inventory data on a plurality of articles to be inventoried.SELECTED DRAWING: Figure 2

Description

The present invention relates to a technical field of an inventory management device, an inventory management method, and a computer program for managing data related to inventory of goods.

In the field of goods management, the presence or absence and location of delivered goods are managed by using inventory data associated with the goods. For example, Patent Document 1 discloses a technique for automatically notifying an administrator of information on the progress rate of inventory and devices that have not been inventoried in a system that reads inventory data using a non-contact IC tag attached to an information device. Has been done.

Inventory data is often managed by associating it with various codes and tags attached to products, for example. For example, Patent Document 2 discloses a technique for identifying a seal attached to an asset by image analysis. Patent Document 3 discloses a technique for identifying an individual product by detecting a characteristic symbol from an image of the product. Patent Document 4 discloses a technique for registering that an asset has been confirmed when a unique color code is included in an image of an asset as a subject to be managed.

Japanese Unexamined Patent Publication No. 2009-110035 Japanese Unexamined Patent Publication No. 2016-212848 Japanese Unexamined Patent Publication No. 2013-210971 Japanese Unexamined Patent Publication No. 2015-172589

In the techniques described in Patent Documents 2 to 4 described above, it is required to attach various codes and tags to the articles to be inventoried in advance, so that the work is troublesome. In addition, depending on the size and shape of the item, it may be physically difficult to attach various codes and tags, and such items cannot be treated as inventory items. There is a problem.

The present invention has been made in view of the above problems, and provides an inventory management device, an inventory management method, and a computer program capable of performing inventory of various types of articles without much effort. That is the issue.

One aspect of the inventory management device of the present invention is an extraction means for extracting a feature amount peculiar to the article from the image data of the article to be inventoried, and the article based on the feature amount extracted by the extraction means. A specific means for specifying, a generation means for generating inventory data for managing the article specified by the specific means, and the inventory data generated by the generation means for a plurality of the articles to be inventoried. It is provided with a registration means for registering the inventory data in an inventory ledger that can be registered.

One aspect of the inventory management method of the present invention is an extraction step of extracting a feature amount peculiar to the article from the image data of the article to be inventoried, and the article based on the feature amount extracted in the extraction step. A specific step for specifying, a generation step for generating inventory data for managing the article specified in the specific step, and the inventory data generated in the generation step for a plurality of the articles to be inventoried. The registration process of registering the inventory data in a registerable inventory ledger is included.

One aspect of the computer program of the present invention is an extraction step of extracting a feature amount unique to the article from the image data of the article to be inventoried, and an extraction step of extracting the article based on the feature amount extracted in the extraction step. The specific step to be specified, the generation step of generating inventory data for managing the article specified in the specific step, and the inventory data generated in the generation step are the said of the plurality of articles to be inventoried. Have the computer execute the registration process of registering the inventory data in the registerable inventory ledger.

According to each one aspect of the inventory management device, the inventory management method, and the computer program described above, it is possible to carry out inventory of various types of articles without much effort.

It is a block diagram which shows the hardware composition of the inventory management apparatus which concerns on embodiment. It is a block diagram which shows the functional block realized in the CPU which concerns on embodiment. It is a flowchart which shows the flow of the whole operation of the inventory management apparatus which concerns on embodiment. It is a flowchart which shows the flow of operation of the article identification part. It is a table which shows an example of the registration data acquired by the article identification part. It is a table which shows an example of delivery data acquired by an inventory data generation part. It is a table which shows an example of the position data acquired by the inventory data generation unit. It is a table which shows an example of the user data acquired by the inventory data generation part. It is a flowchart which shows the flow of operation of the article list generation part. It is a table which shows an example of the inventory data registered in the inventory ledger storage unit. It is a block diagram which shows another example of the functional block realized in the CPU which concerns on embodiment.

Hereinafter, embodiments of an inventory management device, an inventory management method, and a computer program will be described with reference to the drawings.

<Hardware configuration>
First, the hardware configuration of the inventory management device according to the embodiment will be described with reference to FIG. FIG. 1 is a block diagram showing a hardware configuration of the inventory management device according to the embodiment.

