Waste lead storage battery recycling industry chain digital service platform based on block chain technology

Abstract

The invention relates to the technical field of battery recovery service, in particular to a waste lead storage battery recovery industry chain digital service platform based on a block chain technology, which comprises a recovery point identity verification and access unit, a recovery point identity verification and access unit, a recovery point identity verification and trust management unit and a recovery point identity verification and access unit, identity confirmation and recording are carried out on all units and individuals participating in recycling; the waste lead storage battery tracking module is used for recording the flow direction of each waste lead storage battery by using a block chain, and each link from a recovery point to a treatment factory is recorded on the block chain; the cyclic utilization evaluation and authentication module is used for evaluating the quality and safety of cyclic utilization; the transaction and subsidy management module is used for managing and automatically managing all financial transactions in the waste lead storage battery recycling and processing process; according to the method, geographical economic differences, specific characteristics of recycled materials and changes of market demands are considered, so that the response efficiency and accuracy of the whole system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of battery recycling services, and particularly to a digital service platform for the waste lead-acid battery recycling industrial chain based on blockchain technology. Background Art

[0002] The recycling and treatment of waste lead-acid batteries is an important issue involving environmental protection, resource recycling, and economic benefits. With the increasing global emphasis on environmental protection and sustainable development, the effective recycling and reuse of waste lead-acid batteries have become particularly crucial. Traditional recycling methods face many challenges, such as the opacity of the recycling process, the easy tampering of transaction data, large geographical and economic differences, inconsistent treatment standards for different types of waste batteries, and difficult supervision.

[0003] Traditional waste lead-acid battery recycling systems often lack sufficient transparency, making it difficult to effectively monitor recycling activities. Since records are maintained manually and non-digitally, data loss or tampering is likely to occur, which poses a significant challenge to the supervision of environmental protection and resource recycling.

[0004] Without the full use of digital tools, traditional financial and logistics records are easily modified or forged. This data security issue not only affects the trust between trading parties but also increases the difficulty for regulatory authorities to detect and stop illegal activities.

[0005] There are differences in the economic development levels and environmental protection policies in different regions, which directly affect the cost, efficiency, and feasibility of waste lead-acid battery recycling. For example, some remote areas may have difficulty achieving efficient recycling due to inconvenient transportation and backward technology; different types of waste lead-acid batteries require different treatment and recycling technologies due to their different compositions and usage conditions, and this diversity requires the recycling system to be highly flexible and adaptable to meet the specific needs of various batteries.

[0006] In view of these problems, there is an urgent need for a new technical solution to improve the overall efficiency and transparency of the waste lead-acid battery recycling industry, while ensuring data security and accuracy, optimizing resource allocation, and effectively implementing environmental protection policies. Summary of the Invention

[0007] Based on the above purposes, the present invention provides a digital service platform for the waste lead-acid battery recycling industrial chain based on blockchain technology.

[0008] The digital service platform for the waste lead-acid battery recycling industrial chain based on blockchain technology includes: Recycling point identity verification and access unit: Using blockchain technology to achieve the identity verification and trust management of recycling points, and confirm and record the identities of all participating units and individuals; Waste lead-acid battery tracking module: Uses blockchain to record the flow of each waste lead-acid battery, and every link from the recycling point to the processing factory is recorded on the blockchain; Recycling assessment and certification module: Utilizes blockchain technology to track the recycled lead substances and evaluate the quality and safety of their recycling. By comparing with the industry standard smart contract, it automatically issues recycling certifications; Transaction and subsidy management module: Used to manage and automate all financial transactions in the waste lead-acid battery recycling and processing process, including recycling payments, tax incentives, and environmental protection subsidies. Utilizes the smart contract of blockchain to ensure the transparency and fairness of all financial operations. The transaction and subsidy management module also includes abnormal transaction detection and handling. The smart contract has a built-in abnormal detection algorithm for identifying abnormal or suspicious financial activities. After detecting an abnormal transaction, it automatically sends an alarm to the regulatory department and the relevant person in charge, and suspends the transactions of the involved accounts. The abnormal detection algorithm includes using machine learning methods to analyze transaction behavior patterns and identify behaviors significantly different from the normal patterns.

[0009] Furthermore, the recycling point identity authentication and access unit specifically includes: Identity authentication token generation: Uses asymmetric encryption technology to generate a unique identity authentication token for each unit or individual applying to be a recycling point. The identity authentication token is generated based on the specific information provided by the applicant (such as business license number, geographical location information, operator information, etc.) to ensure the uniqueness and non-replicability of each token; Blockchain identity registration: Synchronously registers the generated identity authentication token with the corresponding recycling point information on a blockchain network. This blockchain network adopts a permissioned chain model, and only allows verified nodes (such as functional agencies, industry associations, etc.) to participate in the maintenance of the chain, enhancing the security and trust of the network; Real-time identity authentication and update mechanism: When a recycling point conducts a transaction or submits data, it must confirm its identity through its identity authentication token. The service platform verifies the legality of the identity by checking whether the token information recorded on the blockchain is consistent with the submitted token. Any information update of the recycling point (such as address change, person in charge change, etc.) must also be authenticated before the relevant information can be updated on the blockchain; Trust score: Automatically generates a trust score based on the activity records of the recycling point on the service platform (such as transaction frequency, compliance records, customer evaluations, etc.). The trust score, as an embodiment of the business ability and credit level of the recycling point on the platform, is stored on the blockchain and publicly disclosed.

