Metal recycling analysis system and method

Through the recycling data, material effects and model prediction module of the metal recycling analysis system, combined with neural network and blockchain technology, the problem of subjective influence in traditional methods is solved, and systematic metal recycling analysis and prediction is realized. Accurate recycling indicators.

CN114297937BActive Publication Date: 2024-12-06INST OF GEOGRAPHICAL SCI & NATURAL RESOURCE RES CAS
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111666501.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-12-31
Publication Date
2024-12-06
Estimated Expiration
2041-12-31

AI Technical Summary

Technical Problem

Traditional metal recycling research methods mainly stay at the theoretical level, lack specific and effective methods for recycling metal materials, and are subjectively affected by experts or the industry, making it difficult to achieve systematic and standardized recycling analysis.

Method used

It provides a metal recycling analysis system, including a recycling data analysis module, a material effect analysis module and a model prediction analysis module. It simulates subjective and objective data through preset theory and operation model to reduce subjective impact and standardize recycling analysis. The system uses neural network models to predict recycling results, and uses blockchain technology to visualize results and consensus scoring to improve data credibility and transparency.

Benefits of technology

The systematic prediction of the recycling results of the target metal is achieved, the subjective impact is reduced, and the comprehensive reference of recycling indicators is provided, the problems of inconsistent and missing multi-source data are solved, and the accuracy and credibility of the analysis are improved. .

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114297937B_ABST
    Figure CN114297937B_ABST
Patent Text Reader

Abstract

The present invention relates to a metal recycling analysis system and method, which uses a recycling data analysis module to obtain the usage data of the target metal, simulates the usage data according to a preset theoretical model, and determines the recycling data and regeneration potential data; a material effect analysis module obtains the subjective data of the target metal, simulates the subjective data according to a preset operation model, and determines the operation data; a model prediction analysis module is used to substitute the recycling data, regeneration potential data and operation data into the preset prediction model to predict the recycling result of the target metal. In the recycling analysis of the target metal, the present invention obtains the subjective and objective data of the system, and simulates the subjective and objective results synchronously on the basis of traditional theories, and predicts the metal recycling results, which can reduce the subjective influence on the recycling analysis, and standardize the recycling analysis of the target metal in a system fixed processing mode.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of resource recycling, and in particular to a metal recycling analysis system and method. Background Art

[0002] Metals have the typical characteristic of being recyclable. In the context of economic globalization, the mutual coupling and correlation of metal cycles in different countries and at different stages of the life cycle are increasingly strengthened. Carrying out research on the recycling of strategic key metal minerals from a global, full life cycle and dynamic perspective is not only an applied basic issue to meet the country's major needs for ensuring the safety of strategic key metal minerals, but also a cutting-edge issue in current scientific research.

[0003] Among them, the traditional theories and methods for conducting research on the recycling of metal materials mainly include life cycle assessment, input-output method, multi-regional input-output analysis method, material flow analysis method and system dynamics method, etc. However, the traditional methods mainly remain at the theoretical level, are greatly influenced by the subjective influence of experts or industries, and lack specific and effective ways to recycle metal materials. Summary of the invention

[0004] Based on this, it is necessary to provide a metal recycling analysis system and method to address the deficiencies in the prior art.

[0005] A metal recycling analysis system, comprising:

[0006] A recycling data analysis module is used to obtain the usage data of the target metal, simulate the usage data according to the preset theoretical model, and determine the recycling data and regeneration potential data;

[0007] Material effect analysis module, used to obtain subjective data of target metals, simulate the subjective data according to the preset operation model, and determine the operation data;

[0008] The model prediction and analysis module is used to predict the recycling results of the target metal by substituting the recycling data, regeneration potential data and operation data into the preset prediction model.

[0009] The above-mentioned metal recycling analysis system includes a recycling data analysis module, a material effect analysis module and a model prediction analysis module. The recycling data analysis module obtains the usage data of the target metal, simulates the usage data according to the preset theoretical model, and determines the recycling data and regeneration potential data; the material effect analysis module obtains the subjective data of the target metal, simulates the subjective data according to the preset operation model, and determines the operation data; the model prediction analysis module is used to substitute the recycling data, regeneration potential data and operation data into the preset prediction model to predict the recycling results of the target metal. In the recycling analysis of the target metal, the subjective and objective data of the system are obtained, and the simulation of the subjective and objective results is performed simultaneously on the basis of traditional theory to predict the recycling results. Based on this, the subjective influence on the recycling analysis is minimized, and the recycling analysis of the target metal is standardized in a fixed system processing method.

[0010] In one embodiment, it also includes:

[0011] The prediction result presentation module is used to visualize the recycling results.

[0012] In one embodiment, the cycle data analysis module includes:

[0013] A trade association unit, used to simulate the usage data according to a preset trade association model to determine the trade association data;

[0014] The demand forecasting unit is used to simulate the usage data according to a preset demand forecasting model to determine the demand forecasting data.

