Intelligent recycling method and system for old furniture

Abstract

The invention provides an intelligent recycling method and system for old furniture. The method comprises the following steps that S1, a user takes a picture of the old furniture needing to be recycled through a user client and uploads the picture to a recycling platform; inputting the category and brand name of the old furniture through a user client; s2, the recycling platform recognizes the old and new degree of furniture according to the received pictures through an intelligent algorithm, the recycling value is evaluated, and a recycling scheme is generated; the recovery scheme comprises whole piece recovery and disassembly recovery; the recovery platform sends the recovery scheme to the user client; and the user selects a specific recycling scheme to recycle the old furniture. Compared with the prior art, the method has the advantages that the old and new degree of the to-be-recycled old furniture is accurately identified through an intelligent algorithm, and then the residual value of the to-be-recycled furniture is accurately estimated in combination with factors such as furniture categories, brand scarcity degree and actual region requirements. By means of the method, it is guaranteed that a user without furniture disassembling experience can rapidly master disassembling skills, and follow-up efficient disassembling and recycling work is facilitated.

Description

A Smart Recycling Method and System for Old Furniture Technical Field

[0001] This application relates to the field of waste furniture recycling technology, and in particular to an intelligent recycling method and system for old furniture. Background Technology

[0002] As people's living standards continue to improve, the problem of disposing of constantly updated furniture also arises. Current technologies for furniture recycling mainly utilize large-scale equipment to crush and separate the materials. For example, patent document CN120552254A describes using equipment to crush and separate the wood and plastic from waste furniture, thereby recycling and reusing both materials.

[0003] How to recycle discarded old furniture is a major issue. Recycling can be categorized into two types: whole-piece recycling and dismantling recycling. Whole-piece recycling can better preserve the value of the furniture, but due to the large size of some pieces, additional handling and / or logistics costs may arise during the recycling process. Dismantling recycling, on the other hand, can effectively reduce the volume of old furniture, thereby reducing handling and / or logistics costs; however, the dismantling process may damage the furniture, thus affecting its value. Both recycling methods have their advantages and disadvantages, but current technology lacks a specific solution for choosing between them.

[0004] Furthermore, if the recycling solution involves disassembly, disassembling the furniture can be difficult for users without disassembly experience. Although users may have assembled the furniture when purchasing it, they often forget the assembly process when recycling it, leaving them unsure how to disassemble it. Current technology lacks specific solutions to teach users how to disassemble and recycle furniture.

[0005] Furthermore, choosing the right transport vehicle is a crucial issue for recycling companies. Selecting a vehicle with a large cargo capacity means higher transportation costs (i.e., handling fees), while choosing a vehicle with a small cargo capacity carries the risk of not being able to fit all the furniture, especially when collecting multiple pieces of old furniture at once. For disassembly and recycling, it is even more difficult to estimate the dimensions of the disassembled furniture. Current technology lacks specific guidelines for recycling companies on how to select the right transport vehicle. Summary of the Invention

[0006] In order to achieve efficient recycling of waste furniture, this invention provides an intelligent recycling method and system for old furniture.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a smart recycling method for old furniture, comprising the following steps: S1: A user uploads photos of the old furniture to be recycled to the recycling platform via a user client; and inputs the category and brand name of the old furniture via the user client; S2: The recycling platform uses an intelligent algorithm to identify the condition of the furniture based on the received photos, assesses its recycling value, and generates a recycling plan; the recycling plan includes whole-item recycling and disassembly recycling; the recycling platform sends the recycling plan to the user client; S3: If the recycling plan is a whole-item recycling plan, the user client sends a confirmation of whole-item recycling information to the recycling platform; the recycling platform sends a whole-item recycling request to the recycling manufacturer's client based on the confirmation of whole-item recycling information; the recycling manufacturer's client goes to a designated location to recycle the furniture based on the whole-item recycling request; S4: If the recycling plan is a disassembly recycling plan... The recycling process involves the platform comparing received photos with furniture models in its database. If the database contains the same type of furniture, it retrieves the corresponding disassembly tutorial and sends it back to the user's client. If the database does not contain the same type of furniture, the platform dispatches a professional to disassemble the furniture, record the disassembly tutorial, and upload it to the platform's database. The user then disassembles the furniture according to the tutorial and sends a confirmation message to the platform via their client. The platform then sends a disassembly and recycling request to the recycling company's client, specifying a recycling station. The user places the disassembled parts at the designated recycling station, and the recycling company collects the parts from the station based on the platform's request.