[0010] Furthermore, the automatic generation of the trust score is automatically calculated based on the activity records of the recycling point on the platform. The indicators on which the score is based include Transaction Frequency TF: The number of transactions completed at the collection point; Compliance Record CR: The proportion of compliance with environmental protection regulations and industry standards; Customer Evaluation CE: The average rating from users on other platforms; The trust score is calculated as: Trust Score , where , and are weight coefficients, adjusted according to the business importance.

[0011] Furthermore, the waste lead-acid battery tracking module specifically includes: Waste lead-acid battery identification: At each moment of waste lead-acid battery collection, each battery is marked with a unique identification code (UID), implemented through QR codes or RFID tags, ensuring the uniqueness and traceability of each battery; Blockchain data record: When the battery is collected, the relevant unique identification code and its corresponding collection point information, timestamp, and battery status are recorded in a blockchain transaction. When the battery moves from one location to another, the details of each movement are recorded in a new blockchain transaction; Blockchain smart contract application: Implement smart contracts to automatically verify and record each movement and processing of waste lead-acid batteries, automatically execute according to preset rules, and ensure the compliance and efficiency of the process.

[0012] Furthermore, the preset rules specifically include: Compliance time window rule: The waste lead-acid battery must be transferred from the collection point to the designated processing factory within 72 hours after collection. The smart contract monitors the timestamp record of each battery. If the battery is not transferred within the specified time, it automatically notifies the relevant authorities and sends a reminder to the collection point; Transportation condition monitoring rule: The waste lead-acid battery must be maintained under preset temperature and humidity conditions during transportation (for example, the temperature does not exceed 30°C and the humidity does not exceed 60%); by connecting to IoT devices inside the battery distribution vehicle, the transportation conditions are monitored in real time. If the conditions exceed the specified range, the smart contract will automatically record the violation event and notify the relevant responsible parties and authorities; Data integrity rule: Each battery movement must record complete data on the blockchain, including the geographical locations of the starting and ending points, timestamp, and transporter identity. The smart contract verifies when the data is uploaded to ensure that all necessary fields are filled and in the correct format. If incomplete or incorrectly formatted data is detected, the transaction is automatically rejected and a resubmission is required; Final Processing Certification Rule: All waste lead-acid batteries must start the processing within 24 hours after arriving at the processing plant, and upload the processing certificate on the blockchain within 48 hours after the processing is completed. The smart contract records the timestamps of the start and completion of processing at the processing plant. If the processing certificate is not uploaded on time, the smart contract will warn the plant and notify the relevant authorities; Third-Party Audit and Certification Rule: Conduct at least one third-party audit of the processing and recycling of waste lead-acid batteries every quarter. The smart contract automatically tracks the audit cycle and notifies the third-party audit agency and relevant enterprises to prepare for the audit before the deadline approaches. After the audit is completed, the audit results must be uploaded to the blockchain for recording.

[0013] Furthermore, the recycling evaluation and certification module specifically includes: Lead Substance Tracking: During the processing and smelting of waste lead-acid batteries, the lead extracted from the batteries is marked in batches. Each batch of lead uses a unique serial number, and its source, smelting date, and chemical composition information are recorded; Blockchain Recording: Record the information of all lead batches on the blockchain. The information includes batch number, weight, extraction date, chemical purity, name of the processing plant, and relevant environmental protection certification information; Quality and Safety Evaluation: Design a smart contract to automatically perform the quality evaluation of lead. The evaluation is based on preset chemical composition and purity standards, automatically calculate the applicability and safety ratings of lead. According to the evaluation results of the smart contract, if the lead batch meets all the specified quality and safety standards, an electronic safety certification is automatically issued, and the certification information is recorded on the blockchain and permanently associated with the corresponding lead batch.

[0014] Furthermore, the transaction and subsidy management module also includes: Financial Transaction Recording: Record every financial transaction related to the recycling and illegal processing of waste lead-acid batteries, including recycling payments, transportation costs, and processing fees, on the blockchain. Each transaction includes the amount, identity verification information of both parties to the transaction, timestamp, and transaction content. Use the smart contract of the blockchain to automatically verify the legality and compliance of each transaction, ensuring that the qualifications of both parties to the transaction and the transaction conditions meet the preset standards and policies; Tax Incentives and Environmental Protection Subsidy Management: Design a smart contract to automatically identify transactions eligible for tax incentives and environmental protection subsidies, including evaluating the compliance, processing efficiency, and environmental standard compliance of recycling points. When a transaction meets the subsidy conditions set by the relevant authorities, the smart contract automatically executes the subsidy disbursement procedure, directly transferring the subsidy amount to the account of the eligible recycling unit or processing plant. All transaction records regarding tax incentives and subsidies will be detailedly recorded on the blockchain and generate an easy-to-understand report for the relevant authorities to review.

[0015] Furthermore, the anomaly detection algorithm further includes: Define the anomaly types to include: Non-standard payment anomaly, where the payment amount significantly deviates from the industry average or expected value; Frequent small transactions, extremely frequent small payments used to evade audits or legalize illegal proceeds; Subsidy eligibility fraud, where transactions that do not meet the subsidy conditions are wrongly marked as eligible; Abuse of tax incentives, obtaining improper tax incentives through falsely reported recycling volumes or treatment efficiencies; Data preprocessing: Collect all transaction-related data, including amount, time, parties involved, payment method, establish and update transaction standards and averages for the waste lead-acid battery recycling industry for comparison and standardization, and collect all relevant policies, tax incentives, and environmental subsidy standards; Algorithm design and implementation: Use z-score analysis to identify transactions that deviate significantly from the average; Smart contract trigger: When detecting abnormal behavior, the smart contract automatically executes verification steps, such as requesting additional transaction proofs or notifying auditors for manual review.

