Automobile supply chain tracing method based on block chain

Abstract

The invention discloses an automobile supply chain tracing method based on a block chain, and the method comprises the steps: collecting production data of automobile parts, classifying the production data, and storing the production data in a database; generating a unique traceability code for each automobile part; grading the production data of the automobile parts according to the importance and the sensitivity of the data, wherein the production data comprises proprietary data and basic data; respectively processing the proprietary data and the basic data, associating the data with a unique traceability code, and uploading the data to a block chain through an intelligent contract; if the automobile part is damaged, abnormal or updated, uploading and recording the state and time through the smart contract; the production data, the service life, the maintenance information and the inventory information are displayed in real time through the augmented reality technology. According to the invention, through the non-tampering property of the block chain technology, in combination with the data visual display of the augmented reality technology and the intelligent analysis of machine learning, the intelligent level of the tracing management, fault detection and after-sales service of the automobile parts is comprehensively improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an automobile supply chain tracing method based on blockchain. Background Art

[0002] Nowadays, the production, transportation and sales of auto parts require multiple links, which makes the parts face a high risk of damage during transportation and delivery. The current auto parts sales model is usually: the parts manufacturer sells the parts in bulk to the agent, and the agent distributes the parts to the final consumer. In this process, the parts manufacturer usually purchases freight insurance for its products to deal with accidental damage that may occur during transportation. When an accident occurs, the insurance company will manually determine whether the auto parts are damaged based on the image to decide whether to make a claim.

[0003] In the current operating process, when a damage accident occurs, manual judgment of the extent of damage to auto parts is required. Manual evaluation is not only time-consuming and labor-intensive, but also easily affected by human factors, resulting in misjudgment or inefficiency. In the production, transportation, sales and use of accessories, the flow of information is not transparent, making it difficult for consumers and other participants to fully understand the production process and status changes of auto parts. In the existing after-sales service process, when consumers find problems with accessories during use, they cannot obtain the production and maintenance records of the accessories in real time, and the after-sales response speed is slow, making it difficult to troubleshoot and handle the faults in a timely manner. The current system cannot predict and warn future faults through data analysis, lacks targeted data support, and easily leads to sudden failures of accessories during use, causing inconvenience and risks to users. Summary of the invention

[0004] In view of this, the purpose of an embodiment of the present invention is to provide a blockchain-based automobile supply chain traceability method, which can comprehensively improve the intelligent level of automobile parts traceability management, fault detection and after-sales service through the immutability of blockchain technology, combined with data visualization display of augmented reality technology and intelligent analysis of machine learning.

[0005] The embodiment of the present invention is achieved as follows:

[0006] A blockchain-based automotive supply chain traceability method, applied to suppliers, includes:

[0007] Collect production data of auto parts, classify and store them in the database.

[0008] A unique traceability code is generated for each of the automotive parts.

[0009] The production data of the automotive parts are graded according to the importance and sensitivity of the data, including proprietary data and basic data.

[0010] The proprietary data and the basic data are processed separately, associated with a unique traceability code, and uploaded to the blockchain through a smart contract.

[0011] If a car part is damaged, abnormal, or updated, the status and time will be uploaded and recorded through a smart contract.

[0012] Through augmented reality technology, production data, service life, maintenance information and inventory information are displayed in real time.

[0013] In a preferred embodiment of the present invention, in the above-mentioned blockchain-based automobile supply chain traceability method, the processing of the proprietary data and the basic data respectively, associating them with a unique traceability code, and uploading them to the blockchain through a smart contract includes:

[0014] Use D proprietary Represents proprietary data, wherein the proprietary data includes at least one of material formula, process parameters, and supplier's internal process.

[0015] Use D basic Represents basic data, wherein the basic data includes at least one of production date, batch number, and quality inspection data.

[0016] Hash the proprietary data to generate a proprietary data hash value Among them, d i is the i-th production parameter in the proprietary data, w i is the weighting coefficient of different production parameters, and H(·) is the hash function.

[0017] The unique traceability code is associated with the proprietary data hash value and uploaded to the blockchain through a smart contract.

[0018] The unique traceability code is associated with the basic data and uploaded to the blockchain through a smart contract.

[0019] The technical effect is that by hashing proprietary data, only authorized parties in the supply chain can verify the consistency of the data. By associating the hash values ​​of basic data and proprietary data with unique traceability codes and uploading them to the blockchain through smart contracts, the data is guaranteed to be tamper-proof and traceable. By introducing weighted coefficients into proprietary data, key parameters are given higher protection weights during the encryption process.

[0020] In a preferred embodiment of the present invention, in the above-mentioned automobile supply chain tracing method based on blockchain, the real-time display of production data, service life, maintenance information and inventory information by augmented reality technology includes:

[0021] The image of the auto part is captured by a camera, and the corresponding unique traceability code is identified.

