Excess material management device and method for managing excess material

Abstract

This system provides a convenient way to manage surplus materials. [Solution] The surplus material management device comprises: an image acquisition unit that acquires image information of surplus material; an image analysis unit that acquires surplus material information, including at least information regarding the type of surplus material, based on the image information; and a surplus material information output unit that outputs the surplus material information in association with the image information.

Description

Technical Field

[0001] The present invention relates to a surplus material management device and a surplus material management method.

Background Art

[0002] As background art in this technical field, there is JP 2024-145809 A (Patent Document 1). This publication describes that: "The offcut management device 21 includes a nesting determination unit 21a that allocates products to a base material and determines the nesting layout, a cutting region setting unit 21b that sets cutting lines on the base material for separating the region with allocated products and the region with no allocated products based on the nesting layout, and divides the base material into a plurality of cutting regions by the cutting lines, an identification mark setting unit 21c that arranges identification marks on the base material so as not to place identification marks on the cutting regions with no allocated products, and an offcut registration unit 21d that registers the cutting regions with no allocated products as offcuts." (See the abstract).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Patent Document 1 describes a processing unit 40 controlled by an NC device, comprising a processing machine 41 and a marking device 42. The marking device 42 marks the material or scraps processed by the processing machine 41 with an identification mark such as a two-dimensional code that can be read by a camera. However, according to the technology of Patent Document 1, there is a problem in that scraps generated by processing by a processing machine not controlled by an NC device, or scraps generated when there is no marking device 42, cannot be properly managed. As a result, surplus materials such as scraps generated at equipment that exists for a relatively short predetermined period, such as at a construction site, are discarded without being managed.

[0005] In view of the circumstances of the prior art described above, this application provides a mechanism for easily managing surplus materials. [Means for solving the problem]

[0006] To solve the above problems, for example, the configuration described in the claims may be adopted. This application includes several means for solving the above-mentioned problems, but to give one example, the surplus material management device according to this application is: An image acquisition unit that acquires image information of surplus material, An image analysis unit that acquires surplus material information, which includes at least information regarding the type of surplus material, based on the aforementioned image information. A surplus material information output unit that outputs the surplus material information in association with the aforementioned image information, It is equipped with these features. [Effects of the Invention]

[0007] This technology allows for easy management of surplus materials. Other issues, configurations, and effects not mentioned above will be clarified by the following description of the embodiments. [Brief explanation of the drawing]

[0008] [Figure 1] Figure 1 is an example of an overall configuration diagram of the scrap material management system 100. [Figure 2] Figure 2 is an example of the hardware configuration of the management server 101. [Figure 3] Figure 3 is an example of the hardware configuration of the user terminal 102. [Figure 4] Figure 4 is an example of the hardware configuration of the administrator terminal 103. [Figure 5] Figure 5 is an example of user information 500. [Figure 6] Figure 6 is an example of leftover material image information 600. [Figure 7] Figure 7 is an example of leftover material information 700. [Figure 8] Figure 8 is an example of a leftover material management flow 800. [Figure 9] Figure 9 is an example of a leftover material image information acquisition flow 900. [Figure 10] Figure 10 is an example of a residence display information acquisition flow 1000. [Figure 11] Figure 11 is an example of a leftover material information acquisition flow 11100. [Figure 12] Figure 12 is an example of an estimation flow 1200. [Figure 13] Figure 13 is an example of a leftover material information acquisition screen 1300. [Figure 14] Figure 14 is another example of the leftover material information acquisition screen 1400. [Figure 15] Figure 15 is an example of a leftover material utilization screen 1500. [Figure 16] Figure 16 is another example of the leftover material image information acquisition flow 1600. [Figure 17] Figure 17 is another example of the estimation flow 1700. [Figure 18] Figure 18 is another example of the leftover material information acquisition screen 1800. [Figure 19] Figure 19 is another example of the hardware configuration of the management server 101. [Figure 20] Figure 20 is an example of billing information 2000. [Figure 21] Figure 21 is an example of negotiation information 2100. [Figure 22] Figure 22 is an example of a billing flow 2200. [Figure 23] Figure 23 is an example of a negotiation flow 2300. [Mode for Carrying Out the Invention]

[0009] [Embodiment 1] Hereinafter, the surplus material management system, surplus material management device, surplus material management method, and program according to the present technology will be described with reference to the drawings as appropriate. The present technology manages surplus material generated at the hands of one or more users across the entire system. According to this surplus material management system, for example, surplus material generated under each individual user can be provided to other users who need the surplus material. As a result, surplus material that would otherwise be discarded can be effectively utilized as a resource.

[0010] [Scrap Material Management System] In the following, the present technology will be described based on a case where scrap materials of building materials are managed as an example of surplus materials, by exemplifying a case where the scrap materials of building materials are managed using the scrap material management system (an example of the surplus material management system), the scrap material management device, the scrap material management method, and the program according to the present technology. Figure 1 is an example of an overall configuration diagram of a scrap material management system 100 according to an embodiment. The scrap material management system 100 is configured to include one or a plurality of management servers 101, one or a plurality of user terminals 102, one or a plurality of administrator terminals 103, and one or a plurality of machine learning model servers 104. Each of the one or more user terminals 102 is configured to be connectable to the one or more management servers 101 via a network. Further, each of the one or more administrator terminals 103 is configured to be connectable to the one or more management servers 101 via a network. Note that the network may be wired or wireless, and each server and terminal can transmit and receive information to and from each other via the network.

[0011] The machine learning model server 104 may be provided separately from the management server 101, or it may be provided integrally with the management server 101. The administrator terminal 103 may be provided separately from the management server 101, or it may be provided integrally with the management server 101. The user terminal 102 may be provided separately from the management server 101, or it may be provided integrally with the management server 101.

[0012] In the scrap material management system 100, the management server 101, user terminal 102, and administrator terminal 103 (hereinafter, user terminal 102 and administrator terminal 103 may simply be referred to as "terminals") may each be a mobile device such as a smartphone, tablet, mobile phone, or personal digital assistant (PDA), or a wearable device such as glasses (including goggles), a wristwatch, or clothing. Furthermore, the management server 101 and each of the terminals may be a stationary or portable computer, or a server located in the cloud or on a network. From a functional standpoint, the management server 101 and each of the terminals may also be a VR (Virtual Reality) terminal, an AR (Augmented Reality) terminal, or an MR (Mixed Reality) terminal. Alternatively, the management server 101 and each of the terminals may be a combination of several of these. For example, a combination of one smartphone and one wearable device can logically function as a single management server 101, user terminal 102, and administrator terminal 103. Each of these management servers 101, user terminal 102, and administrator terminal 103 may be other information processing terminals.

[0013] The management server 101 and terminals of the scrap material management system 100 may optionally include a processor that runs the operating system, applications, and programs; main memory such as RAM (Random Access Memory); auxiliary storage such as IC cards, hard disk drives, SSDs (Solid State Drives), and flash memory; a communication control unit such as a network card, wireless communication module, or mobile communication module; input devices such as a touch panel, keyboard, mouse, voice input device, motion controller, and motion detection by imaging from a camera; and output devices such as monitors, displays, printers, audio output devices, and oscillators. The input devices may also include sensors such as GPS, gyro sensors, and acceleration sensors. The output devices may be devices or terminals that transmit information for output to external monitors, displays, printers, or other equipment.

[0014] The main memory stores various programs and applications (software modules), and the processor executes these programs and applications to realize each functional element of the overall system. Each module may be implemented by one or more programs or applications. Furthermore, each module may be implemented by an independent program or application, or as a subprogram or function within a single integrated program or application. These modules may also be implemented as hardware (hardware modules) by integrating circuits or employing a microcomputer.

[0015] Furthermore, each module may be implemented by a single processor or by multiple processors. Also, each module may be installed in a single terminal (including a management server) or divided among two or more terminals (including management servers) interconnected via a network. Furthermore, each module may be installed in each, or one or more, of the two or more terminals (including management servers) interconnected via a network. Consideration is also given to cases where some modules are implemented in different countries from others.

[0016] In this specification, each module is described as the entity (subject) that performs the processing; however, in reality, processing is carried out by the processor executing various programs and applications.

[0017] Auxiliary storage devices store various databases (DBs). A "database" is a collection of data organized and gathered to accommodate any data operations (e.g., extraction, addition, deletion, overwriting, etc.) from a processor or external computer. An auxiliary storage device is a functional element (storage unit) that stores one or more data collections. The implementation method of a database is not limited; for example, it may be a database management system, spreadsheet software, or text files such as XML or JSON. Some or all of this information may be stored in relational or non-relational databases. Databases may be independently provided and connectable to processors, etc.

[0018] [Management Server] Figure 2 illustrates the hardware configuration of the management server 101. The management server 101 is an element that manages this scrap material management system 100. The management server 101 is composed of, for example, a computer server provided by cloud computing.

[0019] The management server 101 includes a main memory 201 and an auxiliary memory 202. The management server 101 also includes the processor 203 as described above, an input device 204, an output device 205, and a communication control unit 206.

[0020] The main memory 201 stores programs and applications such as the basic management module 211, image acquisition module 212, location information acquisition module 213, dimension information acquisition module 214, image analysis module 215, scrap material information output module 216, and reuse management module 217. Each functional element of the management server 101 is realized by the processor 203 executing these programs and applications stored in the main memory 201. Furthermore, the implementation method of each module in the main memory 201 is not limited to this embodiment, and each module may be realized in a form in which multiple servers or cloud applications cooperate with each other.

[0021] The auxiliary storage device 202 stores information necessary for the operation of the scrap material management system 100. For example, the auxiliary storage device 202 stores user information 500, scrap material image information 600, scrap material information 700, model information MI, etc. Details of this information will be described later. Note that the implementation of each piece of information contained in the auxiliary storage device 202 is not limited to this embodiment, and each piece of information may be distributed across multiple database servers or cloud applications.

[0022] A brief explanation of each functional element of the management server 101 follows. The basic management module 211 manages the operations of the user terminal 102 and the administrator terminal 103. For example, the basic management module 211 works in conjunction with the user management module 311 of the user terminal 102 and the basic management module 411 of the administrator terminal 103 to control the basic operations for executing the scrap material management service on the user terminal 102 and the administrator terminal 103.

[0023] For example, the basic management module 211 works in conjunction with the user management module 311 of the user terminal 102 to output (display) a login screen for connecting to the scrap material management service executed by the management server 101, a scrap material information acquisition screen, etc., to the output device 305 of the user terminal 102, such as the display. The basic management module 211 also works in conjunction with the user management module 311 of the user terminal 102 to acquire input information entered from this terminal. The basic management module 211 operates based on the acquired information (various information, instructions, etc.) and outputs (records) the acquired information as user information 500, etc., to the auxiliary storage device 202.

[0024] The image acquisition module 212 acquires image information of scrap materials that are managed by the scrap material management service. The image acquisition module 212, for example, works in conjunction with the image acquisition module 312 of the user terminal 102 to control the operation for acquiring image information of scrap materials from the user terminal 102. The image acquisition module 212 may be configured to, for example, activate the camera 306 of the user terminal 102 and acquire image information of scrap materials on the spot. Alternatively, the image acquisition module 212 may be configured to acquire image information of scrap materials stored in the user terminal 102. The image acquisition module 212 stores (outputs) the acquired image information of scrap materials as scrap material image information 600, etc., in the auxiliary storage device 202.

[0025] The location information acquisition module 213 acquires location information (an example of scrap material information) related to the scrap material being managed. The location information acquisition module 213 acquires location information related to the location where the image information was generated, for example, by associating it with the image information of the scrap material. The location information acquisition module 213, for example, works in cooperation with the location information acquisition module 313 of the user terminal 102 to acquire the location information of the user terminal 102 as location information related to the location where the image information of the scrap material was generated. The location information acquisition module 213 turns on the location information service, for example, when the camera 306 of the user terminal 102 is activated. Here, the location information service is a function that collects information called location information metadata from mobile data communication or GPS network, etc., and associates it with the image information captured by the camera 306. As a result, the location information acquisition module 213 acquires the location coordinates of the place where the image of the scrap material was captured. The location information acquisition module 213 may also be configured to accept input from the user terminal 102 and acquire location coordinate information of the scrap material. The location information acquisition module 213 may also be configured to acquire address information based on the location information, for example. The location information acquisition module 213 stores (outputs) the acquired location information and / or address information of the scrap material in the auxiliary storage device 202 as scrap material information 700, etc., by associating it with the image information.