[0016] Furthermore, the z-score analysis specifically includes: Grouping standard definition: Group by geographical region. Since recycling payment standards vary due to different costs and economic conditions in different regions, transactions are first grouped by geographical region. Group by waste battery type. Waste lead-acid batteries have different recycling values according to their types (such as automotive batteries, industrial batteries). Group by the size of the recycling volume. Large-scale recycling enjoys volume discounts, so transactions are grouped according to the battery weight of each transaction; Grouped data processing: Independently calculate the average transaction amount for each group and the standard deviation , where represents the group. For each transaction , its Z-score is calculated as: ; Calculate the Z-score for each group: For each transaction, according to the group it belongs to , use the average and standard deviation of that group to calculate the Z-score; Identify abnormal transactions: Set a dynamic threshold, which is adjusted according to the risk characteristics and historical data fluctuations of each group. If the of a certain transaction exceeds the threshold of its group, the transaction is marked as abnormal.

[0017] Furthermore, the machine learning method uses an improved gradient boosting machine model, specifically including: Based on all the collected transaction-related data, including amount, time, parties involved, and payment method, construct indicators reflecting transaction characteristics, including time factors, geographical factors, and transaction scale, and use the characteristics as model inputs; Features and grouping: In the gradient boosting machine model, introduce one or more "grouping indicator features" to represent different groups, including geographical location coding, waste battery type identification, and recycling volume size identification, enabling the model to identify and adjust its behavior according to the grouping indicator features, and automatically adjust internal parameters during the training process to adapt to different data characteristics by considering the importance of each grouping indicator feature; Model training: Use the entire dataset for model training. Through the evaluation of feature importance, naturally learn the features that are most crucial for predicting abnormal transactions and adjust the branches of the decision tree accordingly; Model application: Apply the trained model to new transaction data and use the knowledge it has learned to predict whether each transaction is abnormal.

[0018] The gradient boosting machine model minimizes the loss function by iteratively constructing decision trees. Each step attempts to correct the prediction error of the previous step and is calculated as follows: Initialization: , where is the initial model, including the mean value of the data (regression model) or log odds (classification model), is the loss function, is the response variable; For each iteration , calculate the residual (negative gradient): , calculate the negative gradient of the loss function at each data point as the target for the next model to learn; Fit a new model On the residuals: The new model is a decision tree trained on ; Update the model: , where is the learning rate (step size), is the th iteration and the th output value of the terminal node (leaf node), is the leaf node region generated by the th decision tree, is the indicator function; Introduce grouping indicator features in the gradient boosting machine model by adding one or more categorical features to represent different groups.

[0019] Advantages of the present invention: The present invention, by introducing "grouping indication features" into the gradient boosting machine model, such as geographic location coding, waste battery type identification, and recycling quantity size identification, the model can more accurately identify and adapt to the specific behaviors and needs of recycling activities in different regions, different types of waste batteries, and different scales. This subdivision enables the model to take into account geographical and economic differences, specific characteristics of recycled materials, and changes in market demand when predicting and processing data, thereby improving the response efficiency and accuracy of the entire system.

[0020] The present invention uses Z-score analysis to detect anomalies in transaction data, especially combining group analysis of geographical regions, waste battery types and recycling volumes, which effectively improves the monitoring system's ability to identify abnormal transaction behaviors. By grouping these key dimensions, it can more sensitively capture various types of abnormal financial fluctuations, such as regional price manipulation, illegal transactions of specific types of waste batteries, or fraudulent activities in large-scale recycling behaviors, which not only enhances the transparency of financial operations, but also improves the security level of the entire industry.

[0021] The present invention uses an integrated learning model to make the digital service platform of the waste lead-acid battery recycling industry chain more efficient in processing complex data. By analyzing various transaction behavior patterns through machine learning algorithms and automatically adjusting model parameters to adapt to different market and operating conditions, the platform can more accurately match policy support with market demand. For example, it can provide customized tax incentives or environmental subsidies for specific regions or companies with large recycling volumes. Such policy implementation is not only fair but also effective, which helps promote the rational allocation and recycling of resources and further promotes the development of the green recycling industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 A schematic diagram of a platform architecture according to an embodiment of the present invention; Figure 2 Schematic diagram of an anomaly detection algorithm according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0025] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention shall have the ordinary meanings understood by those with ordinary skills in the field to which the present invention pertains. The "first", "second" and similar terms used in the present invention do not denote any order, quantity or importance, but are only used to distinguish different components. Words such as "comprising" or "including" mean that the elements or objects appearing before this word cover the elements or objects listed after this word and their equivalents, without excluding other elements or objects. Words such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Upper", "lower", "left", "right", etc. are only used to indicate relative position relationships, and when the absolute position of the object being described changes, the relative position relationship may also change accordingly.