[0022] The smart contract is called to retrieve the production data, service life, maintenance information and inventory information related to the unique traceability code from the blockchain.

[0023] The data retrieved from the blockchain is presented in a visual form based on the user's perspective and operation.

[0024] The basic model of dynamic visual effects of visualization is defined as V(t,D)=A(D)·F(t), where V(t,D) is the visual effect displayed at time t, A(D) is the visual expression function of the data type, and F(t) is the dynamic special effects function of time change.

[0025] Its technical effect is: by capturing the image of the auto parts through the camera and identifying the unique traceability code, the user can obtain the relevant information of the parts without complicated operation steps. The information of the parts is directly superimposed in the user's field of vision through AR technology, which simplifies the information query process and greatly optimizes the user experience. Different types of data are distinguished by different colors, shapes or icons, and combined with dynamic special effects display, so that users can more easily understand and distinguish various types of information when viewing, effectively avoiding the redundancy of information display, and improving the pertinence and efficiency of information use.

[0026] In a preferred embodiment of the present invention, in the above-mentioned blockchain-based automobile supply chain traceability method, the visual representation function of the data type includes:

[0027] For production data D production , design the visual effect of dynamic growth of the bar chart, the performance function is Among them, P is the current production progress and Q is the total production target.

[0028] For service life D lifetime , design the visual effect of the progress bar, and use color changes to reflect the remaining life. The performance function is A(D lifetime )=Progress_Bar(R)·C(R), wherein R is the remaining service life, and the function C(R) represents adjusting the color according to the proportion of the remaining service life.

[0029] For maintenance information D maintenance , the design uses timeline animation to display maintenance information, and the performance function is A(D maintenance )=Timeline_Animation(R t ), where R t The time and information of the most recent maintenance.

[0030] For inventory information Dinventory , the design uses pie charts to display various inventory statuses and dynamically updates them. The performance function is A(D inventory )=Pie_Chart(Stock_Distribution).

[0031] Its technical effect is: by designing different dynamic visualization functions for production data, service life, maintenance information and inventory information, the intuitiveness and understanding of data display are enhanced, the timeline and relevance of information display are improved, real-time dynamic feedback of data status is achieved, and the user experience of information display is improved. At the same time, it provides efficient and accurate support for decision-making in supply chain management, allowing suppliers to better grasp the production and inventory status and make timely adjustments and optimizations.

[0032] In a preferred embodiment of the present invention, in the above-mentioned blockchain-based automobile supply chain tracing method, the time-varying dynamic special effect function is Among them, T is the special effect period, and E is the special effect amplitude used to control the intensity of the dynamic effect.

[0033] Its technical effect is: the introduction of dynamic special effects functions of time changes makes the displayed data more vivid and eye-catching by periodically presenting visual changes within time T, allowing users to intuitively perceive data changes and status updates on the information display interface, helping users to quickly capture key information and make timely adjustments or decisions, enhancing the hierarchy and dynamics of data display, making the data change process more natural and smooth, and making the system interface more attractive by presenting different visual effects at different time points.

[0034] A blockchain-based automobile supply chain traceability method, applied to an e-commerce platform, includes:

[0035] Access the blockchain through smart contracts to obtain production data of auto parts.

[0036] Data access rights are controlled through smart contracts, basic data is displayed to consumers, and proprietary data is used internally by authorized supply chain partners and e-commerce platforms.

[0037] When auto parts are traded, the authenticity of the auto parts is verified through smart contracts.

[0038] After the transaction is completed, the transaction information will be uploaded to the chain through smart contract transfer and traceability.

[0039] If the status of the auto parts is damaged or abnormal, the damage record will be uploaded to the blockchain through the smart contract, and the after-sales service process will be triggered.

[0040] Through augmented reality technology, the production data, service life, maintenance information and inventory information of auto parts can be displayed in real time.

[0041] The performance of accessories is analyzed through machine learning algorithms for monitoring and fault warning.

[0042] In a preferred embodiment of the present invention, in the above-mentioned blockchain-based automobile supply chain traceability method, the analysis of the performance of the accessories by machine learning algorithms, monitoring and fault warning includes:

[0043] The production data of the automobile parts is standardized to obtain a standardized input data set x t .

[0044] For performance monitoring and fault prediction, a deep learning model based on long short-term memory network is established, including input layer, LSTM layer, fully connected layer and output layer.

[0045] The input layer receives the normalized input dataset x t .