[0008] In one embodiment of the present invention, the intelligent algorithm in S2 includes the following steps: S20: classifying and labeling pre-collected furniture image data according to their newness or oldness; inputting the data into a pre-established convolutional neural network model for training; S21: preprocessing the received photos; S22: extracting features from the preprocessed photos; S23: inputting the extracted features into an optimized convolutional neural network for classification to obtain the newness or oldness of the furniture.

[0009] The features in S22 include color features, texture features, and shape features.

[0010] Ideally, in S20, a genetic algorithm is used to optimize the pre-trained convolutional neural network model.

[0011] In one embodiment of the present invention, the evaluation of recycling value in S2 includes the following steps: S24: The recycling platform pre-establishes a residual value prediction model for old furniture using a gradient boosting decision tree, and inputs the category and brand name of the old furniture, the degree of newness of the furniture identified by the recycling platform, and the regional demand generated by the big data model into the residual value prediction model to estimate the residual value of the old furniture; S25: If the estimated residual value is greater than the preset value, the recycling platform provides a whole-piece recycling plan; otherwise, the recycling platform provides a disassembly and parts recycling plan.

[0012] This invention also provides an intelligent old furniture recycling system for implementing the intelligent old furniture recycling method described in the claims, comprising: a recycling platform; the recycling platform including a cloud server, the cloud server having an embedded intelligent algorithm engine; the intelligent algorithm engine storing intelligent algorithms for identifying the condition of furniture and assessing the recycling value of the old furniture to be recycled; the recycling platform sending the recycling plan generated by the intelligent algorithm engine to a user client; the cloud server also including a database storing disassembly videos of different types of furniture; and a client, the client including a user client and a recycling manufacturer client; the user uploads photos of the old furniture to be recycled to the recycling platform through the user client; and inputs the category and brand name of the old furniture through the user client; the user client is also used to receive the recycling plan sent by the recycling platform and confirm the recycling request with the recycling platform; the recycling manufacturer client is used to receive the recycling request sent by the recycling platform.

[0013] In one embodiment of the present invention, the intelligent algorithm for identifying the age of furniture includes the following steps: S20: classifying and labeling pre-collected furniture image data according to their age; inputting the data into a pre-established convolutional neural network model for training; S21: preprocessing the received photos; S22: extracting features from the preprocessed photos; S23: inputting the extracted features into an optimized convolutional neural network for classification to obtain the age of the furniture.

[0014] The features in S22 include color features, texture features, and shape features.

[0015] Ideally, in S20, a genetic algorithm is used to optimize the pre-trained convolutional neural network model.

[0016] In one embodiment of the present invention, an intelligent algorithm for evaluating the recycling value of old furniture includes the following steps: S24: The recycling platform pre-establishes an old furniture residual value prediction model using a gradient boosting decision tree, and inputs the category and brand name of the old furniture, the degree of newness of the furniture identified by the recycling platform, and the regional demand generated by the big data model into the residual value prediction model to estimate the residual value of the old furniture; S25: If the estimated residual value is greater than a preset value, the recycling platform provides a whole-piece recycling plan; otherwise, the recycling platform provides a disassembly and parts recycling plan.

