Intelligent paid recovery system

Abstract

The invention provides an intelligent paid recovery system, and relates to the technical field of recyclable material recovery, the intelligent paid recovery system comprises an intelligent recovery device and a recovery compensation platform, and the intelligent recovery device and the recovery compensation platform are connected through an Internet of Things technology or a cellular network. The intelligent recycling equipment comprises an intelligent recycling box, four collecting barrels, a three-axis moving mechanism, a sensor set and a material classification and recognition module, and the sensor set is installed in the intelligent recyclable material recycling box. According to the method and the device, the classification accuracy of the recyclable materials is improved, the participation enthusiasm of the user is enhanced, in addition, the condition of identification failure can be effectively processed, and the integral of the user is ensured not to be influenced by unfairness due to technical reasons.

Description

Technical Field

[0001] The present invention relates to the field of recycling of recyclable materials, and in particular to an intelligent paid recycling system. Background Art

[0002] Recyclable materials are generally divided into four categories: paper, plastic, metal and glass. In the past, the recycling of materials was mainly based on door-to-door recycling, sorting and transportation at recycling stations, which was not only inefficient but also difficult to ensure the quality of classification. Moreover, when placing recyclable materials, most of them rely on residents to distinguish them by themselves, which can easily lead to the misclassification of recyclable materials, bringing difficulties to the subsequent processing of recyclable materials. Now there are some intelligent recycling devices on the market, some of which automatically weigh the weight of items and recycle them according to the weight. The functional mode is single and the accuracy of recyclable material classification is low. Some are combined with voice playback functions or print out a QR code for people to classify recyclable materials, which is very time-consuming to a certain extent. Some use intelligent recyclable material classification recycling cards. According to the principle of more dumping and more charging, recyclable materials will be charged to the card at a certain price. In the end, special counters or machines need to be set up to withdraw these fees, which will cost more manpower and material resources, and the steps are cumbersome. In addition, the cards are not easy to carry and are troublesome to use.

[0003] Therefore, it is necessary to provide a new intelligent paid recycling system to solve the above technical problems. Summary of the invention

[0004] In order to solve the problems of accuracy of recyclable material classification and enthusiasm of user participation, the present invention provides an intelligent paid recycling system for recyclable materials.

[0005] The intelligent paid recycling system provided by the present invention includes intelligent recycling equipment and a recycling compensation platform, wherein the intelligent recycling equipment and the recycling compensation platform are connected via Internet of Things technology or a cellular network;

[0006] The intelligent recycling device includes an intelligent recycling box, a sensor group and a material classification and identification module, wherein the sensor group is installed inside the intelligent recycling box, and the material classification and identification module is installed in front of the box door of the intelligent recycling box and performs image acquisition through a camera;

[0007] The intelligent recycling box is also provided with a weighing basket and a weighing three-axis basket moving mechanism;

[0008] The material classification and recognition module uses a convolutional neural network to recognize and classify image features, and increases corresponding user points on the recycling compensation platform according to the classification and recognition results.

[0009] Furthermore, the recycling compensation platform includes a points mall, a human-computer interaction module and a mobile application. The points mall is used to redeem goods based on the points obtained from recycling recyclable materials. The human-computer interaction module is located on the front of the smart recycling box and is used to interact with the smart recycling box. The mobile application is used to query the location of nearby recycling stations, understand recycling rules, check one's own points or withdraw cash.

[0010] Furthermore, the identification of the material classification identification module includes the following steps:

[0011] S1. Image acquisition: The user places recyclable materials in front of the smart recycling bin and takes photos of the recyclable materials through the camera on the bin;

[0012] S2, preprocessing: preprocessing the collected images;

[0013] S3, feature extraction: use convolutional neural network to extract features from the preprocessed image and identify the shape, color and texture in the image;

[0014] S4, classification and identification: compare the extracted features with the pre-trained classification model to determine the type of recyclable materials;

[0015] S5. Result feedback: Feedback is given based on the classification and recognition results. If the delivery is confirmed to be correct, the user’s points will be increased. Otherwise, the user will be prompted to deliver again.

[0016] Further, the sensor group includes a temperature and humidity sensor for detecting temperature and humidity data in the intelligent recyclable material recycling box;

[0017] Smoke sensor, used to detect smoke data in the smart recyclable material recycling box;

[0018] Water immersion sensor, used to detect water immersion in the smart recyclable material recycling box;

[0019] The displacement sensor is used to detect the travel of the symmetrical weight basket moving mechanism.

[0020] Further, the weighing basket includes a weighing sensor for weighing.

[0021] Furthermore, the weighing basket moving mechanism includes a vertical moving component, a horizontal moving component and a delivery mechanism, and the vertical moving component is used to drive the horizontal moving component to perform vertical movement.