[0015] In one embodiment, the cycle data analysis module further includes:

[0016] A data set construction unit, used to construct multi-stream data by using data;

[0017] The potential evaluation unit is used to perform corresponding simulation on multi-stream data according to a preset data circulation model to determine potential evaluation data.

[0018] In one embodiment, the material effect analysis module includes:

[0019] Regeneration and recycling law unit, used to obtain subjective law data of target metals;

[0020] A stock determination unit, used to obtain stock data of target metals;

[0021] The life cycle trade unit is used to obtain data on the subjective impact of the life cycle trade of the target metal on recycling;

[0022] The multi-stream fusion unit is used to obtain the multi-stream fusion subjective score of the target metal.

[0023] In one embodiment, the preset prediction model includes a decision tree model, a regression prediction model or a neural network model.

[0024] In one of the embodiments, the preset prediction model includes a neural network model;

[0025] Among them, the model prediction analysis module is configured as follows:

[0026] Inputting the recycling data and the regeneration potential data into the neural network model as training data to obtain the preset classification labels output by the neural network model;

[0027] Based on the difference between the preset classification labels and the corresponding operating data, the recycling results of the target metal are predicted.

[0028] In one embodiment, the process of visualizing the recycling results in the prediction result presentation module includes the steps of:

[0029] Obtaining registration information of expert users and consensus scores of expert users on recycling results;

[0030] Build a consensus node network based on consensus scoring;

[0031] Upload the registration information to the supervision node through the consensus node network;

[0032] Receive the audit results of the registration information by the regulatory node, and mark the audit results accordingly in the consensus node network to form a visual result.

[0033] In one embodiment, the consensus node network is a blockchain network.

[0034] In one embodiment, consensus scoring includes weighted scoring and digital signatures.

[0035] A metal recycling analysis method comprises the following steps:

[0036] Identify target metals in target areas and obtain usage data of target metals in target areas;

[0037] Outputting the usage data to the circulation data analysis module to instruct the circulation data analysis module to simulate the usage data according to a preset theoretical model to determine the recycling data and the regeneration potential data;

[0038] Define the system based on recycling data and regeneration potential data, build a list of products in the target area and establish a data analysis system;

[0039] Conduct historical retrospective research based on the data analysis system to obtain research output data;

[0040] Outputting the research output data as subjective data to the material effect analysis module to instruct the material effect analysis module to simulate the subjective data according to a preset operation model to determine the operation data;

[0041] Analyze the spatiotemporal patterns, multi-flow coupling, and resource and environmental effects of operating data

[0042] The analysis results are sent to the model prediction analysis module to instruct the model prediction analysis module to predict the recycling results of the analysis results according to the preset prediction model.

[0043] The above-mentioned metal recycling analysis method is based on the model processing of the metal recycling analysis system, and is systematically defined according to the recycling data and regeneration potential data, a product list of the target field is constructed and a data analysis system is established. A historical retrospective study is conducted based on the data analysis system to obtain the research output data, and the research output number is output as subjective data to the material effect analysis module to instruct the material effect analysis module to simulate the subjective data according to the preset operation model, determine the operation data, analyze the operation data and send the analysis results to the model prediction analysis module to instruct the model prediction analysis module to predict the recycling results of the analysis results according to the preset prediction model. Based on this, a comprehensive evaluation of the regeneration potential and recycling of the key target metal type is conducted to solve the lack of systematic analysis of target metals such as multiple sources, inconsistent calibers, blank or partial missing data, and provide a comprehensive indicator reference related to recycling. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A module structure diagram of a metal recycling analysis system according to an embodiment;

[0045] Figure 2 is a structural diagram of a cyclic data analysis module according to an embodiment;

[0046] Figure 3 is a structural diagram of a material effect analysis module according to an implementation method;

[0047] Figure 4 A schematic diagram of a visualization process structure of an implementation method;

[0048] Figure 5 A flow chart of a metal recycling analysis method according to an embodiment;

[0049] Figure 6 A flow chart of a metal recycling analysis method according to another embodiment;

[0050] Figure 7 A schematic diagram of a system definition structure of an embodiment;

[0051] Figure 8It is a schematic diagram for historical retrospective research;

[0052] Fig. 9 Schematic diagram for running data analysis;

[0053] Fig.10 Schematic diagram of the optimization indicator calculation process. DETAILED DESCRIPTION

[0054] In order to better understand the purpose, technical solution and technical effect of the present invention, the present invention is further explained below in conjunction with the accompanying drawings and embodiments. At the same time, it is stated that the embodiments described below are only used to explain the present invention and are not used to limit the present invention.

[0055] An embodiment of the present invention provides a metal recycling analysis system.