[0017] Compared with existing technologies, this invention uses intelligent algorithms to accurately identify the condition of the old furniture to be recycled, and then combines factors such as furniture category, brand scarcity, and actual regional (market) demand to accurately estimate the residual value of the furniture to be recycled, thereby determining a recycling plan.

[0018] At the same time, the method of this invention ensures that even users without furniture disassembly experience can quickly master the disassembly skills, which facilitates efficient disassembly and recycling operations in the future.

[0019] Secondly, whether the furniture is recycled as a whole or disassembled, the size information can be estimated so that recycling companies can refer to it when selecting cargo vehicles. Attached Figure Description

[0020] Figure 1 is a schematic diagram of the main structure of the present invention. Detailed Implementation

[0021] To make the objectives, features, and advantages of this application more apparent and understandable, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] A smart recycling method for old furniture includes the following steps: S1: The user uploads photos of the old furniture to be recycled to the recycling platform through a user client; and inputs the category and brand name of the old furniture through the user client; S2: The recycling platform uses a smart algorithm to identify the condition of the furniture, assess its recycling value, and generate a recycling plan; the recycling plan includes whole-item recycling and / or disassembly and parts recycling; the recycling platform sends the recycling plan to the user client; wherein the smart algorithm in S2 includes the following steps: S20: Classifying and labeling the pre-collected furniture image data according to its condition; inputting it into a pre-established convolutional neural network model for training, and using a genetic algorithm to optimize the pre-established model; S21: Preprocessing the received photos; the preprocessing of the photos includes: denoising, enhancing contrast, standardizing, etc., so that the subsequent algorithm can better extract features.

[0023] S22: Feature extraction is performed on the preprocessed photos. The extracted features include: Color features: Analyzing color changes on the furniture surface, such as fading and yellowing, and extracting color histograms or color features (e.g., HSV, LAB). Texture features: Using texture analysis algorithms (e.g., Gabor filters, LBP local binary mode) to extract texture information from the furniture surface, reflecting the degree of wear. Shape features: Through edge detection and shape analysis, identifying the structural integrity of the furniture and determining whether there are obvious scratches or deformations.

[0024] S23: Input the extracted features into the optimized convolutional neural network for classification to determine the age of the furniture.

[0025] In S2, the recycling value is assessed using the following steps: S24: The recycling platform uses historical data to pre-build a residual value prediction model for old furniture using a gradient boosting decision tree (GBDT). The category and brand name of the old furniture, the degree of newness of the furniture identified by the recycling platform, and the regional demand generated by the big data model are input into the residual value prediction model to estimate the residual value of the old furniture; S25: If the estimated residual value is greater than the preset value, the recycling platform provides a whole-piece recycling plan; otherwise, the recycling platform provides a disassembly and parts recycling plan.

[0026] In practical applications, the logistics costs of whole-item recycling are higher than those of disassembly and parts recycling. Therefore, to ensure better economic efficiency, it is necessary to guarantee that the furniture to be recycled has a certain recycling value. Users' emotional investment and unfamiliarity with the recycling market can lead to inaccurate assessments of the recycling value of furniture. Therefore, this invention uses intelligent algorithms to accurately identify the condition of the old furniture to be recycled, and then combines this with factors such as furniture category, brand scarcity, and actual regional (market) demand to accurately estimate the residual value. If the residual value of the furniture is high, handling and / or logistics costs can be ignored, and whole-item recycling better preserves the furniture's value. If the residual value is low, whole-item recycling is not very meaningful, and additional handling and / or logistics costs will be incurred; in this case, disassembly and parts recycling is more economically efficient.

[0027] Whole furniture recycling is mainly used for the resale and refurbishment of furniture; disassembled parts recycling is mainly carried out by recycling companies for the reuse of recyclable materials.

