Description:FIELD OF INVENTION
[0001] Embodiments of a present disclosure relate to a field of waste management, and more particularly to a system and a method for managing segregation and collection of waste using artificial intelligence.
BACKGROUND
[0002] Generally, segregation of waste refers to the sorting and separation of waste types to facilitate recycling and correct onward disposal. There are multiple ways of disposal of the waste such as landfills, burial pits, incineration, recycling, composting, and the like. Moreover, choosing from the multiple ways of disposal is majorly dependent on the segregation of the waste, because if not done, can pose risks. For example, plastic in the waste if incinerated can lead to a release of dioxins that are toxic. Household hazardous waste if not segregated such as spent batteries, can result in compost that is contaminated.
[0003] However, a maximum quantity of waste is not managed in an environmentally sound manner in many parts of the world. Generally, public collects all types of waste in a single dustbin, and the same is collected by garbage collection vehicles. The waste collected by the garbage collection vehicles is then disposed of using one or more multiple ways of disposal. In the case of the landfills, due to the accumulation of garbage, which smells bad and draws street animals, the environment becomes polluted, making the area vulnerable.
[0004] Hence, there is a need for an improved system and method for managing segregation and collection of waste which addresses the aforementioned issues.
BRIEF DESCRIPTION
[0005] In accordance with one embodiment of the disclosure, a system for managing segregation and collection of waste using artificial intelligence is provided. The system includes a processing subsystem hosted on a server. The processing subsystem is configured to execute on a network to control bidirectional communications among a plurality of modules. The processing subsystem includes a bag distribution module. The bag distribution module is configured to link a first predefined count of one or more first unique identifiers with a second unique identifier, by delivering the first predefined count of one or more waste collection bags linked with the corresponding one or more first unique identifiers, to a waste generator entity. The waste generator entity is linked with the second unique identifier. The bag distribution module is also configured to share a plurality of waste segregation guidelines with the waste generator entity, upon the delivery of the first predefined count of the one or more waste collection bags. The processing subsystem also includes a bag collection module operatively coupled to the bag distribution module. The bag collection module is also configured to authenticate an identity associated with the one or more filled waste collection bags, by comparing the corresponding identity with the one or more first unique identifiers corresponding to the one or more waste collection bags, upon collecting the one or more filled waste collection bags. Further, the bag collection module is configured to authenticate and identify the waste generator entity associated with the corresponding one or more filled waste collection bags, by extracting the second unique identifier linked with the corresponding one or more first unique identifiers, upon authentication. Further, the processing subsystem also includes a waste categorization module operatively coupled to the bag collection module. The waste categorization module is configured to identify at least one of quality, quantity, a type, and a plurality of item details corresponding to the segregated waste, by performing semantic segmentation-based object detection and classification using a deep learning technique. Furthermore, the bag collection module is also configured to delink the corresponding one or more first unique identifiers with the second unique identifier, based on the authentication and the identification of the waste generator entity. Furthermore, the processing subsystem also includes a feedback module operatively coupled to the waste categorization module. The feedback module is configured to determine a quality of segregation of the waste by the waste generator entity, based on at least one of the quality, the quantity, the type, the plurality of item details, and a contamination level identified corresponding to the segregated waste. The feedback module is also configured to generate feedback for the waste generator entity corresponding to improving the quality of segregation of the waste, for managing the segregation and the collection of the waste.
[0006] In accordance with another embodiment, a method for managing segregation and collection of waste using artificial intelligence is provided. The method includes linking a first predefined count of one or more first unique identifiers with a second unique identifier, by delivering the first predefined count of one or more waste collection bags linked with the corresponding one or more first unique identifiers, to a waste generator entity, wherein the waste generator entity is linked with the second unique identifier. The method also includes sharing a plurality of waste segregation guidelines with the waste generator entity, upon the delivery of the first predefined count of the one or more waste collection bags. Furthermore, the method also includes authenticating an identity associated with the one or more filled waste collection bags, by comparing the corresponding identity with the one or more first unique identifiers, upon collecting the one or more filled waste collection bags. The method further includes authenticating and identifying the waste generator entity associated with the one or more filled waste collection bags, by extracting the second unique identifier linked with the corresponding one or more first unique identifiers, upon authentication. The method also includes identifying at least one of quality, quantity, a type, and a plurality of item details corresponding to the segregated waste, by performing semantic segmentation-based object detection and classification using a deep learning technique. Moreover, the method also includes delinking the corresponding one or more first unique identifiers with the second unique identifier, based on the authentication and the identification of the waste generator entity. The method also includes determining a quality of segregation of the waste by the waste generator entity, based on the quality, the quantity, the type, the plurality of item details, and a contamination level identified corresponding to the segregated waste. The method further includes generating feedback for the waste generator entity corresponding to improving the quality of segregation of the waste, for managing the segregation and the collection of the waste.
[0007] To further clarify the advantages and features of the present disclosure, a more particular description of the disclosure will follow by reference to specific embodiments thereof, which are illustrated in the appended figures. It is to be appreciated that these figures depict only typical embodiments of the disclosure and are therefore not to be considered limiting in scope. The disclosure will be described and explained with additional specificity and detail with the appended figures.

BRIEF DESCRIPTION OF THE DRAWINGS
The disclosure will be described and explained with additional specificity and detail with the accompanying figures in which:
[0008] FIG. 1 is a block diagram representation of a system for managing segregation and collection of waste using artificial intelligence in accordance with an embodiment of the present disclosure;
[0009] FIG. 2 is a block diagram representation of an exemplary embodiment of a for managing segregation and collection of waste using artificial intelligence of FIG. 1 in accordance with an embodiment of the present disclosure;
[0010] FIG. 3 is a block diagram of a waste management computer or a waste management server in accordance with an embodiment of the present disclosure;
[0011] FIG. 4 (a) is a flow chart representing steps involved in a method for managing segregation and collection of waste using artificial intelligence in accordance with an embodiment of the present disclosure; and
[0012] FIG. 4 (b) is a flow chart representing continued steps involved in a method of FIG. 4 (a) in accordance with an embodiment of the present disclosure.
[0013] Further, those skilled in the art will appreciate that elements in the figures are illustrated for simplicity and may not have necessarily been drawn to scale. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the figures by conventional symbols, and the figures may show only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the figures with details that will be readily apparent to those skilled in the art having the benefit of the description herein.