[0056] The metal recycling analysis system can be run on a computer device or server platform to call the database of corresponding usage data in the form of a data chain or blockchain. Alternatively, relevant personnel can send subjective data to the system level through interaction with the metal recycling analysis system.

[0057] Figure 1 The module structure diagram of the metal recycling analysis system according to one embodiment is as follows: Figure 1 As shown, a metal recycling analysis system according to one embodiment includes:

[0058] A recycling data analysis module 1000 is used to obtain usage data of the target metal, simulate the usage data according to a preset theoretical model, and determine recycling data and regeneration potential data;

[0059] Material effect analysis module 1001, used to obtain subjective data of target metal, simulate the subjective data according to a preset operation model, and determine the operation data;

[0060] The model prediction analysis module 1002 is used to predict the recycling results of the target metal by substituting the recycling data, regeneration potential data and operation data into a preset prediction model.

[0061] The target area is determined based on the target metal to be detected, and may include geographical areas, industries or administrative areas, such as countries, urban agglomeration areas, power industry or transportation industry, etc.

[0062] The target metals are metals that account for a relatively high proportion or are relatively critical in recycling analysis, including strategic key metal minerals such as rubidium, cobalt, and platinum, or bulk metal minerals such as copper and tungsten.

[0063] In this embodiment, the entire life cycle of the target metal includes four major stages: mining and production (mineral products and metals), processing and manufacturing (semi-finished products and final products), use (final products), and waste management (waste), as well as trade (minerals, metals, semi-finished products, final products and waste) throughout the four stages.

[0064] Based on this, the usage data of the target metal includes various types of data throughout the entire life cycle of the target field, including process data, trade-related economic data, product information, usage parameters, its own attribute parameters, literature records, expert subjective parameters and other relevant data.

[0065] The usage data of the target metals refer to the above embodiments. The usage data is related to the preset theoretical model, such as: an assessment model based on the life cycle assessment method, an input-output model, a multi-regional input-output analysis model, a material flow analysis model and a system dynamics model.

[0066] Taking the material flow analysis model as an example, based on the law of conservation of matter, it systematically and quantitatively evaluates the sources, paths and sinks of target metal substances in a specific system. It can be used to evaluate and simulate the target metal’s full life cycle efficiency, regeneration potential, future demand and key regulatory policies, and constitute recycling data or regeneration potential data.

[0067] In one embodiment, in order to cooperate with the determination of partial recycling data and regeneration potential data, the preset theoretical model can also use system models such as econometric models, usage intensity models, stock analysis models, life distribution models and system dynamics models.

[0068] According to the selection of the above model, the recycling data and the regeneration potential data, such as the target metal inventory or the target metal demand, are determined. It should be noted that the recycling data and the regeneration potential data can be determined according to the selected preset theoretical model, and there is no unique limitation in the field of metal recycling.

[0069] At the same time, the system obtains subjective data, including experts in related fields, industry scores, inventory forecasts, etc. The system is open to multiple types of nodes and collects subjective data from various nodes for upload.

[0070] In one embodiment, the preset operation model includes a data classification model, an uncertainty analysis module or a sensitivity analysis module. The preset operation model can also be based on MFA (multiple factor) mathematical analysis to establish a model.

[0071] Referring to the classification of the above preset operation model, the preset operation model is used to reduce the data uncertainty of subjective data, including random variability and cognitive uncertainty, so as to improve the reference value of various subjective data. Based on the above foundation, the preset operation model can also select other analysis models to process subjective data.

[0072] Based on this, the model prediction analysis module combines the corresponding results of the usage data and the subjective data to perform a comprehensive recycling result output. In one embodiment, the preset prediction model includes a decision tree model, a regression prediction model or a neural network model to perform comprehensive data processing.

[0073] In one embodiment, Figure 2 is a structural diagram of a cyclic data analysis module according to an embodiment of the present invention, Figure 2 As shown, the cycle data analysis module 1000 includes:

[0074] The trade association unit 2000 is used to simulate the usage data according to a preset trade association model to determine the trade association data;

[0075] The demand forecasting unit 2001 is used to simulate the usage data according to a preset demand forecasting model to determine the demand forecasting data.

[0076] Among them, the preset theoretical model includes the preset trade association model. Based on the perspective of the whole life cycle, the preset trade association model defines the system boundary of the recycling of strategic key metal minerals in the target metal, describes the spatiotemporal transfer process of strategic key metal minerals in the global trade supply chain, and analyzes the key links and elements therein; analyzes the spatiotemporal evolution characteristics, laws and influencing factors of the recycling of strategic key metal minerals based on trade association in different processes and scales as trade association data.

[0077] Among them, the preset theoretical model includes a preset demand forecast model. Preset demand forecast model. From the perspective of stock drive, study the driving effect of different products (electronic products, electric vehicles, etc.) and different technologies (energy storage technology, renewable energy technology, etc.) on the demand for strategic key metal minerals; analyze the relationship between the target metal stock and demand, and build a global strategic key metal mineral demand forecast model based on stock drive, revealing the changing laws of strategic key metal mineral demand in different social and economic development stages, different products, and different technologies, so as to determine the demand forecast data.

