Estimation device, estimation method, estimation system, determination method, and computer program

Abstract

This estimation device is provided with a control unit that estimates the concentration of an impurity element contained in an iron scrap to be determined, using an estimation model that is pre-constructed using known data, and that estimates the concentration of the impurity element contained in the iron scrap to be determined. The known data includes incidental information, which is information relating to an iron scrap including iron to be recovered, and information relating to the concentration of an impurity element included in the iron scrap.

Description

Technical Field

[0001] This invention relates to a presumption apparatus, a presumption method, a presumption system, a determination method, and a computer program. This application claims priority based on Japanese Patent Application No. 2023-181202, filed on October 20, 2023, the contents of which are incorporated herein by reference. Background Technology

[0002] In recent years, the steel industry has seen increased demands for recycled iron, driven by goals such as reducing carbon dioxide emissions. There are various types of scrap containing recyclable iron (iron scrap). Newly cut waste generated primarily during steel product processing is classified as high-grade iron scrap, while waste such as H2 generated primarily during building demolition is classified as low-grade iron scrap. For the manufacture of high-grade steel, the use of high-quality high-grade iron scrap is preferred; however, relying solely on high-grade iron scrap may lead to future procurement shortages. Therefore, it is necessary to make full use of low-grade iron scrap.

[0003] In low-grade iron scrap, the proportion of impurity elements other than iron is high, and the fluctuation range is also large. This is greatly affected by the contamination of prohibited substances such as motors or switchboards mixed in with the scrap. Among the impurity elements, if elements that are difficult to remove in the steelmaking process (residual elements: TE: tramp element, representative elements: Cu, Sn, Ni, Cr, Mo) are mixed into the steel, they will become the main cause of cracks and substandard material (mechanical properties) during hot rolling. To address this issue, a technique for measuring the concentration of specific impurity elements after dissolution has been proposed (see, for example, Patent Document 1 and Patent Document 2).

[0004] Existing technical documents

[0005] Patent documents

[0006] Patent Document 1: Japanese Patent Application Publication No. 2007-322190

[0007] Patent Document 2: Japanese Patent Application Publication No. 2011-168823 Summary of the Invention

[0008] The technical problem that the invention aims to solve

[0009] However, in previous concentration measurement techniques after dissolution, even if TE was taken above the reference level, it was difficult to remove.

[0010] Therefore, the present invention was made in view of the above circumstances, and provides a technique that can obtain the TE composition of iron in a recoverable object with higher precision.

[0011] Technical solutions for solving technical problems

[0012] (1) One aspect of the present invention is an estimation device comprising a control unit that uses an estimation model to estimate the concentration of impurity elements contained in iron scrap that is to be determined. The estimation model is pre-constructed using known data, which includes information related to the iron scrap containing the iron to be recycled, i.e., incidental information, and information related to the concentration of impurity elements contained in the iron scrap.

[0013] (2) In one aspect of the present invention, in the presumption apparatus of (1) above, the accompanying information includes property information of the iron scrap itself or information related to prior inspection of the iron scrap.

[0014] (3) In one aspect of the present invention, in the presumed apparatus of (1) or (2) above, the accompanying information includes information related to the appearance of the iron scrap.

[0015] (4) In one aspect of the present invention, in the presumption device described in (1) above, the accompanying information includes information relating to the prohibited substances contained in the iron scrap.

[0016] (5) In one aspect of the present invention, in the estimation device described in (4) above, the relevant information of the prohibited substances contained in the iron scrap indicates the quantity or type of prohibited substances estimated using a pre-established prohibited substance estimation model for estimating prohibited substances.

[0017] (6) One aspect of the present invention is a estimation method having an estimation step in which an estimation model is used to estimate the concentration of impurity elements contained in the iron scrap to be determined, the estimation model being pre-constructed using known data, which includes information related to the iron scrap containing the iron to be recovered, i.e., incidental information, and information related to the concentration of impurity elements contained in the iron scrap.

[0018] (7) One aspect of the present invention is a computer program for enabling a computer to function as an estimation device, the estimation device having a control unit that uses an estimation model to estimate the concentration of impurity elements contained in the iron scrap to be determined, the estimation model being pre-constructed using known data, the known data including information related to the iron scrap containing the iron to be recycled, i.e., incidental information, and information related to the concentration of impurity elements contained in the iron scrap.

[0019] (8) One aspect of the present invention is an estimation system comprising: an estimation unit that uses an estimation model to estimate the concentration of impurity elements contained in iron scrap that is to be determined, the estimation model being pre-constructed using known data, the known data including information related to the iron scrap containing the iron to be recycled, i.e., incidental information, and information related to the concentration of impurity elements contained in the iron scrap; and a removal object determination unit that determines, based on the estimation result of the estimation unit, prohibited substances that should be removed from the iron scrap.

[0020] (9) In one aspect of the present invention, in the presumption system described in (8) above, the accompanying information includes information related to the appearance of the iron scrap.

[0021] (10) One aspect of the present invention is a determination method comprising: an estimation step, using an estimation model to estimate the concentration of impurity elements contained in iron scrap that is to be determined, the estimation model being pre-constructed using known data, the known data including information related to iron scrap containing iron to be recycled, i.e., incidental information and information related to the concentration of impurity elements contained in the iron scrap; and a removal object determination step, based on the estimation result in the estimation step, determining prohibited substances that should be removed from the iron scrap.

[0022] (11) One aspect of the present invention is a computer program for enabling a computer to function as an estimation system, the estimation system comprising: an estimation unit that uses an estimation model to estimate the concentration of impurity elements contained in iron scrap that is to be determined, the estimation model being pre-constructed using known data, the known data including incidental information related to the iron scrap containing the iron to be recycled and information related to the concentration of impurity elements contained in the iron scrap; and a removal object determination unit that determines, based on the estimation result of the estimation unit, prohibited substances that should be removed from the iron scrap.

[0023] (12) One aspect of the present invention is an estimation system comprising: an estimation unit that uses an estimation model to estimate the concentration of impurity elements contained in iron scrap that is to be determined, the estimation model being pre-constructed using known data, the known data including information related to iron scrap containing iron to be recycled, i.e., incidental information, and information related to the concentration of impurity elements contained in the iron scrap; and a proportioning information determination unit that determines the proportion of iron scrap based on the estimation result of the estimation unit and the price of the iron scrap in a manner that satisfies predetermined conditions.

[0024] (13) One aspect of the present invention is a determination method comprising: an estimation step, using an estimation model to estimate the concentration of impurity elements contained in the iron scrap to be determined, the estimation model being pre-constructed using known data, the known data including information related to the iron scrap containing the iron to be recycled, i.e., incidental information and information related to the concentration of impurity elements contained in the iron scrap; and a proportioning information determination step, determining the proportion of the iron scrap in a manner that satisfies the specified conditions based on the estimation result in the estimation step and the price of the iron scrap.

[0025] (14) One aspect of the present invention is a computer program characterized in that it enables the computer to function as an estimation system, the estimation system comprising: an estimation unit that uses an estimation model to estimate the concentration of impurity elements contained in the iron scrap to be determined, the estimation model being pre-constructed using known data, the known data including information related to the iron scrap containing the iron to be recycled, i.e., incidental information, and information related to the concentration of impurity elements contained in the iron scrap; and a proportioning information determination unit that determines the proportion of the iron scrap based on the estimation result of the estimation unit and the price of the iron scrap in a manner that satisfies predetermined conditions.

[0026] (15) One aspect of the present invention is an estimation system comprising: an estimation unit that uses an estimation model to estimate the concentration of impurity elements contained in iron scrap that is to be determined, the estimation model being pre-constructed using known data, the known data including information related to iron scrap containing iron to be recycled, i.e., incidental information, and information related to the concentration of impurity elements contained in the iron scrap; and a price determination unit that determines the price of the iron scrap based on the estimation result of the estimation unit.

[0027] (16) One aspect of the present invention is a determination method comprising: an estimation step, using an estimation model to estimate the concentration of impurity elements contained in iron scrap that is to be determined, the estimation model being pre-constructed using known data, the known data including information related to iron scrap containing iron to be recycled, i.e., incidental information and information related to the concentration of impurity elements contained in the iron scrap; and a price determination step, determining the price of the iron scrap based on the estimation result in the estimation step.

[0028] (17) One aspect of the present invention is a computer program for enabling a computer to function as an estimation system, the estimation system comprising: an estimation unit that uses an estimation model to estimate the concentration of impurity elements contained in iron scrap that is to be determined, the estimation model being pre-constructed using known data, the known data including information related to iron scrap containing iron to be recycled, i.e., incidental information, and information related to the concentration of impurity elements contained in the iron scrap; and a price determination unit that determines the price of the iron scrap based on the estimation result of the estimation unit.

[0029] Invention Effects

[0030] According to the present invention, the concentration of impurity elements in the iron of the object to be recovered can be obtained with higher precision. Attached Figure Description

[0031] Figure 1 This is a schematic block diagram illustrating the system structure of the first embodiment of the estimation system 100 of the present invention.

[0032] Figure 2 This is a diagram illustrating an application example of the estimation system 100 in this embodiment.

[0033] Figure 3 This is a schematic block diagram illustrating a specific example of the functional structure of the terminal device 10.

[0034] Figure 4 This is a schematic block diagram illustrating a specific example of the functional structure of the estimation device 30.

[0035] Figure 5 This is a graph representing the first specific instance of teacher data.

[0036] Figure 6 It means that it has been used Figure 5 The figure shows an example of a presumption model obtained by learning from teacher data, as shown.

[0037] Figure 7 This is a graph representing the second specific instance of teacher data.

[0038] Figure 8 It means that it has been used Figure 7 The figure shows an example of a presumption model obtained by learning from teacher data, as shown.

[0039] Figure 9 This is a graph representing the third specific instance of teacher data.

[0040] Figure 10 It means that it has been used Figure 9 The figure shows an example of a presumption model obtained by learning from teacher data, as shown.

[0041] Figure 11 This is a graph representing the fourth specific instance of teacher data.

[0042] Figure 12 It means that it has been used Figure 11 The figure shows an example of a presumption model obtained by learning from teacher data, as shown.

[0043] Figure 13 This is a flowchart illustrating a specific example of the processing of the estimation device 30.

[0044] Figure 14 This is a schematic block diagram representing a specific example of the functional structure of the model building device 40.

[0045] Figure 15 This is a flowchart illustrating a specific example of the processing of the model building device 40.

[0046] Figure 16 This is a diagram showing a modified example of the estimation device 30.

[0047] Figure 17 This is a diagram showing a modified example of the estimation device 30.

[0048] Figure 18 This is a schematic block diagram illustrating the system structure of the second embodiment of the estimation system 100 of the present invention.

[0049] Figure 19 This is a schematic block diagram illustrating a specific example of the functional structure of the incompatible substance presumption device 50;

[0050] Figure 20 This is a flowchart illustrating a specific example of the processing of the incompatible substance presumption device 50;

[0051] Figure 21 This is a diagram showing a modified example of the estimation device 30.