DETAILED DESCRIPTION
[0014] For the purpose of promoting an understanding of the principles of the disclosure, reference will now be made to the embodiment illustrated in the figures and specific language will be used to describe them. It will nevertheless be understood that no limitation of the scope of the disclosure is thereby intended. Such alterations and further modifications in the illustrated system, and such further applications of the principles of the disclosure as would normally occur to those skilled in the art are to be construed as being within the scope of the present disclosure.
[0015] The terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such a process or method. Similarly, one or more devices or sub-systems or elements or structures or components preceded by "comprises... a" does not, without more constraints, preclude the existence of other devices, sub-systems, elements, structures, components, additional devices, additional sub-systems, additional elements, additional structures or additional components. Appearances of the phrase "in an embodiment", "in another embodiment" and similar language throughout this specification may, but not necessarily do, all refer to the same embodiment.
[0016] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this disclosure belongs. The system, methods, and examples provided herein are only illustrative and not intended to be limiting.
[0017] In the following specification and the claims, reference will be made to a number of terms, which shall be defined to have the following meanings. The singular forms “a”, “an”, and “the” include plural references unless the context clearly dictates otherwise.
[0018] Embodiments of the present disclosure relate to a system for managing segregation and collection of waste using artificial intelligence. Waste is basically any unwanted or un-useful material. Typically, the waste is solid products. There are various types of waste such as plastics, paper, wood, glass, metals, unwanted food, torn clothes, kitchen waste, and the like. Further, segregation of waste refers to the sorting and separation of waste types to facilitate recycling and correct onward disposal. Moreover, segregation of the waste during the collection of the waste is important, because if not done, then can pose risks and constraints on the choice of operation of waste processing technologies. Thus, the system described hereafter in FIG. 1 is the system for managing the segregation and the collection of the waste.
[0019] FIG. 1 is a block diagram representation of a system (10) for managing segregation and collection of waste in accordance with an embodiment of the present disclosure. The system (10) includes a processing subsystem (20) hosted on a server (30). In one embodiment, the server (30) may include a cloud server. In another embodiment, the server (30) may include a local server. The processing subsystem (20) is configured to execute on a network (not shown in FIG. 1) to control bidirectional communications among a plurality of modules. In one embodiment, the network may include a wired network such as a local area network (LAN). In another embodiment, the network may include a wireless network such as wireless fidelity (Wi-Fi), Bluetooth, Zigbee, near field communication (NFC), infrared communication, or the like.
[0020] Basically, the segregation of the waste at source is important. In one embodiment, the source may be waste generators or waste generating entities such as households, commercial establishments, institutional establishments, and the like. Therefore, to promote, the segregation of the waste at the source, one or more waste collector entities may use the system (10). In one embodiment, the one or more waste collector entities may include one or more waste management companies, one or more waste management urban local bodies, one or more waste collector agents, and the like. In another embodiment, the one or more waste collector entities may be one or more waste collection centers, wherein the one or more waste collection centers may be Material Recovery Facilities (MRFs) of the one or more waste management companies that are authorized by one or more local government bodies to manage and channelize city waste. Further, for the one or more waste collector entities to be able to use the system (10), the one or more waste collector entities may have to be registered with the system (10).
[0021] Therefore, in an embodiment, the processing subsystem (20) may include a registration module (as shown in FIG. 2). The registration module may register the one or more waste collector entities upon receiving a plurality of waste collector-related details via a waste collector device. In one embodiment, the plurality of waste collector-related details may include at least one of a name, an address, contact details, and the like corresponding to the one or more waste collector entities. The plurality of waste collector-related details may be stored in a database of the system (10). In one exemplary embodiment, the database may be a local database or a cloud database. Also, in an embodiment, the waste collector device may be a mobile phone, a tablet, a laptop, or the like.
[0022] Upon registration, the one or more waste collector entities may have to get created uniquely identifiable waste collection bags, and then distribute the same among one or more uniquely identifiable waste generator entities for the collection of segregated waste. Therefore, the processing subsystem (20) includes a bag distribution module (40). The bag distribution module (40) may be operatively coupled to the registration module. The bag distribution module (40) may initially generate and digitally link one or more first unique identifiers to one or more waste collection bags based on a plurality of bag-related details, upon registration of the one or more waste collector entities.
[0023] Further, upon registration of the one or more waste collector entities, the bag distribution module (40) may also be able to collect information corresponding to the behavior of the waste generator entity. In an embodiment, the information corresponding to the behavior may correspond to at least one of understanding a bag inventory with each of the one or more waste generator entities, identifying the one or more waste generator entities with zero bags or one bag, frequency of collection of the one or more waste collection bags from each of the one or more waste generator entities, a total count of the one or more waste generator entities within the purview of the corresponding one or more waste collector entities, and the like.
[0024] In one embodiment, the one or more first unique identifiers may include one or more bar codes, one or more Quick Response (QR) codes, one or more unique tags, or the like. Further, in one embodiment, the plurality of bag-related details may include at least one of batch details, quantity, one or more bag-related parameters, and the like. The batch details may include information about a batch or a lot of the one or more waste collection bags that may be created for distributing among the one or more uniquely identifiable waste generator entities. Similarly, the one more bag-related parameters may include a size, a color, material, and the like, of the bag. Therefore, for generating and digitally linking the one or more first unique identifiers to the one or more waste collection bags, the corresponding plurality of bag-related details may have to be specified. In one embodiment, the one or more waste collector entities may directly print the one or more first unique identifiers onto the one or more waste collection bags. In another embodiment, the one or more waste collector entities may generate a separate sticker for each of the one or more first unique identifiers that may be applied on each of the one or more waste collection bags.
[0025] Furthermore, for the one or more waste collector entities to be able to distribute the one or more waste collection bags in public, the public may also have to be registered with the system (10). In an embodiment, the public may be referred to as one or more waste generator entities or a waste generator entity. Therefore, the registration module may also register the waste generator entity upon receiving a plurality of waste generator-related details via a waste generator device. In one embodiment, the plurality of waste generator-related details may include at least one of a name, an address, contact details, and the like corresponding to the waste generator entity. The plurality of waste generator-related details may be stored in the database of the system (10). In an embodiment, the waste generator device may be a mobile phone, a tablet, a laptop, or the like.