[0022] Furthermore, the weighing basket delivery (unloading) mechanism is respectively provided with four collecting buckets for storing recyclable materials.

[0023] Furthermore, the recycling system also includes an automatic fire extinguishing bag, an LED light strip for lighting in front of the box, a face recognition camera, a personnel stay detection module in front of the cabinet, and a voice broadcast module.

[0024] Furthermore, the recycling compensation platform also includes a help button, which is used to press the button to seek help when encountering problems. The backend customer service guides the user to the correct operation through remote video or voice calls.

[0025] Furthermore, the material classification and identification failure also includes temporary storage and point adjustment. When an item cannot be identified immediately, it is temporarily stored in a temporary storage box, and then an estimated temporary point is given. After the item type is confirmed, the point is adjusted according to the actual situation.

[0026] Compared with the related art, the intelligent paid recycling system provided by the present invention has the following beneficial effects:

[0027] 1. The present invention provides users with a more humane interactive experience by adding multiple sensors, monitoring various states, recording in real time, and enhancing interactive capabilities. It also makes billing more accurate and classification simpler. The intelligent paid recycling system for recyclable material classification can not only effectively promote the recycling of resources, but also greatly improve the user experience and encourage more people to participate in the classification of recyclable materials.

[0028] 2. The present invention can effectively confirm whether the items placed by the user are correctly classified through material photo identification, and calculate the corresponding point rewards according to the type and weight of the items. This not only improves the accuracy of recyclable material classification, but also enhances the enthusiasm of user participation. In addition, it can effectively handle the situation of identification failure, ensuring that the user's points will not be unfairly affected due to technical reasons. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 A front view structural diagram of the intelligent recyclable material recycling box provided by the present invention;

[0030] Figure 2 A schematic diagram of the internal structure of the intelligent recyclable material recycling box provided by the present invention;

[0031] Figure 3 A schematic diagram of the structure of the three-axis moving mechanism of the weighing basket and the weighing basket provided by the present invention;

[0032] Figure 4 A structural block diagram of the intelligent paid recycling system provided by the present invention;

[0033] Figure 5 This is a flowchart of the material classification identification module provided by the present invention.

[0034] Numbers in the figure: 1. Intelligent recycling bin for recyclable materials; 2. Weighing basket; 3. Three-axis moving mechanism for weighing basket; 4. Vertical moving component; 5. Horizontal moving component; 6. Release mechanism. DETAILED DESCRIPTION

[0035] The present invention will be further described below in conjunction with the accompanying drawings and implementation modes.

[0036] In the specific implementation process, Figure 1-Figure 5 As shown, the intelligent paid recycling system includes intelligent recycling equipment and a recycling compensation platform. The intelligent recycling equipment and the recycling compensation platform are connected through the Internet of Things technology or cellular network. Various devices are connected through the Internet of Things technology or cellular network to realize real-time transmission and processing of data. When the intelligent recycling equipment is close to full load, the system can promptly notify the operator to transfer and empty it;

[0037] The intelligent recycling equipment includes an intelligent recycling box 1 for recyclable materials, a sensor group, and a material classification and identification module. The sensor group is installed inside the intelligent recycling box 1 for recyclable materials, and the material classification and identification module is installed in front of the box door of the intelligent recycling box 1 for recyclable materials and performs image acquisition through a camera.

[0038] Among them, the sensor group includes a temperature and humidity sensor for detecting the temperature and humidity data in the intelligent recyclable material recycling box 1;

[0039] A smoke sensor is used to detect smoke data in the intelligent recyclable material recycling box 1;

[0040] A water immersion sensor, used to detect water immersion in the intelligent recyclable material recycling box 1;

[0041] A displacement sensor, used to detect the travel of the carrying plate 11;

[0042] The intelligent recyclable material recycling box 1 is also provided with a weighing basket 2 and a three-axis moving mechanism 3 of the weighing basket. By installing a variety of sensors, various states are monitored, real-time records are made, and the interactive capability is enhanced, providing users with a more humane interactive experience, more accurate billing, and simpler classification;

[0043] It should be noted that the intelligent recyclable material recycling box 1 is internally installed with an electromagnetic switch for driving the box door to close and open;

[0044] The delivery mechanism 6 is installed at the bottom of the weighing basket 2, and is used to drive the bottom door of the weighing basket 2 to open. The delivery mechanism 6 can be a component such as a hydraulic cylinder that can drive the door to rotate;

[0045] When the user puts in recyclable materials, the system automatically weighs them. After image recognition and user confirmation, the weighing basket 2 is horizontally moved to the top of the collection baskets corresponding to the four types of recyclable materials by the horizontal moving component 5. Then the weighing basket 2 and the materials are moved downward by the Z-axis lifting component 9. After reaching the bottom of the collection box, the bottom door of the weighing basket 2 is opened by the delivery mechanism 6 to unload the materials.