[0078] In one embodiment, if Figure 2 As shown, the cycle data analysis module 1000 also includes:

[0079] A data set construction unit 2002, used to construct multi-stream data by using data;

[0080] The potential evaluation unit 2003 is used to perform corresponding simulation on the multi-stream data according to a preset data circulation model to determine the potential evaluation data.

[0081] Among them, taking strategic key metal minerals as an example, the different data sources involved in the recycling process are analyzed in terms of data structure and accuracy, and their sources of uncertainty are identified; a general data structure for material flow analysis of strategic key metal minerals is constructed; and multi-stream data is constructed for different conditions such as blanks, missing data, inconsistent calibers, and low accuracy.

[0082] Among them, the preset theoretical model includes the preset data cycle model. The recycling of strategic key metal minerals includes ore grade, efficiency of mining, smelting, processing and manufacturing processes, metal content and changes of products and technologies, and service life of products and technologies; through the preset data cycle model of each link of strategic key metals, the potential assessment is determined.

[0083] It should be noted that the above-mentioned target metals take strategic key metals as an example. Similar models are also constructed in other metal fields.

[0084] In one embodiment, Figure 3 is a structural diagram of a material effect analysis module according to an embodiment of the present invention, Figure 3 As shown, the material effect analysis module 1001 includes:

[0085] Regeneration and recycling law unit 3000, used to obtain subjective law data of target metals;

[0086] The stock determination unit 3001 is used to obtain the stock data of the target metal;

[0087] Life cycle trade unit 3002 is used to obtain data on the subjective impact of the life cycle trade of the target metal on recycling;

[0088] The multi-stream fusion unit 3003 is used to obtain the multi-stream fusion subjective score of the target metal.

[0089] Among them, subjective law data can be divided by industry field, etc. For example, the recycling and recycling law unit 3000 selects three types of strategic key metals, analyzes their consumption fields, characteristics and domestic recycling laws, etc.; from a global and full life cycle perspective, determines the flow direction, flow and stock time series changes of the above three types of strategic key metal minerals in various regions of the world, determines the laws and main influencing factors of the recycling and recycling of the three types of strategic key metal minerals, and compares and analyzes the commonalities and differences with specific regions as subjective law data.

[0090] Among them, the stock determination unit 3001 uses the typical strategic key metal mineral flow, stock spatiotemporal evolution pattern and law of the target metal in the power (power generation, transmission and storage) and transportation (passenger cars, public transportation, etc.) industries in a specific region to determine the evolution characteristics of its trade spatiotemporal change pattern as stock data.

[0091] Among them, the life cycle trade unit 3002 constructs a global-life cycle trade network of typical strategic key metal minerals based on the global (regional) typical strategic key metal mineral flow routes throughout the life cycle, selects differences in the recycling of typical strategic key metal minerals throughout the life cycle in various regions, and reveals the spatial connection between the life cycle trade network and recycling of typical strategic key metal minerals, so as to determine the main impact of the life cycle trade of typical strategic key metal minerals on recycling and determine the subjective impact data.

[0092] Among them, the multi-stream fusion unit 3003 quantitatively evaluates the changing characteristics and laws of the spatiotemporal patterns of metal flows, energy flows, value flows, etc. of typical strategic key metal mineral recycling based on the entire life cycle according to the data obtained by the system; sets up multi-strategy fusion scenarios, and dynamically simulates the multi-stream fusion process of typical strategic key metal mineral recycling, which is used to evaluate its multi-stream fusion effect and determine the multi-stream fusion subjective score.

[0093] In one embodiment, the model prediction analysis module 1002 selects a neural network model.

[0094] The model prediction analysis module 1002 is configured as follows:

[0095] Inputting the recycling data and the regeneration potential data into the neural network model as training data to obtain the preset classification labels output by the neural network model;

[0096] Based on the difference between the preset classification labels and the corresponding operating data, the recycling results of the target metal are predicted.

[0097] Among them, since the subjective data and the usage data can be determined in advance, in the training process of the neural network model, the neural network model is trained by using the usage data as the training data and the subjective data as the label output result.

[0098] Based on the correlation between usage data, recycling data and regeneration potential data, after training the neural network model, the recycling data and regeneration potential data are used as training data. Among them, the preset classification labels output by the neural network model are associated with the subjective data. Based on this, the association between the operating data and the preset classification labels is realized, and the recycling results of the target metal are predicted through the difference between the preset classification labels and the corresponding operating data. Among them, through the first layer of the neural network, the processing results corresponding to the usage data and the subjective data are labeled, eliminating the uncertainty and complexity of the data and improving the consistency of the prediction of the recycling results.