[0052] Figure 22 This is a schematic block diagram illustrating the system structure of the third embodiment of the estimation system 100 of the present invention.

[0053] Figure 23 This is a schematic block diagram illustrating a specific example of the functional structure of the object removal determination device 60.

[0054] Figure 24 This is a diagram showing specific examples of contraindications;

[0055] Figure 25 This is a flowchart illustrating a specific example of the processing of the object removal determination unit 632.

[0056] Figure 26 This is a diagram illustrating an application example of the estimation system 100 in this embodiment.

[0057] Figure 27 This is a schematic block diagram illustrating the system structure of the fourth embodiment of the estimation system 100 of the present invention.

[0058] Figure 28 This is a schematic block diagram illustrating a specific example of the functional structure of the proportioning information determination device 70.

[0059] Figure 29 This is a diagram showing a specific example of inventory information.

[0060] Figure 30 This is a schematic block diagram illustrating the system structure of the fifth embodiment of the estimation system 100 of the present invention.

[0061] Figure 31 This is a schematic block diagram illustrating a specific example of the functional structure of the price determination device 80.

[0062] Figure 32 This is a diagram showing a specific example of price information.

[0063] Figure 33 This is a schematic diagram showing an example of the hardware structure of the information processing apparatus 90 applied in this embodiment. Detailed Implementation

[0064] [First Implementation Method]

[0065] Specific structural examples of the present invention will be described with reference to the accompanying drawings. Figure 1 This is a schematic block diagram illustrating the system structure of the estimation system 100 according to a first embodiment of the present invention. The estimation system 100 is used to estimate the concentration of impurity elements contained in iron scrap (hereinafter referred to as "target scrap"). In the following description, copper is used as a specific example of an impurity contained in the target scrap. However, the types of impurities that can be estimated using the estimation system 100 are not limited to copper. Furthermore, in the following description, impurities refer to elements other than iron (e.g., copper), and prohibited substances refer to parts other than iron in the scrap (e.g., electric motors).

[0066] The estimation system 100 includes a terminal device 10, an imaging device 20, an estimation device 30, and a model building device 40. The terminal device 10, imaging device 20, and estimation device 30 are communicatively connected via a network 200. The estimation device 30 and model building device 40 are also communicatively connected via the network 200. The network 200 can be a wireless communication network or a wired communication network. For example, the network 200 can be constructed using the Internet or a local area network (LAN). The network 200 can also be constructed by combining multiple networks. The network used by the terminal device 10 to communicate with the estimation device 30 and the network used by the imaging device 20 to communicate with the estimation device 30 can be different networks.

[0067] First, the overall situation of the waste flow path of the estimation system 100 applied in this embodiment will be described. First, iron structures are demolished or abandoned, thereby generating iron waste. The demolition of the structures can be carried out by demolition companies, for example. At this time, information related to the structure before demolition or abandonment, information related to the demolition company, information indicating the condition at the time of demolition, and information indicating the condition at the time of abandonment can be processed as part of the incidental information.

[0068] The resulting scrap iron is collected by recyclers. The collected scrap iron is then processed by waste processing companies. These recyclers and waste processing companies are collectively referred to as waste operators. Waste operators may also photograph the scrap iron during collection (at acceptance). These images can be used as part of the accompanying information. Waste operators sort the received scrap iron and transport the sorted pieces to waste utilization companies. When the received scrap iron is large, waste operators may also process it. Such processing includes, for example, shearing (using guillotine cutters, gas-fired cutting), shredding (crushing), and stamping. The scrap iron is processed into smaller shapes.

[0069] In the screening of iron scrap, estimated values ​​of the residual element composition of each piece of iron scrap obtained from the estimation system 100 can also be used. By conducting screening using such estimated values, scrap operators can predict in advance the concentration of residual element components contained in the iron scrap, and establish and achieve screening targets that meet the requirements of the purchaser (scrap utilization operator). Information related to scrap operators that process iron scrap, information related to the processing of iron scrap, information related to the person in charge of the scrap operator, and information indicating the screening results of iron scrap can also be processed as part of the supplementary information.

[0070] Scrap metal recyclers receive incoming scrap metal from scrap metal recyclers and purchase some or all of it. At this time, images of the scrap metal taken during transport and information related to the person transporting the scrap metal can be included as supplementary information. The purchase price can also be determined according to prescribed criteria. For example, it can be based on the shape and size of the scrap metal, or on the residual element composition contained in the scrap metal. The residual element content can be estimated using the aforementioned supplementary information estimation system 100. The purchased scrap metal is managed in batches, and after fine crushing, the proportions are determined, and it is melted using an electric furnace. At this time, the purchase price and images taken during crushing can also be used as supplementary information. By using the estimation system 100 to estimate the residual element composition contained in each batch of purchased scrap metal, scrap metal recyclers can obtain the desired steel composition.

[0071] By performing component analysis on the dissolved substances, the measured values ​​of the residual elemental composition can be obtained. These measured values ​​can also be fed back to the estimation system 100 for updating the estimation model using the estimation results and measured values.

[0072] Figure 2 This diagram illustrates an application example of the estimation system 100 of this embodiment (excluding the terminal device 10 and the imaging device 20). Figure 2 In the illustrated application example, the estimation system 100 is applied to a scrap metal yard, a location for storing and recycling scrap metal (object scrap). The scrap metal yard is equipped with a camera device 20 and a handling device 300. The camera device 20 is installed, for example, at the location of the scrap metal loaded in the cargo compartment of a truck transporting the scrap metal, within the premises of the aforementioned demolition company, scrap metal company, or scrap metal recycling company. For example, the camera device 20 can also be installed to photograph the cargo compartment of a truck parked in a designated parking position. The handling device 300 is configured to transport the scrap metal from the truck cargo compartment to the scrap metal loading site. The handling device 300 includes, for example, a lifting electromagnet 301, a crane 302, and a crane rail 303.

[0073] Iron scrap generated from the demolition of buildings in factories and urban areas is transported by trucks to iron scrap yards. The trucks, loaded with iron scrap, park in designated parking areas. While the trucks are parked, a camera device 20 takes pictures of the area including the truck bed and generates image data. The camera device 20 sends the generated image data to an estimation device 30. When the camera device 20 finishes taking pictures, a transport device 300 removes the iron scrap from the truck bed to the iron scrap loading area.

[0074] At the scrap yard, operators performing tasks related to the loading and unloading of scrap operate the terminal device 10 to input inspection performance information with accompanying information. This inspection performance information includes information related to the delivery company (e.g., file data), information indicating the location of the scrap, etc. The delivery company can also input the inspection performance information by operating the terminal device 10. The terminal device 10 accepts the input inspection performance information based on the operator's operation and sends the input inspection performance information to an estimation device 30 (not shown). The estimation device 30 uses accompanying information (including inspection performance information and / or image data) obtained from the aforementioned demolition company, scrap company, scrap utilization company, etc., to perform estimation processing. The estimation device 30 sends the estimation result obtained through estimation processing to the terminal device 10. Upon receiving the estimation result from the estimation device 30, the terminal device 10 displays the received estimation result. Next, the devices used in the estimation system 100 will be described.

[0075] Figure 3 This is a schematic block diagram illustrating a specific example of the functional structure of the terminal device 10. The terminal device 10 is configured using information devices such as smartphones, graphics tablets, personal computers, and dedicated equipment. The terminal device 10 includes a communication unit 11, an operation unit 12, an output unit 13, a storage unit 14, and a control unit 15.

[0076] Communication unit 11 is a communication device. Communication unit 11 may also be configured as a network interface, for example. Communication unit 11 communicates with other devices via network 200 under the control of control unit 15. Communication unit 11 can be a device for wireless communication or a device for wired communication.

[0077] The operation unit 12 is constructed using existing input devices such as a keyboard, pointing devices (mouse, graphics tablet, etc.), buttons, and touch panels. The operation unit 12 is operated by the user when user instructions are input to the terminal device 10. The operation unit 12 can also be an interface for connecting the input device to the terminal device 10. In this case, the operation unit 12 inputs the input signal generated in the input device based on the user's input to the terminal device 10. The operation unit 12 can also be constructed using a microphone and a voice recognition device. In this case, the operation unit 12 performs voice recognition on the statements spoken by the user and inputs the string information of the recognition result to the terminal device 10. In this case, the operation unit 12 can also only accept voice input, with voice recognition performed by the control unit 15. The operation unit 12 can be constructed arbitrarily as long as it has a structure capable of inputting user instructions to the terminal device 10.

[0078] The output unit 13 outputs information in a form that is understandable to the user. The output unit 13 may be, for example, an image display device such as a liquid crystal display (LCD) or an organic EL (Electro-Luminescence) display. The output unit 13 may also be an interface for connecting the image display device to the terminal device 10. In this case, the output unit 13 generates an image signal for displaying image data and outputs the image signal to the image display device connected to it. The output unit 13 may also be a sound output device such as a speaker. The output unit 13 may also be an interface for connecting an audio output device such as a speaker or headphones to the terminal device 10. In this case, the output unit 13 generates an audio signal for reproducing audio data and outputs the audio signal to the audio output device connected to it.

[0079] The storage unit 14 is constructed using storage devices such as magnetic hard disk drives and semiconductor storage devices. The storage unit 14 stores data used by the control unit 15. The storage unit 14 stores data required by the control unit 15 during processing.

[0080] The control unit 15 is constructed using one or more hardware processors, such as a CPU (Central Processing Unit), and one or more memory devices (main storage devices). The memory may be constructed using storage devices such as RAM (Random Access Memory) or ROM (Read Only Memory). The control unit 15 executes one or more programs stored in the memory via the one or more hardware processors, thereby performing various operations and functions. Furthermore, all or part of the functions of the control unit 15 may also be implemented using hardware such as ASIC (Application Specific Integrated Circuit), PLD (Programmable Logic Device), or FPGA (Field Programmable Gate Array). The aforementioned programs may also be recorded on a computer-readable recording medium. Computer-readable recording media may include removable media such as floppy disks, optical disks, ROMs, CD-ROMs, semiconductor storage devices (e.g., SSDs), hard disks built into the computer system, and other storage devices. The aforementioned programs may also be transmitted via electrical communication lines.

[0081] The control unit 15 may also execute applications installed on this device (terminal device 10). As a specific example of such an application, there is an application provided to the terminal device 10 as a dedicated application for the estimation system 100. Another specific example of such an application is a web browser application. Such applications may be pre-installed on the terminal device 10 or downloaded each time estimation processing is performed. For example, if installed as a web browser application, it may be configured as follows: Depending on the connection between the terminal device 10 and a specific web server, the terminal device 10 downloads the application from a device specified by the web server. Then, the terminal device 10 executes the downloaded application. Furthermore, the device specified by the web server may be, for example, the web server itself or another server. The control unit 15 operates according to the program of the executing application.

