Method and apparatus for recycling feedstock identification

Abstract

The present invention is related to a method for recycling feedstock identification, the method comprising the steps of: Identifying (S1) a delivery portion of a recycling feedstock by providing at least one delivery identifier for delivery identification; Recording (S2) at least one image of at least one portion of the delivery portion of the recycling feedstock; Annotating (S3) at least one data identifier on the recorded at least one image, the data identifier identifying an impurity of the at least one portion of the delivery portion of the recycling feedstock; Evaluating (S4) a quality level of the at least one portion of the delivery portion of the recycling feedstock based on the recorded at least one image and the at least one annotated data identifier; and Deciding (S5) an acceptance of the delivery portion of the recycling feedstock based on the evaluated quality level of the at least one portion of the delivery portion of the recycling feedstock.

Description

[Technical Field]

[0001] The present invention relates to a method and apparatus for identifying recycled raw materials, and more particularly to a tool-based method and apparatus for identifying recycled raw materials for use in quality control. [Previous Technology]

[0002] In industries such as recycling or chemicals, quality control (QC) engineers at recycling facilities are informed about new deliveries because relevant information is manually copied to electronic forms. The QC engineer continues to evaluate the fields using handwritten memos and images captured by a camera. Back in the office, the evaluated data is manually copied to the aforementioned electronic form. A final report is generated, printed, and stored offline in a cabinet. All relevant images are manually moved to a folder.

[0003] This leads to problems, namely, that manually entering data into larger electronic forms is a time-consuming process for raw material QC and is prone to errors - misdelivery or typos.

[0004] Because the evaluation is stored locally and most of the data entered is in free fields rather than predefined categories, the data is not ready for further processing. Proper statistical evaluation and visualization of historical data is not feasible, or only feasible if it requires a great deal of extra effort.

[0005] Electronic forms stored on this site may result in unintentional changes or deletions of items. There is no option to label contaminants in images to provide the necessary training for future image recognition settings, which would be required for discussions with suppliers regarding existing contaminants. [Summary of the Invention]

[0006] The foregoing and other objectives are achieved by the subject matter of the invention as defined in the independent paragraph. Other embodiments are defined in the appendices.

[0007] According to a first aspect of the present invention, a method is provided, which is a method for identifying recycled raw materials in relation to a tool-based recycled raw material identification method for use in quality control.

[0008] A method for identifying recycled raw materials includes the following steps: identifying a delivery portion of recycled raw materials by providing at least one delivery identifier for delivery identification; recording at least one image of at least one portion of the delivery portion of recycled raw materials; annotating at least one data identifier on the recorded at least one image, the data identifier identifying impurities in at least one portion of the delivery portion of recycled raw materials; evaluating the quality grade of at least one portion of the delivery portion of recycled raw materials based on the recorded at least one image and the annotated at least one data identifier; and determining acceptance of the delivery portion of recycled raw materials based on the evaluated quality grade of at least one portion of the delivery portion of recycled raw materials.

[0009] Therefore, differences between different delivery parts are possible.

[0010] In other words, as a difference from prior art, the present invention advantageously provides a time saving and a simpler life for production engineers entering QC. Furthermore, the present invention advantageously allows for direct connection via electronic data processing to any Enterprise Resource Planning (ERP) system and to any Production Planning and Management (PPM) system.

[0011] Furthermore, the present invention advantageously allows for the avoidance of evaluation of erroneous deliveries.

[0012] Furthermore, in exemplary embodiments, the present invention advantageously provides an improvement to scanning barcode data to initiate an evaluation process and to mark impurities in an image by means of annotated identifiers, which is a pre-work for possible deep learning.

[0013] Furthermore, the present invention advantageously provides an improvement in the functionality of predefined categories in the evaluation process and the dashboard regarding delivery company and QC evaluation results. Additionally, the present invention advantageously allows for the avoidance of typos, and advantageously enables simple post-processing for the delivery process.