[0099] Then, by comparing the differences between the running data and the preset classification labels, the recycling results are deeply optimized.

[0100] In one embodiment, the operational data is further processed by determining a mean or variance of the differences, including summing the operational data with the mean of the differences.

[0101] In one embodiment, the recycling results include a list of key recycling technology parameters, efficiency, economy, enterprise acceptance, policy support or social path of key recycling technologies.

[0102] In one embodiment, the recycling results include technology (reduction, substitution, regeneration), cost, environment, and policy.

[0103] In one embodiment, if Figure 1 As shown, the metal recycling analysis system of one embodiment further includes:

[0104] The prediction result presentation module 1003 is used to visualize the recycling results.

[0105] Among them, the recycling results can be visualized as policy combinations, technology development routes or policy orientation recommendations.

[0106] For example: (1) Development strategies for the recycling industry of strategic key metal minerals in typical regions. With the maximization of comprehensive benefits as the primary goal, a reasonable and effective policy combination is selected to formulate a spatial layout plan and implementation plan covering the entire life cycle of the recycling of typical strategic key metal minerals.

[0107] (2) Development roadmaps for typical strategic key metal mineral recycling technologies. From the perspectives of reducing supply risks and improving the efficiency of recycled resource utilization, identify and evaluate the types and development potential of key common technologies, cutting-edge technologies, and disruptive technologies, and design development roadmaps for various technologies.

[0108] (3) Policy orientations and recommendations for typical strategic key metal mineral recycling. Research and determine supporting policies in trade, prices, taxes, subsidies, etc. related to the development plan of the strategic key metal mineral recycling industry and the development of related technologies, and summarize the orientations of various supporting policies.

[0109] In one embodiment, Figure 4 FIG. 1 is a schematic diagram of a flow structure of a visualization method of an implementation method, such as Figure 4 As shown, the process of visualizing the recycling results in the prediction result presentation module includes the following steps:

[0110] Obtaining registration information of expert users and consensus scores of expert users on recycling results;

[0111] Build consensus node network S1 based on consensus scoring;

[0112] Upload the registration information to the supervision node through the consensus node network;

[0113] Receive the audit results of the registration information by the regulatory node, and mark the audit results accordingly in the consensus node network to form a visual result.

[0114] In one embodiment, the consensus node network is a blockchain network.

[0115] Among them, expert users include user login representatives from the above-mentioned industries or regions at the system level.

[0116] In one embodiment, consensus scoring includes weighted scoring and digital signatures.

[0117] Digital signatures are used to identify the identity of each expert user in the consensus node network.

[0118] Each expert user builds a consensus node network in the form of blockchain based on consensus scoring. Figure 4 As shown in the figure, after forming a consensus, adjacent expert users upload the consensus score to the supervision node. The supervision node selects whether to visualize the consensus score based on the registration information. Based on this, the supervision center is used as the central server to share information and authenticate identities in the form of blockchain to prevent the problem of excessive concentration of authority of a certain expert user, thereby improving the reference value of visualization.

[0119] In one of the embodiments, the registration information generates a public key and a user information summary through the RSA algorithm on the expert user side, and the supervision node performs the corresponding user information summary decryption based on the public key to ensure the security of the registration information.

[0120] Based on this, based on the consensus node network in the form of blockchain, the consensus score of any expert user is arbitrarily transmitted among the expert users to form adjacent expert users. When the consensus scores of adjacent expert users are close or the difference is less than the preset difference, it is considered that a consensus has been reached and uploaded to the supervision node by the consensus scoring network. Through the decentralized characteristics of blockchain and the unique upload design, the weight of an expert user is weakened as much as possible.

[0121] The metal recycling analysis system of any of the above-mentioned embodiments includes a recycling data analysis module, a material effect analysis module and a model prediction analysis module. The recycling data analysis module obtains the usage data of the target metal, simulates the usage data according to the preset theoretical model, and determines the recycling data and the regeneration potential data; the material effect analysis module obtains the subjective data of the target metal, simulates the subjective data according to the preset operation model, and determines the operation data; the model prediction analysis module is used to substitute the recycling data, the regeneration potential data and the operation data into the preset prediction model to predict the recycling results of the target metal. In the recycling analysis of the target metal, the subjective and objective data of the system are obtained, and the simulation of the subjective and objective results is performed simultaneously on the basis of traditional theories to predict the recycling results. Based on this, the subjective influence on the recycling analysis is minimized, and the recycling analysis of the target metal is standardized in a system-fixed processing method.

[0122] The embodiment of the present invention also provides a metal recycling analysis method, which utilizes the above-mentioned metal recycling analysis system.