[0046] For each time t, the state update formula of the LSTM layer includes the input gate i t =σ(W i x t +U i h t-1 +b i ), forget gate f t =σ(W f x t +U f h t-1 +b f ), output gate o t =σ(W o x t +U o h t-1 +b o ), cell status Hidden State Among them, σ is the activation function, W and U are weight matrices, and b is the bias term;

[0047] The calculation formula of the fully connected layer is S=w s ·h T +b s , where w s is the weight vector, b s is the bias term.

[0048] The output layer outputs the performance score S and the failure probability P. The calculation formula of the failure probability P is: Among them, w p is the weight used for fault prediction, bp is the bias term.

[0049] When the failure probability P exceeds the failure threshold θ, a failure warning is triggered.

[0050] Adopting the time-based performance decay function S t =S 0 exp(-αg), predicting the performance degradation of the component over time, where S 0 is the initial performance score, α is the attenuation coefficient, and g is the usage time of the accessory.

[0051] Upload fault information and performance data to the blockchain through smart contracts.

[0052] Its technical effects are: using a deep learning model based on long short-term memory network to effectively capture the time series characteristics of accessory performance data. The design of LSTM input gate, forget gate, output gate, cell state and hidden state can retain past state information, while flexibly adjusting the newly input data, so as to accurately predict the changes in accessory performance and potential failures. Through the automated early warning mechanism, in the event of accessory failure or performance degradation, the fault information is uploaded to the blockchain through smart contracts, and the after-sales service process is automatically triggered, reducing the steps of manual intervention and ensuring the transparency and non-tamperability of fault information. Through the design of a time-based performance decay function, the performance degradation trend of automotive accessories over time can be accurately predicted to help optimize the maintenance and replacement time points of accessories.

[0053] A blockchain-based automotive supply chain traceability method, applied to consumers, includes:

[0054] Enter the traceability code and query the basic data of auto parts with access rights through the blockchain.

[0055] When using an auto part, if a fault occurs, the fault state of the auto part is detected.

[0056] Perform differential analysis on the fault status and blockchain data, and determine whether the status of auto parts is damaged or abnormal based on the analysis results, triggering the corresponding after-sales service process.

[0057] Upload the test results and maintenance information to the blockchain through smart contracts.

[0058] Scan auto parts through augmented reality technology to display the production data, service life, maintenance information and inventory information of the scanned auto parts in real time.

[0059] In a preferred embodiment of the present invention, in the above-mentioned blockchain-based automobile supply chain tracing method, the difference analysis between the fault status and the blockchain data, and judging whether the status of the automobile parts is damaged or abnormal according to the analysis results, includes:

[0060] By comparing the function The fault status is analyzed differently from the blockchain data, where: The fault status data of the auto parts detected by consumers in the i-th dimension, is the basic data of auto parts in the i-th dimension extracted from the blockchain, Δ i is the allowable deviation range of various parameters within the normal use range of the accessories, i is the different detection dimensions, and p is the sensitivity.

[0061] If the difference degree F exceeds the threshold, the state of the automobile accessory is determined to be damaged or abnormal.

[0062] The technical effect is: by comparing the fault status of auto parts detected by consumers with the basic data extracted from the blockchain, the difference analysis can be carried out to effectively identify whether the parts are beyond the normal use range. By using the parameter deviation range and combining sensitivity, the accurate judgment of abnormal situations can be ensured, the fault status can be monitored in real time, and the status of the parts can be quickly judged as damaged or abnormal, and the after-sales service process can be triggered, which promotes intelligent decision-making and resource optimization, and improves the safety and reliability of the overall supply chain.

[0063] In a preferred embodiment of the present invention, the above-mentioned automobile supply chain tracing method based on blockchain further includes:

[0064] By building a risk index model Predict possible future failures, where w i is the weight coefficient, R is the comprehensive risk index, and when the comprehensive risk index R exceeds the threshold, a preventive fault warning is triggered.

[0065] Its technical effect is: predicting possible future failures through the risk index model, improving the prediction ability and preventing potential failures from occurring; weighting the key factors that affect the life of automotive parts through weight coefficients to achieve accurate risk assessment.

[0066] The beneficial effects of the embodiments of the present invention are:

[0067] The present invention uses blockchain technology to trace the production data of auto parts, ensuring that the data cannot be tampered with and has high credibility. Each auto part generates a unique traceability code, and the production data is associated with it and uploaded to the blockchain, so that all parties in the supply chain can query the historical information of the parts, ensuring information transparency and traceability. According to the importance and sensitivity of the data, the data is divided into proprietary data and basic data, which are processed and uploaded to the blockchain separately. The access rights are controlled by smart contracts. The basic data is publicly displayed to consumers, and the proprietary data protects the supplier's business secrets and is only used by partners and internally. This data classification processing improves data security and meets the needs of different users.