[0026] In addition, to make the waste generator entity, uniquely identifiable, the bag distribution module (40) may generate and digitally link a second unique identifier to the waste generator entity based on at least one of a plurality of generator behavior-related details and the plurality of waste collector-related details, upon registration. In one embodiment, the second unique identifier may include a bar code, a QR code a tag, or the like. Also, in an embodiment, the plurality of generator behavior-related details may include at least one of the plurality of waste generator-related details, personal unique identifier details, a geographical location, a ward details, a circle details, one or more additional parameters, and the like corresponding to the waste generator entity.
[0027] The personal unique identifier details may include at least one of Aadhaar card details, permanent Account Number (PAN) details, voter identifier (ID) details, and the like. Similarly, in an embodiment, the one or more additional parameters may include a count of one or more waste generator entities resident in a specific ward or a specific circle, a distance of the corresponding one or more waste generator entities from the corresponding one or more waste collector entities, and the like. Therefore, for generating and digitally linking the second unique identifier to the waste generator entity, the corresponding plurality of generator behavior-related details and the plurality of waste collector-related details may have to be known by the system (10). In one embodiment, the second unique identifier may then be pasted on a door of a house of the waste generator entity by the one or more waste collector entities.
[0028] Later, the one or more waste collection bags may have to be distributed to the waste generator entity. Therefore, the bag distribution module (40) is further configured to link a first predefined count of the one or more first unique identifiers with the second unique identifier, by delivering the first predefined count of the one or more waste collection bags linked with the corresponding one or more first unique identifiers, to the waste generator entity. The waste generator entity is linked with the second unique identifier.
[0029] In one embodiment, the first predefined count of the one or more waste collection bags may form a lot of the one or more waste collection bags given to the waste generator entity. In one exemplary embodiment, such multiple lots of the one or more waste collection bags may be distributed among the one or more waste generator entities. Basically, the linking of the first predefined count of the one or more first unique identifiers with the second unique identifier may happen upon scanning the corresponding first predefined count of the one or more first unique identifiers and the second unique identifier using a scanning device. In an embodiment, the scanning device may include a QR code scanner, a bar code scanner, a tag scanner, a camera of the waste collector device, or the like.
[0030] Upon receiving the one or more waste collection bags, the waste generator entity may have to fill the corresponding one or more waste collection bags with segregated waste. The segregated waste may refer to the waste that may have been segregated into wet waste and dry waste, and then filled in different bags. Further, the bag distribution module (40) is also configured to share a plurality of waste segregation guidelines with the waste generator entity, upon the delivery of the first predefined count of the one or more waste collection bags. In one embodiment, the said guidelines represent general awareness campaigns and sessions that are offered to the public while distributing the one or more waste collection bags. In one embodiment, the plurality of waste segregation guidelines may include a suggestion to the waste generator entity to separate the dry waste from the wet waste and fill only the dry waste in the corresponding one or more waste collection bags, encouraging the waste generator entity to do so by associating the suggestion with a reward point, appreciation, and the like. Therefore, the one or more waste collection bags linked with the one or more first unique identifiers may be meant to be used for collecting only the dry waste.
[0031] Once the one or more waste collection bags are filled, the corresponding one or more waste collection bags that are filled may have to be collected from the waste generator entity in real-time. Therefore, the processing subsystem (20) also includes a bag collection module (50) operatively coupled to the bag distribution module (40).
[0032] The one or more waste collector entities may collect the one or more filled waste collection bags from the waste generator entity, and transport to a location of collecting and analyzing the segregated waste. The location may correspond to one or more destination collection centers. While collecting, an identifier associated with each of the one or more filled waste collection bags and the second unique identifier may be scanned using the scanning device (200b). In one embodiment, the scanning device (200b) is not portable. Therefore, the bag collection module (50) is also configured to authenticate an identity associated with the one or more filled waste collection bags, by comparing the corresponding identity with the one or more first unique identifiers corresponding to the one or more waste collection bags, upon collecting the one or more filled waste collection bags. Authenticating the identity associated with the one or more filled waste collection bags may be needed to track the bag inventory of the system (10), the waste generator entity, the one or more waste collector entities, and the like.
[0033] Subsequently, the bag collection module (50) is configured to authenticate and identify the waste generator entity associated with the corresponding one or more filled waste collection bags, by extracting the second unique identifier linked with the corresponding one or more first unique identifiers, upon authentication. Furthermore, the bag collection module (50) is also configured to delink the corresponding one or more first unique identifiers with the second unique identifier, based on the authentication and the identification of the waste generator entity. Basically, identifying the waste generator entity associated with the corresponding one or more filled waste collection bags may assist in tracing one or more features of the segregated waste collected in the one or more filled waste collection bags, back to the waste generator entity for improving a quality of segregation of the waste.
[0034] Upon identifying the waste generator entity associated with the corresponding one or more filled waste collection bags, the one or more filled waste collection bags may be emptied, and further processing of the segregated waste may be carried out by the system (10). However, the bag inventory may also have to be tracked. Therefore, in an embodiment, the processing subsystem (20) may also include a bag inventory tracking module (as shown in FIG. 2) operatively coupled to the bag collection module (50). The bag inventory tracking module may be configured to update a count of at least one of one or more new waste collection bags, one or more reusable waste collection bags, and one or more damaged waste collection bags in the bag inventory, upon delinking the one or more first unique identifiers with the second unique identifier.
[0035] Further, the bag inventory tracking module may also be configured to discard and deactivate the one or more damaged waste collection bags from the bag inventory, upon updating the corresponding bag inventory. Basically, upon emptying the one or more filled waste collection bags, one or more emptied waste collection bags may be obtained, and a checking of any kind of damage that might have occurred to the corresponding one or more emptied waste collection bags may be done. Upon checking, the bag inventory may be updated via the bag inventory tracking module.
[0036] Upon emptying the one or more filled waste collection bags, the segregated waste received from the corresponding one or more filled waste collection bags may have to be checked for the one or more features. In one embodiment, the one or more features may include at least one of quality, quantity, a type, and a plurality of item details corresponding to the segregated waste. Therefore, the processing subsystem (20) also includes a waste categorization module (60) operatively coupled to the bag collection module (50). The waste categorization module (60) is configured to identify at least one of the quality, the quantity, the type, and the plurality of item details corresponding to the segregated waste, by performing semantic segmentation-based object detection and classification using a deep learning (DL) technique, upon delinking.