[0026] The dimension information acquisition module 214 acquires dimension information of the scrap material being managed. The dimension information acquisition module 214, for example, works in conjunction with the dimension information acquisition module 314 of the user terminal 102 to control the operation for acquiring dimension information of the scrap material from the user terminal 102. The dimension information acquisition module 214 may be configured to acquire information about the shape (contour) and dimensions of the scrap material by, for example, launching the measurement application on the user terminal 102 and utilizing the camera 306 and AR (augmented reality) technology. The dimension information acquisition module 214 can, for example, extract feature points (for example, vertices (which may be convex or concave angles)) relating to the surface and contour of the scrap material from the image of the scrap material, calculate the distance from the camera 306 to the feature point to obtain the three-dimensional coordinates of each feature point, and calculate the distance between feature points to understand the dimensions of each part of the scrap material. The dimension information acquisition module 214 may also be configured to accept input from the user terminal 102 and acquire dimension information of the scrap material. The dimension information acquisition module 214, for example, associates the acquired dimension information of the scrap material (e.g., width dimension and length dimension) with the image information and stores (outputs) it to the auxiliary storage device 202 as scrap material information 700, etc.

[0027] The image analysis module 215 acquires attribute information (scrap material information) of the scrap material by analyzing the scrap material based on its image information. For example, the image analysis module 215 acquires scrap material information, which includes at least information about the type of scrap material, based on the image information. The scrap material information may include, for example, information about the type, material, quantity, etc. The image analysis module 215 may also be configured to acquire scrap material information based on the image information, for example, by using a machine learning model. For example, the image analysis module 215 associates the acquired scrap material information with the image information and stores (outputs) it to the auxiliary storage device 202 as scrap material information 700, etc.

[0028] The image analysis module 215 then performs preprocessing on the image information 621, as described below, to obtain preprocessed image information 622. Preprocessing may include various processes to improve the accuracy of the analysis (including estimation) based on the image information of the scrap material performed by the image analysis module 215. Examples of preprocessing performed by the image analysis module 215, but not limited to these, include noise reduction, background removal, and contrast adjustment.

[0029] The scrap material information output module 216 outputs scrap material image information 600 and scrap material information 700. The scrap material information output module 216 works in conjunction with, for example, the scrap material information output module 316 of the user terminal 102 to output (display) the scrap material image information 600 and scrap material information 700, etc., to the output device 305 of the user terminal 102, such as a display.

[0030] The reuse management module 217 manages information for reusing scrap materials. The reuse management module 217, in cooperation with, for example, the reuse management modules 317 of one or more user terminals 102, receives usage requests from a second user's (user's) user terminal 102 for scrap materials belonging to the first user (provider) that are under management. Furthermore, when the reuse management module 217 receives a usage request for scrap materials from the first user (provider), for example, the reuse management module 217, in cooperation with the reuse management module 317 of the first user's (provider's) user terminal 102, outputs usage request information 733 to the output device 305 of the first user's user terminal 102, such as a display, indicating that a usage request has been made for the corresponding scrap material of the first user.

[0031] Furthermore, the management server 101 does not necessarily need to have all of the above-mentioned functional modules; one or more functional modules may be provided by other servers or terminals. Also, the above-mentioned functional modules are categorized for the sake of simplicity in explaining this technology, and one functional module may be configured to perform the functional processing of other functional modules.

[0032] [User terminal] Figure 3 shows an example of the hardware configuration of user terminal 102. The user terminal 102 is a terminal used by users (for example, site supervisors of construction companies) who utilize the scrap material management service provided by the management server 101. The user terminal 102 consists of terminals such as mobile information terminals like smartphones and tablets, notebook PCs, and desktop PCs. The user terminal 102 related to this technology is equipped with sensors such as GPS, gyroscopes, and accelerometers.

[0033] The user terminal 102 includes a main memory 301 and an auxiliary memory 302. The user terminal 102 also includes the processor 303 as described above, an input device 304, an output device 305, a camera 306, and a communication control unit 307.

[0034] The main memory 301 stores programs and applications such as the user management module 311, image acquisition module 312, location information acquisition module 313, dimension information acquisition module 314, scrap material information output module 316, and reuse management module 317. The processor 303 executes these programs and applications to realize each functional element of the user terminal 102. These modules work in conjunction with the basic management module 211, image acquisition module 212, location information acquisition module 213, dimension information acquisition module 214, scrap material information output module 216, and reuse management module 217 of the management server 101, respectively, to perform processing in the user terminal 102 that corresponds to the processing performed by each functional element in the management server 101. Therefore, the functional elements of each of these modules are the same as those of the management server 101 described above, and their explanation will be omitted. In addition, in the following explanation, the processing performed by each module in the user terminal 102 in conjunction with each module of the management server 101 may be omitted.

[0035] The location information acquisition module 313 acquires the location information of the user terminal 102 while acquiring image information of the target scrap material. The location information acquisition module 313 is configured to, for example, receive signals transmitted from GPS satellites, etc., while acquiring image information of the target scrap material, and to determine the location of the user terminal 102 based on triangulation, etc. However, the method of acquiring location information is not limited to this example.

[0036] Furthermore, the dimension information acquisition module 314 acquires the dimension information of the target scrap material. The dimension information acquisition module 314 is configured to, for example, recognize a landscape including the target scrap material with a camera, extract feature points including the outer contour of the target scrap material, calculate the distance to each feature point to create a coordinate map of each feature point, and acquire three-dimensional dimensions corresponding to the width, length, and thickness of the target scrap material based on this coordinate map. However, the method of acquiring dimension information is not limited to this example.

[0037] The auxiliary storage device 302 stores information necessary for the operation of the user terminal 102. For example, the auxiliary storage device 302 stores user information 500, scrap material image information 600, scrap material information 700, etc. This information may be some or all of the information related to the scrap material registered by the user, from the user information 500, scrap material image information 600, scrap material information 700, etc. stored in the management server 101. The auxiliary storage device 302 does not have to store some of the same information as the information stored in the auxiliary storage device 202 of the management server 101.

[0038] [Administrator terminal] Figure 4 shows an example of the hardware configuration of administrator terminal 103. The administrator terminal 103 is a terminal used by the administrator who manages the scrap material management service provided by the management server 101. The administrator terminal 103 consists of terminals such as mobile information terminals like smartphones and tablets, notebook PCs, and desktop PCs.

[0039] The administrator terminal 103 includes a main memory 401 and an auxiliary memory 402. The administrator terminal 103 also includes the processor 403 as described above, an input device 404, an output device 405, a camera 406, and a communication control unit 407.

[0040] The main memory 401 stores programs and applications such as the basic management module 411, image acquisition module 412, location information acquisition module 413, dimension information acquisition module 414, scrap material information output module 416, and reuse management module 417. The processor 403 executes these programs and applications to realize each functional element of the administrator terminal 103. These modules work in conjunction with the basic management module 211, image acquisition module 212, location information acquisition module 213, dimension information acquisition module 214, scrap material information output module 216, and reuse management module 217 of the management server 101, respectively, to perform processing in the administrator terminal 103 that corresponds to the processing performed by each functional element in the management server 101. Therefore, the functional elements of each of these modules may be the same as those of the management server 101 described above, and their explanation will be omitted. In addition, in the following explanation, the processing performed by each module in the administrator terminal 103 in conjunction with each module of the management server 101 may be omitted.

[0041] [Machine learning model server] The machine learning model server 104 provides estimation results based on machine learning. The machine learning model server 104 implements a machine learning model M and is configured to output estimation results for an input by having the processor execute a machine learning model driving application. For example, the machine learning model server 104 implements a machine learning model that has been trained to output classification results for materials and / or scraps based on image information of those materials and / or scraps. The classification content may consist only of major categories, or it may include major categories and at least one of the subcategories and minor categories within each category.

[0042] For example, if the scrap material is board material, the broad categories could include, for example, wood, lightweight aggregate, board material, panel material, etc. Further subcategories could include, for example, solid wood, laminated wood, hardwood, softwood, cypress, cedar, Japanese red pine (Douglas fir, Japanese red pine), zelkova, hemlock, paulownia, whitewood, walnut, pine, etc. For board material, examples could include plasterboard, reinforced board, fireproof board, water-resistant (waterproof) board, rock wool sound-absorbing board, calcium silicate board, decorative gypsum board, etc. For panel material, examples could include kitchen panels, decorative panels, etc. Below the broad categories, further subcategories could include, for example, Japanese larch, Yezo spruce, cedar, Japanese red pine, etc.

[0043] Furthermore, a second subcategory could include, for example, the quantity of boards (e.g., 1 board, 2 boards, 3 boards, etc.) or dimensions (e.g., length dimensions such as 900mm, 1820mm, 2420mm, 2730mm, etc.). Note that the classification method is not limited to these examples.

[0044] A machine learning model may consist of a single model trained to estimate only major categories, or a model trained to estimate major categories and their subcategories (and possibly even their minor categories). Alternatively, a machine learning model may be composed of one or more machine learning models combined. In this case, the model may be a combination of machine learning models trained to estimate, for example, the subcategories (and possibly their minor categories) for each major category. Another example is a combination of a first machine learning model that estimates major categories and a second machine learning model that estimates subcategories using the output of the first model as input. By using a combination of multiple machine learning models, highly accurate classification (estimation) can be achieved across a wide range of classifications.

[0045] Furthermore, for example, a machine learning model may be trained to estimate the subcategory (and even the subcategories) corresponding to each major category. Alternatively, for example, a machine learning model may be used that accepts user selection for major categories and estimates the corresponding subcategory, etc. This can suppress the occurrence of fundamental estimation errors by the machine learning model.

[0046] The machine learning model server 104 of this embodiment implements a machine learning model configured to output, for example, the type of scrap material as a major classification, the material of the scrap material as a medium classification, and the quantity and dimensions (width, length, thickness) of the scrap material as a second medium classification (for example, all at once) based on image information of the material and / or scrap material. However, the machine learning model server 104 may also be implemented by combining, for example, a first machine learning model trained to output information about the type of material and / or scrap material based on image information of the material and / or scrap material, a second machine learning model trained to output information about the material and / or scrap material based on image information of the material and / or scrap material, a third machine learning model trained to output information about the quantity of the material and / or scrap material based on image information of the material and / or scrap material, and a fourth machine learning model trained to output information about the dimensions of the material and / or scrap material.

[0047] In this embodiment, the machine learning model server 104 is provided independently of the management server 101 and is configured to communicate with each other, for example, via API technology (Application Programming Interface technology). The machine learning model server 104 may be configured as a computer server provided by cloud computing, for example, or it may be provided on the same computer as the management server 101. The first machine learning model, the second machine learning model, and the third machine learning model may be partially or entirely implemented on different servers.

[0048] [data] Figures 5-7 show examples of various types of information stored in the management server 101. Figure 5 shows an example of user information 500. User information 500 is information about users who manage scrap materials using the scrap material management service provided by the management server 101. User information 500 includes information such as user ID 511, user name 521, login password 522, contact information 523 (e.g., telephone number, email address, etc.), site address 524, scrap material ID group 525, scrap material ID group scheduled for storage 526, and requested scrap material ID group 527, and each is stored with attributes such as those exemplified by Value 520 associated with Key 510.