As shown in FIG. 1, the inventory management device 1 according to the present embodiment includes a CPU (Central Processing Unit) 11, a RAM (Random Access Memory) 12, a ROM (Read Only Memory) 13, and a storage device 14. It includes an input device 15 and an output device 16. The CPU 11, the RAM 12, the ROM 13, the storage device 14, the input device 15, and the output device 16 are connected via the data bus 17.

The CPU 11 reads a computer program. For example, the CPU 11 may read a computer program stored in at least one of the RAM 12, the ROM 13, and the storage device 14. For example, the CPU 11 may read a computer program stored in a computer-readable recording medium using a recording medium reading device (not shown). The CPU 11 may acquire (that is, may read) a computer program from a device (not shown) arranged outside the inventory device 1 via a network interface. The CPU 11 controls the RAM 12, the storage device 14, the input device 15, and the output device 16 by executing the read computer program. In this embodiment, in particular, when a computer program read by the CPU 11 is executed, a functional block for managing inventory data is realized in the CPU 11. That is, the CPU 11 can function as a controller for managing inventory data. The configuration of the functional block realized in the CPU 11 will be described in detail later with reference to FIG.

The RAM 12 temporarily stores a computer program executed by the CPU 11. The RAM 12 temporarily stores data temporarily used by the CPU 11 when the CPU 11 is executing a computer program. The RAM 12 may be, for example, a D-RAM (Dynamic RAM).

The ROM 13 stores a computer program executed by the CPU 11. The ROM 13 may also store fixed data. The ROM 13 may be, for example, a P-ROM (Programmable ROM).

The storage device 14 stores data stored in the inventory management device 1 for a long period of time. The storage device 14 may operate as a temporary storage device of the CPU 11. The storage device 14 may include, for example, at least one of a hard disk device, a magneto-optical disk device, an SSD (Solid State Drive), and a disk array device.

The input device 15 is a device that receives an input instruction from the user of the inventory management device 1. The input device 15 may include, for example, at least one of a keyboard, a mouse and a touch panel.

The output device 16 is a device that outputs information about the inventory management device 1 to the outside. For example, the output device 16 may be a display device capable of displaying information about the inventory management device 1.

<CPU functional block>
Subsequently, the functional block realized in the CPU 11 will be described with reference to FIG. FIG. 2 is a block diagram showing a functional block realized in the CPU 11.

As shown in FIG. 2, an inventory management unit 100 and an article list generation unit 200 are realized in the CPU 11 as logical functional blocks for managing inventory data. The data output as the processing result of each of the inventory management unit 100 and the article list generation unit 200 is registered in the inventory ledger stored in the inventory ledger storage device 300. The inventory ledger storage device 300 may be configured as the storage device 14 shown in FIG. 1, or may be a recording medium external to the inventory management device 1. The inventory management unit 100 includes a feature amount extraction unit 110, an article identification unit 120, an inventory data generation unit 130, and an inventory data registration unit 140. The article list generation unit 200 is a specific example of the “list generation means” in the appendix described later, and includes a delivery data acquisition unit 210 and a list data registration unit 220.

The feature amount extraction unit 110 is configured to be able to extract the feature amount peculiar to the article from the image data of the article taken by a photographing terminal having a communication function such as a smartphone. As for the specific extraction method of the feature amount, an existing method can be appropriately adopted, and therefore detailed description thereof will be omitted here. The feature amount extracted by the feature amount extraction unit 110 is output to the article identification unit 120. The feature amount extraction unit 110 is a specific example of the “extraction means” in the appendix described later.

The article identification unit 120 is configured to be able to identify (in other words, identify) the article based on the feature amount of the article extracted by the feature amount extraction unit 110. The article specified by the article identification unit 120 is in a state of being associated with the identification information unique to the article such as the serial number and the article name of the article. A specific method for identifying the article will be described in detail later with reference to FIG. The identification result by the article identification unit 120 is output to the inventory data generation unit 130. The article identification unit 120 is a specific example of the “specific means” in the appendix described later.