[0026] As Figure 1 - Figure 2 shown, the digital service platform for the waste lead-acid battery recycling industrial chain based on blockchain technology includes: Recycling point identity verification and access unit: Using blockchain technology to achieve the identity verification and trust management of recycling points, confirm and record the identities of all participating units and individuals, and utilize the public transparency of blockchain to ensure that the access qualifications of all participants are widely recognized by functional institutions and society, solving the environmental risks and data opacity problems brought by informal recycling points in the waste lead-acid battery recycling industry; Waste lead-acid battery tracking module: Using blockchain to record the flow of each waste lead-acid battery, and record every link from the recycling point to the processing factory on the blockchain, solving the problems of unclear flow of waste batteries, illegal disposal and resource waste in the existing industry, and ensuring the legality and efficiency of the recycling process; Recycling and utilization evaluation and certification module: Using blockchain technology to track the recycled lead materials, evaluate the quality and safety of their recycling and utilization, and automatically issue recycling and utilization certifications by comparing with industry standard smart contracts, motivating more factories and enterprises to participate in environmental protection and resource recycling and utilization; Transaction and subsidy management module: Used to manage and automate all financial transactions in the waste lead-acid battery recycling and processing process, including recycling payments, tax incentives and environmental protection subsidies. Using the smart contract of blockchain to ensure the transparency and fairness of all financial operations. The transaction and subsidy management module also includes abnormal transaction detection and processing. The smart contract is built-in with an abnormal detection algorithm for identifying abnormal or suspicious financial activities. After detecting an abnormal transaction, an alarm is automatically sent to the regulatory department and relevant responsible persons, and the transaction of the involved account is suspended. The abnormal detection algorithm includes using machine learning methods to analyze transaction behavior patterns and identify behaviors significantly different from the normal patterns.

[0027] The recycling point authentication and access unit specifically includes: Authentication token generation: Using asymmetric encryption technology, a unique authentication token is generated for each unit or individual applying to be a recycling point. The authentication token is generated based on the specific information provided by the applicant (such as business license number, geographical location information, operator information, etc.) to ensure the uniqueness and non-replicability of each token; The generation of the authentication token is based on asymmetric encryption technology, and the specific steps are as follows: Key generation: A pair of keys (public key and private key) is generated for each unit applying to be a recycling point. The public key will be publicly available on the blockchain, while the private key is securely held by the applicant and is not transmitted or stored in the network.

[0028] Token structure: The token consists of the basic information of the recycling point (such as business license number, geographical location, ID number of the person in charge, etc.) and a timestamp. This information will be encrypted with the public key to generate the encrypted authentication token.

[0029] Token registration: The encrypted token is signed with the applicant's private key and then uploaded to the blockchain network and stored together with the applicant's public key for subsequent verification and transaction confirmation.

[0030] Blockchain identity registration: The generated authentication token is synchronously registered with the corresponding recycling point information on a blockchain network. This blockchain network adopts a permissioned blockchain model, which only allows verified nodes (such as functional institutions, industry associations, etc.) to participate in the maintenance of the chain, enhancing the security and trust of the network; The main features of the permissioned blockchain model are as follows: Restriction of network participants: Different from public blockchains, participants in permissioned blockchains must be authorized. In this platform, participants include environmental protection departments, industry associations, and other core business-related stakeholders.

[0031] Consensus mechanism: The Proof of Stake (PoS) consensus mechanism is adopted, aiming to improve the speed and efficiency of transaction processing and ensure the consistency and security of data in the network.

[0032] Data access control: The permissioned blockchain provides a more complex access control mechanism, allowing for fine-grained access permission settings for different types of data and information to ensure data security.

[0033] Real-time authentication and update mechanism: When a recycling point conducts a transaction or submits data, it must be authenticated through its authentication token. The service platform verifies the legitimacy of the identity by checking whether the token information recorded on the blockchain is consistent with the submitted token. Any information update of the recycling point (such as address change, change of person in charge, etc.) must also be authenticated before the relevant information can be updated on the blockchain; Trust Score: Based on the activity records of collection points on the service platform (such as transaction frequency, compliance records, customer evaluations, etc.), a trust score is automatically generated. The trust score, as an indication of the business capabilities and credit levels of collection points on the platform, is stored on the blockchain and publicly available for all participants to query.

[0034] The changes in the trust score are automatically updated according to smart contracts. Every change in the score needs to be confirmed through the consensus mechanism of the blockchain network to ensure the fairness and transparency of the score.

[0035] In key business processes, including major transactions or access to sensitive information, multi-factor authentication will be required, including biometrics (such as fingerprint or facial recognition), geographical location verification, etc., to enhance the security of identity verification. Using the distributed ledger technology of the blockchain, multiple verification nodes (different authentication institutions) can participate in the identity verification process to achieve cross-verification and confirmation of identity information.

[0036] The automatic generation of the trust score is calculated based on the activity records of collection points on the platform. The indicators for the score include Transaction Frequency TF: The number of transactions completed by the collection point; Compliance Record CR: The proportion of compliance with environmental protection regulations and industry standards; Customer Evaluation CE: The average score from other platform users; The trust score is calculated as: Trust Score , where , and are weight coefficients, adjusted according to business importance. For example, if compliance is crucial in the recycling industry, can be set higher.

[0037] TF (Transaction Frequency): Measures the business activity level of the collection point.

[0038] CR (Compliance Record): Reflects the performance of the collection point in terms of environmental protection and safety.

[0039] CE (Customer Evaluation): Indicates the market's recognition of the collection point.