[0049] User ID 511 is information that identifies the user (e.g., site manager) who registers and stores scrap materials in the system, and may be, for example, an identification number (id) issued by this system, an employee identification number of a construction company associated with the user name, a site management number, etc. Also, for example, User Name 521 may be the name of the user (e.g., site manager), a personal nickname (e.g., contact_name), a business name of a sole proprietor (company_name), etc. Login Password 522 is the password required to log in to this system, Contact Information 523 is, for example, the user's email address, Site Address 524 is the address of the construction site managed by the user, and Scrap Material ID Group 525 is the identification information of one or more scrap materials stored at that construction site. That is, in this specification, for example, multiple "Scrap Material IDs" will be expressed as "Scrap Material ID Group". The same applies below. Note that the address of a site, etc., can be composed of a combination of, for example, prefecture information, city / ward / town / village information, and street address information (e.g., prefecture + city + address).

[0050] The storage-planned scrap ID group 526 is the identification information for one or more scraps expected to be generated at the construction site, and the requested scrap ID group 527 is the identification information for one or more scraps that the user wants to use at the construction site. Here, the scrap ID group 525 is, for example, identification information for scraps actually generated at the construction site, and the storage-planned scrap ID group 526 is, for example, identification information for pre-registering scraps that are expected to be generated at the construction site in the future. The requested scrap ID group 527 differs in that, if possible, it is identification information for scraps that the user wants to use from the scraps registered in this system. Note that the user information 500 does not necessarily have to include all of this information. For example, the user information 500 does not have to include the storage-planned scrap ID group 526 or the requested scrap ID group 527.

[0051] Figure 6 shows an example of scrap material image information 600. The scrap material image information 600 is information about images of scrap materials managed by this system. The scrap material image information 600 includes, for example, scrap material ID 611, image information 621, and pre-processed image information 622, and each is stored with a value such as the one exemplified by Value 620 associated with Key 610. However, the scrap material image information 600, such as image information 621 and pre-processed image information 622, does not necessarily need to be stored in the database long-term; for example, it may be stored temporarily until the first scrap material information described later is obtained.

[0052] The scrap material ID 611 is information that identifies the scrap material registered in this system, and is, for example, a unique identification number issued by this system. The scrap material ID 611 corresponds, for example, to an individual scrap material ID in the scrap material ID group 525. The image information 621 is image information of the scrap material, and the pre-processed image information 622 is image information obtained by applying the pre-processing described later to the image information 621. The scrap material image information 600 is associated with user information 500 via the scrap material ID 611, for example.

[0053] Figure 7 shows an example of scrap material information 700. Scrap material information 700 is information about scrap materials managed by this system, excluding scrap material image information 600. Scrap material information 700 includes, for example, scrap material ID 721, location information (latitude) 722, location information (longitude) 723, address information 724, type information 725, material information 726, dimension information 1 727, dimension information 2 728, dimension information 3 729 (optional and not required), quantity information 730, remarks information 731, deadline date and time information 732, and usage request information 733, with values ​​such as those exemplified by sample value 720 entered for each item name 710. Of this scrap material information 700, the information acquired by the image analysis module 215 is sometimes called "first scrap material information," and the other scrap material information is sometimes called "second scrap material information." In this embodiment, the first scrap material information includes type information 725, material information 726, dimension information 727-729, and quantity information 730.

[0054] The scrap material ID 721 is the same as the scrap material ID in the scrap material image information 600, and other scrap material information 700 is stored in association with the scrap material ID 721, and is also associated with the scrap material image information 600 and user information 500 via this scrap material ID. The location information (latitude) 722 and location information (longitude) 723 are information about the location (latitude and longitude) where the scrap material image information 621 was generated (i.e., photographed), respectively, and the address information 724 is information about the address corresponding to the location information (latitude) 722 and location information (longitude) 723, and can be composed of a combination of, for example, prefecture information, city / ward / town / village information, and street number information (e.g., m_prefecture + m_city + m_address). Type information 725, material information 726, dimension information 1-3 727-729, and quantity information 730 are information regarding the type, material, dimensions, and quantity of the scrap material, respectively, obtained by performing the analysis process described later based on image information 621 and / or pre-processed image information 622. Remarks information 731 is information regarding remarks related to the scrap material, deadline date and time information 732 is information regarding the date and time when the acceptance of usage requests related to the scrap material will be closed, and usage request information 733 is information indicating whether or not there are usage requests from other users for the scrap material.

[0055] Model information MI is the information necessary to operate the machine learning model M. Model information MI may include, for example, connection information for connecting to the machine learning model server 104, parameter information that characterizes the estimation process of the machine learning model M, etc. Parameter information is an element that determines the performance and behavior of the model, and may be, for example, one or more functional equations or variables that have been adjusted during the model's learning process. If the machine learning model M is, for example, a neural network, the parameter information will indicate information corresponding to the "weights" and "biases" of each neuron.

[0056] [Methods for managing scrap materials] The scrap material management method related to this technology will be explained based on an example of the operation of the scrap material management system 100. In the following, the technology will be explained using the example of a user accessing the management server 101 from a user terminal 102, registering scrap materials, and starting scrap material management.

[0057] Figure 8 shows an example of the scrap material management flow 800. The scrap material management flow 800 generally includes acquiring image information of scrap material (step S810), acquiring scrap material information (first scrap material information) that includes at least information about the type of scrap material based on this image information (step S820), outputting the scrap material information associated with the image information (step S830), evaluating whether to modify or approve the scrap material information (step S840), updating the scrap material information based on the modification information if it is to be modified (step S850), receiving a usage request (step S860), and, if a usage request is received, outputting that a usage request has been received (step S870).

[0058] The steps S840-S850 related to modifying the information in this embodiment, and the steps S860-S870 related to receiving usage requests, are additional elements and not essential steps. Each step will be described below.

[0059] (1. Acquisition of image information) Figure 13 shows an example of the scrap material information acquisition screen 1300. The scrap material information acquisition screen 1300 is a screen displayed on the user terminal 102 by the cooperation of the basic management module 211 of the management server 101 and the user management module 311 of the user terminal 102, for example, when a user registers their scrap material in the scrap material management system 100. Through this scrap material information acquisition screen 1300, the user can easily register their scrap material in the scrap material management system 100. For example, the user management module 311 assigns scrap material identification information (scrap material ID) to the scrap material registered through this scrap material information acquisition screen 1300.

[0060] The basic management module 211 and image acquisition module 212 of the management server 101 work in conjunction with the user management module 311 and image acquisition module 312 of the user terminal 102 to display (output) the scrap material information acquisition screen 1300 on, for example, the output device 305 of the user terminal 102, such as a display. The image acquisition module 212 also outputs scrap material information fields 1310, image information acquisition fields 1320, registration buttons 1330, etc., to the scrap material information acquisition screen 1300. In the scrap material information field 1310, the image acquisition module 212 outputs, for example, scrap material type information field 1311, dimension information field 1312, location information field 1313 (delivery location), quantity information field 1314, deadline date and time information field 1315, remarks information field 1316, etc.

[0061] The image acquisition module 212 acquires image information of the scrap material (step S810). The image information acquisition step in this embodiment includes acquiring second scrap material information (an example of scrap material information). Figure 9 shows an example of the image information acquisition flow 900 of scrap material according to one embodiment. The image information acquisition flow 900 generally includes acquiring image information of the scrap material (step S910), acquiring position information (step S920), and outputting the image information of the scrap material with the position information associated with it (step S930).

[0062] For example, if the image acquisition module 212 receives information from the user terminal 102 via the image information acquisition field 1320 indicating that "Activate Camera" has been selected, it will work in cooperation with the image acquisition module 312 of the user terminal 102 to activate the camera 306 of the user terminal 102, and will also work in conjunction with the location information acquisition module 213 to acquire image information 621 of the scrap material (step S910) and location information (step S920) via the camera 306 of the user terminal 102. Steps S910 and S920 can be performed in any order.

[0063] For example, the image acquisition module 212 launches the camera application on the user terminal 102 and, through the user's operation of the user terminal 102, acquires image information 621 of the scrap material and stores (outputs) it in the auxiliary storage device 202, associating it with the scrap material ID 611. The location information acquisition module 213 also uses the location information acquisition function of the user terminal 102 to acquire location information metadata of the user terminal 102 at the time of imaging (location information (latitude) 722, location information (longitude) 723) and stores (outputs) it in the auxiliary storage device 202, associating it with the scrap material ID 721.

[0064] Each module checks in advance whether the imaging function and location information acquisition function of the user terminal 102 are turned on, and if either is turned off, it requests the user terminal 102 to turn on those functions. For example, the location information acquisition module 213 displays the location information service settings screen of the user terminal 102 and requests that the location information service be turned on, for example, (a) only this time, (b) while using the scrap material management service, or (c) while using the camera. Then, if the location information service is turned on in any of (a) to (c), the image acquisition module 212 puts the user terminal 102 into a state where it can image the target scrap material with the camera 306.

[0065] As a result, the location information acquisition module 213 can associate location information metadata (latitude information, longitude information) and other scrap information 700 (second scrap information) with the image information 621 of the scrap material via the scrap material ID and record it (output to the auxiliary storage device 202). The location information acquisition module 213 also outputs the acquired location information metadata (latitude information, longitude information) to the location information field 1313.

[0066] Furthermore, if a user uploads image information 621 of scrap material via the image information acquisition field 1320 on the scrap material information acquisition screen 1300, the image acquisition module 212 may acquire the image information 621 by accepting the uploaded image information 621. When uploading image information 621, the image file may be accepted via a file selection dialog, or an image file may be accepted by dragging and dropping it into the image information acquisition field 1320. In this case, location information (e.g., longitude information, latitude information) is pre-associated with the image information 621. The image acquisition module 212 can acquire the image information 621 and location information together.

[0067] Furthermore, each field on the scrap material information acquisition screen 1300 is configured to accept user input, for example. For instance, the basic management module 211 of the management server 101 can acquire the deadline date and time information 732 and the remarks information 731 by accepting user input for the deadline date and time information field 1315 and the remarks information field 1316 on the scrap material information acquisition screen 1300.

[0068] Furthermore, if, for example, image information of the scrap material cannot be obtained, the image analysis module 215 cannot obtain the scrap material type information field 1311, the dimension information field 1312, the quantity information field 1314, etc. In such cases, for example, the basic management module 211 can obtain this scrap material information by accepting input of this scrap material information from the user to the scrap material information acquisition screen 1300 on the user terminal 102.

[0069] Figure 14 shows another example of the scrap material information acquisition screen 1400. The basic management module 211 displays the scrap material information acquisition screen 1400 on the user terminal 102's display and outputs an unprocessed image display field 1410, a pre-processed image display field 1420, and a scrap material information display field 1430 on this scrap material information acquisition screen 1400. The basic management module 211 may also display this scrap material information acquisition screen 1400 as a modal window or the like, overlaid on top of the scrap material information acquisition screen 1300. Here, the basic management module 211 includes a pre-processed result field 1440 showing scrap material information based on a pre-processed image, and an unprocessed result field 1450 showing scrap material information based on an unprocessed image without preprocessing, in the scrap material information display field 1430. The basic management module 211 also outputs display fields for each scrap material information and "Select this result" buttons 1446 and 1456 in the pre-processed result field 1440 and the unprocessed result field 1450, respectively.

[0070] The image acquisition module 212 may be configured to, for example, when it acquires image information 621, display the image of the scrap material represented by the acquired image information 621 in real time in the unprocessed image display area 1410. Furthermore, the location information acquisition module 213 may be configured to, for example, display address information acquired based on location information in the location information display area 1445 within the scrap material information display area 1430.

[0071] Figure 10 shows an example of the 1000-flow chart for acquiring address information. Furthermore, the location information acquisition module 213 can execute the address information acquisition flow 1000 at any time after step S920. The address information acquisition flow 1000 is a processing flow for converting latitude and longitude information acquired as location information into address information. In the address information acquisition flow 1000, the location information acquisition module 213 includes acquiring location information 722 and 723 (step S1010), performing reverse geocoding processing (step S1020), and acquiring address information (step S1030).