[0082] The control unit 15 controls the terminal device 10 based on user operations and information received from the estimation device 30. For example, the control unit 15 sends information input by the user through the operation unit 12 via the communication unit 11 to the estimation device 30. For example, when the communication unit 11 receives information sent from the estimation device 30 via the network 200, the control unit 15 generates screen data based on the received information and causes the output unit 13 to display the screen data. Such screen data includes images and text sent from the estimation device 30. For example, when the communication unit 11 receives information sent from the estimation device 30 via the network 200, the control unit 15 generates sound data based on the received information and outputs the sound data from the output unit 13.

[0083] The operation of the control unit 15 will now be described in detail. In the following examples, an image display device is used as a specific example of the output unit 13. However, as mentioned above, the output unit 13 does not need to be configured using an image display device; it can be configured using a sound output device, or it can be configured using both an image display device and a sound output device.

[0084] The control unit 15 generates screen data containing text and images that provide information required for the estimation process to be performed by the user-instructed estimation device 30. The control unit 15 then causes the output unit 13 to display the generated screen data. For example, the information input to the user may include supplementary information related to the object waste. The user inputs this supplementary information into the terminal device 10 by operating the operation unit 12. The control unit 15 may also, for example, input a start command for the estimation process while inputting supplementary information. The user inputs a start command instruction to the terminal device 10 by operating the operation unit 12. The control unit 15 uses the communication unit 11 to transmit the input supplementary information and the start instruction for the estimation process to the estimation device 30.

[0085] The control unit 15 receives the estimation result from the estimation device 30. The control unit 15 generates screen data that represents information indicating the estimation result. The control unit 15 causes the output unit 13 to display the generated screen data. By checking such a display, the user can easily obtain information related to the amount of impurities (copper) contained in the iron scrap (object scrap) that is the object of estimation.

[0086] The imaging device 20 acquires information related to the appearance of the object waste by photographing it. The imaging device 20 can also be configured using a camera (image sensor) that receives, for example, visible light from a space containing the object waste to generate two-dimensional image data. Such a camera is used to photograph the object waste. The imaging device 20 can also be a sensor that acquires information related to the three-dimensional shape of the object waste. In this case, the imaging device 20 can also be configured using a device that measures the distance between itself and various points on the surface of the object waste. More specifically, the imaging device 20 can also be configured using a measuring device that irradiates the object waste with laser light to measure the scattered light, thereby measuring the distance from the imaging device 20 to various parts of the surface of the object waste. A specific example of such an imaging device 20 is LIDAR (Laser Imaging Detection and Ranging). The imaging device 20 sends the acquired appearance information to the estimation device 30.

[0087] The estimation device 30 estimates the concentration of impurity elements contained in the target waste. The estimation device 30 is constructed, for example, using an information processing device such as a personal computer or server. Figure 4 This is a schematic block diagram illustrating a specific example of the functional structure of the estimation device 30. As shown in the example, the estimation device 30 includes a communication unit 31, a storage unit 32, and a control unit 33.

[0088] Communication unit 31 is a communication device. Communication unit 31 may also be configured as a network interface, for example. Under the control of control unit 33, communication unit 31 communicates with other devices via network 200. Communication unit 31 can be a device for wireless communication or a device for wired communication.

[0089] The storage unit 32 is constructed using a storage device such as a magnetic hard disk drive or a semiconductor storage device. The storage unit 32 stores data used by the control unit 33. The storage unit 32 can also function as, for example, a presupposition model storage unit 321.

[0090] The estimation model storage unit 321 stores information used to estimate the concentration of impurity elements contained in the target waste (hereinafter referred to as the "estimation model"). The estimation model is generated in advance through a model building process. Such a model building process can be performed by other devices (e.g., model building device 40), by this device (estimation device 30), or by human operation. Hereinafter, the estimation model stored in the estimation model storage unit 321 will be described.

[0091] The inference model can be obtained, for example, through model building processing using known data. The inference model can represent information about a completed learning model obtained by performing teacher-based learning processing using multiple known data (teacher data) with truth labels, or information obtained through statistical processing using known data, or other information. Specific examples of learning processing include multivariate analysis, machine learning, deep learning, etc. As a learning process, a classification learning process or a regression learning process can be used based on the truth labels used in the teacher data. The control unit 33 estimates the concentration of impurity elements contained in the target waste using the inference model stored in the inference model storage unit 321. The teacher data in this embodiment will be described below.

[0092] As teacher data, for each collection (hereinafter referred to as a "batch") of iron scrap as a set of specified units, a combination of supplementary information and truth labels (information indicating the concentration of impurity elements) is used. In this case, the supplementary information is equivalent to the explanatory variable, and the information indicating the concentration of impurity elements is equivalent to the target variable. A batch can also be a collection as shown below: A collection of iron scrap loaded onto the same truck when the iron scrap is transported to the loading and unloading site. A collection of iron scrap transported from the same scrap dealer within a specified time (e.g., 15 minutes, 30 minutes, 1 hour, etc.). A collection of iron scrap loaded on multiple trucks designated by the scrap dealer. A collection of scrap that is attached to a lifting electromagnet by a single application of magnetic force during unloading. A batch can be defined in any way as long as it is a collection of iron scrap that is presumed to contain the same amount of impurities; for example, it can also be a collection of iron scrap that can be transported at one time by a handling device such as a crane or heavy machinery. In the following description, a collection of scrap metal loaded onto the same truck when it is transported to the loading and unloading site will be described as a batch.

[0093] Additional information refers to information related to the scrap metal. This additional information may include, for example, inspection record information or appearance information. Inspection record information includes the inherent properties of the scrap metal itself, or information related to prior inspections of the scrap metal (including inspection conditions and results). The data format of inspection record information can be any form, such as strings, numbers, or images. Attribute information may include, for example, information indicating the source of the scrap metal (the demolished building) or the time period in which the scrap metal was generated (the period when demolition took place). Inspection-related information includes information such as the scrap metal supplier, the scrap metal demolition company, the person in charge of the scrap metal removal operation (screening operation) (hereinafter referred to as the "screening manager"), delivery date and time, and the scrap metal grade.

[0094] Figure 5 This is a graph representing the first specific instance of teacher data. Figure 5 The teacher data shown is an example where past inspection information is used as the explanatory variable and past melt steel composition is used as the target variable. The past inspection information consists of values ​​for multiple inspection items (x1~xp) for each batch, denoted as No. The past melt steel composition consists of values ​​for the composition (y1~yq) measured from the actual melt steel for each batch based on the past inspection information. These values ​​can also be used to train an unlearned model, thereby generating a presumptive model. Figure 6 It means that it has been used Figure 5 The diagram illustrates an example of a presumption model obtained by learning from teacher data, as shown. By inputting the current inspection information as an explanatory variable into the presumption model, the predicted molten steel composition is obtained as the target variable. The current inspection information represents the values ​​of each item x1~xp related to the iron scrap of the presumption object. The predicted molten steel composition represents the estimated values ​​of each component related to the iron scrap of the presumption object.

[0095] Figure 7 This is a graph representing the second specific instance of teacher data. Figure 7 The teacher data shown is an example where the explanatory variable has a past image and the target variable has a past molten steel composition. The past image is one or more images taken during a specified process for each batch, denoted as No. Figure 7 In the example, one image is used for each batch. The past melt steel composition has the values ​​of the composition (y1~yq) obtained from the actual melt steel determination for each batch of the past images. These values ​​can also be used to teach an unlearned model, thereby generating an inference model. Figure 8 It means that it has been used Figure 7The figure shows an example of a presumption model obtained by learning from teacher data as shown. By inputting the current image (No. A1) as an explanatory variable into the presumption model, the current predicted molten steel composition is obtained as the target variable. The current image represents an image taken of the iron scrap for the presumption object during a specified process. The current predicted molten steel composition represents the estimated values ​​of each component related to the iron scrap for the presumption object.

[0096] Figure 9 This is a graph representing the third specific instance of teacher data. Figure 9 The teacher data shown is an example where past inspection information and past images are used as explanatory variables, and past steel composition is used as the target variable. The past inspection information and past images are as described above. These values ​​can also be used to train an unlearned model, thereby generating a presumptive model. Figure 10 It means that it has been used Figure 9 The figure shows an example of a presumption model obtained by learning from teacher data as shown. By inputting the presumption model with the current inspection information and the current image (e.g., the image of the scrap before melting) as explanatory variables, the predicted molten steel composition is obtained as the target variable.

[0097] In addition, as part of the inspection results, the data may include, for example, the grade of the scrap determined by a system that identifies the type, quantity, and grade of foreign matter presumed to have been mixed into the scrap, and the structural data of all the components that make up the scrap. Structural data may include, for example, the proportion of different types of components such as sheet metal, reinforcing bars, and H-beams.

[0098] Figure 11 This is a graph representing the fourth specific instance of teacher data. Figure 11 The teacher data shown is an example with past inspection information and past contraindication detection results as explanatory variables, and past melt steel composition as the target variable. Past inspection information is as described above. Past contraindication detection results have values ​​associated with multiple contraindications (residual elemental composition z1~zq) for each batch, denoted as No. Past melt steel composition has values ​​(y1~yq) obtained from actual melt steel determinations for each batch based on past inspection information. These values ​​can also be used to learn from unlearned models, thereby generating a presumptive model. Figure 12 It means that it has been used Figure 11 The diagram illustrates an example of a presumption model obtained by learning from teacher data, as shown. By inputting the current inspection information and the current incompatible substance detection results as explanatory variables into the presumption model, the predicted molten steel composition is obtained as the target variable. The current inspection information represents the values ​​of x1~xp for each item related to the iron scrap of the presumption object. The current incompatible substance detection results represent the values ​​of z1~zq for each item related to incompatible substances in the presumption object scrap. The predicted molten steel composition represents the estimated values ​​of each component related to the iron scrap of the presumption object.

[0099] Furthermore, teacher data is not limited to the examples mentioned above and can utilize various supplementary information. In addition, teacher data can also include information indicating the cause of scrap metal generation and information about the supplier. Causes of generation include, for example, generation during building demolition or as scrap during steel processing.

[0100] It should be noted that prohibited substances in iron scrap include impurities such as residual elements, sealed materials that pose an explosive hazard upon dissolution (such as gas cylinders), and iron with a large amount of non-conductive material (such as insulation materials). Among these prohibited substances, substances containing residual elements are relatively more numerous. Therefore, the concentration of impurity elements in iron scrap is related to the amount of prohibited substances contained in the iron scrap. Some of the prohibited substances contained in iron scrap are removed by the supplier's screening manager during the process before the iron scrap is delivered. Therefore, the amount of prohibited substances contained in iron scrap is related to the supplier. For example, among multiple suppliers, there are suppliers that remove more prohibited substances and suppliers that remove less. In addition, the amount of prohibited substances contained in iron scrap is also related to the screening manager. This is because, for example, even among multiple screening managers belonging to the same supplier, there are screening managers who remove more prohibited substances and screening managers who remove less.