[0028] The intelligent recycling method for old furniture of the present invention further includes: S3: If the recycling plan is a whole-item recycling plan, the user client sends a confirmation of whole-item recycling information to the recycling platform; the recycling platform sends a whole-item recycling request to the recycling manufacturer client based on the confirmation of whole-item recycling information; the recycling manufacturer client goes to the designated location to recycle according to the whole-item recycling request; S4: If the recycling plan is a disassembly recycling plan, the recycling platform needs to compare the received photo information with the furniture model in the database. If the database stores the same type of furniture, the corresponding furniture disassembly tutorial is retrieved and sent back to the user client; if the database does not store the same type of furniture, the recycling platform assigns a professional to disassemble the furniture and record the relevant disassembly tutorial, and uploads the relevant disassembly tutorial to the database of the recycling platform for storage; the user disassembles the furniture according to the received furniture disassembly tutorial, and after disassembly, sends a confirmation of disassembly recycling information to the recycling platform through the user client; the recycling platform sends a disassembly recycling request to the recycling manufacturer client based on the confirmation of disassembly recycling information and designates a recycling station; the user places the disassembled parts in the designated recycling station; the recycling manufacturer goes to the designated recycling station to recycle according to the disassembly recycling request sent by the recycling platform.

[0029] Through S4, the method of the present invention ensures that even users without furniture disassembly experience can quickly master disassembly skills, facilitating efficient subsequent disassembly and recycling operations.

[0030] Of course, in practical applications, users can also choose to recycle the entire piece or disassemble it for parts recycling based on their own needs. In this case, step S2 can be skipped. Alternatively, users can choose to maximize savings on handling and / or logistics costs based on actual needs. Ignoring the potential impact of the disassembly process on the furniture's value and rigidly setting the recycling plan to only include disassembly recycling, steps S2 and S3 are unnecessary; only steps S1 and S4 need to be executed. In step S4, replace "If the recycling plan is a disassembly recycling plan" with "Set the recycling plan to a disassembly recycling plan".

[0031] To provide a reference for recycling companies when selecting cargo vehicles, in the case of a whole-item recycling plan, step S3.5 is also included, which is performed after step S3: obtaining the size information of the furniture based on the photos of the furniture, and sending the size information of the furniture to the recycling company's client.

[0032] Alternatively, it may include step S3.5: obtaining the furniture size information based on the furniture photo, obtaining the recommended vehicle information based on the furniture size information, and sending the recommended vehicle information to the recycling company's client.

[0033] Specifically, the furniture photos include pictures of the furniture from various angles. The size information of the furniture in the photo can be deduced based on the dimensions of preset reference objects (such as common everyday items like bottled water or coins). Existing technologies have mature solutions for object recognition and size information acquisition, which will not be elaborated upon here. If the furniture photos provided by the user lack preset reference objects or the angle of the photos is insufficient, the user can be prompted to supplement or retake the photos.

[0034] After obtaining the furniture's dimensions, this information is sent to the recycling company's client. Upon receiving the dimensions, the recycling company can arrange delivery vehicles according to its needs. In a more preferred embodiment, delivery vehicle recommendations are obtained based on the furniture's dimensions. Specifically, this can be achieved by providing pre-trained artificial intelligence with the furniture's dimensions and the cargo dimensions of existing types (or models) of delivery vehicles. The AI ​​then outputs recommended vehicle types (or models), which are sent as delivery vehicle recommendations to the recycling company's client.

[0035] In the case of a dismantling and recycling scheme, step S4.5 is also included, which is executed after step S4: obtaining the dismantling type of the furniture based on the furniture photo; obtaining the preset first size information and preset second size requirement of the furniture based on the furniture dismantling type; obtaining the second size information corresponding to the second size requirement of the furniture based on the furniture photo; obtaining the dismantling size information of the furniture based on the dismantling type, the first size information and the second size information; sending the dismantling size information of the furniture to the recycling manufacturer's client; or obtaining the recommended information of the cargo vehicle based on the dismantling size information of the furniture and sending the recommended information of the cargo vehicle to the recycling manufacturer's client.