[0072] The location information acquisition module 213 is configured to cooperate with an external geocoding service, for example, via API technology. The location information acquisition module 213 acquires location information 722 and 723 from the auxiliary storage device 202 and provides this to the geocoding service, thereby acquiring address information 724 corresponding to the location information 722 and 723. The location information acquisition module 213 stores (outputs) the acquired address information 724 as scrap material information 700 (second scrap material information) in the auxiliary storage device 202.

[0073] A geocoding service is a function that allows you to obtain place names, such as addresses, from a location represented by latitude and longitude, and can utilize services such as the Google Maps Geocoding API (Google) or the Temporary Geocoding API (Mapbox). However, this system 100 may also have a database (DB) that associates location information 722,723 with address information 724.

[0074] (2. Obtaining information on leftover materials) Next, the image acquisition module 212 acquires scrap material information 700 (first scrap material information) based on the image information 621 of the scrap material (step S820). Figure 11 shows an example of the scrap material information acquisition flow 1100. The scrap material information acquisition flow 1100 includes acquiring image information 621 of the scrap material (step S1110), applying noise reduction processing to the image information (step S1120), applying background removal processing to the image information (step S1130), adjusting the contrast of the image information (step S1140), using a machine learning model to acquire information regarding the type of scrap material, information regarding the material of the scrap material, information regarding the quantity of scrap material, and information regarding the dimensions of the scrap material from the unprocessed and preprocessed image information (step S1150), and outputting the acquired information from the unprocessed and preprocessed image information (step S1160).

[0075] (2-1. Pre-treatment process) The scrap material information acquisition step of this embodiment includes pre-processing steps S1120 to S1140 for pre-processing image information 621. Pre-processing steps S1120 to S1140 are not essential steps in this technology and can be performed additionally. The order in which pre-processing steps S1120 to S1140 are performed can be, for example, S1120, S1130, and S1140, but is not limited to this. Furthermore, the pre-processing of image information 621 is not limited to the pre-processing steps S1120 to S1140 shown below, but may be other processing steps, or may be part of pre-processing steps S1120 to S1140, or any combination of pre-processing steps S1120 to S1140 with other processing steps may be arbitrarily performed.

[0076] The image analysis module 215 acquires image information 621 of the scrap material from the auxiliary storage device 202 and applies noise reduction processing to the acquired image information 621 (step S1120). Noise reduction processing includes, for example, applying an averaging filter that blurs and smooths the image. An example of an averaging filter is a Gaussian filter. For example, a Gaussian filter (Gaussian Blur) and a median filter (Median Blur) may be applied consecutively. This makes it possible to blur the image (i.e., reduce noise) while retaining more information about the vicinity of each pixel that makes up the image.

[0077] The image analysis module 215, for example, applies background removal processing to the pre-processed image information 622 that has undergone noise reduction processing (step S1130). Background removal processing is a process that extracts only the scrap material that is the target of management from all objects appearing in the image and deletes the information of the parts other than the scrap material. Specifically, as part of the background removal processing, for example, the pre-processed image information 622 is converted to grayscale, then binarized by converting it to 0 (black) and 1 (white) based on a threshold, and by detecting the contour (contour of the scrap material) using edge analysis, for example, the area outside the contour is judged to be the background and the background can be deleted. In this case, the threshold for binarization can be determined by, for example, the Otsu method. Alternatively, the background may be deleted using a mask (for example, a chroma key mask).

[0078] The image analysis module 215, for example, applies contrast adjustment processing to the preprocessed image information 622 that has undergone background removal processing (step S1140). Contrast adjustment processing involves appropriately adjusting the brightness (difference in brightness) of the image to make the details and features of the image clearer. One example of a contrast adjustment method is the CLAHE (Contrast Limited Adaptive Histogram Equalization) algorithm, which performs histogram equalization for each local region. This makes it possible to appropriately adjust the contrast (enhance features, optimize brightness) for each small region of the image of the scrap material, for example.

[0079] The preprocessing applied to image information by the image analysis module 215 is not limited to the above examples. In addition to the above processing, the image analysis module 215 can arbitrarily incorporate the following processes into the image information: noise reduction processing to reduce image blur and fine noise, resizing processing to convert to the image size proposed to the machine learning model used, edge enhancement (sharpening) processing to emphasize the appearance features of the scrap material, perspective transformation processing to correct camera distortion, gamma correction processing to adjust brightness and contrast, etc. For example, if the scrap material is wood, suitable combinations include noise reduction processing, grayscale conversion processing to extract only brightness information and emphasize the wood grain, histogram uniformization processing to increase contrast and make the wood grain easier to see, edge enhancement processing to emphasize the features of the wood grain, binarization processing to clarify the shape and contour of the wood grain, and background removal processing to extract only the wood part.

[0080] The image analysis module 215 can, for example, acquire the pre-processed image information 622 obtained by performing the above pre-processing and store (output) it as scrap material image information 600 in the auxiliary storage device 202. The image analysis module 215 may also be configured to, for example, display the image of the scrap material represented by the pre-processed image information 622 in the pre-processed image display field 1420 each time the image information 621 or the pre-processed image information 622 is pre-processed.

[0081] (2-2.Analysis process) Next, the image analysis module 215 acquires scrap information (first scrap information) that includes at least information about the type of scrap material, based on the image information 621 and / or the preprocessed image information 622 (step S820). The scrap information acquisition step in this embodiment includes, for example, an analysis step S1150 (which may be an estimation step) in which the image information 621 and / or the preprocessed image information 622 are analyzed using a machine learning model. In step 1150, the image analysis module 215 acquires the image information 621 and / or the preprocessed image information 622 from, for example, the auxiliary storage device 202 and transmits them to, for example, the machine learning model server 104.

[0082] Figure 12 shows another example of an estimated flow of 1200. The machine learning model server 104, for example, acquires image information 621 or preprocessed image information 622 from the management server 101 (step 1210). The machine learning model server 104, for example, supplies the acquired image information 621 and / or preprocessed image information 622 to the machine learning model and outputs information regarding the type of scrap material, the material of the scrap material, the quantity of the scrap material, and the dimensions of the scrap material (an example of first scrap material information) (step 1220). The machine learning model server 104 transmits the outputted information regarding the type of scrap material, material, quantity, and dimensions of the image information 621 and / or preprocessed image information 622 (first scrap material information) to the management server 101 (step 1230).

[0083] Here, the machine learning model is a machine learning model that has been trained to output information about the type of material and / or scrap, information about the material of the scrap, information about the quantity of the scrap, and information about the dimensions of the scrap, based on image information of the material and / or scrap.

[0084] For example, various machine learning models can be used as pre-training models, capable of recognizing and processing images and videos. Examples of such machine learning models include large-scale language models (LLMs) using deep learning (e.g., the Gemini model) used in the field of natural language processing (NLP). While not limited to this, supervised learning can be employed, for example, using supervised learning where image information of scrap materials is tagged with the correct output (in this case, type, material, and quantity) as training data. Control parameters for the trained model can be stored, for example, as model information MI in the auxiliary storage device 202 or the machine learning model server 104.

[0085] As a result, the image analysis module 215 of the management server 101 can acquire information regarding the type, material, quantity, and dimensions of the scrap material for the image information 621 and / or the pre-processed image information 622 (step S1150). In this embodiment, information regarding the type, material, quantity, and dimensions of the scrap material is acquired for both the image information 621 and the pre-processed image information 622. Subsequently, the scrap material information output module 216 outputs the first scrap material information associated with the image information 621 and / or the pre-processed image information 622, respectively (step S830). The scrap material information output module 216 outputs the image information 621 and / or the pre-processed image information 622 to the unprocessed image display field 1410 and / or the pre-processed image display field 1420 of the scrap material information acquisition screen 1400, respectively, and also outputs information related to the acquired type, material, quantity, and dimensions to the corresponding fields of the results field 1440 with pre-processing and the results field 1450 without pre-processing, respectively.

[0086] (2-3. Approval confirmation process) Next, the basic management module 211 evaluates whether to modify or approve the scrap material information 700 (process S840). For example, the scrap material information fields in the result field 1440 with pre-processing and the result field 1450 without pre-processing are configured to accept modifications of values ​​(information related to type, material, quantity, and dimensions) by the user operating the user terminal 102. When the basic management module 211 receives a modification of the output value from user input (in step S840 (i)), it updates the value of the corresponding scrap material information field based on the modified information (step S850) and outputs (displays) the modified scrap material information 700 in association with the image information 621 and / or the pre-processed image information 622 (step S830).

[0087] Furthermore, when the basic management module 211 receives a selection from either the result field 1440 with preprocessing or the result field 1450 without preprocessing (in step S840 (ii)), it determines that the selected scrap information has been approved as the scrap information 700 for the target scrap, and records the selected scrap information (in this case, information relating to type, material, quantity, and dimensions) as scrap information 700 in the auxiliary storage device 202. For example, if the selection from the "Select this result" button 1446 is received, the scrap information estimated (output) by the machine learning model based on the preprocessed image information 622 is adopted. Also, for example, if the selection from the "Select this result" button 1456 is received, the scrap information estimated (output) by the machine learning model based on the unprocessed image information 621 is adopted. Furthermore, the scrap material information output module 216 deletes the scrap material information acquisition screen 1400 and displays the selected scrap material information (in this case, information related to type, material, quantity, and dimensions) as scrap material information 700 in the corresponding field of the scrap material information acquisition screen 1300. When the registration button 1330 on the scrap material information acquisition screen 1300 is selected, the acquisition of information related to the target scrap material is completed.

[0088] In estimating scrap material information 700 using a machine learning model, for example, if the scrap material is a board, preprocessing the image information may actually make it more difficult to obtain accurate estimation results. This is because, in the case of boards, it is extremely difficult to classify the type and material of the scrap material by its shape and surface morphology, or to classify the pattern and texture of the board surface from a single image. Depending on the original image as it was captured, preprocessing may alter the image in a way that leads the machine learning model to make an incorrect estimation. Therefore, by providing an opportunity for the photographer of the scrap material to make an actual judgment, it is possible to obtain scrap material information 700 easily while ensuring accuracy.

[0089] (3. Process for utilizing scrap materials) By using this scrap material management system 100, for example, scrap materials held by one user can be effectively utilized by another user. Figure 15 shows an example of the scrap material utilization screen 1500. The scrap material utilization screen 1500 is a screen that displays information about each scrap material registered in the scrap material management system 100, and can be viewed by all users of the scrap material management system 100.

[0090] The reuse management module 217 outputs (displays) the scrap material utilization screen 1500 to the user terminal 102 of a second user, for example, in response to a request from the user terminal 102 of a second user. The reuse management module 217 displays, for example, a scrap material information field 1510, a scrap material image field 1520, and an application button 1530 on the scrap material utilization screen 1500. The scrap material image field 1520 outputs the scrap material information 700 stored in the auxiliary storage device 202.

[0091] The process for utilizing scrap materials includes, for example, receiving a request for the use of scrap materials from a second user's (user's) user terminal (step S860), and outputting usage request information to the first user's (provider's) user terminal related to the scrap material for which the usage request was received (step S870). The reuse management module 217 receives a request to use scrap materials managed by the scrap material management system 100, for example, from a second user (user) (step S860). When the application button 1530 on the scrap material usage screen 1500 is selected, the reuse management module 217 obtains information from the user using that user terminal indicating a request to use the scrap materials displayed on the scrap material usage screen 1500. If the reuse management module 217 has received a request, it can display (output) that the request has been received on the scrap material usage screen 1500 or store (output) it in the auxiliary storage device 202.

[0092] Furthermore, the reuse management module 217 transmits information to the user terminal of the first user (providing user) who provides the requested scrap material, indicating that a request for use of that scrap material has been made. This allows one user (providing user) and another user (using user) to communicate regarding the transfer of scrap material, and enables one user to transfer scrap material to another user. As a result, scrap material held by one user can be effectively utilized by another user without being discarded.

[0093] The reuse management module 217 may determine that a contract for the delivery of scrap materials has been concluded by transmitting information to the user terminal of the first user (provider) indicating that a request for the use of scrap materials has been made. Alternatively, the reuse management module 217 may be configured to output an approval button to the user terminal of the first user, along with information indicating that a request for the use of scrap materials has been made. The reuse management module 217 may then determine that a contract for the delivery of scrap materials has been concluded when the approval button is selected on the user terminal of the first user (provider) and approval information indicating that the approval button has been selected is received from the user terminal of the first user.