[0101] The amount of contaminants contained in scrap metal varies significantly depending on the structure from which it originates. Therefore, the amount of contaminants in scrap metal is related to the structure from which the scrap metal originates (the source of the contaminants). Furthermore, scrap metal from the same structure is often delivered in concentrated periods close to the demolition date of that structure. Therefore, the amount of contaminants contained in scrap metal is related to both the time of delivery and the time of its occurrence.

[0102] The types and amounts of impurities contained in iron scrap can be inferred based on information obtained from its appearance, namely its shape and color. For example, the grade of heavy scrap can be determined based on its shape (especially its thickness). Additionally, the amount of rust and the color of coated copper wires can be determined based on their color. Furthermore, contaminants such as those found in motors or switchboards can be identified based on information obtained from their appearance. Therefore, the concentration of impurity elements contained in iron scrap is related to information obtained from its appearance (two-dimensional images, etc.).

[0103] The appearance information is information obtained by the imaging device described above. In the following description, an example of using a two-dimensional image obtained by receiving visible light as appearance information will be explained.

[0104] In generating the presumption model, both the inspection data and the two-dimensional image (appearance information) from the accompanying information can be used, or only one of them can be used. If only the inspection data is used in generating the presumption model, only the inspection data will also be used in the presumption processing using that model. If only the two-dimensional image is used in generating the presumption model, only the two-dimensional image will also be used in the presumption processing using that model. If both the inspection data and the two-dimensional image are used in generating the presumption model, it is preferable to use both in the presumption processing using that model, but either the inspection data or the two-dimensional image can also be used. Furthermore, the information used as appearance information can be any information that can represent the appearance of the iron scrap. For example, information representing the three-dimensional shape obtained using a three-dimensional shape measurement system such as LIDAR can also be used as appearance information. Additionally, image information from other sources, such as multispectral images and infrared images, can also be used as appearance information.

[0105] When only empirical information is used in generating the inference model, regression models such as multiple regression and decision trees can be used. Alternatively, models that output predicted values ​​with probability distributions, such as Gaussian process regression, can be used. Furthermore, classification models such as Support Vector Machines (SVMs) can be used, outputting which of the multiple categories representing the range of predicted values ​​the inference model belongs to. When only two-dimensional images are used in generating the inference model, neural networks such as CNNs (Convolutional Neural Networks) can be used, as well as other learning algorithms. When only two-dimensional images are used in generating the inference model, regression models that output predicted values ​​can be used, as well as classification models that output which of the multiple categories representing the range of predicted values ​​the inference model belongs to.

[0106] When using inspection data and two-dimensional images in the generation of an inference model, multimodal learning models (e.g., multimodal deep learning) can also be used. Specific examples of image-based multimodal techniques (meta-information input techniques) include early-fusion and late-fusion. In early-fusion, to enable the use of a single prediction model, the inspection data and image information are transformed into vectors of the same dimension. This results in an inference from a single prediction model. In late-fusion, TE component prediction models utilizing inspection data (such as Gaussian process regression) and TE component prediction models utilizing image information (such as CNNs) are used independently, and the individual predictions are weighted to obtain the final prediction. Multimodal techniques are not limited to these specific examples; other techniques can also be applied. When using inspection data and two-dimensional images in the generation of an inference model, a regression model that outputs the predicted value can be used, or a classification model that outputs which of several categories representing the range of predicted values ​​can be used.

[0107] Next, the control unit 33 will be described. The control unit 33 is constructed using one or more hardware processors such as a CPU and one or more memory devices (main storage devices). The memory is constructed using storage devices such as RAM and ROM (Read Only Memory). The control unit 33 executes one or more programs stored in the memory via one or more hardware processors, thereby performing various operations and performing its functions. The control unit 33 functions, for example, as an information control unit 331, an estimation unit 332, and an output control unit 333. Furthermore, all or part of the functions of the control unit 33 can also be implemented using hardware such as ASICs, PLDs, and FPGAs. The aforementioned programs can also be recorded on a computer-readable recording medium. Computer-readable recording media include, for example, removable media such as floppy disks, optical disks, ROMs, CD-ROMs, semiconductor storage devices (e.g., SSDs), and storage devices such as hard disks built into computer systems. The aforementioned programs can also be transmitted via electrical communication lines.

[0108] The information control unit 331 acquires information from other devices such as the terminal device 10 and the imaging device 20. Specific examples of the acquired information include, for instance, information accompanying the object waste. Specifically, the information control unit 331 may also acquire either or both of inspection results information and two-dimensional images (appearance information). The information control unit 331 records the acquired information in a storage device such as a memory. The information control unit 331 transmits information to other devices such as the terminal device 10. Specific examples of the transmitted information include, for instance, information estimated by the estimation unit 332. Such information exchange between the information control unit 331 and other devices can also be achieved, for example, through communication via the communication unit 31.

[0109] Next, the estimation unit 332 will be described. The estimation unit 332 estimates the concentration of impurity elements contained in the target waste based on the incidental information obtained by the information control unit 331 and the estimation model stored in the estimation model storage unit 321. A specific example of such processing will be described. The estimation unit 332 obtains incidental information corresponding to the estimation model. In other words, the estimation unit 332 obtains information equivalent to the explanatory variables of the known data used in obtaining the estimation model. The estimation unit 332 uses the information equivalent to the obtained explanatory variables (the information contained in the incidental information) and the estimation model to estimate the concentration of impurity elements contained in the target waste.

[0110] The output control unit 333 outputs information representing the estimation result of the estimation unit 332. The output control unit 333 may also output information representing the estimation result by sending it to the terminal device 10, for example. The output control unit 333 may also output information representing the estimation result by controlling an output device connected to this device. For example, the output control unit 333 may also cause an image display device connected to this device to display a string or image representing the estimation result. For example, the output control unit 333 may also cause a speaker connected to this device to output sound representing the estimation result.

[0111] Figure 13 This is a flowchart illustrating a specific example of the processing of the estimation device 30. First, the information control unit 331 obtains incidental information about the target waste from other devices (terminal device 10 or imaging device 20) (step S101). The estimation unit 332 uses the obtained incidental information and estimation model to estimate the concentration of impurity elements contained in the target waste (step S102). The estimated concentration can be calculated, for example, by the following formula: Mass percentage concentration (%) = (mass of TE component (g) / mass of waste (g)). Then, the output control unit 333 outputs the estimation result (step S103).

[0112] Figure 14This is a schematic block diagram illustrating a specific example of the functional structure of the model building apparatus 40. The model building apparatus 40 is configured using, for example, an information processing device such as a personal computer or a server. The model building apparatus 40 includes a communication unit 41, a storage unit 42, and a control unit 43.

[0113] Communication unit 41 is a communication device. Communication unit 41 may also be configured as a network interface, for example. Communication unit 41 communicates with other devices via network 200 under the control of control unit 43. Communication unit 41 can be a device for wireless communication or a device for wired communication.

[0114] Storage unit 42 is constructed using storage devices such as magnetic hard disk drives or semiconductor storage devices. Storage unit 42 stores data used by control unit 43. Storage unit 42 can also function as, for example, a known data storage unit 421 and a presumed model storage unit 422.

[0115] The known data storage unit 421 stores known data used in the model building process performed in the model building apparatus 40. The known data may, for example, be teacher data used for teacher learning processes. The known data stored in the known data storage unit 421 may be, for example, data containing supplementary information and truth labels related to the concentration of impurity elements contained in the object waste having that supplementary information. In this case, the supplementary information contained in the known data corresponds to descriptive variables, and the concentration of impurity elements contained in the object waste corresponds to target variables. The supplementary information contained in the known data may also be, for example, a two-dimensional image (appearance information) acquired by the imaging device 20.

[0116] The truth labels contained in the known data can be obtained by analyzing the iron scrap, which is the known data and has accompanying information. Specifically, for example, they can be obtained through the following analyses: For example, the amount of impurities (e.g., copper) contained in the iron scrap can be obtained by performing optical analysis on the entire iron scrap using laser, X-ray, neutron beam, etc. For example, when dissolving multiple iron scraps together, while keeping the combination of the mixed iron scraps in the same proportion, multiple dissolution results with only the proportions changed can be used, and the truth labels of each known data can be calculated based on the concentration of impurity elements in the molten steel. For example, the truth labels can also be obtained by dissolving the batch of scrap to which the TE concentration is to be determined separately and measuring the composition of the molten steel.

[0117] The estimation model storage unit 422 stores the estimation model obtained by using the model construction process of the known data stored in the known data storage unit 421.

[0118] The control unit 43 is constructed using a processor such as a CPU and memory. The control unit 43 executes programs through the processor and functions as an information control unit 431 and a model building control unit 432. Furthermore, all or part of the functions of the control unit 43 can be implemented using hardware such as ASICs, PLDs, and FPGAs. The aforementioned programs can also be recorded on computer-readable recording media. Examples of computer-readable recording media include removable media such as floppy disks, optical disks, ROMs, CD-ROMs, and semiconductor storage devices (e.g., SSDs), as well as storage devices such as hard disks built into computer systems and semiconductor storage devices. The aforementioned programs can also be transmitted via electrical communication lines.

[0119] The information control unit 431 controls the input and output of information. For example, the information control unit 431 obtains known data from other devices (information processing devices or storage media) and records it in the known data storage unit 421. For example, the information control unit 431 sends the estimated model stored in the estimated model storage unit 422 to other devices (e.g., estimated device 30).

[0120] The model building control unit 432 constructs a presumptive model by performing model building processing using known data stored in the known data storage unit 421. For example, the model building control unit 432 can also construct a presumptive model by performing teacher-assisted learning processing using supplementary information stored in the known data storage unit 421 as teacher data. Furthermore, the processing performed by the model building control unit 432 is not limited to teacher-assisted learning processing. For example, the model building control unit 432 can also construct a presumptive model by performing learning processing using known data and employing statistical methods such as multivariate analysis.

[0121] As a specific example of such learning processing, regression machine learning processing can be used, or other learning techniques such as neural networks and deep learning can be used. The model building control unit 432 records the generated estimation model in the estimation model storage unit 422. The estimation model obtained by such a model building control unit 432 can also be sent to the estimation device 30 and recorded in the estimation model storage unit 321 of the estimation device 30. By providing explanatory variables containing accompanying information as input, such an estimation model can produce an estimated value of the concentration of impurity elements corresponding to the estimation model as output.

[0122] Figure 15This is a flowchart illustrating a specific example of the processing of the model building apparatus 40. First, the information control unit 431 acquires known data (step S201). The known data may be input by a user, acquired via communication from other information devices, or acquired from a recording medium connected to the model building apparatus 40. The model building control unit 432 uses the known data to perform model building processing and records the estimated model in the estimated model storage unit 422 (step S202).

[0123] In this estimation system 100, the concentration of impurity elements contained in the target scrap is estimated based on an estimation model derived from known data of other iron scrap and accompanying information about the target scrap. Therefore, compared to methods that estimate the concentration of impurity elements in the target scrap using images and accompanying information separately, the estimation can be performed with high accuracy.