[0036] The following uses a common four-legged chair as an example to explain the detailed process of step S4.5: Specifically, obtain the disassembly type of the furniture based on the furniture photo. For a four-legged chair, it can be simplified into two disassembly types (the actual disassembly type is set according to the requirements; this is just an example). Type A has four independent chair legs connected to the seat, and the backrest is then separately connected to the seat. Type B has two chair legs forming an integrated backrest with the seat connected to the backrest, and the remaining two chair legs connected to the seat.

[0037] There are two scenarios at this point. In the first scenario, if the furniture model has already been obtained in step S4, the corresponding dismantling type can be directly obtained based on the furniture model (the recycling platform has a database of furniture model-dismantling type). In the second scenario, if the furniture model has not been obtained in step S4, the dismantling type can be identified through a photo of the furniture; alternatively, different types of dismantling types can be illustrated for the user's reference, allowing the user to select the appropriate dismantling type.

[0038] Based on the furniture disassembly type, obtain the preset first dimension information and preset second dimension requirements for the furniture. Specifically, for certain dimensions of smaller furniture parts, or smaller dimensions of certain parts (such as the width of a single chair leg, in which case all chair legs can be approximated as square prisms), these dimensions are not very accurate when obtained from photographs. However, these dimensions do not differ significantly across different models of similar furniture and will not have a major impact on the final disassembly dimensions as a whole. These dimensions are categorized as first dimension information. Therefore, the first dimension information can be set through preset methods. For example, the first dimension information in type A and type B could be the width of the chair legs, the thickness of the chair back, the thickness of the chair seat, etc. Note that the number and specific elements of the first dimension information may vary depending on the disassembly method and can be preset according to actual needs.

[0039] Dimensions that significantly impact the final disassembly dimensions are categorized as secondary dimension information. Based on the furniture disassembly type, the pre-defined secondary dimension requirements indicate which secondary dimension information needs to be measured. For example, in Type A and Type B, the secondary dimension requirements might include: leg height, seat length, seat width, backrest length, and backrest width. Note that the number of secondary dimension requirements and the specific disassembly methods may vary depending on the disassembly type; these can be pre-defined according to actual needs.

[0040] Obtain the second dimension information of the furniture corresponding to the second dimension requirement based on the furniture photo. For example, for type A and type B, obtain the dimensions of the chair legs height, seat length, seat width, backrest length, and backrest width based on the furniture photo. Obtaining the furniture dimension information from the furniture photo is similar to the method described in step S3.5 above, and will not be repeated here. For furniture for which obtaining the second dimension information from the photo fails, the user can manually input it; similarly, the user can also manually input the first dimension information.

[0041] Based on the furniture's disassembly type, first dimension information, and second dimension information, the disassembly dimension information of the furniture is obtained. The disassembly dimension information can be the dimensions of each individual component after disassembly. For example, the disassembly dimension information for type A includes the dimensions of the chair back, seat, and four chair legs. (The second instance is a repetition of the first instance.)

[0042] Send the disassembled dimensions of the furniture to the recycling company's client; or, based on the disassembled dimensions, obtain recommended truck information and send the recommended truck information to the recycling company's client. This step is similar to the method described in step S3.5 and will not be repeated here.

[0043] This invention also provides an intelligent old furniture recycling system, the main structure of which is shown in Figure 1. It is used to implement the intelligent old furniture recycling method described in the claims, and includes: a recycling platform; the recycling platform includes a cloud server, the cloud server having an embedded intelligent algorithm engine; the intelligent algorithm engine stores intelligent algorithms for identifying the condition of furniture and assessing the recycling value of the old furniture to be recycled; the recycling platform sends the recycling plan generated by the intelligent algorithm engine to a user client; the cloud server also includes a database, the database storing disassembly videos of different types of furniture; and a client, the client including a user client and a recycling manufacturer client; the user uploads photos of the old furniture to be recycled to the recycling platform through the user client; and inputs the category and brand name of the old furniture through the user client; the user client is also used to receive the recycling plan sent by the recycling platform and confirm the recycling request with the recycling platform; the recycling manufacturer client is used to receive the recycling request sent by the recycling platform.