[0014] In other words, the present invention advantageously provides direct decision support for (supplier) management and price negotiation, and prerequisites for raw material-process-characteristic relationships. By implementing internal solutions, the present invention advantageously provides the possibility of applying AI to assist in QC entry control / automating QC entry control, and better documentation and verification of rejected materials.

[0015] Furthermore, the present invention advantageously provides improved data transmission and reduced energy consumption, due to the real-time monitoring and analysis of material quality.

[0016] According to an exemplary embodiment of the present invention, the data identifier further specifies the specifications and / or impurity content of at least one portion of the delivery portion of each delivery of recycled raw materials.

[0017] According to one embodiment of the present invention, annotating at least one data identifier on at least one recorded image includes marking at least one recorded image by the at least one annotated data identifier, thereby generating at least one enhanced image having computer-generated perceptual information.

[0018] According to an exemplary embodiment of the present invention, the method further includes the following steps: performing a login procedure on a tablet computer using multi-factor authentication (MFA) to initiate a multi-user environment, wherein at least one data identifier and at least one recorded image are mapped to a specific user of the initiated multi-user environment.

[0019] According to an exemplary embodiment of the present invention, the method further includes the steps of: mapping a measured quality grade of a plurality of portions of the delivery portion of the recycled material to an evaluated quality grade of the recycled material; and / or performing machine learning by constructing a model based on the measured quality grade of the plurality of portions of the delivery portion of the recycled material and the evaluated quality grade of the recycled material to improve the evaluation of the quality grade of the recycled material.

[0020] In other words, the deep learning model can be based on labeled images depicting multiple parts of the delivery section of the recycled material, and the measured quality grade and the evaluated quality grade are aligned based on the applied deep learning model.

[0021] According to an exemplary embodiment of the present invention, the method further includes the step of scanning a barcode marked to the recycled material, the barcode providing at least one delivery identifier for delivery identification.

[0022] According to an exemplary embodiment of the present invention, the method further includes the step of: evaluating the quality grade of at least one portion of the delivery portion of the recycled material based on at least one recorded image and at least one annotated data identifier and a delivery identifier for delivery identification.

[0023] According to an exemplary embodiment of the present invention, the method further includes the step of generating input data that provides at least one parameter of the recycled raw material.

[0024] According to an exemplary embodiment of the present invention, the method further includes the step of: evaluating the quality grade of at least one portion of the delivery portion of the recycled material based on at least one recorded image, at least one annotated data identifier, and at least one parameter of the recycled material.

[0025] According to an exemplary embodiment of the present invention, the input data is generated by user input.

[0026] According to a second aspect of the present invention, a computer program product is provided, which includes computer-readable instructions that, when loaded and executed on a processor, perform any embodiment of the embodiments of the first aspect or, in relation to the first aspect itself, a method.

[0027] According to a third aspect of the present invention, an apparatus is provided, the apparatus being configured for identifying recycled materials, the apparatus including an image sensor configured to identify a delivery portion of the recycled materials by providing at least one delivery identifier for delivery identification, and to record at least one image of at least one portion of the delivery portion of the recycled materials.

[0028] The device further includes a processor configured to annotate at least one data identifier on at least one recorded image, the data identifier identifying impurities in at least one portion of the delivery portion of the recycled material; and the processor is further configured to evaluate the quality grade of at least one portion of the delivery portion of the recycled material based on the at least one recorded image and the at least one annotated data identifier, and to determine acceptance of the delivery portion of the recycled material based on the evaluated quality grade of at least one portion of the delivery portion of the recycled material.

[0029] According to one embodiment of the present invention, the data identifier further specifies the specifications and / or impurity content of at least one portion of the delivery portion of each delivery of recycled raw materials.

[0030] According to one embodiment of the present invention, annotating at least one data identifier on at least one recorded image includes marking at least one recorded image by the at least one annotated data identifier, thereby generating at least one enhanced image having computer-generated perceptual information.

[0031] According to one embodiment of the present invention, the processor is further configured to use multi-factor authentication (MFA) to execute a login procedure on the tablet computer to start a multi-user environment, wherein at least one data identifier and at least one recorded image are mapped to a specific user of the multi-user environment.