[0094] [Structure and Effects] In the above embodiment, the management server 101 (an example of a scrap material management device) includes an image acquisition module 212 (image acquisition unit) that acquires image information 621 of scrap materials, an image analysis module 215 (image analysis unit) that acquires scrap material information 700, including at least scrap material type information 725 (information regarding the type of scrap material), based on the image information 621, and a scrap material information output module 216 (scrap material information output unit) that outputs the scrap material information 700 associated with the image information 621. With this configuration, the management server 101 can acquire information such as the type of scrap material associated with the image information 621 simply by acquiring image information 621 of scrap materials from the user. As a result, the burden on the user is reduced, and information regarding scrap materials can be acquired.

[0095] In the above embodiment, the image analysis module 215 of the management server 101 provides image information 621 to a machine learning model that has been trained to output at least one piece of information from among the type of material and / or scrap material, material information, quantity information, and dimensions information, based on image information of the material and / or scrap material. As a result, at least one piece of information from among the type of scrap material, material information, quantity information, and dimensions information is obtained as output from the machine learning model. With this configuration, scrap material information 700 (for example, information on type) such as information on the type, material, quantity, and dimensions of the scrap material can be obtained with reduced burden such as user input.

[0096] In the above embodiment, the image analysis module 215 of the management server 101 applies at least one of the following processes to the image information 621: noise reduction, background removal, and contrast adjustment, and then acquires scrap material information 700 based on the pre-processed image information 622. With this configuration, the accuracy of the estimation of the above-mentioned type information 725, material information 726, quantity information 730, etc. by the machine learning model can be improved.

[0097] In the above embodiment, the image analysis module 215 of the management server 101 is configured to obtain pre-processed image information 622 (processed image information) by applying at least one of the following processes to the image information 621: noise reduction, background removal, and contrast adjustment. It is also configured to obtain scrap information for both the unprocessed image information 621 and the pre-processed image information 622. Furthermore, the image analysis module 215 is configured to accept the selection of either scrap information 700 based on the unprocessed image information or scrap information 700 based on the pre-processed image information 622. This reduces the burden on scrap providers in collecting and registering scrap information, while enabling the acquisition of more appropriate scrap information 700.

[0098] In the above embodiment, the management server 101 further includes a location information acquisition module 213 (location information acquisition unit) that acquires location information 722,723 related to the location where the image information 621 was generated, and the scrap material information output module 216 (scrap material information output unit) outputs the image information 621 with the scrap material information 700 and the location information 722,723 associated with it. With this configuration, the management server 101 can acquire location information 722,723 as the location of the scrap material while suppressing the burden on the user. Furthermore, if the location information 722,723 is information acquired using GPS or the like, the reliability of the information regarding the scrap material can be increased.

[0099] In the above embodiment, the location information acquisition module 213 acquires address information 724 related to the location where the image information 621 was generated, based on the location information 722, 723, and the scrap information output module 216 (scrap information output unit) outputs the image information 621 with the scrap information 700 and the address information 724 in association. With this configuration, the management server 101 can acquire the location information 722, 723 as the location of the scrap in the form of address information 724 that is easy for people to understand, while minimizing the burden on the user.

[0100] In the above embodiment, the management server 101 further includes a reuse management module 217 (reuse management unit) that, upon receiving a request to use scrap material, outputs usage request information indicating that a request for use of scrap material has been received, in association with the scrap material information 700. For example, when the management server 101 receives a request to use (i.e., an offer to take possession) from a second user for scrap material managed by a first user and registered in the scrap material management system 100, the management server 101 stores information indicating that a usage request has been received (usage request information 733) in the auxiliary storage device 202, and notifies the first user that usage request information for the scrap material has been received. The scrap material management system 100 also outputs (displays) information indicating that usage request information for the scrap material has been received, for example, on the scrap material usage screen of the scrap material management system 100. With this configuration, it is possible to provide a mechanism that allows other users to easily use scrap material managed by one user.

[0101] <Variation> (1) In the above embodiment, the first scrap information acquired by the image analysis module 215 is type information 725, material information 726, dimension information 727-729, and quantity information 730. This first scrap information was acquired from the machine learning model server 104 by the image analysis module 215 providing image information to the machine learning model server 104. The machine learning model server 104 was configured to output the first scrap information when image information was input to one machine learning model. However, the first scrap information acquired by the image analysis module 215 may be configured to be output by two or more machine learning models based on the image information. For example, the machine learning model server 104 may include a first machine learning model that takes image information as input and is trained to output type information 725 and material information 726, and a second machine learning model that takes image information as input and is trained to output dimension information 727-729 and quantity information 730.

[0102] In this case, for example, a machine learning model capable of classifying and identifying objects with relatively high accuracy can be used as the first machine learning model before training, and a machine learning model capable of estimating the quantity and measurement values ​​of objects with relatively high accuracy can be used as the second machine learning model before training. The image analysis module 215 may be configured to send, for example, image information, a first request phrase that causes the first machine learning model to output type information 725 and material information 726 based on this image information, and a second request phrase that causes the second machine learning model to output dimension information 727-729 and quantity information 730 based on this image information to the machine learning model server 104. As a result, the image analysis module 215 can obtain type information 725, material information 726, dimension information 727-729, and quantity information 730 with higher accuracy from the machine learning model server 104.

[0103] (2) In the above embodiment, the first scrap information acquired by the image analysis module 215 is type information 725, material information 726, dimension information 727-729, and quantity information 730. However, the first scrap information acquired by the image analysis module 215 may be type information 725, material information 726, and quantity information 730, and the dimension information acquisition module 214 may be configured to acquire dimension information 727-729.

[0104] Figure 16 shows another example of the image information acquisition flow 1600 for scrap material. The image information acquisition flow 1600 may include acquiring image information 621 of the scrap material (step S1610), acquiring position information (step S1620), outputting the image information of the scrap material with the position information associated (step S1630), acquiring dimensional information of the scrap material (step S1640), and outputting the image information of the scrap material with the dimensional information associated (step S1650). Here, steps 1610 to 1630 are the same as steps 910 to 930 of the image information acquisition flow 900 in the above embodiment, so a further explanation is omitted. Also, steps 1620 and 1640 are not in any order, and steps 1630 and 1650 may be executed after steps 1620 and 1640, respectively, and some of these may be executed simultaneously or in parallel.

[0105] For example, when the image acquisition module 212 receives information from the user terminal 102 via the image information acquisition field 1320 indicating that "Start Camera" has been selected, it cooperates with the image acquisition module 312 of the user terminal 102 to start the camera 306 of the user terminal 102. The dimension information acquisition module 214 may also be configured to cooperate with the dimension information acquisition module 314 of the user terminal 102 to acquire the dimensions of the scrap material. For example, the dimension information acquisition module 214 starts the measurement application of the user terminal 102 and measures the width dimension (example of dimension information 1), length dimension (example of dimension information 2), and thickness dimension (example of dimension information 3) of the scrap material. The dimension information acquisition module 214 stores (outputs) the measured dimension information 1 to 3 in the auxiliary storage device 202, associating them with the scrap material ID 721. Even with this configuration, the management server 101 can acquire the dimension information of the scrap material while minimizing the burden on the user.

[0106] The dimension information acquisition module 214 may be configured to check in advance whether the measurement function of the user terminal 102 is turned on, and if it is turned off, to request that the measurement function be turned on. The details are the same as for the imaging function and the position information acquisition function. In addition, the dimension information acquisition module 214 may be configured to display, for example, the process of measuring the dimensions of the scrap material by the measurement application in real time on the scrap material information acquisition screen 1300.

[0107] (3) In the above embodiment, the machine learning model server 104 was equipped with one machine learning model, and this one machine learning model was configured to estimate the type, material, quantity, and dimensions of the scrap material based on the image information of the scrap material. However, the machine learning model server 104 may be equipped with two or more machine learning models, and these two or more machine learning models may estimate the type, material, quantity, and dimensions of the scrap material based on the image information of the scrap material.

[0108] Figure 17 shows another example of an estimated flow of 1700. The estimation flow 1700 can be executed, for example, in place of step S1220 of the estimation flow 1200 in the above embodiment. That is, the image analysis module 215 acquires image information 621 and / or preprocessed image information 622 from the auxiliary storage device 202 (step S1210), and acquires information about the type of scrap material by supplying it to, for example, a first machine learning model (step S1710). The image analysis module 215 also acquires information about the material of the scrap material by supplying the above information to, for example, a second machine learning model (step S1720). The image analysis module 215 also acquires information about the quantity of scrap material by supplying the above information to, for example, a third machine learning model (step S1730). The image analysis module 215 may also be configured to store (output) the acquired type information 725, material information 726, and quantity information 730 to the auxiliary storage device 202 as, for example, scrap material information 700 (step S1230).

[0109] In this case, the first machine learning model is a machine learning model trained to output information about the type of material and / or scrap based on image information of the material and / or scrap. Examples of scrap types include wood, lightweight aggregate, board material, panel material, etc. Furthermore, the second machine learning model is a machine learning model trained to output information about the material of the material and / or scraps based on image information of the material and / or scraps. For example, if the scraps are wood boards, the materials could be solid wood, laminated wood, hardwood, softwood, etc. Furthermore, the third machine learning model is a machine learning model trained to output information about the quantity of material and / or scraps based on image information of the material and / or scraps. For example, if the scraps are wood boards, the quantity could be 1, 2, 3, 4, ...

[0110] The order in which the analysis steps S1710 to S1730 are performed can be, for example, S1710, S1720, and S1730, but these steps can be performed in any order. For example, they may be performed as asynchronous processes, executing the next step without waiting for the completion of the previous step, or they may be executed simultaneously. Furthermore, the analysis of the image information 621 or the pre-processed image information 622 is not limited to the above analysis steps S1710 to S1730, but may be performed in other analysis steps, or as part of analysis steps S1710 to S1730, or any combination of analysis steps S1710 to S1730 with other analysis steps may be used. This allows for obtaining highly accurate estimation results in the subsequent analysis (which may be an estimation) stage. It also improves the accuracy of classification in individual machine learning models.

[0111] (4) The first, second, and third machine learning models may be deployed on a single machine learning model server 104. However, one or more of the first, second, and third machine learning models may be built on different machine learning model servers. This allows estimation results from the first, second, and third machine learning models to be obtained in a shorter time.

[0112] (5) In addition, the first, second, and third machine learning models were deployed on a machine learning model server 104 separate from the management server 101. However, at least one of the first, second, and third machine learning models may be provided on the management server 101.

[0113] (6) The scrap material management system 100 may be configured to obtain a system usage fee (hereinafter sometimes simply referred to as a usage fee) from at least one of the first user (providing user) and the second user when scrap material provided by the first user (providing user) is provided to the second user (using user) via the system and reused. The management server 101 may, for example, include a billing module that manages the usage fee when the system is used.

[0114] Figure 19 shows another example of the hardware configuration of the management server 101. In the modified example, the management server 101 may further include, for example, a billing module 218, billing information 2000, and a building materials information database. For example, the main memory 201 of the management server 101 stores the program and application for the billing module 218, and the billing module 218 is functionally realized by the execution of this program and application by the processor 203. In addition, the auxiliary memory 202 of the management server 101 stores the billing information 2000 and the building materials information database. Note that the management server 101 in the modified example shown in Figure 19 may be the same as in the above embodiment except that it further includes the billing module 218, billing information 2000, and building materials information database, and a further explanation of the same configuration and effects will be omitted.

[0115] In addition to the functions described in the above embodiment, the reuse management module 217 is configured to accept approval of requests for the use of scrap materials (surplus materials). The reuse management module 217 is also configured to accept information indicating that the transfer of scrap materials from the first user (provider) to the second user (user) has been completed.