The inventory data generation unit 130 is configured to be able to generate inventory data for managing the articles specified by the article identification unit 120. The inventory data is associated with the identification information of the article (that is, the information obtained as a specific result by the article identification unit 120) and various data required for the inventory of the article (for example, location information, user information, etc.). It is generated as data. The inventory data generated by the inventory data generation unit 130 is output to the inventory data registration unit 140. The inventory data generation unit 130 is a specific example of the “generation means” in the appendix described later.

The inventory data registration unit 140 is configured so that the inventory data generated by the inventory data generation unit 130 can be registered in the inventory ledger stored in the inventory ledger storage device 300. The inventory data registration unit 140 is a specific example of the "registration means" in the appendix described later.

The delivery data acquisition unit 210 is configured to be able to acquire delivery data existing in a manufacturer, a store, or the like that is a manufacturer of the article. The delivery data acquired by the delivery data acquisition unit 210 is output to each of the inventory data generation unit 130 and the list data registration unit 220.

The list data registration unit 220 generates list data indicating a list of articles to be inventoried based on the delivery data acquired by the delivery data acquisition unit 210, and the inventory ledger storage device 300 stores the generated list data. It is configured so that it can be registered in the memorized inventory ledger. The method of registering the list data will be described in detail later with reference to FIG.

<Operation explanation>
Next, with reference to FIG. 3, the operation of the inventory management device 1 according to the present embodiment (specifically, the operation of automatically generating and registering the inventory data of articles) will be described. FIG. 3 is a flowchart showing the overall operation flow of the inventory management device according to the embodiment.

As shown in FIG. 3, when the inventory management device 1 according to the present embodiment is operating, the feature amount extraction unit 110 first acquires image data of the article (step S11). Then, the feature amount extraction unit 110 extracts the feature amount peculiar to the article from the acquired image data (step S12).

Subsequently, the article specifying unit 120 identifies the article using the feature amount extracted by the feature amount extracting unit 110 (step S13). Here, the operation of the article specifying unit 120 in step S13 will be described in detail with reference to FIGS. 4 and 5. FIG. 4 is a flowchart showing the flow of operation of the article identification unit. FIG. 5 is a table showing an example of registration data acquired by the article identification unit.

As shown in FIG. 4, the article identification unit 120 first acquires the registered article data (step S101). The registered article data is data including a feature amount unique to the article registered in advance at the time of manufacturing the article (in other words, data including a feature amount as a reference for identifying the article), for example, a manufacturer of the article or It can be obtained from retailers.

As shown in FIG. 5, the registered article data is acquired as data corresponding to a plurality of registered articles, and for example, the “model name”, “ID (serial number)”, and “feature amount data” of the article ( That is, it contains information on "data showing the feature amount)". The registered article data is required to have accuracy that can identify the article, and therefore has a size of, for example, several hundred kilobytes. Therefore, it is difficult to use the registered article data as it is as an ID, and it is required to generate inventory data described later.

Subsequently, the article identification unit 120 calculates a score indicating the degree of coincidence with each other by comparing the feature amount extracted by the feature amount extraction unit 110 with the feature amount included in the registered article data (step S102). ). The score here is calculated as a numerical value as the degree of agreement is higher (that is, the more the extracted feature amount and the feature amount of the registered article data are similar), and in the present embodiment, " It is calculated in the range of "0.00 to 1.00".

Subsequently, the article identification unit 120 determines whether or not the calculated score is greater than 0.99 (step S103). The numerical value "0.99" here is a specific example of the "predetermined threshold value" in the appendix described later, and the degree of agreement between the extracted feature amount and the feature amount of the registered article data is extremely high. (That is, it is a threshold value set for determining that the article is the same article). As long as the threshold value is set from such a viewpoint, a numerical value different from 0.99 may be used as the threshold value in step S103.

When it is determined that the score is greater than 0.99 (step S103: YES), the article identification unit 120 identifies the article from which the feature amount has been extracted as the article indicated by the registered article data (step S104). On the other hand, when it is determined that the score is not larger than 0.99 (step S103: NO), the article identification unit 120 temporarily stores the calculated score (step S105). Then, the article identification unit 120 determines whether or not all the scores of the registered article data have been calculated (step S106). That is, it is determined whether or not the scores have been calculated for each of the plurality of registered articles.