[0124] Furthermore, in the estimation system 100, the concentration of impurity elements contained in the target waste is estimated based on information obtained without dissolving the target waste. Therefore, in the estimation system 100, the concentration of impurity elements contained in the target waste can be estimated before the target waste is actually dissolved. Therefore, multiple target wastes can be appropriately proportioned based on the concentration of impurity elements, and deviations from the standard value of the concentration of impurity elements after dissolution can be prevented.

[0125] Furthermore, by making predictions in the estimation system 100 before the actual dissolution of the waste, the contamination of copper and other substances can be prevented. Additionally, since predictions can be made before the waste is dissolved, if TE content exceeds a certain threshold, measures such as screening and removal processes for prohibited substances that would be the primary cause can be implemented.

[0126] (Modified example)

[0127] In this embodiment, the terminal device 10 and the estimation device 30 are configured as different devices, but they can also be configured as an integrated device. Figure 16 This is a diagram showing a modified example of the presumption device 30 constructed in this way. Figure 16 The estimation device 30 shown includes an operation unit 34 and an output unit 35. Figure 16 The operation unit 34 and output unit 35 of the estimation device 30 shown function in the same way as the operation unit 12 and output unit 13 of the terminal device 10. The control unit 33 operates according to the operation of the operation unit 34 and outputs information using the output unit 35.

[0128] In this embodiment, the estimation device 30 and the model building device 40 are configured as different devices, but they can also be configured as an integrated device. Figure 17 This is a diagram showing a modified example of the presumption device 30 constructed in this way. Figure 17The storage unit 32 of the estimation device 30 shown also functions as a known data storage unit 322. Figure 17 The control unit 33 of the estimation device 30 also functions as the model building control unit 334. The known data storage unit 322 functions in the same way as the known data storage unit 421 of the model building device 40. The model building control unit 334 functions in the same way as the model building control unit 432 of the model building device 40.

[0129] The estimation device 30 can also be installed using multiple information processing devices. For example, the estimation device 30 can also be installed using a cloud device. For example, in the estimation device 30, the storage unit 32 and the control unit 33 can also be installed in different information processing devices. For example, the storage unit 32 of the estimation device 30 can also be distributed and installed in multiple information processing devices. The model building device 40 can also be installed using multiple information processing devices. For example, the model building device 40 can also be installed using a cloud device. For example, in the model building device 40, the storage unit 42 and the control unit 43 can also be installed in different information processing devices. For example, the storage unit 42 of the model building device 40 can also be distributed and installed in multiple information processing devices.

[0130] The estimation model stored in the estimation model storage unit 321 of the estimation device 30 can also be updated at a predetermined time interval. For example, the estimation model storage unit 321 can also be configured to store estimation models generated solely based on known data about iron scrap generated within a predetermined period, traced back to the past. With this configuration, estimation processing can be performed using estimation models that reflect the latest accompanying information. As a result, the accuracy of the estimation processing can be improved. As another specific example of the predetermined time interval, there is a time interval at which a change in the tendency to detect data increases in accordance with a predetermined benchmark. More specifically, for example, this could be a time interval at which a change in the tendency to detect changes in the predetermined benchmark is detected through unguided learning, or other algorithms for detecting changes in the tendency could be used.

[0131] A spectral sensor can also be used instead of the imaging device 20. In this case, the spectral information of the light received from the object scrap is obtained as appearance information. In this case, an estimation model obtained by model building using known data containing the same spectral information is used in the estimation process. The estimation device 30 performs estimation processing using the spectral information obtained from the spectral sensor. The estimation device 30 may perform estimation processing using spectral information without using the accompanying information, or it may perform estimation processing using both the accompanying information and the spectral information. The estimation device 30 may also perform estimation processing using the accompanying information, the spectral information, and image data. In any case, known information containing each of the information used is used for model building processing. With this configuration, information that is difficult to detect through visible light and three-dimensional shape information (such as information related to the material of the components contained in the iron scrap) can be obtained, and estimation processing can be performed with higher accuracy.

[0132] [Second Implementation]

[0133] Figure 18 This is a schematic block diagram illustrating the system structure of a second embodiment of the estimation system 100 of the present invention. The estimation system 100 of the second embodiment further includes a contraindication estimation device 50. The contraindication estimation device 50 estimates information related to contraindications contained in the target waste. Specific examples of the information related to contraindications include, for instance, the type of contraindication contained in the target waste, the quantity of each type of contraindication contained in the target waste, and the total number of contraindications contained in the target waste. The information related to contraindications may include all of the above information, or may include only a portion thereof. In the following description, as an example, aspects including the type of contraindication contained in the target waste and the quantity of each type of contraindication contained in the target waste will be described. The estimation device 30 also performs estimation processing using the estimation result of the contraindication estimation device 50. Hereinafter, a second embodiment of the estimation system 100 will be described.

[0134] The incompatible substance presumption device 50 presumes incompatible substances contained in the target waste. The incompatible substance presumption device 50 is configured, for example, using an information processing device such as a personal computer or server. Figure 19 This is a schematic block diagram illustrating a specific example of the functional structure of the contraindication presumption device 50. As shown, the contraindication presumption device 50 includes a communication unit 51, a storage unit 52, and a control unit 53.

[0135] The communication unit 51 is a communication device. For example, the communication unit 51 may also be configured as a network interface. Under the control of the control unit 53, the communication unit 51 communicates with other devices via the network 200. The communication unit 51 can be a device for wireless communication or a device for wired communication.

[0136] The storage unit 52 is constructed using a storage device such as a magnetic hard disk drive or a semiconductor storage device. The storage unit 52 stores data used by the control unit 53. The storage unit 52 can function as, for example, a forbidden object presumption model storage unit 521.

[0137] The incompatible substance presumption model storage unit 521 stores information used to presume incompatible substances contained in the target waste (hereinafter referred to as the "incompatible substance presumption model"). The incompatible substance presumption model is generated in advance through a model building process. Such a model building process can be performed by other devices (e.g., model building device 40), by this device (incompatible substance presumption device 50), or by human operation. Hereinafter, the incompatible substance presumption model stored in the incompatible substance presumption model storage unit 521 will be described.

[0138] The contraindication model can be obtained, for example, through model building processing using known data. The contraindication model can represent information about a learned model obtained through teacher-learning processing using multiple known data (teacher data) with truth labels, or information obtained through statistical processing of known data, or other information. Specific examples of learning processing include multivariate analysis, so-called machine learning, deep learning, etc. As a learning process, a classification learning process or a regression learning process can be used based on the truth labels used in the teacher data. The control unit 53 uses the contraindication model stored in the contraindication model storage unit 521 to contraindicate the contraindications contained in the target waste. The teacher data in this embodiment will be described below.

[0139] As teacher data, a combination of an image of the taboo object and a truth label (indicating the category of the taboo object contained in the image) is used. Taboo objects in iron scrap refer to objects containing a large amount of impurities, such as residual elements. Images of the taboo object can be images of individual taboo objects or images of taboo objects mixed into the iron scrap. Alternatively, images of taboo objects mixed into the iron scrap can be generated by superimposing images of individual taboo objects onto an image of the iron scrap, and this generated image can be used as the taboo object image. In these cases, a portion of the image of the object scrap (a partial image) can be input into the taboo object estimation model, and an estimation result indicating whether that portion of the image contains a taboo object can be output.

[0140] As teacher data, a combination of images of object scrap and truth labels (information indicating the categories of prohibited items contained in the image) can also be used. For example, an image of a collection of multiple pieces of iron scrap can be used, as in the case of an image captured by the imaging device 20. In this case, the truth labels can include the number of prohibited items of each category included in the object scrap appearing in the image.

[0141] Next, the control unit 53 will be described. The control unit 53 is constructed using one or more hardware processors such as a CPU and one or more memory devices (main storage devices). The memory is constructed using storage devices such as RAM and ROM (Read Only Memory). The control unit 53 performs various operations by executing one or more programs stored in the memory through one or more hardware processors. The control unit 53 functions, for example, as an information control unit 531, a prohibition presumption unit 532, and an output control unit 533. Furthermore, all or part of the functions of the control unit 53 can also be implemented using hardware such as ASICs, PLDs, and FPGAs. The aforementioned programs can also be recorded on a computer-readable recording medium. Computer-readable recording media include, for example, removable media such as floppy disks, optical disks, ROMs, CD-ROMs, semiconductor storage devices (e.g., SSDs), and storage devices such as hard disks built into computer systems. The aforementioned programs can also be transmitted via electrical communication lines.

[0142] The information control unit 531 acquires information from other devices such as the terminal device 10 and the imaging device 20. A specific example of the acquired information is an image captured by the imaging device 20. The information control unit 531 records the acquired information in a storage device such as a memory. The information control unit 531 transmits information to other devices such as the terminal device 10 and the estimation device 30. A specific example of the transmitted information is information estimated by the prohibition presumption unit 532. Such information exchange between the information control unit 531 and other devices can also be achieved, for example, through communication via the communication unit 51.

[0143] Next, the contraindication estimation unit 532 will be described. The contraindication estimation unit 532 estimates the contraindications contained in the target waste based on the image acquired by the information control unit 531 and the contraindication estimation model stored in the contraindication estimation model storage unit 521. A specific example of such processing will be described. The contraindication estimation unit 532 acquires an image corresponding to the contraindication estimation model. In other words, the contraindication estimation unit 532 acquires information corresponding to the explanatory variables used to acquire the known data for the contraindication estimation model. The contraindication estimation unit 532 uses the information corresponding to the acquired explanatory variables (an image of the same size) and the contraindication estimation model to estimate the contraindications contained in the target waste.

[0144] The output control unit 533 outputs information indicating the estimation result of the contraindication estimation unit 532. The output control unit 533 outputs information by sending information indicating the estimation result to the estimation device 30. The output control unit 533 can also send information indicating the estimation result to a device such as the terminal device 10. The output control unit 533 can also output information indicating the estimation result by controlling an output device connected to this device. For example, the output control unit 533 can also cause an image display device connected to this device to display a string or image indicating the estimation result. For example, the output control unit 533 can also cause a speaker connected to this device to output sound indicating the estimation result.

[0145] Figure 20 This is a flowchart illustrating a specific example of the processing of the contraindication estimation device 50. First, the information control unit 531 acquires an image of the target waste from another device (image capturing device 20) (step S301). The contraindication estimation unit 532 uses the acquired image and the contraindication estimation model to estimate the contraindication contained in the target waste (step S302). Then, the output control unit 533 outputs the estimation result to the estimation device 30 (step S303).