[0116] For example, when the reuse management module 217 receives a request from the second user terminal 102B to use scrap material identified by a predetermined scrap material ID, it outputs information indicating that there is a request to use the scrap material, and an approval button for the request, to the first user terminal 102A, which belongs to the first user who registered the scrap material identified by the scrap material ID. When the reuse management module 217 receives a selection signal for the approval button from the first user terminal 102A, it determines, for example, that the reuse of the scrap material identified by the predetermined scrap material ID has been decided (for example, that a delivery contract has been concluded). Then, when the reuse management module 217 receives signals indicating the completion of the transfer from both the first user terminal 102A and the second user terminal 102B, it determines that the delivery of the scrap material identified by the predetermined scrap material ID has been completed.

[0117] The reuse management module 217 may be configured to accept cancellation requests for the delivery contract from the first user terminal 102A and / or the second user terminal 102B. In this case, the reuse management module 217 may determine that the delivery contract has been canceled when another terminal approves the cancellation request. It may also be configured to automatically determine that the delivery is complete if no signal is received after a predetermined period has elapsed since the conclusion of the delivery contract.

[0118] The billing module 218 is an element that manages billing related to the scrap material management system 100. For example, when the reuse management module 217 determines that the delivery of scrap material identified by a predetermined scrap material ID has been completed, the billing module 218 executes billing processing (including invoice processing) related to the delivery of said scrap material.

[0119] The billing module 218 may be configured to estimate, for example, the price of a scrap material identified by a predetermined scrap material ID and the cost required to dispose of the scrap material, based on scrap material information 700. The billing module 218 may also refer to a building materials information DB, described later, to obtain information on market prices and disposal costs based on the type, material, dimensions, etc., of the scrap material. The billing module 218 also calculates the amount to be charged to at least one of the first user (provider) and the second user (user) based on this information. The billing module 218 may then output information regarding the amount calculated for the use of this system to at least one (for example, both) of the first user terminal 102A related to the first user and the second user terminal 102B related to the second user, and bill accordingly.

[0120] For example, when scrap material registered in the scrap material management system 100 is transferred from the first user (provider) to the second user (user), the billing module 218 charges at least one of the first user terminal 102A and the second user terminal 102B for the use of this system. The billing module 218 may also initiate the following billing process (for example, the billing information acquisition flow described later) when the reuse management module 217 determines that a delivery contract for scrap material identified by a predetermined scrap material ID has been concluded. This promotes the effective use of scrap material while recovering the maintenance costs of the system.

[0121] Furthermore, the billing module 218 may be configured to accept requests for adjustments to the billing amount from at least one of the first user (provider) or the second user (user). The billing module 218 may, for example, accept a request for adjustment of the billing amount, evaluate whether the request is valid, and if it is valid, adjust the billing amount in accordance with the request (for example, recalculate and change it). The billing module 218 may, for example, output a message indicating that the request is invalid if it evaluates the request as invalid, and be configured to accept the request again. The billing module 218 may, for example, set an upper limit on the number of requests it can accept per transaction or per predetermined unit (for example, a unit period such as one month, or a unit number such as 100 units).

[0122] The building materials information database includes information on the type, material, dimensions, etc., of various building materials, as well as information on their prices. The building materials information database may also include, for example, information on the cost of disposing of each building material (e.g., disposal unit price). This building materials information database may also include information that can be associated with, for example, information on scrap materials (building materials) used to train the machine learning model implemented in the machine learning model server 104 in the above embodiment. The building materials information database may include, for example, image information of scrap materials (building materials), information on the type, material, and quantity of the scrap materials, information on the price of the building materials (e.g., price per unit), and information required for the disposal of the building materials. The building materials information database may also include, for example, information corresponding to sales catalog information for various building materials or price lists of waste disposal companies.

[0123] Figure 20 shows an example of billing information 2000. The billing information 2000 is information used to perform billing related to the scrap material management system 100. The billing information 2000 is stored, for example, in the auxiliary storage device 202. The billing information 2000 includes, for example, billing ID 2021, user ID 2022, billing category information 2023, payment information 2024, reduction amount information 2025, billing rate information 2026, billing amount information 2027, billing month 2028, occurrence date 2029, status 2030, etc., with values ​​such as those shown in sample value 2020 for each item name 2010 being entered. These billing information 2000 items are associated with each other, for example, by billing ID 2021.

[0124] The billing ID 2021 is an identifier used to uniquely identify billing information generated in this system. The billing ID 2021 is generated, for example, when the reuse of scrap material is decided (for example, when a delivery contract is concluded). The billing ID 2021 is created for each of the following: the billing information related to the provider of the scrap material to be reused (first user) and the billing information related to the user of the scrap material to be reused (second user). User ID 2022 is information that identifies the user subject to billing. User ID 2022 may be, for example, user identification information relating to the provider of scrap materials (first user) or user identification information relating to the user of scrap materials (second user). Billing category information 2023 indicates whether the user identified by user ID 2022 is a provider (first user) or a user (second user).

[0125] Payment information 2024 is information that identifies the payment method of the user being charged, and is, for example, information that enables the execution of a transaction. Payment information 2024 may be, but is not limited to, credit card information, debit card information, electronic payment information, bank account information, or tokenized identification information thereof. Payment information 2024 may be, for example, user input information obtained from user terminal 102 and may be associated with user ID 2022.

[0126] Reduction Information 2025 is information regarding the costs (reduction amount) saved by reusing scrap materials. For example, depending on the billing category information 2023, Reduction Information 2025 is calculated for scrap material providers (first users) based on at least one of the following costs (e.g., the sum of these) that would be incurred if the scrap materials were disposed of: processing costs (disposal costs), storage costs, transportation costs, etc. For example, for scrap material users (second users), Reduction Information 2025 is calculated based on at least one of the following costs (e.g., the sum of these) that would be incurred if the scrap materials were newly purchased: purchase costs, delivery costs, etc. If the waste materials were transferred for a fee, the transaction amount may also be taken into consideration.

[0127] The billing rate information 2026 is a value that shows the percentage of the billing target that is charged (billing rate). The billing target may be, for example, the reduction amount information 2025, or the transaction amount if waste materials are transferred for a fee. This billing rate may be set to the same amount for all users, or it may be set to different amounts depending on arbitrary conditions (for example, each user's usage rate of this system or the company they belong to).

[0128] Billing Information 2027 is information regarding the billing amount to be charged to the billed user. Billing Information 2027 can be calculated, for example, based on Reduction Information 2025 and Billing Rate Information 2026.

[0129] The billing month 2028 indicates the period for which billing is performed. For example, if billing is done monthly, billing month 2028 is expressed in year-month format and can be used for monthly billing processing. The occurrence date 2029 indicates the date on which the billing information was generated. The occurrence date 2029 can be set based on, for example, the date on which the transaction related to the provision and use of scrap materials was concluded, or the date on which the billing information was finalized. Status 2030 is information indicating the processing status of the billing information. Status 2030 indicates a state such as "Not billed," "Billed," or "Paid," and the progress of billing processing can be checked and the billing processing can be controlled based on this status.

[0130] Note that the billing information 2000 is not limited to the above example, as long as it is a combination of information that enables billing to the scrap material provider (first user) and / or user (second user). The billing module 218 can, for example, output the corresponding billing information 2000 for each user to the user terminal 102 as a billing information table or the like.

[0131] Figure 21 shows an example of negotiation information 2100. Negotiation information 2100 is information used to respond to billing negotiations regarding the scrap material management system 100. Negotiation information 2100 is stored, for example, in the auxiliary storage device 202. Negotiation information 2100 includes, for example, negotiation ID 2121, billing ID 2122, negotiating user ID 2123, desired billing rate information 2124, determined billing rate information 2125, negotiation content information 2126, negotiation deadline information 2127, occurrence date 2128, status 2129, etc., and values ​​such as the sample value 2120 are entered for each item name 2110. These negotiation information items 2100 are associated with each other, for example, by negotiation ID 2121.

[0132] Negotiation ID 2121 is an identifier used to uniquely identify negotiation information generated in this system. Negotiation ID 2121 is used to identify negotiations regarding billing conditions for off-waste material transactions. The billing ID 2122 is identification information for uniquely identifying the billing information subject to negotiation. The billing ID 2122 is used to identify the billing information 2000 to which the result of the negotiation is reflected. The billing ID 2122 may be the same as, for example, the billing ID 2021 in the billing information 2000, and for example, the negotiation information 2100 and the billing information 2000 can be associated via the billing ID 2122. Alternatively, for example, the billing ID 2122 may be information that identifies some or all of the billing information 2000 related to the user.

[0133] Negotiation User ID 2123 is identification information used to identify the user who is the subject of the negotiation. Negotiation User ID 2123 indicates either the providing user or the user, and is associated with user information registered in this system. Desired billing rate information 2124 is information indicating the billing rate proposed by the negotiating user. Desired billing rate information 2124 is used as the initial condition or desired billing rate applied to the reduction amount, transaction amount, etc. The determined billing rate information 2125 is information that shows the billing rate determined as a result of negotiations. The determined billing rate information 2125 can be determined, for example, based on multiple desired billing rate information, negotiation details, or predetermined conditions set by the system, and is reflected in the billing information table.

[0134] Negotiation content information 2126 is information presented by the negotiating user or administrator that indicates the conditions, reasons for adjustment, or grounds to be considered in the negotiation. Negotiation content information 2126 may include, for example, the following: • Preferential conditions applicable when purchasing scrap materials for the first time (e.g., negotiated rates, quantity discounts, and terms of continued business). • Preferential conditions applicable when disposing of scrap materials (e.g., relative rates, collection conditions, disposal frequency) • Cost reduction or environmental impact reduction effect through reuse or redistribution of scrap materials. • Supply and demand situation, market information, or inventory status regarding the offcuts in question. • Adjustments based on past trading performance, trading frequency, or trading volume (e.g., tiered fees, billing rates based on cumulative trading volume) • Information regarding future transactions, reservations, or continued use • Other conditions or reasons to justify the reasonableness of the desired billing rate These negotiation details 2126 may be obtained as free-text information, or as selection information for predefined items or categories.

[0135] Negotiation deadline information 2127 indicates the deadline for accepting negotiations. The deadline for accepting negotiations can be, for example, the day after a predetermined period (for example, one week) has elapsed from the date and time the negotiation was accepted. Negotiation deadline information can be used, for example, as a criterion for determining whether to terminate negotiations if the deadline has passed. The occurrence date 2128 indicates the date the negotiation information was generated. The occurrence date 2128 is set based on the date the negotiation started or the date the negotiation terms were registered. Status 2129 is information indicating the progress or outcome of negotiations. Negotiation status 2129 may indicate, for example, "in progress," "successful," "unsuccessful," or "expired," and subsequent billing processes are controlled based on this status.

[0136] The negotiation information 2100 is not limited to the above example, as long as it is a combination of information that enables negotiation of the billing rate between the administrator, etc., and the provider (first user) or user (second user). The billing module 218 can, for example, output the corresponding negotiation information 2100 for each user to the user terminal 102 as a negotiation information table or the like.

[0137] The user terminals 102 (first user terminal 102A, second user terminal 102B) and the administrator terminal 103 may have the same configuration as the management server 101 in this example. The user terminals 102 may, for example, be equipped with a user terminal billing module that cooperates with the billing module 218 of the management server 101. In addition, the user terminals 102 may store information corresponding to the building materials information DB and billing information 2000. Similarly, the administrator terminal 103 may include, for example, an administrator terminal billing module that cooperates with the billing module 218 of the management server 101. The administrator terminal 103 may also store information corresponding to the building materials information DB, billing information 2000, and negotiation information 2100.

[0138] [Payment Methods] Figure 22 shows an example of the billing flow 2200. The billing flow 2200 is executed, for example, after the scrap material information acquisition flow 11100. The billing flow in this example includes, for example, the steps of acquiring scrap material information 700 (S2210), calculating reduction amount information (S2220), acquiring the billing rate (S2230), calculating the billing amount (S2240), and executing the billing process (S2250). Steps S2210 to S2230 can be performed in any order.