[0123] Figure 5 A flow chart of a metal recycling analysis method according to an embodiment of the present invention is shown in FIG. Figure 5 As shown, a metal recycling analysis method according to an embodiment includes steps S100 to S104:

[0124] S100, determining a target metal in a target field, and obtaining usage data of the target metal in the target field;

[0125] S101, outputting the usage data to the circulation data analysis module to instruct the circulation data analysis module to simulate the usage data according to a preset theoretical model to determine the recycling data and the regeneration potential data;

[0126] S102, based on the recycling data and regeneration potential data, define the system, build a list of products in the target area and establish a data analysis system;

[0127] S103, conduct historical retrospective research based on the data analysis system to obtain research output data;

[0128] S104, outputting the research output data as subjective data to the material effect analysis module to instruct the material effect analysis module to simulate the subjective data according to a preset operation model to determine the operation data;

[0129] S105, analyzing the spatiotemporal patterns, multi-flow coupling, and resource and environmental effects of operating data;

[0130] S106, sending the analysis result to the model prediction analysis module to instruct the model prediction analysis module to predict the recycling result of the analysis result according to the preset prediction model.

[0131] In one embodiment, the usage data screening of the target metal can be determined according to the subsequent indicator monitoring requirements, and the usage data screening is performed according to the definition requirements of step S102 and the specific type of the target area.

[0132] In one embodiment, Figure 6 A flow chart of a metal recycling analysis method according to another embodiment of the present invention is shown in FIG. Figure 6 As shown, the process of defining the system according to the recycling data and the regeneration potential data, constructing the target field product list and establishing the data analysis system in step S102 includes step S200:

[0133] S200, defines the scope, boundaries, time frame and topology of material flows of target metals in each life cycle process based on recycling data and recycling potential data.

[0134] Taking strategic key metal minerals as an example, the use data determined by expert seminars, discussions (academia, industry, government management agencies, etc.), literature research, field research (mines, factories), etc. can be used to analyze the process and main characteristics of the life cycle of strategic key mineral resources from mining, smelting, production, processing, semi-finished products, final products, waste to recycling and treatment, and define the scope, boundaries, time frame and topological structure of material flow of the entire system and each life cycle process in the system.

[0135] In one embodiment, if Figure 6 As shown, the process of constructing a product list in a target field and establishing a data analysis system also includes step S201 and step S202:

[0136] S201, calling the product list and product details of the relevant database, classifying the product list and product details according to the life cycle process, and establishing a product list in the target field;

[0137] S202, establish a data analysis system based on the product list and life cycle process in the target field.

[0138] For the convenience of explaining this embodiment, Figure 7 FIG. 1 is a schematic diagram of a system definition structure of an embodiment. Figure 7 As shown, the system definition in step S200 includes resource reserves, mining and production, processing and manufacturing, use, waste management, and accumulation / landfilling, and the system boundary, process definition, and topological structure division are performed based on the system definition.

[0139] In the corresponding establishment of the target field product list in step S201, as Figure 7 As shown, the process of constructing a product list includes product screening, product categories and product details. In one embodiment, the product categories containing strategic key metal minerals are screened out through product lists and product details based on databases such as major mineral statistics (such as the USGS Mineral Information Center database), trade statistics databases (such as the UN Comtrade database, and national customs statistics databases); products are classified according to the life cycle stage to build a systematic and comprehensive list of strategic key metal mineral products.

[0140] In one embodiment, a data analysis system is constructed based on the system definition in step S200 and the target product list in step S201. Figure 7 As shown, the data analysis system includes data analysis and processing, such as data sources and attributes, data quality and data processing.

[0141] In one embodiment, if Figure 7 As shown, the data usage is analyzed from the aspects of reporting organization, time series, consistency, etc., and the quality of each usage data node is comprehensively evaluated to provide a reference for the uncertainty of each parameter in the analysis model; a general data structure is established, and a processing method for large quantities of data is used to uniformly convert, correct, and supplement usage data from different sources to provide consistent data for the data analysis system. According to the law of material balance, the functions and related parameters of the flow of target metals in each life cycle process (local) are analyzed and defined; according to the topological structure of material flow, the mutual correlation between each life cycle process of the entire system (global) is analyzed, and the relationship between each function and parameter is defined; using the theory and method of uncertainty and sensitivity analysis, a local and global sensitivity analysis method system is established; on the basis of the above, starting from the four dimensions of historical retrospection-forward scenario and top-down-top-up, a four-quadrant analysis framework is constructed to establish a data analysis system serving the subsequent step S102.

[0142] In one embodiment, if Figure 6 As shown, the process of performing historical retrospective research based on the data analysis system in step S104 to obtain research output data includes step S203:

[0143] S203, calling regional cases or industry cases and substituting them into the data analysis system to conduct historical retrospective research and obtain research output data.