[0037] Basically, in one embodiment, to get information corresponding to the quantity, the waste categorization module (60) may include a weight recording submodule (as shown in FIG. 2). The weight recording submodule may be configured to record weight of the one or more filled waste collection bags using a weighing technique, thereby identifying an overall quantity of the segregated waste collected in the one or more filled waste collection bags. In one exemplary embodiment, the weighing technique may include using a weighing machine for measuring the weight of the one or more filled waste collection bags. In a specific embodiment, weighing of the one or more filled waste collection bags and scanning of the identifier associated with the corresponding one or more filled waste collection bags may be carried out at the same time.
[0038] Further, the segregated waste from the one or more filled waste collection bags may be emptied by pouring onto a moving conveyor. Upon pouring, for identifying the quality and the type of each item in the segregated waste, one or more images of the segregated waste may have to be carried out. Thus, the waste categorization module (60) may also include an image-based analysis submodule (as shown in Fig. 2) operatively coupled to the weight recording submodule. The image-based analysis submodule may be configured to receive the one or more images corresponding to the segregated waste, upon pouring the segregated waste from the one or more filled waste collection bags onto the moving conveyor, upon recording the weight. In one embodiment, the one or more images may be captured using a camera mounted on top of the moving conveyor.
[0039] Also, in an embodiment, the moving conveyor may be compartmentalized with one or more color-coded strips or one or more color-coded tapes, thereby forming one or more sections on the corresponding moving conveyor. Further, unloading of the one or more filled waste collection bags may be done onto the moving conveyor such that the segregated waste from each of the one or more filled waste collection bags is dropped onto at least one of the one or more sections on the moving conveyor, thereby making sure that mixing of the segregated waste from different bags of the one or more filled waste collection bags is avoided.
[0040] The scanning device and the camera may be operatively coupled to an Internet of Things (IoT) device, wherein the IoT device may be a controlling unit adapted to transmit a scanning result and the one or more images to the system (10) via the image-based analysis submodule. Also, in general, the IoT device may be adapted to exchange data between the scanning device, the camera, and the system (10). Examples of the IoT devices includes, but is not limited to, BeagleBone Black, Esp8266, ASUS Tinker Board S and Clockwork Pi. In a preferred embodiment, the IoT device may be a Raspberry Pi. Moreover, in an embodiment, the camera connected to the IoT device may be adapted to identify the one or more sections on the moving conveyor by detecting the one or more color-coded strips on the moving conveyor.
[0041] In addition, the image-based analysis submodule may also be configured to generate a trained model using an artificial intelligence (AI) technique. The trained model may be trained with a custom-made dataset of at least one of a plurality of images of one or more waste items and information corresponding to a type, an item weight, an item monetary value associated with the corresponding one or more waste items. As used herein, the term “artificial intelligence” is defined as the ability of machines and computers to do things that exhibit traits associated with human intelligence. In one embodiment, the one or more waste items and the type may correspond to a Polyethylene terephthalate (PET) water bottle, High-Density Polyethylene (HDPE)-rigid medicine bottles, plastic bags, and the like. The trained model continuously keeps learning from the custom-made dataset, thereby enabling the system (10) to understand more about each and every type of the one or more waste items present in the one or more images of the segregated waste and corresponding weights.
[0042] Therefore, the image-based analysis submodule may also be configured to identify at least one of the quality, the quantity, the type, and the plurality of item details corresponding to the segregated waste by performing the semantic segmentation-based object detection and classification using the DL technique, based on the trained model. In one embodiment, the plurality of item details may include information related to at least one of material type, product type, product details, and the like. Further, as used herein, the term “semantic segmentation” refers to the process of linking each pixel in the given image to a particular class label. For example, in an image suppose the pixels are labeled as car, tree, pedestrian, and the like. These segments are then used to find the interactions or relations between various objects. Thus, the semantic segment is used mainly for object detection and then classification in an image. Moreover, as used herein, the term “deep learning” is defined as a type of machine learning based on artificial neural networks in which multiple layers of processing are used to extract progressively higher-level features from data.
[0043] In one exemplary embodiment, the processing subsystem (20) may also include a contamination level identification module (as shown in FIG. 2) operatively coupled to the waste categorization module (60). The contamination level identification module may be configured to determine weight of the wet waste in the segregated waste based on the quantity identified by the waste categorization module (60), corresponding to the segregated waste. In an embodiment, the quantity identified may correspond to weight of the dry waste in the segregated waste poured on the moving conveyor. Thus, for determining the weight of the wet waste, the weight of the dry waste is subtracted from weight of the overall quantity of the one or more filled waste collection bags. The contamination level identification module may also be configured to identify the contamination level corresponding to the segregated waste received from the one or more filled waste collection bags, based on the weight of wet waste determined in the corresponding segregated waste. Basically, the weight of the wet waste may be used as metric for identifying the contamination level corresponding to the segregated waste received from the one or more filled waste collection bags.
[0044] Subsequently, in an embodiment, the processing subsystem (20) may also include a monetary value estimation module (as shown in FIG. 2) operatively coupled to the waste categorization module (60). The monetary value estimation module may be configured to estimate an overall monetary value corresponding to the segregated waste based on at least one of historic data and the type identified corresponding to one or more waste items in the segregated waste. In one embodiment, the historic data may include per kilogram (kg) price for each type of a material category for each of the one or more waste items. Moreover, in an embodiment, the historic data may be stored in the database of the system (10), and may be updated in real-time with the latest price for each type of the one or more waste items by the one or more waste collector entities via the system (10). Thus, based on the historic data, the monetary value estimation module may calculate total prices for different types of the waste and estimate the overall monetary value corresponding to the segregated waste in each of the one or more sections on the moving conveyor.
[0045] Moreover, the processing subsystem (20) also includes a feedback module (70) operatively coupled to the waste categorization module (60). The feedback module (70) is configured to determine a quality of segregation of the waste by the waste generator entity, based on at least one of the quality, the quantity, the type, the plurality of item details, and the contamination level identified corresponding to the segregated waste. As used herein, the term “quality of segregation” refers to how well the waste is segregated at the source into the dry waste and the wet waste. The feedback module (70) is also configured to generate feedback for the waste generator entity corresponding to improving the quality of segregation of the waste, for managing the segregation and the collection of the waste. In one embodiment, the feedback may include at least one of awarding with one or more reward points, deducting the one or more reward points, organizing one or more awareness programs and one or more capacity-building events for efficient segregation of the waste, enabling the waste generator entity to take one or more assessments, and the like.