[0139] The billing module 218 initiates the billing flow 2200, for example, when the reuse management module 217 determines that a delivery contract has been concluded for scrap material identified by predetermined scrap material IDs 611 and 721. The billing module 218 first generates a billing ID for the billing process for both the provider (first user) and the user (second user), and records the corresponding user ID and billing category information.

[0140] The billing module 218 acquires information such as the type, material, dimensions, and quantity of the target scrap material based on the scrap material information 700 (process S2110).

[0141] The billing module 218 matches this information (for example, information on the type, material, dimensions, and quantity of scrap material) with the building material information DB and obtains price information (for example, unit price information) for the building material corresponding to the scrap material in question. Then, the billing module 218 calculates the price of the scrap material by multiplying the obtained unit price of the scrap material by the dimensions and quantity of the scrap material, and calculates the reduction amount for the user by adding the price of the scrap material and the delivery cost (step S2220). Next, the billing module 218 obtains the billing rate information for the user from the billing information 2000 (step S2230). Then, the billing module 218 calculates the amount billed for the user by multiplying the reduction amount for the user by the billing rate for the user (step S2240). The billing module 218 stores the deduction amount and billed amount for the user as billing information 2000 in the auxiliary storage device 202, associating them with the billing ID 2021, and also outputs them to the billing information table displayed on the user's user terminal 102.

[0142] Furthermore, the billing module 218 matches the above scrap material information (for example, information on the type, material, dimensions, and quantity of the scrap material) with the building material information DB and obtains information on the cost required for the disposal of the building material corresponding to the scrap material in question (for example, disposal unit price information). The billing module 218 then calculates the disposal cost of the scrap material by multiplying the disposal unit price of the provided scrap material by the dimensions and quantity of the scrap material and adding the transportation cost, and calculates the reduction amount for the provider (step S2220). Next, the billing module 218 obtains the billing rate information for the provider from the billing information 2000 (step S2230). The billing module 218 then calculates the amount billed for the provider by multiplying the reduction amount for the provider by the billing rate for the provider (step S2240). The billing module 218 stores, for example, the deduction amounts and billing amounts for these providers as billing information 2000 in the auxiliary storage device 202, associated with the billing ID 2021, and also outputs them to the billing information table displayed on the provider's user terminal 102.

[0143] The billing module 218 performs billing processing for the provider (first user) regarding the use of the scrap material management system 100 based on predetermined billing conditions (e.g., billing processing date, first user payment information) (step S2250). The billing module 218 outputs information to the first user terminal 102A indicating that billing processing has been performed. This completes the billing processing for the provider (first user).

[0144] Furthermore, the billing module 218 performs billing processing for the user (second user) regarding the use of the scrap material management system 100, for example, based on predetermined billing conditions (e.g., billing processing date, second user payment information). The billing module 218 outputs information to the second user terminal 102B, for example, indicating that the billing processing has been performed. This completes the billing processing for the user (second user).

[0145] According to the scrap material management system 100 in this example, for example, no money is exchanged between the scrap material provider (first user) and the user (second user) regarding the transfer of scrap material. On the other hand, the administrator can charge a usage fee for the scrap material management system 100 between the administrator and at least one (for example, both) of the scrap material provider (first user) and the user (second user). With this configuration, the effective utilization of scrap material can be promoted, and the costs necessary for the maintenance and management of the scrap material management system 100 can be recovered.

[0146] In this example, the technology was explained based on an example in which the billing module 218 acquires provider billing amount information 2024d and user billing amount information 2027e based on scrap material information 700 and building material information DB. However, the billing module 218 may acquire provider billing amount information 2024d and user billing amount information 2027e by other methods. For example, such a method could be the use of a fourth machine learning model. For example, a fourth machine learning model could be one that takes image information of various building materials as input and is trained to output information regarding the disposal cost and price (e.g., unit price) of the building materials. Smooth billing processing can also be performed with such a configuration.

[0147] [Negotiation Methods] Figure 23 shows an example of negotiation flow 2300. Here, "negotiation" refers to the process by which a user of this system (i.e., a provider or user) negotiates with the administrator to adjust the billing rate. Negotiation flow 2300 can be executed at any time, for example. For negotiations regarding the billing rate for any given transaction, negotiation flow 2300 can be executed to be completed by a predetermined negotiation deadline (for example, a predetermined number of days prior to the billing processing date).

[0148] The billing information acquisition flow in this example includes, for example, a step of accepting negotiations (S2310), a step of obtaining the desired billing rate (S2320), a step of evaluating whether the desired billing rate is reasonable (S2330), a step of calculating the billing amount based on the desired billing rate (S2340), a step of executing the recalculated billing process (S2250), a step of accepting the adjusted billing rate (S2360), a step of outputting the adjusted billing rate (S2370), a step of evaluating whether the adjusted billing rate has been approved (S2380), and a step of calculating the billing amount based on the adjusted billing rate (S2390). Steps S2360 to S2390 are optional steps that are executed as needed.

[0149] The billing module 218 displays, for example, a negotiation button on the user terminal 102 along with the billing table for negotiating the billing rate. For example, when the user selects the negotiation button on the user terminal 102, and the management server 101 receives the selection signal from the user terminal 102 (S2310), the billing module 218 executes the negotiation flow 2300.

[0150] The billing module 218 outputs, for example, input fields for the desired billing rate and optionally negotiation content information, as well as a send button, to the user terminal 102. When the desired billing rate and optional negotiation content information are entered into these input fields and sent, the billing module 218 obtains information regarding the desired billing rate and optional negotiation content from the user terminal 102 (S2320). The billing module 218 evaluates whether the obtained desired billing rate is appropriate based on predetermined criteria (S2330). The predetermined criteria may include, for example, the range of variation in the desired billing rate, the user's usage history, user evaluation, the type and content of the adjustment reasons included in the negotiation content information 2126, the effect value calculated based on the negotiation content information, or consistency with past negotiation results, one or more of which may be used to evaluate the appropriateness of the desired billing rate. For example, predetermined criteria may include one or more combinations of the following examples. If multiple criteria are set, predetermined points may be awarded when each criterion is met, and the appropriateness of the desired billing rate may be evaluated based on whether the total points exceed a predetermined threshold.

[0151] • Does the negotiation information include the specified keywords or structure (reason, conditions, period)? • Does the negotiation details information include predefined categories of reasons for adjustment? • Is the reduction effect or added value calculated based on the negotiation details above a predetermined standard? • Is the information regarding the negotiation content able to reasonably explain the reduction in the desired billing rate? • Is it possible to calculate the reduction amount, increase in transaction volume, or contribution to revenue based on negotiation details? • Does the calculated effect value outweigh the impact of changing the desired billing rate? Based on identical or similar negotiation information, does it fall within a range of previously approved billing rates? • Is it consistent with past negotiation results from the same user? • The degree of agreement with negotiation patterns that have been approved in the past for similar reasons is above a certain level. • Within 20% of the initial billing rate (80% or more) • The user's usage rate of this system exceeds a specified standard (for example, 5 or more times in the past year). • User reviews and ratings meet or exceed a specified standard (for example, a rating of 4 or higher on a 5-point scale). • Continuous usage period within a specified period in the past exceeds the specified period (e.g., continuous use for 6 months or more in the past year) • Future usage information (planned / estimated number of transactions, planned / estimated transaction volume) exceeds the specified standard. Even if the desired billing rate is applied, the cumulative amount billed over the specified period will exceed the standard amount. • The average system processing load by the user in question is below a predetermined standard. • Number of inquiries handled and trouble rate are below the specified standards. • The frequency of requiring additional support is below a specified standard. • The difference from the average billing rate of other users in the same category is within a specified range. • Above the median of a group of users with the same conditions • Past negotiation success rates fall within a specified fee range. • Past instances of non-payment, refund requests, or violations of terms and conditions exceed a specified number of times. • Users with a high cancellation rate after negotiations are concluded. • Conducting multiple billing rate negotiations in a short period of time.

[0152] If the desired charge rate is deemed reasonable (Yes in S2330), the charge module 218 adopts the desired charge rate, stores it as determined charge rate information, and recalculates the billing amount (S2340). The charge module 218 stores the recalculated billing amount in the auxiliary storage device 202 as charge information 2000, associated with charge ID 2021. The charge module 218 also outputs information indicating that the desired charge rate has been approved, along with the recalculated billing amount, to the negotiating user's user terminal 102 (S2350).

[0153] If the requested billing rate is deemed unreasonable (No in S2330), the billing module 218 accepts, for example, an adjusted billing rate from the administrator (S2360). This adjusted billing rate may, for example, be pre-set by the administrator, or it may be obtained from the administrator terminal by displaying a message to the administrator terminal requesting input of an adjusted billing rate for the user's negotiation request. The billing module 218 outputs, for example, information indicating that the requested billing rate was not approved, the adjusted billing rate, and an approve / deny button to the negotiating user's terminal 102 (S2370).

[0154] For example, when the billing module 218 receives a selection signal for the approval button from the user terminal 102, it determines that the negotiating user has approved the adjusted billing rate (Yes in S2380) and recalculates the billing amount based on the adjusted billing rate (S2390). After the recalculation, it executes step S2350.

[0155] The billing module 218, for example, if it receives a rejection button selection signal from the user terminal 102, determines that the negotiating user did not approve the adjusted billing rate (No in S2380) and returns to process S2320. The billing module 218 may continue the negotiation flow until, for example, the desired billing rate is deemed reasonable or the adjusted billing rate is approved. Alternatively, the billing module 218 may terminate the negotiation flow when, for example, predetermined negotiation termination criteria are met. Examples of negotiation termination criteria include the following. If the negotiation flow is terminated based on the negotiation termination criteria, the billing module 218 may perform billing based on, for example, the billing amount calculated using the original billing rate. Alternatively, it may perform billing based on a predefined standard billing rate.

[0156] If a specified period of time (e.g., 24 hours, 7 days, etc.) has elapsed since the start of negotiations. - If a specified amount of time has elapsed since the last negotiation operation (entering the desired billing rate, approving / denying operation). If there is no response within the specified time after the adjusted charge rate is output • The desired billing rate is obtained more than the specified number of times (e.g., 2 times). • The denial of the adjusted charge rate exceeds a certain number of times (e.g., 2 times).

[0157] Furthermore, in negotiation flow 2300, if the desired charge rate is evaluated as unreasonable (No in S2330), the process may be returned to, for example, step S2320. Also, if the negotiating user does not approve the adjusted charge rate (No in S2380), the process may be returned to, for example, step S2360. In these cases, the process may be returned to steps S2320 or S2360 if certain criteria are met.

[0158] This configuration allows for a multifaceted evaluation of the appropriateness of the billing rate based on the user's requested billing rate and negotiation details. As a result, it is possible to suppress unreasonable discount requests while enabling flexible billing adjustments for users who continue to use the service or have high transaction value. Furthermore, by establishing negotiation termination criteria based on the number of negotiations and negotiation period, it is possible to prevent the negotiation process from becoming endless and reduce the system operation load and administrator burden. In addition, by using negotiation details as evaluation criteria, the transparency and objectivity of billing rate determination can be improved.

[0159] (7) In the above embodiment, the image analysis module 215 outputs the dimensional values ​​(scrap material information) obtained from the machine learning model output values ​​(scrap material information) acquired from the machine learning model server 104 directly to the scrap material information acquisition screens 1300, 1400, etc. However, the image analysis module 215 may be configured to evaluate whether the output values ​​(scrap material information) acquired from the machine learning model server 104 are within an appropriate range, and if they are not within an appropriate range, to output information indicating that they are not within an appropriate range.