[0032] According to one embodiment of the present invention, the processor is further configured to map the measured quality grades of multiple portions of the recycled material to the evaluated quality grades of the recycled material; wherein the processor is further configured to perform machine learning by building a model based on the measured quality grades of multiple portions of the delivery portion of the recycled material and the evaluated quality grades of the recycled material, to improve the evaluation of the quality grades of the recycled material. In other words, the deep learning model can be based on labeled images depicting multiple portions of the delivery portion of the recycled material. The measured quality grades and the evaluated quality grades are aligned based on the applied deep learning model.

[0033] According to one embodiment of the present invention, the image sensor and processor are further configured to scan a barcode marked to the recycled material, the barcode providing at least one delivery identifier for delivery identification; and wherein the processor is further configured to evaluate the quality grade of at least one portion of the delivery portion of the recycled material based on at least one recorded image and at least one annotated data identifier and the delivery identifier for delivery identification.

[0034] According to one exemplary embodiment of the present invention, the processor is further configured to generate input data that provides at least one parameter of the recycled material.

[0035] According to one embodiment of the present invention, the processor is further configured to evaluate the quality grade of the recycled raw materials based on at least one recorded image, at least one annotated data identifier, and at least one parameter of the recycled raw materials.

[0036] According to one embodiment of the present invention, the processor is further configured to generate input data by user input.

[0037] According to another aspect of the present invention, a computer program data structure is provided, the computer program data structure including image data relating to at least one recorded image of at least one portion of a recycled material and at least one annotated data identifier on the at least one recorded image, the data identifier identifying impurities in at least one portion of the recycled material, and the at least one recorded image of at least one portion of the recycled material and the at least one annotated data identifier being used to evaluate the quality grade of the recycled material based on the at least one recorded image and the at least one annotated data identifier.

[0038] The computer program executing the method of the present invention can be stored on a computer-readable storage medium. The computer-readable storage medium can be a floppy disk, hard disk, CD, DVD, Universal Serial Bus (USB) storage device, random access memory (RAM), read-only memory (ROM), and erasable programmable read-only memory (EPROM).

[0039] Computer-readable media may also be data communication networks, such as the Internet, which allow code to be downloaded via a connection through WLAN or 3G / 4G or any other wireless data technology.

[0040] The methods, systems and apparatus described herein may be implemented as software in a digital signal processor (DSP), a microcontroller or any other side processor, or as hardware in an application-specific integrated circuit (ASIC), CPLD, or field programmable gate array (FPGA).

[0041] The present invention can be implemented in digital electronic circuits or computer hardware, firmware, software or combinations thereof, for example in the hardware available for conventional mobile devices or in new hardware specifically designed for processing the methods described herein.

Implementation Method

[0043] The illustrations in the drawings are schematic and not to scale. Similar or identical elements have the same reference numerals in different drawings. Generally, identical parts, units, entities, or steps have the same reference symbols in the drawings.

[0044] FIG1 shows a schematic diagram of a method for identifying recycled materials according to an exemplary embodiment of the present invention.

[0045] Specifically, Figure 1 illustrates a method for identifying recyclable materials, which includes the following steps.

[0046] As a first step of the method, the delivery portion of the recycled raw material of S1 is identified by providing at least one delivery identifier for delivery identification.

[0047] As a second step of the method, at least one image of at least one part of the delivery portion of the raw material recovery process in S2 is recorded.

[0048] As a third step of the method, at least one data identifier is annotated on at least one recorded image, and the data identifier is used to identify impurities in at least one part of the delivery section of the recycled raw material.

[0049] As a fourth step of the method, the quality grade of at least one part of the delivery section of the S4 recycled material is evaluated based on at least one recorded image and at least one annotated data identifier.

[0050] As the fifth step of the method, S5 is performed to determine the acceptance of the delivery portion of the recycled material based on the assessed quality grade of at least one portion of the delivery portion of the recycled material.

[0051] Acceptance of full delivery may be fully accepted, partially accepted, or partially or fully rejected.