[0044] In a specific embodiment of the present invention, the client can exist in the form of an app.

[0045] In one embodiment of the present invention, the intelligent algorithm for identifying the age of furniture includes the following steps: S20: classifying and labeling pre-collected furniture image data according to their age; inputting the data into a pre-established convolutional neural network model for training; S21: preprocessing the received photos; S22: extracting features from the preprocessed photos; S23: inputting the extracted features into an optimized convolutional neural network for classification to obtain the age of the furniture.

[0046] The features in S22 include color features, texture features, and shape features.

[0047] Ideally, in S20, a genetic algorithm is used to optimize the pre-trained convolutional neural network model.

[0048] In one embodiment of the present invention, an intelligent algorithm for evaluating the recycling value of old furniture includes the following steps: S24: The recycling platform pre-establishes an old furniture residual value prediction model using a gradient boosting decision tree, and inputs the category and brand name of the old furniture, the degree of newness of the furniture identified by the recycling platform, and the regional demand generated by the big data model into the residual value prediction model to estimate the residual value of the old furniture; S25: If the estimated residual value is greater than a preset value, the recycling platform provides a whole-piece recycling plan; otherwise, the recycling platform provides a disassembly and parts recycling plan.

[0049] The smart recycling system for old furniture may also include a furniture size processing module, configured to perform the methods described in steps S3.5 and S4.5 above.

[0050] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this application can be achieved, and this is not limited herein.

[0051] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for intelligent recycling of old furniture, characterized in that: Includes the following steps: S1: Users upload photos of the old furniture to be recycled to the recycling platform through the user client; and enter the category and brand name of the old furniture through the user client; S2: The recycling platform uses intelligent algorithms to identify the condition of the furniture in the received photos, assess its recycling value, and generate a recycling plan. Recycling plans include whole-item recycling and disassembly recycling. The recycling platform sends the recycling plan to the user's client. S3: If the recycling plan is for whole-item recycling, the user's client sends a confirmation message to the recycling platform. The recycling platform then sends a whole-item recycling request to the recycling manufacturer's client. The recycling manufacturer's client collects the furniture at the designated location based on the whole-item recycling request. S4: If the recycling plan is for disassembly recycling, the recycling platform needs to compare the received photo information with the furniture model in its database. If the database contains the same model... If the furniture is a specific model, the system retrieves the corresponding disassembly tutorial and sends it back to the user's client. If the database does not store the same model of furniture, the recycling platform dispatches a professional to disassemble the furniture, record the disassembly tutorial, and upload it to the platform's database. The user then disassembles the furniture according to the received tutorial and sends a confirmation message to the recycling platform via their client. The platform then sends a disassembly and recycling request to the recycling company's client, specifying a recycling station. The user places the disassembled parts at the designated recycling station, and the recycling company collects them from the station based on the platform's request.

2. The intelligent recycling method for old furniture according to claim 1, characterized in that: The intelligent algorithm in S2 includes the following steps: S20: Classify and label the pre-collected furniture image data according to their newness or oldness; input the data into a pre-established convolutional neural network model for training; S21: Preprocess the received photos; S22: Extract features from the preprocessed photos; S23: Input the extracted features into the optimized convolutional neural network for classification to obtain the newness or oldness of the furniture.

3. The intelligent recycling method for old furniture according to claim 2, characterized in that: The features in S22 include color features, texture features, and shape features.

4. The intelligent recycling method for old furniture according to claim 1, characterized in that: In S2, the recycling value is assessed. The process includes the following steps: S24: The recycling platform pre-establishes a residual value prediction model for old furniture using a gradient boosting decision tree. The category and brand name of the old furniture, the degree of newness of the furniture identified by the recycling platform, and the regional demand generated by the big data model are input into the residual value prediction model to estimate the residual value of the old furniture; S25: If the estimated residual value is greater than the preset value, the recycling platform provides a whole-piece recycling plan; otherwise, the recycling platform provides a disassembly and parts recycling plan.