[0040] The waste lead-acid battery tracking module specifically includes: Waste Lead-Acid Battery Identification: At the moment of collecting each waste lead-acid battery, each battery is marked with a unique identification code (UID), achieved through QR codes or RFID tags, to ensure the uniqueness and traceability of each battery; Blockchain Data Recording: When the battery is collected, the relevant unique identification code, its corresponding recycling point information, timestamp, and battery status are recorded in a blockchain transaction. When the battery moves from one location to another, such as from the recycling point to the processing plant, the details of each movement (including the geographical locations of the starting and ending points, timestamp, transportation conditions, etc.) are recorded in a new blockchain transaction. These transactions are encrypted and uploaded to the blockchain to ensure the security, transparency, and immutability of the data; Application of Blockchain Smart Contracts: Implement smart contracts to automatically verify and record each movement and processing of waste lead-acid batteries. It is automatically executed according to preset rules (such as the battery must be moved from the recycling point to the processing plant within a specific time), ensuring the compliance and efficiency of the process. The smart contract can also automatically trigger alarms and notifications. For example, when the tracking data shows that the battery is not transported according to the specified time or conditions, it sends alarms to relevant functional agencies and participants.

[0041] The preset rules specifically include: Compliance Time Window Rule: Waste lead-acid batteries must be transferred from the recycling point to the designated processing plant within 72 hours after collection. The smart contract monitors the timestamp record of each battery. If the battery is not transferred within the specified time, it automatically notifies the functional agency and sends a reminder to the recycling point; Transportation Condition Monitoring Rule: Waste lead-acid batteries must be maintained under preset temperature and humidity conditions during transportation (for example, the temperature does not exceed 30°C and the humidity does not exceed 60%); by connecting to IoT devices in the battery distribution vehicle, the transportation conditions are monitored in real time. If the conditions exceed the specified range, the smart contract will automatically record the violation event and notify the relevant responsible parties and functional agencies; Data Integrity Rule: Each battery movement must record complete data on the blockchain, including the geographical locations of the starting and ending points, timestamp, and transporter identity. The smart contract verifies during data upload to ensure that all necessary fields are filled and in the correct format. If incomplete or incorrectly formatted data is detected, the transaction is automatically rejected and a resubmission is required; Final Processing Proof Rule: All waste lead-acid batteries must start the processing process within 24 hours after arriving at the processing plant and upload the processing proof on the blockchain within 48 hours after the processing is completed. The smart contract records the timestamps of the start and completion of processing at the processing plant. If the processing proof is not uploaded on time, the smart contract will warn the plant and notify the functional agency; Third-Party Audit and Certification Rule: Conduct at least one third-party audit of the processing and recycling of waste lead-acid batteries every quarter. The smart contract automatically tracks the audit cycle and notifies the third-party audit agency and relevant enterprises to prepare for the audit before the approaching deadline. After the audit is completed, the audit results must be uploaded to the blockchain for recording.

[0042] The recycling assessment and certification modules include: Lead material tracking: During the treatment and smelting of waste lead-acid batteries, the lead extracted from the batteries is marked in batches. Each batch of lead uses a unique serial number and records its source, smelting date, and chemical composition information; Blockchain records: All lead batches are recorded on the blockchain, including batch number, weight, extraction date, chemical purity, treatment plant name and relevant environmental certification information; Quality and safety assessment: Design smart contracts to automatically perform quality assessments of lead. The assessments are based on preset chemical composition and purity standards, and automatically calculate the suitability and safety ratings of lead. Based on the assessment results of the smart contract, if the lead batch meets all specified quality and safety standards, an electronic safety certification is automatically issued. The certification information is recorded on the blockchain and is permanently associated with the corresponding lead batch.

[0043] The transformation process of all lead batches from extraction to final product is recorded on the blockchain, including the details of each step of processing, transportation and use in the middle. This allows the complete history of each batch of lead to be traced at any point in time. Authorized third parties, such as environmental protection agencies and consumers, can access the detailed information and safety certification status of lead batches through the blockchain, enhancing the credibility and transparency of the entire system.

[0044] Smart contracts regularly check and update lead safety data, including responses to new environmental regulations and industry standards, which ensures that the system's information is always the latest and most accurate.

[0045] The scheme for automatically calculating the suitability and safety rating of lead is as follows: In order to ensure that the recycling of lead materials meets environmental protection and safety standards and improve the accuracy and efficiency of the assessment, an automated assessment system based on blockchain technology is designed to calculate the suitability and safety rating of lead by combining multiple factors. The following is a detailed calculation scheme: 1. Establish an evaluation indicator system: First, define the key evaluation indicators of lead quality, including: Purity: The chemical purity of lead, expressed as a percentage.

[0046] Impurities: The types and contents of key impurities, such as arsenic, cadmium, antimony, etc.

[0047] Physical State: The physical form of lead, such as lump, powder, etc.

[0048] Environmental Compatibility: The environmental performance of lead materials, such as whether they are easy to handle or utilize in an environmentally friendly manner.

[0049] 2. Set standards and thresholds Define the passing thresholds and excellent standards for each indicator, for example: Chemical purity: Passing > 98%, excellent > 99.5% Impurity content: The maximum allowable limit for each key impurity, such as arsenic < 0.01%, cadmium < 0.01%.

[0050] Environmental compatibility: Rated according to the lead recovery and reuse ability, divided into low, medium, and high levels.