[0052] The term "impurity" as used in the description of this invention may include impurities or visual anomalies, visual indications of components or additives that cause impurities in other substances, or visual indications of homogeneous or non-homogeneous mixtures.

[0053] FIG2 shows a schematic diagram of an apparatus for identifying recycled raw materials according to an exemplary embodiment of the present invention.

[0054] An apparatus 100 for identifying recycled materials is provided. The apparatus 100 includes an image sensor 10 configured to identify a delivery portion of the recycled materials by providing at least one delivery identifier for delivery identification, and to record at least one image of at least one portion of the delivery portion of the recycled materials.

[0055] In addition, the device 100 includes a processor 20 configured to annotate at least one data identifier on at least one recorded image, the data identifier identifying impurities in at least one portion of the delivery portion of the recycled material; and the processor is further configured to evaluate the quality grade of at least one portion of the delivery portion of the recycled material based on the at least one recorded image and the at least one annotated data identifier, and to decide on the acceptance of the delivery portion of the recycled material based on the evaluated quality grade of at least one portion of the delivery portion of the recycled material.

[0056] The image sensor 10 may be implemented in a tablet computer, a terminal, or a mobile phone. As used in the description of the present invention, the term "tablet computer" may include a tablet computer in relation to a mobile device, typically having a portable computer configured to operate by an operating system.

[0057] The image sensor 10 may be implemented as an image sensor that detects and transmits information for causing image recording to recover at least one portion of at least one image of the raw material. The image sensor 10 may be implemented as an image sensor by converting light wave information into a signal for transmitting information or by emitting a small current. The wave may be light or other electromagnetic radiation.

[0058] The processor 20 is further configured to assess the quality grade of the recycled material based on at least one recorded image and at least one annotated data identifier.

[0059] The processor 20 may be implemented as a digital signal processor (DSP) in a microcontroller or in any other side processor, or as hardware circuitry in an application-specific integrated circuit (ASIC), CPLD, or field programmable gate array (FPGA).

[0060] The processor 20 may be implemented as a field programmable gate array for an integrated circuit containing a large number of identical logic units.

[0061] According to an exemplary embodiment of the present invention, the device for identifying recycled raw materials can run as an application on a tablet computer to facilitate and digitize the quality control of raw material intake, or the device for identifying recycled raw materials can be implemented as a desktop computer having a method as a desktop application version to provide transparent and structured data for supplier management.

[0062] According to an exemplary embodiment of the present invention, a system for identifying recycled materials is provided, wherein the system includes a tablet computer having a device.

[0063] According to an exemplary embodiment of the present invention, the system further includes a database configured to map the measured quality grades of multiple portions of the recycled material to the evaluated quality grades of the recycled material.

[0064] According to an exemplary embodiment of the present invention, the device is configured to provide a notification to a quality control engineer regarding a new delivery. According to an exemplary embodiment of the present invention, the device is configured to perform a start-up assessment, for example, by scanning a barcode or by selecting a delivery.

[0065] According to an exemplary embodiment of the present invention, the device is configured to perform automated identification of the delivery, and preferably the device is configured to cross-check by recording images of recycled materials and annotating impurities, thereby generating a marked image.

[0066] According to an exemplary embodiment of the present invention, the device is configured to provide the user with package specifications for accepting or rejecting individual delivery portions or packages of recycled materials.

[0067] According to an exemplary embodiment of the present invention, the device is configured to provide a definition of the specifications of the recycled material, for example, by means of impurity range, transparency, or a certain amount of visible black film or other impurities in the recycled material.

[0068] According to an exemplary embodiment of the present invention, the system further includes a cloud structure configured to perform machine learning by building a model based on the measured quality grades of multiple portions of the recycled material and the assessed quality grades of the recycled material, so as to improve the assessment of the quality grades of the recycled material.

[0069] According to an exemplary embodiment of the present invention, the machine learning model is further used based on the type of material of the recycled raw material and the assessed quality grade of the recycled raw material to improve the assessment of the quality grade of the recycled raw material.