When it is determined that all the scores of the registered article data have not been calculated (step S106: NO), the article identification unit 120 re-executes the processing of step S102 and subsequent steps for the registered article data for which the score has not been calculated yet. In this way, when a score greater than 0.99 is not calculated (that is, when the article cannot be immediately identified from the score), the process of repeatedly calculating the score using the registered article data that has not been used yet is performed. Will be executed. Then, when it is determined that all the scores of the registered article data have been calculated (step S106: YES), the article identification unit 120 compares the stored scores (that is, with each of the plurality of registered article data). The one with the highest score is selected from the calculated scores), and the article from which the feature amount is extracted is identified as the registered article with the highest score (step S107). That is, when there is no registered article data having a score greater than 0.99, the article from which the feature amount is extracted is the registered article having the highest score (that is, the highest degree of matching of the feature amount). Specified as.

Returning to FIG. 3, when the article is specified by the article identification unit 120, the inventory data generation unit 130 generates inventory data for managing the specified article (step S14). Here, the operation of the inventory data generation unit 130 in step S14 will be described in detail with reference to FIGS. 6 to 8. FIG. 6 is a table showing an example of delivery data acquired by the inventory data generation unit. FIG. 7 is a table showing an example of position data acquired by the inventory data generation unit. FIG. 8 is a table showing an example of user data acquired by the inventory data generation unit.

As shown in FIG. 6, the inventory data generation unit 130 may generate inventory data using the delivery data acquired from the delivery data acquisition unit 210. The delivery data includes, for example, information about an "order ID", an "ID (identification number)", a "quantity", and a "purchaser". Therefore, by associating the specified article with the delivery data, it is possible to generate inventory data indicating the quantity of the article and the purchaser.

As shown in FIG. 7, the inventory data generation unit 130 may generate inventory data using position data (for example, map information or the like) acquired from the outside of the device. The position data includes, for example, information on a "range" in which the location of the article is indicated by a numerical value (coordinates) and "area information" that can be converted from the range. Therefore, by associating the specified article with the delivery data, it is possible to generate inventory data indicating the location of the article.

As shown in FIG. 8, the inventory data generation unit 130 may generate inventory data using user data acquired from outside the device. The user data includes, for example, information regarding a "range" indicating the position of the user and "user information" indicating the name and affiliation of the user. Therefore, by associating the specified article with the delivery data, it is possible to generate inventory data indicating the location of the article and the user.

Returning to FIG. 3 again, when the inventory data is generated by the inventory data generation unit 130, the inventory data registration unit 140 registers the inventory data in the inventory ledger stored in the inventory ledger storage unit 300 (step S15). .. Then, the inventory data registration unit 140 determines whether or not the registration of the inventory data of all the articles is completed (step S16). That is, it is determined whether or not all the inventory data of the articles to be inventoried are registered. When it is determined that the registration of the inventory data of all the articles is not completed (step S16: NO), the process is executed again from step S11 for the other articles. When it is determined that the registration of the inventory data of all the articles is completed (step S16: YES), the series of operations ends.

The articles to be inventoried can be confirmed by using the list data generated by the article list generation unit 200. In the following, the operation of generating the list data by the article list generation unit 200 and the confirmation operation using the list data will be described in detail with reference to FIGS. 9 and 10. FIG. 9 is a flowchart showing the operation flow of the article list generation unit. FIG. 10 is a table showing an example of inventory data registered in the inventory ledger storage unit.

As shown in FIG. 9, when the article list generation unit 200 operates, the delivery data acquisition unit 210 first acquires the delivery data (step S201). Subsequently, the list data registration unit 220 determines whether or not the acquired delivery data is the delivery data of the company (that is, the user who uses the inventory management device 1) (step S202). If it is determined that the delivery data is not the delivery data of the company (step S202: NO), the subsequent processing is not executed for the delivery data, and the process returns to step S201 to acquire other delivery data. ..