[0051] 3. Calculation formula: Design a weighted formula to synthesize these indicators and calculate the final rating of lead. The formula is expressed as: Lead quality rating Purity Impurities Physical State Environmental Compatibility)); where are the weights of each factor, which are determined according to the actual situation and industry standards, and the function is the evaluation function for each factor, which can be linear or non-linear, depending on the impact degree of each factor on the total rating.

[0052] 4. Automation and smart contracts: Smart contract coding includes receiving the test data of each batch of lead, automatically calculating the rating according to the preset calculation formula, and recording the results on the blockchain. If the lead quality does not meet the minimum standard, the smart contract will automatically trigger an alarm and notify the relevant parties for handling. The smart contract is also responsible for verifying the integrity and accuracy of the input data to ensure the reliability of the rating results. All rating results are transparently recorded on the blockchain, facilitating auditing and traceability.

[0053] The transaction and subsidy management module also includes: Financial transaction records: Every financial transaction related to the recycling and treatment of waste lead-acid batteries, including recycling payments, transportation costs, and treatment costs, is recorded on the blockchain. Each transaction includes the amount, identity verification information of both parties, timestamp, and transaction content. The smart contract of the blockchain is used to automatically verify the legality and compliance of each transaction to ensure that the qualifications of both parties and the transaction conditions meet the preset standards and policies; Tax Incentives and Environmental Protection Subsidy Management: Design smart contracts to automatically identify transactions eligible for tax incentives and environmental protection subsidies, including assessing the compliance, processing efficiency, and environmental standards compliance of recycling points. When a transaction meets the subsidy conditions set by the functional agency, the smart contract automatically executes the subsidy disbursement process, directly transferring the subsidy amount to the account of the eligible recycling unit or processing plant. All transaction records related to tax incentives and subsidies will be detailedly recorded on the blockchain and generate an easy-to-understand report for the functional agency to review.

[0054] The anomaly detection algorithm also includes: Define the types of anomalies including: Non-standard payment anomalies, where the payment amount significantly deviates from the industry average or expected value; Frequent small transactions, extremely frequent small payments used to evade audits or legitimize illegal income; Subsidy eligibility fraud, where transactions that do not meet the subsidy conditions are wrongly marked as eligible; Abuse of tax incentives, obtaining improper tax incentives through false reporting of recycling volume or processing efficiency; Data preprocessing: Collect all transaction-related data, including amount, time, parties involved, payment method, establish and update transaction standards and averages for the waste lead-acid battery recycling industry for comparison and standardization, and collect all relevant policies, tax incentive, and environmental protection subsidy standards; Algorithm design and implementation: Use z-score analysis to identify transactions that deviate significantly from the average; Smart contract trigger: When abnormal behavior is detected, the smart contract automatically executes verification steps, such as requesting additional transaction proofs or notifying auditors for manual review.

[0055] The z-score analysis specifically includes: Grouping standard definition: Group by geographical region. Since recycling payment standards vary due to different costs and economic conditions in different regions, transactions are first grouped by geographical region. Group by waste battery type. Waste lead-acid batteries have different recycling values according to their types (such as automotive batteries, industrial batteries). Group by the size of the recycling volume. Large-scale recycling enjoys volume discounts, so transactions are grouped according to the battery weight of each transaction; Grouped data processing: Independently calculate the average transaction amount for each group and the standard deviation , where represents the group. For each transaction , its Z-score is calculated as: ; Calculate the z-score for each group: For each transaction, according to the group it belongs to , the mean and standard deviation of the group are used to calculate the Z - score; Identifying abnormal transactions: Set dynamic thresholds, which are adjusted according to the risk characteristics and historical data fluctuations of each group. For example, for groups with large fluctuations in normal transactions, a higher threshold can be set (such as ), while for groups that are usually more stable, a lower threshold is set (such as ). If the of a certain transaction exceeds the threshold of its group, the transaction is marked as abnormal.

[0056] The machine - learning method adopts an improved gradient - boosting machine model, specifically including: Based on all the transaction - related data collected, including amount, time, parties involved, payment method, construct indicators reflecting transaction characteristics, including time factors, geographical factors, and transaction scale, and use the characteristics as model inputs; Features and grouping: In the gradient - boosting machine model, introduce one or more "group - indicating features" to represent different groups, including geographical location coding, waste - battery type identification, recycling - volume size identification, enabling the model to identify and adjust its behavior according to the group - indicating features. During the training process, consider the importance of each group - indicating feature and automatically adjust internal parameters to adapt to different data characteristics; Model training: Use the entire dataset for model training. Through the evaluation of feature importance, naturally learn the features that are most critical for predicting abnormal transactions and accordingly adjust the branches of the decision tree; Model application: Apply the trained model to new transaction data and use the knowledge it has learned to predict whether each transaction is abnormal.

[0057] Although the model is trained uniformly, different response thresholds can be set for different groups. For example, for groups with frequent abnormal transactions in history, set a more stringent (lower) threshold, and regularly evaluate the performance of the model on different groups to confirm whether the model effectively identifies abnormal transactions in all important groups.

[0058] The gradient - boosting machine model iteratively constructs decision trees to minimize the loss function. At each step, it tries to correct the prediction error of the previous step, and the calculation is as follows: Initialization: , where is the initial model, including the mean of the data (regression model) or log - odds (classification model), is the loss function, is the response variable; For each iteration , calculate the residual (negative gradient): , calculate the negative gradient of the loss function at each data point as the target for the next model to learn; Fit a new model On the residuals: The new model is a decision tree trained on ; Update the model: , where is the learning rate (step size), is the -th iteration and the output value of the -th terminal node (leaf node), is the leaf node region generated by the -th decision tree, is the indicator function; Introduce grouped indicator features in the gradient boosting machine model. By adding one or more categorical features to represent different groups. For example, a feature named "geographical area code" can be added, which has discrete values such as {1, 2, 3, ...}, and each value represents a different geographical area. Similarly, another feature can be introduced for the types of waste lead batteries and the size of the recycling volume.