[0070] According to an exemplary embodiment of the present invention, the machine learning model is further used based on the type of contaminant or impurity material of the recycled raw material and the assessed quality grade of the recycled raw material, so as to improve the assessment of the quality grade of the recycled raw material.

[0071] According to an exemplary embodiment of the present invention, the machine learning model is a hybrid model based on at least one recorded image, at least one annotated data identifier, or the type of material of the recycled raw material, or category quality measurements (such as the amount of different impurities) provided by a QC engineer.

[0072] According to an exemplary embodiment of the present invention, the machine learning model is implemented as an artificial neural network.

[0073] According to an exemplary embodiment of the present invention, the machine learning model is implemented as a neural network model, a machine learning model, a deep learning model, a regression model, or other such cognitive or artificial intelligence for performing cognitive operations.

[0074] FIG3 shows a schematic diagram of a recorded image with an annotated identifier for identifying recycled materials according to an exemplary embodiment of the present invention.

[0075] According to an exemplary embodiment of the present invention, the present invention can be implemented in two different computer application programs, tablet computer application programs, and desktop versions. The computer application programs, or simply the application programs, are used by QC engineers to evaluate incoming materials.

[0076] According to an exemplary embodiment of the present invention, an individual login procedure can be used on a tablet computer using a Borealis credential with multi-factor authentication (MFA).

[0077] According to an exemplary embodiment of the present invention, upon login, a startup page with a delivery overview is displayed and provides different further actions according to an exemplary embodiment of the present invention: • Log out of the account and change the language • Scan the barcode to start the evaluation process • Filter the overview of the status and categorize them by date • Expand the row to view more details • Start an evaluation of a specific delivery by clicking the 'Analyze Package' button • Skip the evaluation by clicking the 'Skip Analysis' button

[0078] According to an exemplary embodiment of the present invention, in the case of the evaluation procedure, the next step is to acquire images and annotate impurities: • View the delivery details on the left bar • Acquire multiple images and delete them • Indicate impurities and delete them • Mark the images as 'rejected' • Proceed to the next step by clicking 'Next' • Now exit the procedure. This delivery will be in a 'processing' state and can be resumed at any time.

[0079] According to an exemplary embodiment of the present invention, once the image is acquired and annotated, the indication of the different specifications and contents of impurities is as follows: • View the delivery details on the left bar • View the album containing the images and can enlarge the images by clicking the thumbnails • View the two tabs: Accept and Reject • Indicate the specification value by scrolling • Indicate the impurity content or deselect the impurities • Proceed to the next step by clicking 'Next' • Now exit the program. This delivery will be in a 'Processing' state and can be resumed at any time.

[0080] According to an exemplary embodiment of the present invention, the final step is a final evaluation of the quality: • Review an overview of your evaluation • Review the right-hand bar for an overall assessment of the delivery • Instruct acceptance of the package • Score the quality of the delivery • Generate an agreement by clicking the button • Exit the process now. This delivery will then be in a 'processing' status and can be resumed at any time.

[0081] According to an exemplary embodiment of the present invention, the desktop version will serve as an overview and management tool for all topics related to raw material entry into a wider audience, such as raw material procurement, operations, and quality control. It also provides the possibility of performing QC assessments. It may include two different tabs: First, "Delivery Overview": • Log out of your account and change language • Filter overviews for status, date, and umbrella organization • Categorize overviews by date • Search for a specific delivery • Expand rows to view more details • Download agreements and images of assessed deliveries • Skip the assessment by clicking the "Skip Analysis" button Second, "Dashboard": • Log out of your account and change language • Visualize overall quality indicators, impurity content, and seasonal effects scattered across umbrella organizations or classification companies • Download relevant data or visualizations • Filter graphs for specifications, umbrella organizations, classification companies, overall quality scores, and timeframes

[0082] FIG4 shows a schematic diagram of a user input system according to an exemplary embodiment of the present invention.

[0083] FIG5 shows a schematic diagram of an instrument panel according to an exemplary embodiment of the present invention.