[0046] Furthermore, the recovery system also includes an automatic fire extinguishing firefighting package for automatically initiating fire extinguishing in an emergency;

[0047] The LED light strip on the front of the box is used to provide lighting for the user's operating area;

[0048] Face recognition camera, used for human detection, identity verification, etc.;

[0049] The personnel cabinet stay detection module is used to monitor whether someone stays in front of the cabinet;

[0050] The voice broadcast module is used to provide voice prompts.

[0051] It should be noted that the recycling compensation platform includes a points mall, a human-computer interaction module and a mobile application. The points mall is used to redeem goods based on the points obtained from recycling recyclable materials. The human-computer interaction module is located on the front of the smart recycling box 1 and is used to interact with the smart recycling box 1. The mobile application is used to query the location of nearby recycling stations, understand recycling rules, check one's own points or withdraw cash.

[0052] The material classification and recognition module uses a convolutional neural network to recognize and classify image features, and increases corresponding user points on the recycling compensation platform based on the classification and recognition results.

[0053] It should be noted that the identification of the material classification identification module includes the following steps:

[0054] S1. Image acquisition: The user places recyclable materials in front of the intelligent recyclable material recycling box 1, and takes photos of the recyclable materials through the camera on the box;

[0055] S2, preprocessing: preprocessing the collected images;

[0056] S3, feature extraction: use convolutional neural network to extract features from the preprocessed image and identify the shape, color and texture in the image;

[0057] S4, classification and identification: compare the extracted features with the pre-trained classification model to determine the type of recyclable materials;

[0058] S5. Result feedback: Feedback is given based on the classification and recognition results. If the delivery is confirmed to be correct, the user’s points will be increased. Otherwise, the user will be prompted to deliver again.

[0059] Train an image classification model that can identify four common recyclables: paper, plastic, metal, and glass. Set different points rewards for each type of item:

[0060] Paper products: 60 points per kilogram;

[0061] Plastics: 70 points per kilogram;

[0062] Metals: 90 points per kilogram;

[0063] Glass: 60 points per kilogram;

[0064] Assume that a user places a 0.5 kg plastic bottle. The system needs to use image recognition technology to confirm that the item belongs to the plastic category and calculate the points the user deserves:

[0065] S1. Image acquisition: The camera captures an image containing a plastic bottle.

[0066] S2. Preprocessing: Convert the image into a grayscale image and perform necessary denoising.

[0067] S3, feature extraction: extract shape, color distribution, and texture features from the image.

[0068] S4, classification and recognition: Use the trained model for classification, and the output result is "plastic bottle".

[0069] S5. Result feedback: The system confirms that the item is a plastic bottle and calculates points based on weight;

[0070] Points = weight (kg) × points per kg

[0071] Therefore, the user received 35 points for disposing of 0.5 kg of plastic bottles.

[0072] Embodiment 2

[0073] Following the same content as in the first embodiment, a help button is also provided on the recycling compensation platform, which is used to press the button to seek help when encountering a problem, and the backstage customer service guides the user to operate correctly through remote video or voice calls;

[0074] Furthermore, the temporary score adjustment is also included after the material classification recognition fails. When the item cannot be recognized immediately, the system records it as pending manual confirmation, and then gives an estimated temporary score. After the item type is confirmed, the score is adjusted according to the actual situation:

[0075] Suppose a user places an unrecognizable item. The system prompts the user to place it again and provides a manual confirmation option. The user selects "plastic bottle" as the item type and enters the approximate weight (assuming 0.5 kg). Since the system cannot confirm it temporarily, it first gives an average score of 35 points (assuming the average score of paper, plastic, metal and glass), and will make adjustments after subsequent confirmation;

[0076]

[0077] If 60 points per kilogram for paper, 70 points for plastic, 90 points for metal, and 60 points for glass, then

[0078]

[0079] For items weighing 0.5 kg:

[0080] Provisional points = 0.5 × 70 = 35

[0081] If it is later confirmed that the object is indeed a plastic bottle, the points are adjusted:

[0082] Final score = 0.5 × 60 = 30

[0083] The system can effectively handle situations where recognition failures occur, ensuring that users’ points are not unfairly affected due to technical reasons.

[0084] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, or of course by hardware. Based on this understanding, the above technical solution, in essence, or the part that contributes to the relevant technology, can be embodied in the form of a software product, which can be stored in the terminal device or in the cloud system.