[0146] In addition, in the second embodiment Figure 18 The estimation unit 332 of the estimation device 30 shown differs from that of the first embodiment in that it uses information related to incompatible substances contained in the target waste as one of the incidental information. Specifically, the estimation unit 332 uses information indicating the type and quantity of incompatible substances contained in the target waste as explanatory variables to perform estimation processing of the concentration of impurity elements in the target waste. The information used in the estimation processing uses the estimation results of the incompatible substance estimation device 50. That is, the estimation unit 332 receives the estimation results from the incompatible substance estimation device 50, and the estimation model in the second embodiment is generated by performing model building processing using known data containing information related to incompatible substances in the incidental information. Therefore, the model building device 40 in the second embodiment stores the known data containing information related to incompatible substances in the incidental information in the known data storage unit 421, and the model building control unit 432 uses the known data to generate the estimation model.

[0147] In this estimation system 100, when estimating the concentration of impurity elements contained in the target waste, information related to the prohibited substances presumed to be contained in the target waste (e.g., category and quantity) is used as explanatory variables. Since prohibited substances contain a large number of impurities, it can be said that the information related to the prohibited substances contained in the target waste is highly correlated with the concentration of impurity elements contained in the target waste. Therefore, with this configuration, the concentration of impurity elements in the target waste can be estimated with higher accuracy.

[0148] (Modified example)

[0149] In this embodiment, the presumption device 30 and the contraindication device 50 are configured as different devices, but they can also be configured as an integrated device. Figure 21 This is a diagram showing a modified example of the presumption device 30 constructed in this way. Figure 21 The storage unit 32 of the presumption device 30 shown also functions as a presumption model storage unit 323 for taboos. Figure 21 The control unit 33 of the estimation device 30 also functions as the contraindication estimation unit 335. The contraindication estimation model storage unit 323 functions in the same way as the contraindication estimation model storage unit 521 of the contraindication estimation device 50. The contraindication estimation unit 335 functions in the same way as the contraindication estimation unit 532 of the contraindication estimation device 50.

[0150] The contraindication presumption device 50 can be installed using multiple information processing devices. For example, the contraindication presumption device 50 can be installed using a device such as a cloud. For example, in the contraindication presumption device 50, the storage unit 52 and the control unit 53 can be installed in different information processing devices. For example, the storage unit 52 of the contraindication presumption device 50 can be distributed and installed in multiple information processing devices.

[0151] [Third Implementation Method]

[0152] Figure 22 This is a schematic block diagram illustrating the system structure of the third embodiment of the estimation system 100 of the present invention. The estimation system 100 of the third embodiment further includes a removal target determination device 60 and a weight measuring device 400 in the second embodiment of the estimation system 100. In the removal target determination device 60, an upper limit value (hereinafter referred to as the "impurity upper limit value") is set for the concentration of impurity elements permissible in the target waste. The impurity upper limit value can be determined as a concentration or as the absolute amount (mass) of the waste per unit weight. The removal target determination device 60 determines that among the prohibited substances contained in the target waste, those that should be removed (hereinafter referred to as "removal target prohibited substances") are below the impurity upper limit value. Based on the determination result of the removal target determination device 60, the operator removes the prohibited substances from the target waste, thereby adjusting the concentration of impurity elements in the target waste to below the impurity upper limit value. The third embodiment of the estimation system 100 will be described below.

[0153] The weight measuring device 400 measures the weight related to the target waste in the estimation system 100. The weight measuring device 400 can also measure the weight of the target waste itself, for example. In this case, the weight of the target waste itself can be measured, for example, by placing the target waste on a weighing scale as described later. The weight measuring device 400 can also measure the weight of the container containing the target waste and the target waste together, for example. In this case, the weight measuring device 400 can also measure the weight of the container after all the target waste has been removed. The weight of the target waste can also be calculated by subtracting the weight of the container after all the target waste has been removed from the weight measurement result of the container and the target waste. Such calculation can be performed by the weight measuring device 400, or by devices such as the estimation device 30 and the target removal determination device 60. The weight measuring device 400 can also measure the weight of the mobile body (e.g., a truck) containing the target waste and the target waste together, for example. In this case, the weight measuring device 400 can also measure the weight of the mobile body after all the target waste has been removed. The weight of the target waste can also be calculated by subtracting the weight of the mobile body after all the target waste has been transported out from the weight measurement result of the mobile body and the target waste. Such calculation can be performed by the weight measuring device 400, or by the estimation device 30, the target removal determination device 60, or other devices.

[0154] The weight measuring device 400 may, for example, have a vessel for loading the object waste on top, and be constructed using a weight gauge that measures the weight of the object loaded on the vessel. The weight measuring device 400 may also be buried in the ground, and be constructed using a vehicle weight gauge that measures the weight of a vehicle located above it. Other structures may also be used for the weight measuring device 400. The weight measuring device 400 sends information indicating the measurement result to the estimation device 30 and the object removal determination device 60.

[0155] The object removal determination device 60 determines the prohibited substances contained in the target waste in a manner that is below the upper limit of impurities. The object removal determination device 60 is configured, for example, using an information processing device such as a personal computer or a server device. Figure 23 This is a schematic block diagram illustrating a specific example of the functional structure of the object removal determination device 60. As shown in the example, the object removal determination device 60 includes a communication unit 61, a storage unit 62, and a control unit 63.

[0156] Communication unit 61 is a communication device. Communication unit 61 may also be configured as a network interface, for example. Under the control of control unit 63, communication unit 61 communicates with other devices via network 200. Communication unit 61 can be a device for wireless communication or a device for wired communication.

[0157] The storage unit 62 is constructed using a storage device such as a magnetic hard disk drive or a semiconductor storage device. The storage unit 62 stores data used by the control unit 63. The storage unit 62 can function as, for example, a forbidden item information storage unit 621.

[0158] The contraindication information storage unit 621 stores contraindication information as information related to the weight of the contraindication. Figure 24 This is a diagram showing specific examples of contraindications. Figure 24 The contraindication information displayed includes three values: contraindication name, copper weight, and average weight. The contraindication name indicates the category of each contraindication. The copper weight represents the average weight of the impurities (copper) contained in each category of contraindications. In this embodiment, copper is used as an example of an impurity contained in a contraindication, but the weight of other impurities can also be recorded in the contraindication information. The average weight represents the average weight of the contraindications in each category. For example, in an electric motor, it is known empirically that approximately 20% of the total weight is copper. The same approach is used for other contraindications.

[0159] Next, the control unit 63 will be described. The control unit 63 is constructed using one or more hardware processors such as a CPU and one or more memory devices (main storage devices). The memory is constructed using storage devices such as RAM and ROM (Read Only Memory). The control unit 63 executes one or more programs stored in the memory via one or more hardware processors, thereby performing various operations and performing its functions. The control unit 63 functions, for example, as an information control unit 631, a removal object determination unit 632, and an output control unit 633. Furthermore, all or part of the functions of the control unit 63 can also be implemented using hardware such as ASICs, PLDs, and FPGAs. The aforementioned programs can also be recorded on a computer-readable recording medium. Computer-readable recording media include, for example, removable media such as floppy disks, optical disks, ROMs, CD-ROMs, semiconductor storage devices (e.g., SSDs), and storage devices such as hard disks built into computer systems. The aforementioned programs can also be transmitted via electrical communication lines.

[0160] The information control unit 631 obtains information from other devices such as the terminal device 10, the estimation device 30, and the contraindication estimation device 50. Specific examples of the obtained information include, for instance, the estimation result from the contraindication estimation device 50. Other specific examples of the obtained information include, for instance, information related to the upper limit value of impurities. The information control unit 631 records the obtained information in a storage device such as a memory. The information control unit 631 transmits information to the terminal device 10, the estimation device 30, and other devices. Specific examples of the transmitted information include, for instance, information determined by the removal target determination unit 632 (information indicating the contraindication to be removed). Such information exchange between the information control unit 631 and other devices can also be performed, for example, through communication with the communication unit 61.

[0161] The removal target determination unit 632 determines the type and amount of prohibited substances to be removed from the target waste based on the weight of the target waste, the estimated concentration of impurity elements contained in the target waste, information related to prohibited substances contained in the target waste, and the upper limit value of impurities. That is, the removal target determination unit 632 accepts the estimated concentration of impurity elements contained in the target waste, information related to prohibited substances contained in the target waste, and the upper limit value of impurities as input. The removal target determination unit 632 determines whether it is necessary to remove prohibited substances to lower the upper limit value of impurities by performing a prescribed process (removal necessity determination process) and outputs the determination result. For example, when this process is performed at a time when unloading from the truck bed using the handling device 300, the process can also be performed so that the concentration of impurity elements in each batch lifted by the lifting electromagnet 301 for unloading is lower than the upper limit value of impurities.

[0162] When this process is performed at a time when unloading from the truck bed using the handling device 300, the process can also be performed as follows: Each time waste is lifted from the truck bed by the lifting electromagnet 301 for unloading, an image of the object waste accumulated in the truck bed is acquired. Then, processing is performed on each newly acquired image to ensure that the concentration of impurity elements is below the upper limit value for impurities. Each time waste is lifted by the lifting electromagnet 301, a new surface layer of the object waste accumulated in the truck bed is exposed and imaged. Therefore, object waste that cannot initially be imaged upon the arrival of the truck and is accumulated on the inside or bottom can also be appropriately identified. The environment in which this structure is employed is not limited to an environment where object waste is lifted from the truck bed. For example, it can be applied to environments where a large amount of object waste is accumulated in a designated area such as the ground, and from there, object waste is gradually moved to other areas using handling equipment such as the lifting electromagnet 301.

[0163] A specific example of whether removal is required will be explained. The removal target determination unit 632 first obtains an estimation result related to the concentration of impurity elements contained in the target waste. Such an estimation result can be obtained, for example, by performing estimation processing using an estimation model stored in the estimation model storage unit 321. The removal target determination unit 632 can also determine whether removal is required based on whether the estimation result (estimated value) of the concentration of impurity elements contained in the target waste is less than a predetermined threshold. For example, if the estimated value is less than the predetermined threshold, removal is deemed unnecessary; if the estimated value is above the predetermined threshold, removal is deemed necessary. The predetermined threshold can also be determined for each type of impurity element.

[0164] Figure 25 This is a flowchart illustrating a specific example of the processing of the object removal determination unit 632. The specific example of the processing of the object removal determination unit 632 will be described below. The object removal determination unit 632 obtains an estimated value of the concentration of impurity elements contained in the target waste (step S401). The object removal determination unit 632 determines whether the estimated value of the impurity element concentration is less than the upper limit value of impurities (step S402). When the estimated value of the impurity element concentration exceeds the upper limit value of impurities (step S402-No), the object removal determination unit 632 determines the prohibited substances that should be removed in order to reduce the concentration of impurity elements below the upper limit value of impurities (removal of prohibited substances) (step S403).

[0165] In step S403, for example, the object removal determination unit 632 determines to remove prohibited substances so that the concentration of impurity elements in the object waste after removing the prohibited substances is less than an upper limit value. For example, by referring to the prohibited substance information stored in the prohibited substance information storage unit 621, the average value of impurities (copper) contained in each type of prohibited substance and the average value of the weight of the prohibited substance itself can be known. When the upper limit value of impurities is given proportionally, the total amount of impurities to be removed can be calculated by multiplying the weight of the object waste by the value obtained by subtracting the upper limit value of impurities from the estimated value of impurity element concentration. The object removal determination unit 632 determines to remove prohibited substances so that the total amount of impurities contained in the prohibited substances actually removed exceeds the total amount calculated here.