[0084] According to an exemplary embodiment of the present invention, a method for identifying recycled materials includes the following steps: performing a search for the assessed quality grade of at least one portion of a delivery segment of recycled materials for historical delivery.

[0085] According to an exemplary embodiment of the present invention, a method for identifying recycled materials includes the following steps: downloading QC protocols and recorded images for historical deliveries.

[0086] According to an exemplary embodiment of the present invention, the method for identifying recycled raw materials includes management tools for all matters relating to the raw materials.

[0087] According to an exemplary embodiment of the present invention, the method for identifying recycled raw materials includes using a dashboard indicating EPR share, raw material quality and price.

[0088] According to another exemplary embodiment of the present invention, a data carrier or data storage medium for manufacturing a downloadable computer program element is provided, the computer program element being configured to perform a method according to one of the embodiments previously described according to the present invention.

[0089] It should be noted that embodiments of the present invention are described with reference to different subjects. In particular, some embodiments are described with reference to method type request items, while others are described with reference to apparatus type request items.

[0090] However, those skilled in the art will gather from the foregoing and following description that, unless otherwise notified, any combination of features relating to different subjects, in addition to any combination of features belonging to one type of subject matter, is also considered to be disclosed in this application. However, all features can be combined to provide a synergistic effect that is more than the simple sum of the features.

[0091] Although the invention has been described and illustrated in detail in the drawings and the foregoing description, such description and illustration should be regarded as illustrative or exemplary rather than limiting; the invention is not limited to the disclosed embodiments. Variations of the disclosed embodiments can be understood and implemented by those skilled in the art and practiced in the application of the accompanying drawings, disclosure and the appended claims.

[0092] In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "a (or an)" does not exclude a plurality. A single processor, controller, or other unit may perform the functions of several items described in the claims. The mere fact that certain measures are described in mutually different appendices does not indicate that combinations of these measures cannot be used advantageously. Any reference numerals or element symbols in the claims should not be considered as limiting the scope. [Simplified Explanation of the Diagram]

[0042] A more complete understanding of the invention and its accompanying advantages will be gained with reference to the following schematic diagrams, which are not to scale, wherein: [Figure 1] is a schematic diagram showing a method for identifying recyclable materials according to an exemplary embodiment of the invention; [Figure 2] is a schematic diagram showing an apparatus for identifying recyclable materials according to an exemplary embodiment of the invention; [Figure 3] is a schematic diagram showing a recorded image with an annotated identifier for identifying recyclable materials according to an exemplary embodiment of the invention; [Figure 4] is a schematic diagram showing a user input system according to an exemplary embodiment of the invention; [Figure 5] is a schematic diagram showing an instrument panel according to an exemplary embodiment of the invention.

Claims

1. A method for identifying recycled material, the method comprising the steps of: identifying (S1) a delivery portion of a recycled material by providing at least one delivery identifier for delivery identification; recording (S2) at least one image of at least one portion of the delivery portion of the recycled material; annotating (S3) at least one data identifier on the recorded at least one image, the at least one data identifier identifying an impurity in the at least one portion of the delivery portion of the recycled material; evaluating (S4) the quality grade of the at least one portion of the delivery portion of the recycled material based on the recorded at least one image and the annotated at least one data identifier; and determining (S5) acceptance of the delivery portion of the recycled material based on the evaluated quality grade of the at least one portion of the delivery portion of the recycled material.

2. The method of claim 1, wherein the at least one data identifier further specifies the specification of one of the at least one portion and / or the content of an impurity in each delivery portion of the recycled material; wherein, Preferably, the at least one data identifier is annotated (S3) on the recorded at least one image, which includes marking the recorded at least one image by means of the annotated at least one data identifier, thereby generating at least one enhanced image having computer-generated perceptual information.

3. The method of claim 1 or 2, wherein the method further comprises the following steps: performing a login procedure on a tablet computer using multi-factor authentication (MFA) to initiate a multi-user environment, wherein the at least one data identifier and the recorded at least one image are mapped to a specific user in the initiated multi-user environment.