[0085] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic features of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the attached claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention, and any figure mark in the claims should not be regarded as limiting the claims involved.

[0086] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. An intelligent paid recycling system for recyclable materials, characterized in that: It includes intelligent recycling equipment and a recycling compensation platform, wherein the intelligent recycling equipment and the recycling compensation platform are connected via Internet of Things technology or a cellular network; The intelligent recycling device comprises an intelligent recycling box (1), four material collection buckets, a sensor group and a material classification and identification module, wherein the collection buckets and the sensor group are installed inside the intelligent recycling box (1), and the material classification and identification module is installed on the inner side of the door of the intelligent recycling box (1) and performs image acquisition through a camera; The intelligent recycling box (1) is also provided with a weighing basket (2) and a weighing basket three-axis moving mechanism (3); The material classification and recognition module uses a convolutional neural network to perform image feature recognition and classified recycling, and increases corresponding user points on the recycling compensation platform according to the classification and recognition results.

2. The intelligent paid recycling system according to claim 1 is characterized in that: The recycling compensation platform includes the IoT underlying framework, an information screen, a points mall, and B-end / C-end mobile application App / applets. The IoT underlying framework is used to carry out data interaction between the platform and the smart recycling bin. The information screen is used to display the status and statistical data of the recycling bin in real-time carousel of key information. The points mall is used to redeem goods based on the points obtained from recycled materials. The B-end mobile application App / applet is used by operation and maintenance personnel to manage smart recycling equipment. The C-end mobile application App / applet is used by users to query the location of nearby recycling equipment, understand recycling rules, check their points or withdraw cash.

3. The intelligent paid recycling system according to claim 1 is characterized in that: The material classification and identification module can identify paper, plastic, metal and glass; its identification includes the following steps: S1. Image acquisition: After the user opens the bin door through the interactive function, the user puts the recyclable materials into the bin door of the smart recycling bin (1), and the camera on the weighing basket inside the bin takes photos of the recyclable materials; S2, preprocessing: preprocessing the collected images; S3, feature extraction: use convolutional neural network to extract features from the preprocessed image and identify the shape, color and texture in the image; S4, classification and recognition: compare the extracted features with the pre-trained classification model to determine the types of recyclables; S5. Result feedback: Feedback is given based on the classification and recognition results. If the placement is confirmed to be correct, the user’s points will be increased. Otherwise, the warehouse door will be opened and the user will be prompted to return the material or re-place it.

4. The intelligent paid recycling system according to claim 1 is characterized in that: A variety of sensor groups are assembled to realize the functions and safety of intelligent recycling equipment; the sensor groups include the following five types: Image sensor, used for material image recognition; Weight sensor, used to measure and detect the weight of materials in the weighing basket; Proximity sensors to detect whether the four material collection buckets are full; Human body detector, used to detect whether someone has passed by the recycling equipment and whether it is operating; A temperature and humidity sensor, used to detect temperature and humidity data in the smart recycling box (1); Used to prevent moisture and mold from affecting the quality of recyclables; A smoke sensor is used to detect smoke in the smart recycling bin (1) to prevent fire; The water immersion sensor is used to detect whether there is water immersion at the bottom of the intelligent recycling box (1) to avoid damage to the equipment and affect the recycling of items.

5. The intelligent paid recycling system according to claim 1 is characterized in that: The weigh basket includes a load cell.

6. The intelligent paid recycling system according to claim 5, characterized in that: The weighing basket moving mechanism comprises a vertical moving component (4), a horizontal moving component (5) and a delivery mechanism (6); the vertical moving component (4) is used to drive the weighing basket to move vertically.

7. The intelligent paid recycling system according to claim 6, characterized in that: The weighing basket three-axis moving mechanism (3) can properly place the materials into the collection bucket in a complete, safe and non-destructive manner.

8. The intelligent paid recycling system according to claim 4 is characterized in that: The recycling system also includes an automatic fire extinguishing firefighting bag, an LED light strip in front of the cabinet, a face recognition camera, a personnel stay detection module in front of the cabinet, and a voice broadcast module. When the system does not detect a person, it will enter the standby state after a certain delay to reduce energy consumption and achieve green environmental protection and energy saving effects.

9. The intelligent paid recycling system according to claim 8, characterized in that: The recycling compensation system also includes local human-computer interaction, which displays photos, single weight, etc. on the display screen, and controls the opening and closing of doors, etc. There is also a help button, which is used to press the button to ask for help when encountering problems. The back-end customer service guides the user to operate correctly through remote video or voice calls.

10. The intelligent paid recycling system according to claim 2, characterized in that: Power supply methods include 220V AC or solar panel power supply to meet market installation needs.

Images