When it is determined that the delivery data is the delivery data of the company (step S202: YES), the list data registration unit 220 saves the product data (for example, serial number, product name, type, etc.) included in the delivery data (for example, serial number, product name, type, etc.). Step S203). After that, the list data registration unit 220 determines whether or not all the delivery data have been acquired (step S204). In other words, it determines whether all the product data of the goods delivered to the company has been saved.

If it is determined that all the delivery data has not been acquired (step S204: NO), the process returns to step S201 and other delivery data is acquired. On the other hand, when it is determined that all the delivery data has been acquired (step S204: YES), the list data registration unit 220 stores the list data summarizing the stored plurality of product data in the inventory ledger storage unit 300. Register in the inventory ledger (step S205).

As shown in FIG. 10, when the inventory data is registered, information as inventory data is added to each item included in the list data. For example, in the example of FIG. 10, information regarding "location", "presence or absence of confirmation", and "name of confirmer" is added. Regarding the first article (model name: 39-03AC) and the second article (model name: S-121-X) from the top in the example of FIG. 10, the location, presence / absence of confirmation, and name of the confirmer are indicated. Each is recorded, and it can be confirmed that the inventory data is normally registered. On the other hand, for the third item from the top (model name: X2243903-A), the location, presence / absence of confirmation, and the name of the confirmer are not recorded. In this case, it is estimated that the operation of generating the inventory data shown in FIG. 3 is not completed for the third article from the top. Therefore, when such an unrecorded article exists, it is determined in step S16 of FIG. 3 described above that the registration of inventory data of all articles has not been completed (step S106: NO), and from step S11. Processing will be resumed.

<Technical effect>
Next, the technical effect obtained by the inventory management device 1 according to the present embodiment will be described.

As described with reference to FIGS. 1 to 10, according to the inventory management device 1 according to the present embodiment, the article is specified based on the feature amount extracted from the image data of the article, and the inventory data is generated and registered. Will be done. In this way, inventory data can be suitably managed without attaching a tag or code to the article. Therefore, it is possible to take an inventory of various kinds of goods without much trouble.

In the above description, the inventory management device 1 includes the inventory management unit 100 and the article list generation unit 200. However, as shown in FIG. 11, the inventory management device 1 (that is, the CPU 11) is the inventory management unit. While the 100 is provided, the article list generation unit may not be provided. In this case, the inventory management unit 100 may acquire the delivery data from an external device of the inventory management device 1.

<Additional notes>
The following additional notes will be further disclosed with respect to the embodiments described above.

(Appendix 1)
The inventory management device according to Appendix 1 identifies the article based on the extraction means for extracting the feature amount peculiar to the article from the image data of the article to be inventoried and the feature amount extracted by the extraction means. The specific means, the generation means for generating inventory data for managing the article specified by the specific means, and the inventory data generated by the generation means are combined with the inventory of a plurality of the articles to be inventoried. It is an inventory management device characterized by including a registration means for registering data in an inventory ledger capable of registering data.

(Appendix 2)
The inventory management device according to Appendix 2 is characterized in that the generation means generates the inventory data so as to include at least one of the position information indicating the position of the article and the user information indicating the user of the article. This is the inventory management device according to Appendix 1.

(Appendix 3)
The inventory management device according to Appendix 3 specifies that the specific means identifies the article by comparing the feature amount extracted by the extraction means with the feature amount of the registered article registered in advance. The inventory management device according to Appendix 1 or 2, which is a feature.

(Appendix 4)
In the inventory management device according to Appendix 4, when the specific means has a degree of agreement between the feature amount extracted by the extraction means and the feature amount of the registered article larger than a predetermined threshold value, the article is registered. The inventory management device according to Appendix 3, which is characterized in that it is identified as an article.

(Appendix 5)
In the inventory management device according to Appendix 5, in the specific means, the degree of agreement between the feature amount extracted by the extraction means and each of the feature amounts of the plurality of registered articles is larger than the predetermined threshold value. If not, the inventory management device according to Appendix 4, wherein the article is identified as the registered article having the highest degree of matching among the plurality of registered articles.