[0059] Feature importance and parameter tuning. During the training of the gradient boosting machine model: Feature importance: GBM evaluates the importance of a feature by calculating the amount of error reduction of each feature when constructing a decision tree. The more a feature can help the model reduce error, the greater its importance.

[0060] Automatic parameter tuning: The importance of features is used to guide the adjustment of model parameters. For example, if a certain grouped indicator feature is very important, it may be necessary to adjust the maximum depth of the decision tree or the minimum number of samples in a leaf node to better capture the characteristics of this group.

[0061] Use methods such as Grid Search or Random Search to optimize the hyperparameters of the model to obtain the best prediction performance.

[0062] Those of ordinary skill in the art should understand that the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the present invention is limited to these examples; under the concept of the present invention, the technical features between the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations in different aspects of the present invention as described above, which are not provided in detail for the sake of brevity.

[0063] The present invention aims to cover all such substitutions, modifications and variations that fall within the broad scope of the claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A digital service platform for the waste lead-acid battery recycling industry chain based on blockchain technology, characterized by: include: Recycling point identity verification and access unit: Use blockchain technology to achieve identity verification and trust management at recycling points, and confirm and record the identities of all units and individuals involved in recycling; Waste lead-acid battery tracking module: Use blockchain to record the flow of each waste lead-acid battery, and every link from the recycling point to the processing plant is recorded on the blockchain; Recycling assessment and certification module: Use blockchain technology to track recycled lead materials and evaluate the quality and safety of their recycling. Automatically issue recycling certification by comparing with industry standard smart contracts; Transaction and subsidy management module: used to manage and automate all financial transactions in the recycling and treatment of waste lead-acid batteries, including recycling payments, tax incentives and environmental subsidies. It uses blockchain's smart contracts to ensure the transparency and fairness of all financial operations. The transaction and subsidy management module also includes abnormal transaction detection and processing. The smart contract has a built-in anomaly detection algorithm to identify abnormal or suspicious financial activities. After detecting an abnormal transaction, it automatically sends an alert to the regulatory department and relevant persons in charge, and suspends transactions of the accounts involved. The anomaly detection algorithm includes the use of machine learning methods to analyze transaction behavior patterns and identify behaviors that are significantly different from normal patterns.

2. According to claim 1, the digital service platform for the waste lead-acid battery recycling industry chain based on blockchain technology is characterized in that: The recycling point identity verification and access unit specifically includes: Authentication token generation: Using asymmetric encryption technology, a unique authentication token is generated for each unit or individual that applies to become a recycling point. The authentication token is generated based on the specific information provided by the applicant to ensure the uniqueness and non-replicability of each token; Blockchain identity registration: The generated authentication token and the corresponding recycling point information are synchronously registered on a blockchain network. The blockchain network adopts a permissioned chain model, which only allows verified nodes to participate in the maintenance of the chain, enhancing the security and trust of the network; Real-time identity authentication and update mechanism: When conducting transactions or submitting data at a recycling point, identity confirmation must be carried out through its identity authentication token. The service platform verifies the legitimacy of the identity by checking whether the token information recorded on the blockchain is consistent with the submitted token. Any information update at the recycling point must also be authenticated before the relevant information can be updated on the blockchain. Trust score: A trust score is automatically generated based on the activity records of the recycling point on the service platform. The trust score is stored on the blockchain and made public as a reflection of the recycling point's business capabilities and credit rating on the platform.

3. The digital service platform for the waste lead-acid battery recycling industry chain based on blockchain technology according to claim 2 is characterized in that: The automatically generated trust score is calculated based on the activity records of the recycling point on the platform. The scoring is based on the following indicators: Transaction frequency TF: the number of transactions completed at the collection point; Compliance Record CR: The percentage of compliance with environmental regulations and industry standards; Customer evaluation CE: average rating from users on other platforms; The trust score is calculated as: Trust Score ,in ,and is the weight coefficient, which is adjusted according to the importance of the business.

4. According to claim 1, the digital service platform for the waste lead-acid battery recycling industry chain based on blockchain technology is characterized in that: The waste lead-acid battery tracking module specifically includes: Waste lead-acid battery identification: At each waste lead-acid battery collection moment, each battery is marked with a unique identification code, which is achieved through a QR code or RFID tag to ensure the uniqueness and traceability of each battery; Blockchain data recording: When a battery is collected, the associated unique identification code and its corresponding recycling point information, timestamp, and battery status are recorded in a blockchain transaction. When a battery is moved from one location to another, the details of each move are recorded in a new blockchain transaction. Blockchain smart contract application: Implement smart contracts to automatically verify and record each movement and processing of waste lead-acid batteries, and automatically execute according to preset rules to ensure the compliance and efficiency of the process.