[0046] In one exemplary embodiment, the feedback module (70) may also generate a personalized profile for the waste generator entity, wherein the personalized profile may include information such as, but not limited to, the average weight returned, frequency of collection, contamination rate along with supporting images of the type and the quality of waste returned, and the like. The personalized profile generated may be used by the one or more waste collector entities for organizing the one or more awareness programs and the one or more capacity-building events, for more efficient segregation at the source. Further, in an embodiment, the feedback module (70) may assist in enforcing better segregation practices by offering incentives and imposing penalties on the waste generator entity based on the quality of segregation determined.
[0047] In addition, in case of awarding the waste generator entity with the one or more reward points, or deducting the one or more reward points, upon reaching a certain threshold, the waste generator entity may be awarded with bonus points, thereby raising a position of the waste generator entity on a leaderboard. Further, one or more top participants of the one or more waste generator entities on the leaderboard would be awarded with sustainability champion certificates co-issued by the one or more urban local bodies, the one or more waste management companies, and the like. Moreover, the waste generator entity may get notified about the one or more awareness programs and the one or more capacity-building events via the feedback module (70).
[0048] FIG. 2 is a block diagram representation of an exemplary embodiment of the system (10) for managing the segregation and the collection of the waste using artificial intelligence of FIG. 1 in accordance with an embodiment of the present disclosure. Consider a non-limiting example in which authorities (80) of a school ‘A’ (90) have decided to spread awareness about an importance of the segregation of the waste among students (100) at the school ‘A’ (90). Suppose the authorities (80) of the school ‘A’ (90) have decided to carry out this activity, upon receiving a suggestion of doing so, from a waste management center ‘B’ (110) within the city of the school ‘A’ (90). Therefore, the authorities (80) register themselves and the school ‘A’ (90) with the system (10) via the registration module (120) upon providing a plurality of school-related details via a school laptop (130). The school ‘A’ (90) also gets the students (100) to register with the system (10) via the registration module (120) by providing a plurality of students (100) details via the school laptop (130). The system (10) includes the processing subsystem (20) hosted in a cloud server (140). The plurality of school-related details and the plurality of student details are stored in a cloud database (150).
[0049] Upon registration, the authorities (80) of the school ‘A’ (90) get unique bag-related QR codes (160) generated and digitally linked with the one or more waste-bags (170) based on the plurality of bag-related details via the bag distribution module (40). Then, the authorities (80) get the corresponding unique bag-related QR codes (160) printed onto the one or more waste-bags (170). Further, student-related QR codes (180) are also generated and distributed to the students (100) along with a lot of the one or more waste-bags (170). The students (100) are suggested to collect the dry waste into the corresponding one or more waste-bags (170) in respective houses and bring the one or more filled waste-bags (170) back to the school ‘A’ (90) upon filling.
[0050] During the distribution of the one or more waste-bags (170) to the students (100), the student-related QR codes (180) and the bag-related QR codes (160) are scanned using a QR code scanner (200a), thereby linking the student-related QR codes (180) with the bag-related QR codes (160) of the one or more waste-bags (170) that are distributed to the corresponding students (100) via the bag distribution module (40). In one embodiment, the said QR code scanner (200a) is portable. Suppose after four days, some of the students (100) brought the one or more filled waste-bags to the school ‘A’ (90). Also, as the one or more waste-bags (170) are now filled, the authorities (80) of the school ‘A’ (90) collects the one or more waste-bags (170). Furthermore, while collecting the one or more filled waste-bags (210), a QR code on the corresponding one or more filled waste-bags (210) is scanned by scanner (200b) and authenticated via the bag collection module (50). Then, an identity of the students (100) to whom the corresponding one or more filled waste-bags (210) belong is authenticated and identified via the bag collection module (50). Later on, upon authentication, and identifying the QR code to be one of the student-related QR codes (180), the corresponding bag-related QR codes (160) are delinked from the corresponding student-related QR codes (180) via the bag collection module (50), so that the corresponding one or more filled waste-bags (210) can be circulated back upon emptying.
[0051] Upon receiving the one or more filled waste-bags (210), they are emptied onto a moving conveyor unit (230) at the waste management center ‘B’ (110), upon recording the weight of the one or more filled waste-bags (210) via the weight recording submodule (240) of the waste categorization module (60). Further, as segregated waste items (250) move on the moving conveyor unit (230), the one or more images are also captured via a camera (260) and shared with the system (10) via an IoT device (270). The system (10) receives the one or more images via the image-based analysis submodule (280) of the waste categorization module (60). Further, the one or more images are analyzed to identify at least one of the quality, the quantity, the type, and the plurality of item details corresponding to the segregated waste items (250) via the image-based analysis submodule (280).
[0052] Moreover, the bag inventory of the system (10) is updated via the bag inventory tracking module (220), upon delinking, and damaged bags are discarded and deactivated from the system (10). Further, as the authorities (80) of the school ‘A’ (90) have performed this activity because of the suggestion from the waste management center ‘B’ (110), this activity basically becomes a collective initiative of the school ‘A’ (90) and the waste management center ‘B’ (110). Thus, the school ‘A’ (90) transfers the one or more filled waste-bags (210) to the waste management center ‘B’ (110) for further processing.
[0053] Moreover, the contamination level corresponding to the segregated waste items (250) is also identified via the contamination level identification module (290) based on the weight of the wet waste available in the segregated waste items (250) poured on the moving conveyor unit (230). Also, the overall monetary value corresponding to the segregated waste items (250) can be estimated via the monetary value estimation module (300). Further, the quality of the segregation of the waste is also determined and then feedback is provided to the students (100) via the feedback module (70). The feedback basically includes at least one of suggestion for improving the quality of the segregation of the waste, information about several types of dry waste, encouraging the students (100) to segregate the waste by associating rewards points with segregation, and the like. This is how the authorities (80) of the school ‘A’ (90) have used the system (10) for managing the segregation and the collection of the waste, and spreading the awareness about the same.