4. The method of claim 1 or 2, wherein the method further comprises the steps of: mapping a measured quality grade of a plurality of portions of the delivery portion of the recycled material to an evaluated quality grade of the recycled material; and / or performing machine learning by constructing a model based on the measured quality grades of the plurality of portions of the delivery portion of the recycled material and the evaluated quality grade of the recycled material to improve the evaluation of the quality grade of the recycled material.

5. The method of claim 1 or 2, wherein the method further comprises the steps of: scanning a barcode marked onto one of the recycled materials, the barcode providing the at least one delivery identifier for delivery identification; and assessing the quality grade of the at least one portion of the delivery portion of the recycled materials based on the recorded at least one image and the annotated at least one data identifier and the at least one delivery identifier for delivery identification.

6. The method of claim 1 or 2, wherein the method further comprises the steps of: generating input data providing at least one parameter of the recycled material; and evaluating the quality grade of at least one portion of the delivery portion of the recycled material based on the recorded at least one image and the annotated at least one data identifier and the at least one parameter of the recycled material.

7. As in request item 6, where the input data is generated by user input.

8. An apparatus (100) for identifying recycled materials, the apparatus comprising: an image sensor (10) configured to identify a delivery portion of a recycled material by providing at least one delivery identifier for delivery identification, and recording at least one image of at least one portion of the delivery portion of the recycled material; and a processor (20) configured to annotate at least one data identifier on the recorded at least one image, the at least one data identifier identifying an impurity in the at least one portion of the delivery portion of the recycled material; and the processor further configured to evaluate the quality grade of the at least one portion of the delivery portion of the recycled material based on the recorded at least one image and the annotated at least one data identifier, and to determine acceptance of the delivery portion of the recycled material based on the evaluated quality grade of the at least one portion of the delivery portion of the recycled material.

9. The equipment of claim 8, wherein the at least one data identifier further specifies the specification of one of the at least one portion of the recycled material and / or the content of an impurity in each delivery.

10. The device of claim 8 or 9, wherein the processor (20) is further configured to execute a login procedure on a tablet computer using multi-factor authentication (MFA) to initiate a multi-user environment, wherein the at least one data identifier and the at least one recorded image are mapped to a specific user in the multi-user environment.

11. The apparatus of claim 8 or 9, wherein the processor (20) is further configured to map the measured quality grades of a plurality of portions of the delivery portion of the recycled material to the evaluated quality grade of the recycled material; and wherein the processor (20) is further configured to perform machine learning by constructing a model based on the measured quality grades of the plurality of portions of the delivery portion of the recycled material and the evaluated quality grade of the recycled material to improve the evaluation of the quality grade of the recycled material.

12. The device of claim 8 or 9, wherein the image sensor (10) and the processor (20) are further configured to scan a barcode marked to one of the recycled materials, the barcode providing the at least one delivery identifier for delivery identification; and wherein the processor (20) is further configured to evaluate the quality grade of the at least one portion of the delivery portion of the recycled materials based on the recorded at least one image and the annotated at least one data identifier and the at least one delivery identifier for delivery identification.

13. The device of claim 8 or 9, wherein the processor (20) is further configured to generate input data providing at least one parameter of the recycled material, wherein the input data is generated by user input as appropriate; and wherein the processor (20) is further configured to evaluate the quality grade of at least one portion of the delivery portion of the recycled material based on the recorded at least one image and the annotated at least one data identifier and the at least one parameter of the recycled material.

14. A system for identifying reclaimed materials, the system comprising a tablet computer having a device as described in any one of claims 8 to 13, wherein, where appropriate, the system further comprises: a database configured to map measured quality grades of multiple portions of the reclaimed material to an assessed quality grade of the reclaimed material; and a cloud architecture configured to perform machine learning by building a model based on the measured quality grades of the multiple portions of the reclaimed material and the assessed quality grade of the reclaimed material, to improve the assessment of the quality grade of the reclaimed material.

15. A computer-readable medium comprising instructions that, when executed by a computer, cause the computer to perform the steps of any one of claims 1 to 7.

Images