5. According to claim 4, the digital service platform for the waste lead-acid battery recycling industry chain based on blockchain technology is characterized in that: The preset rules specifically include: Compliance time window rule: Waste lead-acid batteries must be transferred from the recycling point to the designated treatment plant within 72 hours after collection; Transportation condition monitoring rules: Scrap lead-acid batteries are kept at preset temperature and humidity conditions during transportation; Data integrity rules: Each battery movement must record complete data on the blockchain, including the geographic location of the starting and ending points, timestamps, and the identity of the transporter; Final treatment proof rules: All waste lead-acid batteries must start the treatment process within 24 hours after arriving at the treatment plant, and upload the treatment proof on the blockchain within 48 hours after the treatment is completed; Third-party audit and certification rules: Conduct a third-party audit of waste lead-acid battery processing and recycling at least once a quarter.

6. The digital service platform for the waste lead-acid battery recycling industry chain based on blockchain technology according to claim 1 is characterized in that: The recycling assessment and certification module specifically includes: Lead material tracking: During the treatment and smelting of waste lead-acid batteries, the lead extracted from the batteries is marked in batches. Each batch of lead uses a unique serial number and records its source, smelting date, and chemical composition information; Blockchain records: All lead batches are recorded on the blockchain, including batch number, weight, extraction date, chemical purity, treatment plant name and relevant environmental certification information; Quality and safety assessment: Design smart contracts to automatically perform quality assessments of lead. The assessments are based on preset chemical composition and purity standards, and automatically calculate the suitability and safety ratings of lead. Based on the assessment results of the smart contract, if the lead batch meets all specified quality and safety standards, an electronic safety certification is automatically issued. The certification information is recorded on the blockchain and is permanently associated with the corresponding lead batch.

7. The digital service platform for the waste lead-acid battery recycling industry chain based on blockchain technology according to claim 1 is characterized in that: The transaction and subsidy management module also includes: Financial transaction records: Every financial transaction related to the recycling and treatment of waste lead-acid batteries, including recycling payments, transportation costs and processing costs, is recorded on the blockchain. Each transaction includes the amount, identity verification information of both parties to the transaction, timestamp and transaction content. The blockchain's smart contracts are used to automatically verify the legality and compliance of each transaction to ensure that the qualifications and transaction conditions of both parties meet the preset standards and policies; Tax incentives and environmental subsidies management: Design smart contracts to automatically identify transactions that qualify for tax incentives and environmental subsidies, including evaluating the compliance of recycling points, processing efficiency, and compliance with environmental standards. When a transaction meets the subsidy conditions set by the functional agency, the smart contract automatically executes the subsidy payment procedure and transfers the subsidy directly to the account of the eligible recycling unit or treatment plant. All transaction records of tax incentives and subsidies will be recorded in detail on the blockchain, and easy-to-understand reports will be generated for review by the functional agencies.

8. The digital service platform for the waste lead-acid battery recycling industry chain based on blockchain technology according to claim 1 is characterized in that: The anomaly detection algorithm also includes: The defined exception types include: Non-standard payment anomalies, where the payment amount deviates significantly from the industry average or expected value; Frequent small transactions, unusually frequent small payments, used to evade audits or legalize illegal gains; subsidy eligibility fraud, where transactions that are not eligible for subsidies are mistakenly marked as eligible; Tax benefit abuse, obtaining undue tax benefits through false reporting of recycling volumes or processing efficiencies; Data preprocessing: Collect all transaction-related data, including amount, time, participants, and payment methods; establish and update transaction standards and averages for the waste lead-acid battery recycling industry for comparison and standardization; and collect all relevant policies, tax incentives, and environmental protection subsidy standards; Algorithm design and implementation: Use z-score analysis to identify trades that deviate significantly from the mean; Smart contract triggering: When abnormal behavior is detected, the smart contract automatically performs the verification steps.

9. The digital service platform for the waste lead-acid battery recycling industry chain based on blockchain technology according to claim 8 is characterized in that: The z-score analysis specifically includes: Definition of grouping criteria: grouping by geographical area, grouping by waste battery type, and grouping by recycling volume; Group data processing: Calculate the average transaction amount for each group independently and standard deviation ,in Indicates grouping, for each transaction , whose Z score is calculated as: ； Calculate the z-score for each group: For each transaction, calculate the z-score for each group , use the mean and standard deviation of the group to calculate the Z score; Identify abnormal transactions: Set dynamic thresholds. The thresholds are adjusted according to the risk characteristics of each group and historical data fluctuations. Exceeding the threshold of its group, the transaction is marked as abnormal.

10. The digital service platform for the waste lead-acid battery recycling industry chain based on blockchain technology according to claim 9 is characterized in that: The machine learning method adopts a gradient boosting machine model, specifically including: Based on all the transaction-related data collected, including amount, time, parties involved, and payment method, construct indicators that reflect transaction characteristics, including time factors, geographical factors, and transaction size, and use the characteristics as model input; Features and grouping: In the gradient boosting model, one or more "grouping indicator features" are introduced to represent different groups, including geographic location codes, waste battery type identifiers, and recycling quantity identifiers, so that the model can recognize and adjust its behavior according to the grouping indicator features. During the training process, the importance of each grouping indicator feature is taken into account, and the internal parameters are automatically adjusted to adapt to different data characteristics; Model training: Use the entire data set for model training. By evaluating the importance of features, we naturally learn the most critical features for predicting abnormal transactions and adjust the branches of the decision tree accordingly. Model application: Apply the trained model to new transaction data and use the knowledge it has learned to predict whether each transaction is abnormal; The gradient boosting model minimizes the loss function by iteratively building a decision tree, each step trying to correct the prediction error of the previous step.

Images