[0054] FIG. 3 is a block diagram of a waste management computer or a waste management server (310) in accordance with an embodiment of the present disclosure. The waste management server (310) includes processor(s) (320), and memory (330) operatively coupled to a bus (340). The processor(s) (320), as used herein, means any type of computational circuit, such as, but not limited to, a microprocessor, a microcontroller, a complex instruction set computing microprocessor, a reduced instruction set computing microprocessor, a very long instruction word microprocessor, an explicitly parallel instruction computing microprocessor, a digital signal processor, or any other type of processing circuit, or a combination thereof.
[0055] Computer memory elements may include any suitable memory device(s) for storing data and executable program, such as read only memory, random access memory, erasable programmable read only memory, electrically erasable programmable read only memory, hard drive, removable media drive for handling memory cards and the like. Embodiments of the present subject matter may be implemented in conjunction with program modules, including functions, procedures, data structures, and application programs, for performing tasks, or defining abstract data types or low-level hardware contexts. Executable program stored on any of the above-mentioned storage media may be executable by the processor(s) (320).
[0056] The memory (330) includes a plurality of subsystems stored in the form of executable program which instructs the processor(s) (320) to perform method steps illustrated in FIG. 4. The memory (330) includes a processing subsystem (20) of FIG 1. The processing subsystem (20) further has following modules: a bag distribution module (40), a bag collection module (50), a waste categorization module (60), and a feedback module (70).
[0057] The bag distribution module (40) is configured to link a first predefined count of one or more first unique identifiers with a second unique identifier, by delivering the first predefined count of one or more waste collection bags linked with the corresponding one or more first unique identifiers, to a waste generator entity, wherein the waste generator entity is linked with the second unique identifier. The bag distribution module (40) is also configured to share a plurality of waste segregation guidelines with the waste generator entity, upon the delivery of the first predefined count of the one or more waste collection bags.
[0058] The bag collection module (50) is configured to authenticate an identity associated with the one or more filled waste collection bags, by comparing the corresponding identity with the one or more first unique identifiers, upon collecting the one or more filled waste collection bags.
[0059] In one embodiment, the bag collection module (50) is configured to receive a bag collection signal, when the one or more waste collection bags are filled with segregated waste based on the plurality of waste segregation guidelines for obtaining one or more filled waste collection bags, wherein the bag collection signal corresponds to a signal for one or more waste collector entities to collect the one or more filled waste collection bags.
[0060] The bag collection module (50) is also configured to authenticate and identify the waste generator entity associated with the corresponding one or more filled waste collection bags, by extracting the second unique identifier linked with the corresponding one or more first unique identifiers, upon authentication. The bag collection module (50) is also configured to delink the corresponding one or more first unique identifiers with the second unique identifier, based on the authentication and the identification of the waste generator entity.
[0061] The waste categorization module (60) is configured to identify at least one of quality, quantity, a type, and a plurality of item details corresponding to the segregated waste, by performing semantic segmentation-based object detection and classification using a deep learning technique, upon delinking.
[0062] The feedback module (70) is configured to determine a quality of segregation of the waste by the waste generator entity, based on at least one of the quality, the quantity, the type, the plurality of item details, and a contamination level identified corresponding to the segregated waste. The feedback module (70) is also configured to generate feedback for the waste generator entity corresponding to improving the quality of segregation of the waste, for managing the segregation and the collection of the waste.
[0063] The bus (340) as used herein refers to be internal memory channels or computer network that is used to connect computer components and transfer data between them. The bus (340) includes a serial bus or a parallel bus, wherein the serial bus transmits data in a bit-serial format and the parallel bus transmits data across multiple wires. The bus (340) as used herein, may include but not limited to, a system bus, an internal bus, an external bus, an expansion bus, a frontside bus, a backside bus and the like.
[0064] FIG. 4 (a) is a flow chart representing steps involved in a method (350) for managing segregation and collection of waste using artificial intelligence in accordance with an embodiment of the present disclosure. FIG. 4 (b) is a flow chart representing continued steps involved in the method (350) of FIG. 4 (a) in accordance with an embodiment of the present disclosure. The method (350) includes linking a first predefined count of one or more first unique identifiers with a second unique identifier, by delivering the first predefined count of one or more waste collection bags linked with the corresponding one or more first unique identifiers, to a waste generator entity, wherein the waste generator entity is linked with the second unique identifier in step 360. In one embodiment, linking the first predefined count of the one or more first unique identifiers with the second unique identifier may include linking the first predefined count of the one or more first unique identifiers with the second unique identifier via a bag distribution module (40).
[0065] The method (350) also includes sharing a plurality of waste segregation guidelines with the waste generator entity, upon the delivery of the first predefined count of the one or more waste collection bags in step 370. In one embodiment, sharing the plurality of waste segregation guidelines with the waste generator entity may include sharing the plurality of waste segregation guidelines with the waste generator entity via the bag distribution module (40).
[0066] In one embodiment, the method (350) may include receiving a bag collection signal, when the one or more waste collection bags are filled with segregated waste based on the plurality of waste segregation guidelines for obtaining one or more filled waste collection bags, wherein the bag collection signal corresponds to a signal for one or more waste collector entities to collect the one or more filled waste collection bags. In such an embodiment, receiving the bag collection signal may include receiving the bag collection signal via a bag collection module (50).
[0067] Furthermore, the method (350) also includes authenticating an identity associated with the one or more filled waste collection bags, by comparing the corresponding identity with the one or more first unique identifiers, upon collecting the one or more filled waste collection bags in step 380. In one embodiment, authenticating the identity associated with the one or more filled waste collection bags may include authenticating the identity associated with the one or more filled waste collection bags via the bag collection module (50).
[0068] The method (350) further includes authenticating and identifying the waste generator entity associated with the one or more filled waste collection bags, by extracting the second unique identifier linked with the corresponding one or more first unique identifiers, upon authentication in step 390. In one embodiment, authenticating and identifying the waste generator entity associated with the one or more filled waste collection bags may include authenticating and identifying the waste generator entity associated with the one or more filled waste collection bags via the bag collection module (50).
[0069] Moreover, the method (350) also includes delinking the corresponding one or more first unique identifiers with the second unique identifier, based on the authentication and the identification of the waste generator entity in step 400. In one embodiment, delinking the corresponding one or more first unique identifiers with the second unique identifier may include delinking the corresponding one or more first unique identifiers with the second unique identifier via the bag collection module (50).