[0160] Figure 18 shows another example of the scrap material information acquisition screen 1800. The image analysis module 215 evaluates, for example, whether the dimensions of the scrap material (scrap material information) obtained from the machine learning model server 104 fall within a predetermined appropriate range. Examples of appropriate ranges include, for example, a width of "2000 mm or less", a length of "3000 mm or less", and a thickness of "100 mm or less". If the dimensions of the scrap material obtained from the machine learning model server 104 fall within the appropriate range, the image analysis module 215 outputs the obtained values ​​as they are. On the other hand, if the dimensions of the scrap material obtained from the machine learning model server 104 fall outside the appropriate range, the image analysis module 215 outputs, for example, the obtained values ​​and an alert 1860 indicating that the values ​​are not within the appropriate range.

[0161] With this configuration, a user who sees alert 1860 can, for example, understand that the dimensional value automatically displayed on the scrap material information acquisition screen 1800 may be inappropriate. Therefore, the user is explicitly given the opportunity to verify whether the dimensional value is appropriate and, if so, to correct it.

[0162] (8) In the above embodiment, the scrap material management system 100 manages construction material scraps generated at construction sites, etc. However, the application field of the scrap material management system 100 is not limited to this example, and can be applied to the management of various types of surplus materials, for example. This can greatly contribute to the effective use of resources, cost reduction, and reduction of environmental impact in various industrial fields. <Other surplus materials> • Aggregates such as gravel and rubble • Cement (powder) • Paints, adhesives, and other coatings ·wallpaper Fasteners such as screws, nails, bolts and nuts • Surplus food <Manufacturing industry> • Management of metalworking scraps Classification of resin molding scraps • Optimization of production efficiency <Recycling Industry> • Automatic classification of renewable materials • Improved processing efficiency • Automation of quality control

[0163] Furthermore, if the surplus material is aggregate such as gravel or rubble, or cement, the machine learning model used to estimate its quantity is configured to appropriately estimate the quantity of the surplus material by using a model that has been trained to output the quantity of images of the surplus material in bags, piles, or as cargo on trucks as input.

[0164] Furthermore, if it is difficult to determine the type and material of surplus material and its quantity from a single image, the image information may include image information for evaluating the type and material of surplus material and its quantity. Additionally, the machine learning model may be configured to estimate the type and material of surplus material and its quantity from image information for evaluating the type and material of surplus material and its quantity.

[0165] (9) <Estimation content by machine learning model 1> Furthermore, in the above embodiment, the image analysis module 215 output information such as the type, material, dimensions, and quantity of surplus material (scrap) estimated by the machine learning model. However, the machine learning model may be trained to take image information of surplus material (scrap) as input and output the condition and quality of that surplus material (scrap). The image analysis module 215 may be configured to additionally acquire information regarding the condition and quality of the surplus material by inputting image information of the surplus material into this machine learning model. In this case, for example, the machine learning model may be trained to take image information of boards with or without scratches or knots (an example of surplus material), boards with or without warping, and boards without warping as input and output evaluation results regarding the condition and quality (presence or absence of scratches, knots, or warping) of each board. In this case, for example, image information with different annotations on the parts with scratches or knots may be used as training data. This allows the user to easily obtain further information useful for reusing surplus material (scrap).

[0166] Furthermore, the image analysis module 215 may be configured to evaluate and output the condition and quality of the surplus material. In that case, the image analysis module 215 may be configured to, for example, detect the contour of a board (an example of surplus material) based on image information, detect the widest surface within the contour of the board as the board surface, detect whether there are shadows other than wood grain (i.e., scratches or knots) on the board surface, evaluate the condition and quality of the board as "excellent" if the ratio of the area of ​​shadows to the area of ​​the board surface is 0.1% or less, evaluate it as "good" if the ratio exceeds 0.1% but is 1% or less, evaluate it as "normal" if it exceeds 1% but is 3% or less, and evaluate it as "requires confirmation" if it exceeds 3%. In this case, the image analysis module 215 may be configured to apply one or more of the preprocessing steps exemplified in the above embodiment to the image information so that it can identify the presence or absence of elements that affect quality and condition (e.g., scratches or knots). Furthermore, the image analysis module 215 may be configured to detect the contour of a sheet material (an example of surplus material) based on image information, detect the degree of deviation of the sheet material's contour from a straight line (for example, (1) the ratio of the maximum dimension of the perpendicular line drawn from the sheet material's contour line to the dimension of the straight line connecting adjacent corner points of the sheet material, or (2) the curvature of the sheet material's contour line), and evaluate the quality as predetermined (for example, 2-3 evaluation levels such as "Excellent" or "Good") if the degree of deviation meets predetermined criteria.

[0167] <Estimated content by machine learning model 2> In other respects, the machine learning model may be trained to take image information of surplus material (scrap) as input and output information on the uses and processing methods of that surplus material (scrap). The image analysis module 215 may be configured, for example, to obtain information on the uses and processing methods of the surplus material by inputting image information of the surplus material into this machine learning model. This allows the user to obtain new ideas for reusing surplus material (scrap) and to make effective use of it.

[0168] <Estimated content by machine learning model 3> Furthermore, the management server 101 may be configured to receive information from the user regarding surplus materials (scrap materials) that the user wants to be provided, and information regarding components that are lacking for the desired finished product. In this case, the management server 101 may be configured to compare the information regarding the desired surplus materials (scrap materials) and the information regarding the missing components with information regarding surplus materials that have already been registered, and to extract information regarding surplus materials that are suitable for manufacturing the desired finished product from the registered information regarding surplus materials, and to provide it to the user. In this case, the extraction of information regarding surplus materials may be performed, for example, by a generative AI model.

[0169] (10) The management server 101 and / or the machine learning model server 104 may be configured to use the image information of surplus materials and the corresponding surplus material information, which has been input or modified by the user, as training data (teaching data) to retrain or additionally train each of the above machine learning models. This makes it possible to improve the estimation accuracy of the machine learning models without placing an excessive burden on them. In addition, it is possible to enrich the estimation content and range of the type and material of the surplus materials.

[0170] (11) In the above embodiment, the management server 101 acquired various information through, for example, the output screen to the user terminal shown in Figures 13-15, 18, etc. However, the management server 101 is not limited to acquiring various information through input via the user terminal screen, but may also be configured to acquire and store various information (for example, surplus material information) by acquiring voice information from the user and recognizing the voice information. This allows the user to register scrap material information in the surplus material management system by voice input, even when their hands are busy or dirty at the worksite.

[0171] (12) In the above embodiment, the management server 101 was configured to output a scrap material usage screen 1500 to users registered in the scrap material management system 100, allowing them to view scrap material information and request its use. However, the management server 101 may be configured to cooperate with other marketplaces and related platforms, and to provide scrap material information and accept usage requests from other users of those marketplaces and platforms. In this case, the management server 101 may be configured to convert the surplus material information obtained from users into a format compatible with the other marketplaces and platforms with which it is cooperated, and to automatically disclose (e.g., list for sale) information about the surplus material on those other marketplaces and platforms.

[0172] (13) In the above embodiment, the management server 101 was configured to output surplus material information based on input from the user. However, the management server 101 may be configured to automatically detect surplus material (which may be stored material) via cameras in the field, factory, or warehouse, automatically acquire information on the detected surplus material, and update the status of the surplus material in real time or at a predetermined time. In this case, the management server 101 may classify the detected one or more surplus materials by type, material, and dimensions, and present a list of the detected surplus materials to the user (the manager of the surplus material). In addition, the management server 101 may, for example, register the surplus material selected by the user from the list of surplus materials as provided surplus material (provided scrap material) in the surplus material management system.

[0173] (14) In the above embodiment, the billing module 218 calculates the amount of savings for the provider and / or user (step S2220). The billing module 218 may be configured to output information regarding the amount of savings for the provider and / or user to an output device 305 such as a display of the provider and / or user. The billing module 218 may output the information regarding the amount of savings, for example, as the amount of savings per unit period (e.g., monthly, yearly, etc.), or as a graph showing the trend of the amount of savings per unit period. Such calculation and output of the amount of savings for the provider and / or user may be performed by another functional module, such as the reuse management module 317, instead of the billing module 218.

[0174] It should be noted that the present invention is not limited to the embodiments described above, and various modifications are included. For example, the embodiments described above are described in detail to make the present invention easier to understand, and are not necessarily limited to those having all the configurations described. Furthermore, it is possible to replace parts of the configuration of one embodiment with the configuration of another embodiment, and it is also possible to add configurations from other embodiments to the configuration of one embodiment. In addition, it is possible to add, delete, or replace parts of the configuration of each embodiment with other configurations.

[0175] Furthermore, each of the above configurations, functions, processing units, and processing means may be implemented in hardware, either partially or entirely, by designing them as integrated circuits, for example. Alternatively, each of the above configurations and functions may be implemented in software by having the processor interpret and execute programs that implement each function. Information such as programs, tables, and files that implement each function can be stored in memory, a recording device such as a hard disk or SSD (Solid State Drive), or a recording medium such as an IC card, SD card, or DVD.

[0176] Furthermore, the control lines and information lines shown are those deemed necessary for explanatory purposes, and not all control lines and information lines are necessarily shown in the actual product. In reality, it is safe to assume that almost all components are interconnected. Furthermore, the above-described embodiments disclose at least the configuration described in the claims. [Explanation of Symbols]

[0177] 100…Scrap material management system, 101…Management server, 102…User terminal, 103…Administrator terminal, 211…Basic management module, 212…Image acquisition module, 213…Location information acquisition module, 214…Dimensional information acquisition module, 215…Image analysis module, 216…Scrap material information output module, 217…Reuse management module, 218…Billing module, 500…User information, 600…Image information, 700…Scrap material information, 2000…Billing information, MI…Model information

Claims

1. An image acquisition unit that acquires image information of surplus material, An image analysis unit that acquires surplus material information, which includes at least information regarding the type of surplus material, based on the aforementioned image information. A surplus material information output unit that outputs the surplus material information in association with the aforementioned image information, A surplus material management device equipped with the following features.

2. The image analysis unit performs at least one of the following processes on the image information: noise reduction, background removal, and contrast adjustment, and then acquires the excess material information based on the processed image information. The surplus material management device according to claim 1.

3. The image analysis unit provides the image information to a machine learning model that has been trained to output at least one piece of information from among the type of material and / or surplus material, the material, the quantity, and the dimensions, based on the image information of the material and / or surplus material, thereby obtaining at least one piece of information from among the type of material, the material, the quantity, and the dimensions as output from the machine learning model. The surplus material management device according to claim 1.

4. The aforementioned image analysis unit, By applying at least one of the following processes to the aforementioned image information, such as noise reduction, background removal, and contrast adjustment, the pre-processed image information is obtained. For each of the unprocessed image information and the preprocessed image information, the excess material information is acquired. The system accepts the selection of either surplus material information based on the unprocessed image information or surplus material information based on the preprocessed image information. The surplus material management device according to claim 1.

5. The system further includes a dimension information acquisition unit that acquires dimension information of the surplus material, The surplus material information output unit outputs the image information in association with the surplus material information and the dimensional information. The surplus material management device according to claim 1.

6. The system further includes a location information acquisition unit that acquires location information relating to the location where the image information was generated, in association with the aforementioned image information. The surplus material information output unit outputs the image information in association with the surplus material information and the position information. The surplus material management device according to claim 1.

7. The location information acquisition unit acquires address information relating to the location where the image information was generated based on the location information. The surplus material information output unit outputs the image information in association with the surplus material information and the address information. The surplus material management device according to claim 6.

8. The system further includes a reuse management unit that receives requests for the use of the surplus material and outputs usage request information indicating that a usage request has been made for the surplus material for which a usage request has been received. The surplus material management device according to claim 1.

9. The aforementioned reuse management unit is configured to accept approval for requests to utilize the surplus materials, When the recycling management unit accepts approval for a request to use the surplus material, at least one of the requesting party and the approving party is provided with a billing unit that performs billing related to the management of the recycling of the surplus material. The surplus material management device according to claim 8.

10. A computer-based method for managing surplus materials, Acquire image information of surplus material, Based on the image information, information on surplus materials is obtained, which includes at least information on the type of surplus material. The excess material information is associated with the aforementioned image information and output. Methods for managing surplus materials.

11. A program for causing a computer to perform each step of the surplus material management method described in claim 10.

Images