5. The intelligent recycling method for old furniture according to claim 1, characterized in that: It also includes the following steps: S3.5: If the recycling plan is a whole-item recycling plan, obtain the furniture's size information based on the furniture's photo; obtain the recommended delivery vehicle information based on the furniture's size information; and send the recommended delivery vehicle information to the recycling company's client. Step S4.5: If the recycling plan is a dismantling recycling plan, obtain the furniture's dismantling type based on the furniture's photo; obtain the furniture's preset first size information and preset second size requirement based on the furniture's dismantling type; obtain the second size information corresponding to the second size requirement based on the furniture's photo; obtain the furniture's dismantling size information based on the furniture's dismantling type, first size information, and second size information; or obtain the recommended delivery vehicle information based on the furniture's dismantling size information; and send the recommended delivery vehicle information to the recycling company's client.

6. A smart recycling system for old furniture, used to implement the smart recycling method for old furniture as described in any one of claims 1-5, characterized in that: include: The recycling platform includes a cloud server, which has an embedded intelligent algorithm engine. The intelligent algorithm engine stores intelligent algorithms for identifying the condition of furniture and assessing its recycling value. The recycling platform sends the recycling plan generated by the intelligent algorithm engine to the user client. The cloud server also includes a database storing disassembly videos of different types of furniture. The client includes a user client and a recycling manufacturer client. Users upload photos of the old furniture to be recycled to the recycling platform via the user client and input the type and brand name of the furniture. The user client also receives the recycling plan from the recycling platform and confirms the recycling request. The recycling manufacturer client is used to receive the recycling request from the recycling platform.

7. The intelligent recycling system for old furniture according to claim 6, characterized in that: The intelligent algorithm for identifying the age of furniture includes the following steps: S20: Classifying and labeling pre-collected furniture image data according to their age; inputting the data into a pre-established convolutional neural network model for training; S21: Preprocessing the received photos; S22: Extracting features from the preprocessed photos; S23: Inputting the extracted features into an optimized convolutional neural network for classification to obtain the age of the furniture.

8. The intelligent recycling system for old furniture according to claim 7, characterized in that: The features in S22 include color features, texture features, and shape features.

9. The intelligent recycling system for old furniture according to claim 6, characterized in that: A smart algorithm used to assess the recycling value of old furniture awaiting recycling. The process includes the following steps: S24: The recycling platform pre-establishes a residual value prediction model for old furniture using a gradient boosting decision tree. The category and brand name of the old furniture, the degree of newness of the furniture identified by the recycling platform, and the regional demand generated by the big data model are input into the residual value prediction model to estimate the residual value of the old furniture; S25: If the estimated residual value is greater than the preset value, the recycling platform provides a whole-piece recycling plan; otherwise, the recycling platform provides a disassembly and parts recycling plan.

10. The intelligent recycling system for old furniture according to claim 6, characterized in that: The system includes a furniture size processing module configured to perform the following steps: S3.5: If the recycling plan is a whole-piece recycling plan, obtain the furniture size information based on the furniture photo; obtain the recommended vehicle information based on the furniture size information; and send the recommended vehicle information to the recycling company client. Step S4.5: If the recycling plan is a dismantling recycling plan, obtain the furniture dismantling type based on the furniture photo; obtain the preset first size information and preset second size requirement of the furniture based on the furniture dismantling type; obtain the second size information corresponding to the second size requirement based on the furniture photo; obtain the dismantling size information of the furniture based on the dismantling type, the first size information, and the second size information; or obtain the recommended vehicle information based on the dismantling size information of the furniture and send the recommended vehicle information to the recycling company client.

Images