[0070] In one exemplary embodiment, the method (350) may further include updating at least one of a first predefined count of one or more new waste collection bags, a second predefined count of one or more reusable waste collection bags, a third predefined count of one or more damaged waste collection bags in a bag inventory, upon delinking the one or more first unique identifiers with the second unique identifier. In such embodiment, updating at least one of the first predefined count of the one or more new waste collection bags, the second predefined count of the one or more reusable waste collection bags, the third predefined count of the one or more damaged waste collection bags in a bag inventory may include updating at least one of the first predefined count of the one or more new waste collection bags, the second predefined count of the one or more reusable waste collection bags, the third predefined count of the one or more damaged waste collection bags in a bag inventory via a bag inventory tracking module (220).
[0071] The method (350) may further include discarding and deactivating the one or more damaged waste collection bags from the bag inventory, upon updating the corresponding bag inventory. In such embodiment, discarding and deactivating the one or more damaged waste collection bags from the bag inventory may include discarding and deactivating the one or more damaged waste collection bags from the bag inventory via the bag inventory tracking module (220).
[0072] The method (350) also includes identifying at least one of quality, quantity, a type, and a plurality of item details corresponding to the segregated waste, by performing semantic segmentation-based object detection and classification using a deep learning technique, upon delinking in step 410. In one embodiment, identifying at least one of the quality, the quantity, the type, and the plurality of item details corresponding to the segregated waste may include identifying at least one of the quality, the quantity, the type, and the plurality of item details corresponding to the segregated waste via a waste categorization module (60).
[0073] In an embodiment, the method (350) may include recording weight of the one or more filled waste collection bags using a weighing technique, thereby identifying an overall quantity of the segregated waste collected in the one or more filled waste collection bags. In such embodiment, recording the weight of the one or more filled waste collection bags may include recording the weight of the one or more filled waste collection bags via a weight recording submodule (240) of the waste categorization module (60).
[0074] Further, the method (350) may also include receiving one or more images corresponding to the segregated waste, upon pouring the segregated waste from the one or more filled waste collection bags onto a moving conveyor, upon recording the weight. In such embodiment, receiving one or more images corresponding to the segregated waste may include receiving one or more images corresponding to the segregated waste via an image-based analysis submodule (280) of the waste categorization module (60).
[0075] The method (350) may further include generating a trained model using an artificial intelligence technique, wherein the trained model is trained with at least one of a custom-made dataset of a plurality of images of one or more waste items and information corresponding to a type, an item weight, an item monetary value associated with the corresponding one or more waste items. In such embodiment, generating the trained model may include generating the trained model via the image-based analysis submodule (280) of the waste categorization module (60).
[0076] Furthermore, the method (350) may also include identifying at least one of the quality, the quantity, the type, and the plurality of item details corresponding to the segregated waste by performing the semantic segmentation-based object detection and classification using the deep learning technique, based on the trained model. In such embodiment, identifying at least one of the quality, the quantity, the type, and the plurality of item details corresponding to the segregated waste via the image-based analysis submodule (280) of the waste categorization module (60).
[0077] In one exemplary embodiment, the method (350) may further include determining a weight of wet waste in the segregated waste based on the quantity identified by the waste categorization module, corresponding to the segregated waste. In such embodiment, determining the weight of the wet waste may include determining the weight of the wet waste via a contamination level identification module (290).
[0078] In a further embodiment, the method (350) may include identifying the contamination level corresponding to the segregated waste received from the one or more filled waste collection bags, based on the weight of wet waste determined in the corresponding segregated waste. In such embodiment, identifying the contamination level corresponding to the segregated waste may include identifying the contamination level corresponding to the segregated waste via the contamination level identification module (290).
[0079] In another embodiment, the method (350) may also include estimating an overall monetary value corresponding to the segregated waste based on at least one of historic data and the type identified corresponding to one or more waste items in the segregated waste. In such embodiment, estimating the overall monetary value corresponding to the segregated waste may include estimating the overall monetary value corresponding to the segregated waste via a monetary value estimation module (300).
[0080] Furthermore, the method (350) also includes determining a quality of segregation of the waste by the waste generator entity, based on the quality, the quantity, the type, the plurality of item details, and a contamination level identified corresponding to the segregated waste in step 420. In one embodiment, determining the quality of segregation of the waste by the waste generator entity may include determining the quality of segregation of the waste by the waste generator entity via a feedback module (70).
[0081] The method (350) further includes generating feedback for the waste generator entity corresponding to improving the quality of segregation of the waste, for managing the segregation and the collection of the waste in step 430. In one embodiment, generating the feedback for the waste generator entity may include generating the feedback for the waste generator entity via the feedback module (70).
[0082] Various embodiments of the present disclosure enable managing the segregation and the collection of the waste, and identifying quality, quantity, a type of the waste using the semantic segmentation-based object detection and classification using a deep learning technique. The system enables the segregation of the waste at the source by providing uniquely identifiable bags to uniquely identifiable waste generators.
[0083] It's critical to segregate the waste at the source. Everybody benefits from the endeavor, which also addresses half of the city's waste management issues. When the waste is divided into two main streams, such as wet (biodegradable) and dry (non-biodegradable), the waste produced is better understood and subsequently recovered and reused with a larger possibility for recovery. Thus, proper waste segregation results in a "circular economy" that fosters investments and innovations while generating green jobs and consuming fewer virgin resources. Additionally, when emissions from waste transportation decrease, landfill life extends, and ecological risk decreases. Segregated waste lessens dangers to waste pickers' health and safety as well as to the ecosystems surrounding waste treatment and disposal facilities.
[0084] While specific language has been used to describe the disclosure, any limitations arising on account of the same are not intended. As would be apparent to a person skilled in the art, various working modifications may be made to the method in order to implement the inventive concept as taught herein.