[0144] Figure 8 This is a schematic diagram of historical retrospective research. Figure 8 As shown in the top-down-top-down four dimensions of the data analysis system, taking strategic key metals as an example:

[0145] From the bottom-up dimension, we take the global countries as regional cases continuously. Based on the principle of material balance, we collect statistical data and literature data of each life cycle stage at the global national scale, supplemented by survey data and experimental data, and use theoretical analysis, spatial analysis, statistical analysis, flow-driven and other research techniques and methods to carry out the flow, flow, flow type and stock analysis of typical strategic key metal minerals at the global national scale under multi-source heterogeneous data, explore the various possible influences of factors such as social and economic development, energy structure transformation, resource conservation and environmental protection on the flow, flow, flow type and stock of strategic key metal minerals, and use dynamic evolution time series analysis models (such as S-curves) and related statistical regression, econometric analysis techniques and methods to reveal the laws of historical changes. Based on this, we explore the nonlinear impact of the time lag effect caused by the continuous use of stocks in the social and economic system on their full life cycle cycle, and reveal the laws and characteristics of this dynamic nonlinear impact. This nonlinearity determines the boundary conditions of the strategic key metal mineral cycle, which is crucial for understanding the long-term supply and demand laws of strategic key metal minerals.

[0146] From the top-down dimension, typical regions and industries are used as regional cases or industry cases. With the help of statistical data, literature research, field sampling, indoor testing, questionnaires, and spatial data collection technology, we systematically collect data on typical industry products and their metal content for typical regions and industries. We will use similar dynamic evolution time series analysis models (such as S-curves) and organically combine them with relevant spatial analysis techniques, statistical analysis and other methods to depict the spatial pattern of typical strategic key metal mineral stocks and flows in typical regions and industries in China, explore the spatiotemporal evolution patterns of different products (electronic products, electric vehicles, etc.) and different technologies (energy storage technology, renewable energy technology, etc.), explore the common laws and spatiotemporal differences in the development of different products or technologies, and obtain the growth paths and related parameters of different products and technologies.

[0147] This is used to output research output data.

[0148] Based on the research output data, traditional data such as spatiotemporal laws, multi-flow coupling, and resource and environmental effects are analyzed and output.

[0149] In one embodiment, if Figure 6As shown, the process of analyzing the spatiotemporal regularity of the operating data in step S105 includes step S204:

[0150] S204, establishing a trade matrix of the target metal according to the operation data, and reflecting the temporal and spatial laws according to the trade matrix.

[0151] Fig. 9 A schematic diagram of running data analysis is shown in Figure 2. Fig. 9 As shown in the figure, the trade network of typical strategic key metal minerals is characterized by the whole life cycle stages using the trade matrix analysis method, and the metal trade transfer and temporal and spatial changes in each stage are quantitatively analyzed; the role and status of each major country in the trade network at each stage are quantitatively evaluated using evaluation systems or indicators such as complex networks, and the temporal and spatial changes of each evaluation indicator are observed; based on the above analysis, the trade characteristics of different countries at different development stages and their impact on the overall metal mineral cycle are compared and analyzed, and their common laws are analyzed.

[0152] In one embodiment, if Figure 6 As shown, the process of analyzing the spatiotemporal regularity of the operating data in step S105 further includes steps S205 and S206:

[0153] S205, analyzing multi-layer effects based on substance amount analysis in operation data;

[0154] S206, perform uncertainty analysis on multi-layer effects.

[0155] Taking strategic key metals as an example, on the basis of understanding the common changing laws of stocks, flows and trade, the constructed country material flow model is expanded into a multi-country, multi-element and multi-system linkage model, and multi-layer effect analysis such as energy, environment and value is carried out based on material quantity analysis. In view of the changes in supply and demand of major metals or changes in alloy technology and their demand fluctuations, the uncertainty and complexity of the primary and recycled supply and composition of strategic key mineral resources are analyzed, and the coupling relationship of multiple metal and multiple "flow" cycles is explored. The coupling relationship of multiple metal and multiple flow cycles is very important for understanding the supply and demand laws of strategic key metal mineral material flows and improving the theories and methods of strategic key metal mineral material flows.

[0156] In one embodiment, if Figure 6 As shown, another embodiment of the metal recycling analysis method further includes step S210:

[0157] S210, calculating the optimization index of the target metal according to the recycling result.

[0158] Fig.10 This is a schematic diagram of the optimization index calculation process, such as Fig.10As shown in the figure, the spatial mapping and analysis method of key elements of recycling of strategic key metal minerals based on multi-source data is based on multi-source data such as multi-period statistics, surveys and remote sensing, and a method combining local spatial autocorrelation and spatial clustering is adopted to organically combine the research results related to the spatiotemporal laws of recycling of typical strategic key metal minerals and multi-stream fusion effects with the developed recycling technology path optimization scheme, so as to provide methodological support for the research on the optimization of the industrial system and regional industrial layout of recycling of strategic key metal minerals.

[0159] Based on the systematic optimization of the industrial layout of typical strategic key metal mineral recycling and drawing up its technology development roadmap, through the multi-objective countermeasures and management model scenario simulation of the multi-source data and multi-scale strategic key metal mineral regeneration potential evaluation model, it provides the optimization strategy of the whole life cycle recycling and regeneration potential management model.