[0166] At this time, when the estimation result of the incompatible substance estimation device 50 is obtained, the removal target determination unit 632 can select the incompatible substance to be removed from the categories and quantities of incompatible substances included in the estimation result of the incompatible substance estimation device 50. In this way, by determining the incompatible substance to be removed by the removal target determination unit 632, information related to the incompatible substances that can be removed more realistically can be output to the operator, making it easier to ensure that the concentration of impurity elements contained in the target waste is less than the upper limit value of impurities.

[0167] The output control unit 633 outputs information indicating the determination result of the object removal determination unit 632. The output control unit 633 may also output information indicating the determination result by sending it to the terminal device 10, for example. The output control unit 633 may also output information indicating the determination result by controlling an output device connected to this device. For example, the output control unit 633 may also cause an image display device connected to this device to display a string or image indicating the determination result. For example, the output control unit 633 may also cause a speaker connected to this device to output sound indicating the determination result.

[0168] Figure 26 This diagram illustrates an application example of the estimation system 100 in this embodiment. Figure 26 In the application example shown, in Figure 2 The application example shown also includes a weight measuring device 400. Figure 26 For example, a weight measuring device 400 is installed within the shooting range of the shooting device 20. With this setup, the object waste can be photographed while the weight is being measured by the weight measuring device 400. The determination result of the object removal determination device 60 can also be sent to the terminal device 10. In this case, the person operating the terminal device 10 (operator) can remove the object removal contraindication from the object waste based on the information indicating the object removal contraindication is output in the terminal device 10.

[0169] In the estimation system 100 configured in this way, the object determination device 60 outputs specific examples of the types and amounts of prohibited substances that need to be removed to ensure that the impurity content in the target waste is below the upper limit of the impurity value. Therefore, prohibited substances can be easily removed in a manner that meets the requirement of the upper limit of the impurity value.

[0170] [Fourth Implementation Method]

[0171] Figure 27 This is a schematic block diagram illustrating the system structure of the estimation system 100 according to the fourth embodiment of the present invention. The estimation system 100 of the fourth embodiment further includes a proportioning information determination device 70 in the first embodiment of the estimation system 100. The proportioning information determination device 70 determines the proportion of multiple batches of waste, to which the concentration of impurity elements is estimated, to meet a prescribed standard. The person determining the proportion of the waste determines the proportion by referring to the output of the proportioning information determination device 70, enabling easier and more accurate iron production using iron scrap. The fourth embodiment of the estimation system 100 will be described below.

[0172] The proportioning information determination device 70 determines the proportions of multiple batches of iron scrap. The proportioning information determination device 70 is constructed, for example, using an information processing device such as a personal computer or server. Figure 28This is a schematic block diagram illustrating a specific example of the functional structure of the proportioning information determination device 70. As shown in the example, the proportioning information determination device 70 includes a communication unit 71, a storage unit 72, and a control unit 73.

[0173] Communication unit 71 is a communication device. Communication unit 71 may also be configured as a network interface, for example. Communication unit 71 communicates with other devices via network 200 under the control of control unit 73. Communication unit 71 can be a device for wireless communication or a device for wired communication.

[0174] The storage unit 72 is constructed using storage devices such as magnetic hard disk drives and semiconductor storage devices. The storage unit 72 stores data used by the control unit 73. For example, the storage unit 72 can also function as an inventory information storage unit 721.

[0175] The inventory information storage unit 721 stores information related to the inventory of iron scrap, namely, inventory information. Figure 29 This is a diagram showing a specific example of inventory information. Figure 29 The inventory information shown includes four values: batch identification information, inventory quantity, average unit price, and impurity concentration. Batch identification information identifies each batch. Inventory quantity represents the total inventory of iron scrap belonging to each batch. Average unit price represents the average unit price of iron scrap belonging to each batch. For example, if each batch contains only one type of scrap, the amount allocated to that scrap is reflected in the average unit price. If each batch contains multiple types of scrap, the average unit price is calculated based on the weight of the scrap in each batch and the purchase price. Impurity concentration represents the average concentration of impurity elements contained in the iron scrap belonging to each batch. For example, if each batch contains only one type of scrap, the estimated concentration of impurity elements in that scrap is reflected in the impurity concentration. If each batch contains multiple types of scrap, the impurity concentration is calculated based on the weight of the scrap in each batch and the estimated concentration of impurity elements.

[0176] Next, the control unit 73 will be described. The control unit 73 is constructed using one or more hardware processors such as a CPU and one or more memory devices (main storage devices). The memory is constructed using storage devices such as RAM and ROM (Read Only Memory). The control unit 73 executes one or more programs stored in the memory via one or more hardware processors, thereby performing various operations and performing its functions. The control unit 73 functions, for example, as an information control unit 731, a proportioning information determination unit 732, and an output control unit 733. Furthermore, all or part of the functions of the control unit 73 can also be implemented using hardware such as ASICs, PLDs, and FPGAs. The aforementioned programs can also be recorded on a computer-readable recording medium. Computer-readable recording media include, for example, removable media such as floppy disks, optical disks, ROMs, CD-ROMs, semiconductor storage devices (e.g., SSDs), and storage devices such as hard disks built into computer systems. The aforementioned programs can also be transmitted via electrical communication lines.

[0177] The information control unit 731 obtains information from the terminal device 10 and other devices such as the estimation device 30. Specific examples of the obtained information include, for instance, information indicating the prescribed conditions that must be met when producing molten steel for a desired steel grade. These prescribed conditions may, for example, indicate an upper limit on the amount of impurities (e.g., copper) that can be contained in the molten steel. Price-related conditions may also be included. For example, an upper limit on the price may be included, or a condition such as "as low as possible" may be included regarding the price. Furthermore, the price in this embodiment is a price already determined based on market conditions, purchase performance, etc., and differs from the price used in subsequent transactions between practitioners (the purchase price). The information control unit 731 records the obtained information in a storage device such as a memory. The information control unit 731 transmits information to the terminal device 10, the estimation device 30, and other devices. Specific examples of the transmitted information include, for instance, the determination result of the proportioning information. Such information exchange between the information control unit 731 and other devices can also be performed, for example, through communication with the communication unit 71.

[0178] The proportioning information determination unit 732 determines the proportion of iron scrap in a manner that satisfies the specified conditions. For example, the proportioning information determination unit 732 may also determine the proportion based on at least one of the following specified conditions (constraints) using a specified algorithm (e.g., linear programming). Furthermore, as a specific example of the specified conditions, there are conditions such as the following.

[0179] • Conditions regarding the concentration of impurity elements in molten steel (e.g., upper limits).

[0180] • Conditions (e.g., minimizing) regarding the total cost of the amount of iron scrap contained in the molten steel.

[0181] • Conditions related to the use of low-stocked iron scrap (e.g., minimization).

[0182] • The higher the purchase price of the iron scrap, the less it should be used.

[0183] • The cheaper the iron scrap was when it was purchased, the more it is used.

[0184] For example, the target value of the total weight of the iron scrap used for proportioning and the upper limit of the concentration of impurities (e.g., copper) can also be used as constraints. Figure 29 The inventory information shown determines the proportions as follows. First, the constraints are determined. As a premise, considering the use of newly cut scrap as a specific example of high-grade iron scrap (high-grade scrap) in proportion to low-grade iron scrap (low-grade scrap). It should be noted that high-grade iron scrap is not limited to newly cut scrap; for example, it can be molten iron obtained from a blast furnace, or other materials can be used. At this time, the average impurity concentration (D high-grade iron scrap) and average unit price of the high-grade iron scrap (newly cut scrap) are obtained, and the inventory quantity of high-grade iron scrap is unlimited. At this time, the following problem is solved by using the impurity concentration of each batch (e.g., D11, D12, D13) and the usage of each batch (e.g., t1, t2, t3). In addition, "C high-grade iron scrap" represents the average unit price of high-grade iron scrap, "D high-grade iron scrap" represents the impurity concentration of high-grade iron scrap, "t high-grade iron scrap" represents the weight of high-grade iron scrap used, and "tn" represents the weight of each batch n used.

[0185] Σ(Dn×tn)+D high-grade iron scrap×t high-grade iron scrap

[0186] = (D11×t1+D12×t2+D13×t3+D high-grade iron scrap×t high-grade iron scrap) / (weight Σtn+t high-grade iron scrap) <= Upper limit of impurity concentration

[0187] The constraints are as follows.

[0188] 1. Weight Σtn+t of high-grade iron scrap meets the target weight.

[0189] 2. Using the price Σ(average unit price n×tn) + Chigh-grade iron scrap×thigh-grade iron scrap minimum

[0190] Additionally, in the above formula, "<=" means that the left side is less than or equal to the value on the right side.

[0191] Furthermore, the materials included in the proportion determined by the proportioning information determination unit 732 may not all be iron scrap. Additionally, inventory levels can be obtained based on delivery data (data indicating how much has been purchased, for example, in tons). Furthermore, if the correct amount of material containing impurities is determined to be used as material, the proportion of iron scrap can be determined based on the difference between the total permissible amount of impurities and the concentration of the corresponding impurity element.

[0192] The output control unit 733 outputs information indicating the determination result of the proportioning information determination unit 732. The output control unit 733 may also output information indicating the determination result by sending it to the terminal device 10, for example. The output control unit 733 may also output information indicating the determination result by controlling an output device connected to this device. For example, the output control unit 733 may also cause an image display device connected to this device to display a string or image indicating the determination result. For example, the output control unit 733 may also cause a speaker connected to this device to output sound indicating the determination result.

[0193] In this estimation system 100, the proportioning information determination device 70 allows for the easy determination of the appropriate proportions for manufacturing molten steel that meets specified conditions using the inventory of iron scrap. Therefore, it can promote the demand for iron scrap.

[0194] [Fifth Implementation Method]

[0195] Figure 30 This is a schematic block diagram illustrating the system structure of the fifth embodiment of the estimation system 100 of the present invention. The estimation system 100 of the fifth embodiment further includes a price determination device 80 in the first embodiment of the estimation system 100. The price determination device 80 determines the price of the target scrap based on the estimation result of the estimation device 30. The fifth embodiment of the estimation system 100 will be described below. Furthermore, the price determined by the price determination device 80 is, for example, the purchase price (transaction price) between a manufacturer and another manufacturer when a manufacturer brings in iron scrap and submits a purchase application.

[0196] The price determination device 80 is composed of information processing devices such as personal computers and server devices. Figure 31 This is a schematic block diagram illustrating a specific example of the functional structure of the price determination device 80. As shown in the example, the price determination device 80 includes a communication unit 81, a storage unit 82, and a control unit 83.