(Appendix 6)
The inventory management device according to Appendix 6 further includes a list generation means for generating a list data of the articles to be inventoried based on the delivery data of the articles, and the registration means is included in the list data. The inventory management device according to any one of Supplementary note 1 to 5, wherein the inventory data of the article is registered in the inventory ledger.

(Appendix 7)
The inventory management method described in Appendix 7 specifies an article based on an extraction step of extracting a feature amount unique to the article from image data of the article to be inventoried and the feature amount extracted in the extraction step. The specific step, the generation step of generating inventory data for managing the article specified in the specific step, and the inventory data generated in the generation step are combined with the inventory of a plurality of the articles to be inventoried. It is an inventory management method characterized by including a registration process of registering data in an inventory ledger in which data can be registered.

(Appendix 8)
The computer program according to Appendix 8 identifies the article based on an extraction step of extracting a feature amount unique to the article from the image data of the article to be inventoried and the feature amount extracted in the extraction step. The specific process, the generation step of generating inventory data for managing the article specified in the specific process, and the inventory data generated in the generation step are combined with the inventory data of a plurality of the articles to be inventoried. It is a computer program characterized in that a computer executes a registration process of registering data in an inventory ledger that can be registered.

(Appendix 9)
The recording medium described in Appendix 9 is a recording medium characterized in that the computer program described in Appendix 8 is recorded.

The present invention can be appropriately modified within the scope of the claims and within the scope not contrary to the gist or idea of the invention which can be read from the entire specification, and the inventory management device, inventory management method and computer program accompanied by such changes are also included in the present invention. It is included in the technical idea of the invention.

1 Inventory management device 11 CPU
100 Inventory management unit 110 Feature quantity extraction unit 120 Item identification unit 130 Inventory data generation unit 140 Inventory data registration unit 200 Item list generation unit 210 Delivery data acquisition unit 220 List data registration unit 300 Inventory ledger recording device

Claims (8)

An extraction means for extracting features unique to the article from image data of the article to be inventoried, and
A specific means for identifying the article based on the feature amount extracted by the extraction means, and
A generation means for generating inventory data for managing the article specified by the specific means, and a generation means.
An inventory management device comprising: a registration means for registering the inventory data generated by the generation means in an inventory ledger capable of registering the inventory data of a plurality of the articles to be inventoried. The inventory management according to claim 1, wherein the generation means generates the inventory data so as to include at least one of the position information indicating the position of the article and the user information indicating the user of the article. apparatus. The specific means according to claim 1 or 2, wherein the specific means identifies the article by comparing the feature amount extracted by the extraction means with the feature amount of a pre-registered registered article. Inventory management device. The specific means is characterized in that when the degree of agreement between the feature amount extracted by the extraction means and the feature amount of the registered article is larger than a predetermined threshold value, the article is identified as the registered article. The inventory management device according to claim 3. In the specific means, when the degree of agreement between the feature amount extracted by the extraction means and each of the feature amounts of the plurality of registered articles does not become larger than the predetermined threshold value, the article is a plurality of said articles. The inventory management device according to claim 4, wherein the registered article is identified as having the highest degree of matching among the registered articles. Further provided with a list generation means for generating list data of the articles to be inventoried based on the delivery data of the articles.
The inventory management device according to any one of claims 1 to 5, wherein the registration means registers the inventory data of the article included in the list data in the inventory ledger. An extraction process for extracting features unique to the article from image data of the article to be inventoried, and
A specific step of specifying the article based on the feature amount extracted in the extraction step, and
A generation process for generating inventory data for managing the article specified in the specific process, and a generation process.
An inventory management method comprising a registration step of registering the inventory data generated in the generation step in an inventory ledger capable of registering the inventory data of a plurality of the articles to be inventoried. An extraction process for extracting features unique to the article from image data of the article to be inventoried, and
A specific step of specifying the article based on the feature amount extracted in the extraction step, and
A generation process for generating inventory data for managing the article specified in the specific process, and a generation process.
A computer program characterized in that a computer executes a registration step of registering the inventory data generated in the generation step in an inventory ledger capable of registering the inventory data of a plurality of the articles to be inventoried.

Images