[0160] The metal recycling analysis method of any of the above embodiments is based on the model processing of the metal recycling analysis system, and is systematically defined according to the recycling data and the regeneration potential data, a target field product list is constructed and a data analysis system is established, and a historical retrospective study is conducted based on the data analysis system to obtain the research output data, and the research output number is output as subjective data to the material effect analysis module to instruct the material effect analysis module to simulate the subjective data according to the preset operation model, determine the operation data, analyze the operation data and send the analysis results to the model prediction analysis module to instruct the model prediction analysis module to predict the recycling results of the analysis results according to the preset prediction model. Based on this, a comprehensive evaluation of the regeneration potential and recycling of the key target metal type is conducted to solve the system analysis deficiencies of the target metals such as multiple sources, inconsistent calibers, blank or partial missing data, and provide a comprehensive indicator reference related to recycling.

[0161] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0162] The above embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for those of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A metal recycling analysis system, characterized in that: include: A recycling data analysis module, used to obtain usage data of target metals, simulate the usage data according to a preset theoretical model, and determine recycling data and regeneration potential data; Based on the recycling data and the regeneration potential data, a system is defined, a list of products in the target area is constructed, and a data analysis system is established; Conduct historical retrospective research based on the data analysis system to obtain research output data; A material effect analysis module, used to obtain subjective data of the target metal, simulate the subjective data according to a preset operation model, and determine the operation data; wherein the subjective data is the research output data; Analyze the spatiotemporal laws, multi-flow coupling and resource and environmental effects of the operating data to obtain analysis results; The model prediction and analysis module is used to predict the recycling results of the target metal by substituting the recycling data, regeneration potential data and operation data into a preset prediction model.

2. The metal recycling analysis system according to claim 1, characterized in that: Also includes: The prediction result presentation module is used to visualize the recycling result.

3. The metal recycling analysis system according to claim 1, characterized in that: The cycle data analysis module comprises: A trade association unit, configured to simulate the usage data according to a preset trade association model to determine trade association data; The demand forecasting unit is used to simulate the usage data according to a preset demand forecasting model to determine the demand forecasting data.

4. The metal recycling analysis system according to claim 1, characterized in that: The cycle data analysis module also includes: A data set construction unit, used for constructing multi-stream data by using the usage data; The potential evaluation unit is used to perform corresponding simulation on the multi-stream data according to a preset data circulation model to determine potential evaluation data.

5. The metal recycling analysis system according to claim 1, characterized in that: The material effect analysis module includes: A regeneration and recycling law unit, used to obtain subjective law data of the target metal; A stock determination unit, used to obtain stock data of the target metal; The life cycle trade unit is used to obtain the subjective impact data of the life cycle trade of the target metal on recycling; A multi-stream fusion unit is used to obtain a multi-stream fusion subjective score of the target metal.

6. The metal recycling analysis system according to claim 1, characterized in that: The preset prediction model includes a decision tree model, a regression prediction model or a neural network model.

7. The metal recycling analysis system according to claim 6, characterized in that: The preset prediction model includes a neural network model; Wherein, the model prediction analysis module is configured as follows: Inputting the recycling data and the regeneration potential data into the neural network model as training data to obtain a preset classification label output by the neural network model; According to the difference between the preset classification label and the corresponding operation data, the recycling result of the target metal is predicted.

8. The metal recycling analysis system according to claim 2, characterized in that: The process of visualizing the recycling result in the prediction result presentation module comprises the steps of: Obtaining registration information of expert users and consensus scores of the expert users on the recycling results; Constructing a consensus node network based on the consensus score; Uploading the registration information to the supervision node through the consensus node network; Receive the audit result of the registration information by the supervision node, and mark the audit result accordingly in the consensus node network to form a visualization result.

9. The metal recycling analysis system according to claim 8, characterized in that: The consensus node network is a blockchain network.

10. A metal recycling analysis method, characterized in that: Includes steps: Identify target metals in target areas and obtain usage data of target metals in target areas; Outputting the usage data to a circulation data analysis module to instruct the circulation data analysis module to simulate the usage data according to a preset theoretical model to determine recycling data and regeneration potential data; Based on the recycling data and the regeneration potential data, a system is defined, a list of products in the target area is constructed, and a data analysis system is established; Conduct historical retrospective research based on the data analysis system to obtain research output data; Outputting the research output data as subjective data to a material effect analysis module to instruct the material effect analysis module to simulate the subjective data according to a preset operation model to determine operation data; Analyze the spatiotemporal laws, multi-flow coupling and resource and environmental effects of the operating data to obtain analysis results; The analysis result is sent to the model prediction analysis module to instruct the model prediction analysis module to predict the recycling result of the analysis result according to a preset prediction model.