[0197] The communication unit 81 is a communication device. For example, the communication unit 81 may also be configured as a network interface. Under the control of the control unit 83, the communication unit 81 communicates with other devices via the network 200. The communication unit 81 can be a device for wireless communication or a device for wired communication.

[0198] The storage unit 82 is constructed using storage devices such as magnetic hard disk drives and semiconductor storage devices. The storage unit 82 stores data used by the control unit 83. For example, the storage unit 82 can also function as a price information storage unit 821.

[0199] Price Information Storage Department 821 stores information related to the price of iron scrap, namely price information. Figure 32 This is a diagram showing a specific example of price information. Figure 32 The price information displayed includes two values: impurity concentration and unit price. Impurity concentration represents the range of impurity element concentrations per unit weight (e.g., 1 ton) of the target waste. Unit price represents the price assigned to the target waste with impurity concentrations within this range. By referring to the price information, the unit price can be obtained based on the impurity element concentration. In other words, by using the price information to determine the price, the price corresponding to the impurity concentration contained in the target waste can be determined.

[0200] Next, the control unit 83 will be described. The control unit 83 is constructed using one or more hardware processors such as a CPU and one or more memory devices (main storage devices). The memory is constructed using storage devices such as RAM and ROM (Read Only Memory). The control unit 83 executes one or more programs stored in the memory via one or more hardware processors, thereby performing various operations and performing its functions. The control unit 83 functions, for example, as an information control unit 831, a price determination unit 832, and an output control unit 833. Furthermore, all or part of the functions of the control unit 83 can also be implemented using hardware such as ASICs, PLDs, and FPGAs. The aforementioned programs can also be recorded on a computer-readable recording medium. Computer-readable recording media include, for example, removable media such as floppy disks, optical disks, ROMs, CD-ROMs, semiconductor storage devices (e.g., SSDs), and storage devices such as hard disks built into computer systems. The aforementioned programs can also be transmitted via electrical communication lines.

[0201] The information control unit 831 obtains information from the terminal device 10 and other devices such as the estimation device 30. For example, the obtained information may include the estimation result of the concentration of impurity elements from the estimation device 30. The information control unit 831 then transmits information to the terminal device 10, the estimation device 30, and other devices. For example, the transmitted information may include the determination result of the price of the target waste. This exchange of information between the information control unit 831 and other devices can also be achieved, for example, through communication with the communication unit 81.

[0202] The price determination unit 832 determines the unit price of the target waste based on the estimation result of the estimation device 30. For example, the price determination unit 832 receives the estimation result of the concentration of impurity elements from the estimation device 30 as input. Figure 32 The price information shown is used to obtain the unit price corresponding to the impurity concentration shown in the input estimation result. When the price determination unit 832 obtains information related to the weight of the target waste from the weight measuring device 400, it can also determine the price of the target waste by multiplying the determined unit price by the weight.

[0203] The output control unit 833 outputs information indicating the determination result of the price determination unit 832. The output control unit 833 may also output information indicating the determination result by sending it to the terminal device 10, for example. The output control unit 833 may also output information indicating the determination result by controlling an output device connected to this device. For example, the output control unit 833 may also cause an image display device connected to this device to display a string or image indicating the determination result. For example, the output control unit 833 may also cause a speaker connected to this device to output sound indicating the determination result.

[0204] In the estimation system 100 configured in this way, the price determination device 80 can determine the price corresponding to the concentration of impurities contained in the target waste.

[0205] Figure 33 This is a schematic diagram illustrating an example of the hardware structure of the information processing apparatus 90 applied in this embodiment. The information processing apparatus 90 includes a processor 91, a main storage device 92, a communication interface 93, an auxiliary storage device 94, an input / output interface 95, and an internal bus 96. The processor 91, main storage device 92, communication interface 93, auxiliary storage device 94, and input / output interface 95 are connected to each other via the internal bus 96 in a manner enabling communication. The information processing apparatus 90 can be applied, for example, to a terminal device 10, an estimation device 30, a model building device 40, a contraindication estimation device 50, a removal object determination device 60, a proportioning information determination device 70, and a price determination device 80. In this case, for example, the communication unit of each device can also be configured using the communication interface 93. For example, the storage unit of each device can also be configured using the auxiliary storage device 94. Furthermore, the control unit of each device can also be configured using the processor 91 and the main storage device 92.

[0206] The embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the specific structure is not limited to these embodiments and may include designs that do not depart from the spirit of the present invention.

[0207] Explanation of reference numerals in the attached figures

[0208] 100: Presumption System

[0209] 10: Terminal device

[0210] 20: Filming equipment

[0211] 30: Estimation device

[0212] 31: Ministry of Communications

[0213] 32: Storage Department

[0214] 321: Estimated Model Storage Unit

[0215] 33: Control Department

[0216] 331: Information Control Department

[0217] 332: Presumption

[0218] 333: Output Control Unit

[0219] 40: Model building device

[0220] 41: Ministry of Communications

[0221] 42: Storage Department

[0222] 421: Known data storage unit

[0223] 422: Estimated Model Storage Unit

[0224] 43: Control Department

[0225] 431: Information Control Department

[0226] 432: Model Building Control Department

[0227] 50: Presumption of contraindications device

[0228] 60: Remove object determination device

[0229] 70: Proportioning Information Determination Device

[0230] 80: Price determination device

Claims

1. A estimation device, characterized in that, The system includes a control unit that uses a estimation model to estimate the concentration of impurity elements contained in the iron scrap to be judged. The estimation model is pre-constructed using known data, which includes incidental information related to the iron scrap containing the iron to be recycled and information related to the concentration of impurity elements contained in the iron scrap.

2. The estimation device according to claim 1, characterized in that, The accompanying information includes property information of the iron scrap itself or information related to prior inspections of the iron scrap.

3. The estimation device according to claim 1 or 2, characterized in that, The accompanying information includes information related to the appearance of the iron scrap.

4. The estimation device according to claim 1, characterized in that, The accompanying information includes information related to prohibited substances contained in the iron scrap.

5. The estimation device according to claim 4, characterized in that, The information related to the prohibited substances contained in the iron scrap indicates the number or type of prohibited substances estimated using a pre-established prohibited substance estimation model for estimating prohibited substances.

6. A method of estimation, characterized in that, It includes a estimation step in which an estimation model is used to estimate the concentration of impurity elements contained in the iron scrap to be determined. The estimation model is pre-constructed using known data, which includes information related to the iron scrap containing the iron to be recycled, i.e., incidental information, and information related to the concentration of impurity elements contained in the iron scrap.

7. A computer program, characterized in that, For enabling a computer to function as a estimation device, the estimation device includes a control unit that uses an estimation model to estimate the concentration of impurity elements contained in the iron scrap to be determined. The estimation model is pre-constructed using known data, which includes information related to the iron scrap containing the iron to be recycled, i.e., incidental information, and information related to the concentration of impurity elements contained in the iron scrap.

8. A estimation system, characterized in that, have: The estimation unit uses an estimation model to estimate the concentration of impurity elements contained in the iron scrap that is to be judged. The estimation model is pre-constructed using known data, which includes information related to the iron scrap containing the iron to be recovered, i.e., incidental information, and information related to the concentration of impurity elements contained in the iron scrap. The object removal determination unit determines the prohibited substances that should be removed from the iron scrap based on the estimation result of the estimation unit.

9. The estimation system according to claim 8, characterized in that, The accompanying information includes information related to the appearance of the iron scrap.

10. A determination method, characterized in that, have: The estimation step uses an estimation model to estimate the concentration of impurity elements contained in the iron scrap that is to be judged. The estimation model is pre-constructed using known data, which includes information related to the iron scrap containing the iron to be recovered, i.e., incidental information, and information related to the concentration of impurity elements contained in the iron scrap. The object removal determination step, based on the presumption result in the presumption step, determines the prohibited substances that should be removed from the iron scrap.

11. A computer program, characterized in that, For enabling a computer to function as a presumption system, the presumption system comprising: The estimation unit uses an estimation model to estimate the concentration of impurity elements contained in the iron scrap that is to be judged. The estimation model is pre-constructed using known data, which includes information related to the iron scrap containing the iron to be recovered, i.e., incidental information, and information related to the concentration of impurity elements contained in the iron scrap. The object removal determination unit determines the prohibited substances that should be removed from the iron scrap based on the estimation result of the estimation unit.

12. A estimation system, characterized in that, have: The estimation unit uses an estimation model to estimate the concentration of impurity elements contained in the iron scrap that is to be judged. The estimation model is pre-constructed using known data, which includes information related to the iron scrap containing the iron to be recovered, i.e., incidental information, and information related to the concentration of impurity elements contained in the iron scrap. The proportioning information determination unit determines the proportion of iron scrap based on the estimation result of the estimation unit and the price of the iron scrap, in a manner that meets specified conditions.

13. A determination method, characterized in that, have: The estimation step uses an estimation model to estimate the concentration of impurity elements contained in the iron scrap that is to be judged. The estimation model is pre-constructed using known data, which includes information related to the iron scrap containing the iron to be recovered, i.e., incidental information, and information related to the concentration of impurity elements contained in the iron scrap. The proportioning information determination step determines the proportion of iron scrap based on the estimation results in the estimation step and the specified conditions related to the iron scrap, in a manner that satisfies the specified conditions.

14. A computer program, characterized in that, For enabling a computer to function as a presumption system, the presumption system comprising: The estimation unit uses an estimation model to estimate the concentration of impurity elements contained in the iron scrap that is to be judged. The estimation model is pre-constructed using known data, which includes information related to the iron scrap containing the iron to be recovered, i.e., incidental information, and information related to the concentration of impurity elements contained in the iron scrap. The proportioning information determination unit determines the proportion of iron scrap based on the estimation result of the estimation unit and the price of the iron scrap, in a manner that satisfies specified conditions.

15. A estimation system, characterized in that, have: The estimation unit uses an estimation model to estimate the concentration of impurity elements contained in the iron scrap that is to be judged. The estimation model is pre-constructed using known data, which includes information related to the iron scrap containing the iron to be recovered, i.e., incidental information, and information related to the concentration of impurity elements contained in the iron scrap. The price determination unit determines the price of the iron scrap based on the estimation result of the estimation unit.

16. A determination method, characterized in that, have: The estimation step uses an estimation model to estimate the concentration of impurity elements contained in the iron scrap that is to be judged. The estimation model is pre-constructed using known data, which includes information related to the iron scrap containing the iron to be recovered, i.e., incidental information, and information related to the concentration of impurity elements contained in the iron scrap. The price determination step determines the price of the iron scrap based on the estimation result in the estimation step.

17. A computer program, characterized in that, For use as a presumption system, the presumption system comprises: The estimation unit uses an estimation model to estimate the concentration of impurity elements contained in the iron scrap that is to be judged. The estimation model is pre-constructed using known data, which includes information related to the iron scrap containing the iron to be recovered, i.e., incidental information, and information related to the concentration of impurity elements contained in the iron scrap. The price determination unit determines the price of the iron scrap based on the estimation result of the estimation unit.

Images