[0085] The figures and the foregoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, order of processes described herein may be changed and are not limited to the manner described herein. Moreover, the actions of any flow diagram need not be implemented in the order shown; nor do all of the acts need to be necessarily performed. Also, those acts that are not dependent on other acts may be performed in parallel with the other acts. The scope of embodiments is by no means limited by these specific examples. , Claims:1. A system (10) for managing segregation and collection of waste comprising:
a processing subsystem (20) hosted on a server (30), and configured to execute on a network to control bidirectional communications among a plurality of modules comprising:
a bag distribution module (40) is configured to:
link a first predefined count of one or more first unique identifiers with a second unique identifier, by delivering the first predefined count of one or more waste collection bags linked with the corresponding one or more first unique identifiers, to a waste generator entity, wherein the waste generator entity is linked with the second unique identifier; and
share a plurality of waste segregation guidelines with the waste generator entity, upon the delivery of the first predefined count of the one or more waste collection bags;
a waste categorization module (60) operatively coupled to the bag collection module (50), wherein the waste categorization module (60) is configured to identify at least one of quality, quantity, a type, and a plurality of item details corresponding to the segregated waste, by performing semantic segmentation-based object detection and classification using a deep learning technique; and
a bag collection module (50) operatively coupled to the bag distribution module (40), wherein the bag collection module (50) is configured to:
authenticate an identity associated with the one or more filled waste collection bags, by comparing the corresponding identity with the one or more first unique identifiers, upon collecting the one or more filled waste collection bags;
authenticate and identify the waste generator entity associated with the corresponding one or more filled waste collection bags, by extracting the second unique identifier linked with the corresponding one or more first unique identifiers, upon authentication; and
delink the corresponding one or more first unique identifiers with the second unique identifier, based on the authentication and the identification of the waste generator entity;
a feedback module (70) operatively coupled to the waste categorization module (60), wherein the feedback module (70) is configured to:
determine a quality of segregation of the waste by the waste generator entity, based on at least one of the quality, the quantity, the type, the plurality of item details, and a contamination level identified corresponding to the segregated waste; and
generate feedback for the waste generator entity corresponding to improving the quality of segregation of the waste, for managing the segregation and the collection of the waste.
2. The system (10) as claimed in claim 1, wherein the feedback comprises at least one of awarding with one or more reward points, deducting the one or more reward points, organizing one or more awareness programs and one or more capacity-building events for efficient segregation of the waste, and enabling the waste generator entity to take one or more assessments.
3. The system (10) as claimed in claim 1, wherein the processing subsystem (20) comprises a bag inventory tracking module (220) operatively coupled to the bag collection module (50), wherein the bag inventory tracking module (220) is configured to:
update a count of at least one of one or more new waste collection bags, one or more reusable waste collection bags, and one or more damaged waste collection bags in a bag inventory, upon delinking the one or more first unique identifiers with the second unique identifier; and
discard and deactivate the one or more damaged waste collection bags from the bag inventory, upon updating the corresponding bag inventory.
4. The system (10) as claimed in claim 1, wherein the waste categorization module (60) comprises a weight recording submodule (240) configured to record weight of the one or more filled waste collection bags using a weighing technique, thereby identifying an overall quantity of the segregated waste collected in the one or more filled waste collection bags.
5. The system (10) as claimed in claim 4, wherein the waste categorization module (60) comprises an image-based analysis submodule (280) operatively coupled to the weight recording submodule (240), wherein the image-based analysis submodule (280) is configured to:
receive one or more images corresponding to the segregated waste, upon pouring the segregated waste from the one or more filled waste collection bags onto a moving conveyor, upon recording the weight;
generate a trained model using an artificial intelligence technique, wherein the trained model is trained with at least one of a custom-made dataset of a plurality of images of one or more waste items and information corresponding to a type, an item weight, an item monetary value associated with the corresponding one or more waste items; and
identify at least one of the quality, the quantity, the type, and the plurality of item details corresponding to the segregated waste by performing the semantic segmentation-based object detection and classification using the deep learning technique, based on the trained model.
6. The system (10) as claimed in claim 1, wherein the processing subsystem (20) comprises a contamination level identification module (290) operatively coupled to the waste categorization module (60), wherein the contamination level identification module (290) is configured to:
determine weight of wet waste in the segregated waste based on the quantity identified by the waste categorization module (60), corresponding to the segregated waste; and
identify the contamination level corresponding to the segregated waste received from the one or more filled waste collection bags, based on the weight of wet waste determined in the corresponding segregated waste.
7. The system (10) as claimed in claim 1, wherein the processing subsystem (20) comprises a monetary value estimation module (300) operatively coupled to the waste categorization module (60), wherein the monetary value estimation module (300) is configured to estimate an overall monetary value corresponding to the segregated waste based on at least one of historic data and the type identified corresponding to one or more waste items in the segregated waste.
8. A method (350) for managing segregation and collection of waste, comprising:
linking, via a bag distribution module (40), a first predefined count of one or more first unique identifiers with a second unique identifier, by delivering the first predefined count of one or more waste collection bags linked with the corresponding one or more first unique identifiers, to a waste generator entity, wherein the waste generator entity is linked with the second unique identifier; (360)
sharing, via the bag distribution module (40), a plurality of waste segregation guidelines with the waste generator entity, upon the delivery of the first predefined count of the one or more waste collection bags; (370)
authenticating, via the bag collection module (50), an identity associated with the one or more filled waste collection bags, by comparing the corresponding identity with the one or more first unique identifiers, upon collecting the one or more filled waste collection bags; (380)
authenticating and identifying, via the bag collection module (50), the waste generator entity associated with the one or more filled waste collection bags, by extracting the second unique identifier linked with the corresponding one or more first unique identifiers, upon authentication; (390)
identifying, via a waste categorization module (60), at least one of quality, quantity, a type, and a plurality of item details corresponding to the segregated waste, by performing semantic segmentation-based object detection and classification using a deep learning technique; (400)
delinking, via the bag collection module (50), the corresponding one or more first unique identifiers with the second unique identifier, based on the authentication and the identification of the waste generator entity; (410)
determining, via a feedback module (70), a quality of segregation of the waste by the waste generator entity, based on the quality, the quantity, the type, the plurality of item details, and a contamination level identified corresponding to the segregated waste; and (430)
generating, via the feedback module (70), feedback for the waste generator entity corresponding to improving the quality of segregation of the waste, for managing the segregation and the collection of the waste (440).
9. The method (350) as claimed in claim 8, comprises determining, via a contamination level identification module (290), weight of wet waste in the segregated waste based on the quantity identified by the waste categorization module, corresponding to the segregated waste.
10. The method (350) as claimed in claim 9, comprises identifying, via the contamination level identification module (290), the contamination level corresponding to the segregated waste received from the one or more filled waste collection bags, based on the weight of wet waste determined in the corresponding segregated waste.

Dated this 19th day of September 2022

Signature

Jinsu Abraham
Patent Agent (IN/PA-3267)
Agent for the Applicant