[0068] The present invention establishes a risk index model to evaluate the health status of auto parts and predict possible future failures. When the comprehensive risk index exceeds the threshold, it triggers a preventive failure warning, which can help suppliers and consumers predict the service life of parts in advance and take preventive measures before problems occur, thereby reducing losses caused by unexpected failures. The performance of parts is monitored and failures are predicted through a long short-term memory network, and the time series information of the parts during use is learned to accurately predict the decline trend of the parts' performance and the probability of possible failures.

[0069] The present invention combines augmented reality technology to greatly improve the convenience and intuitiveness of users in obtaining information, allowing consumers to easily obtain complete background information when repairing, purchasing or using accessories, thereby enhancing the user experience. Through the visual dynamic visual effect function, complex data is displayed in a graphical way, helping users to more intuitively understand the status and performance of accessories.

[0070] When an accessory is damaged or abnormal during use, the present invention records the fault status through blockchain and automatically triggers the after-sales service process, ensuring that the problem can be quickly responded to and handled, shortening the service chain and improving the efficiency of after-sales service. Through the dynamic display and intelligent analysis of inventory information, suppliers and e-commerce platforms can better manage the inventory of accessories, reduce inventory backlogs or shortages, and the traceability information based on blockchain helps all parties in the supply chain to make accurate inventory replenishment plans and improve overall operational efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0072] Figure 1A flowchart of the automobile supply chain traceability method based on blockchain of the present invention applied to suppliers;

[0073] Figure 2 This is a flow chart of the automobile supply chain tracing method based on blockchain applied to an e-commerce platform;

[0074] Figure 3 The present invention is a flowchart of the automobile supply chain traceability method based on blockchain applied to consumers. DETAILED DESCRIPTION

[0075] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0076] Please refer to Figure 1 The first embodiment of the present invention provides a blockchain-based automobile supply chain traceability method, which is applied to suppliers and includes: collecting production data of automobile parts, classifying and storing them in a database; generating a unique traceability code for each of the automobile parts; grading the production data of the automobile parts according to the importance and sensitivity of the data, including proprietary data and basic data; processing the proprietary data and the basic data respectively, associating them with the unique traceability code, and uploading them to the blockchain through a smart contract; if the automobile parts are damaged, abnormal or updated, uploading and recording the status and time through a smart contract; and displaying the production data, service life, maintenance information and inventory information in real time through augmented reality technology.

[0077] In a preferred embodiment of the present invention, in the above-mentioned automobile supply chain tracing method based on blockchain, the processing of the proprietary data and the basic data respectively, associating with the unique traceability code, and uploading to the blockchain through the smart contract includes: using D proprietary Indicates proprietary data, which includes at least one of material formula, process parameters, and supplier internal process; D basic Represents basic data, the basic data includes at least one of production date, batch number, and quality inspection data; the proprietary data is hashed to generate a proprietary data hash value Among them, d i is the i-th production parameter in the proprietary data, w i is the weighted coefficient of different production parameters, H(·) is the hash function; the unique traceability code is associated with the proprietary data hash value and uploaded to the blockchain through a smart contract. The operation is defined as Where C is a unique traceability code; the unique traceability code is associated with the basic data and uploaded to the blockchain through a smart contract. The operation is defined as

[0078] Among them, the weight coefficient w is introduced i , which gives higher weight to key parameters in proprietary data and enhances encryption protection for sensitive information. 1 Specific temperature parameter d 2 More importantly, w 1 >w 2 .

[0079] The technical effect is that by hashing proprietary data, only authorized parties in the supply chain can verify the consistency of the data. By associating the hash values ​​of basic data and proprietary data with unique traceability codes and uploading them to the blockchain through smart contracts, the data is guaranteed to be tamper-proof and traceable. By introducing weighted coefficients into proprietary data, key parameters are given higher protection weights during the encryption process.

[0080] In a preferred embodiment of the present invention, in the above-mentioned blockchain-based automobile supply chain traceability method, the real-time display of production data, service life, maintenance information and inventory information through augmented reality technology includes: capturing the image of the automobile parts through a camera to identify the corresponding unique traceability code; calling the smart contract to retrieve the production data, service life, maintenance information and inventory information related to the unique traceability code from the blockchain; displaying the data retrieved from the blockchain in a visual form according to the user's perspective and operation; defining the basic model of visual dynamic visual effects V(t,D)=A(D)·F(t), wherein V(t,D) is the visual effect displayed at time t, A(D) is the visual expression function of the data type, and F(t) is the dynamic special effects function of time change.

[0081] Its technical effect is: by capturing the image of the auto parts through the camera and identifying the unique traceability code, the user can obtain the relevant information of the parts without complicated operation steps. The information of the parts is directly superimposed in the user's field of vision through AR technology, which simplifies the information query process and greatly optimizes the user experience. Different types of data are distinguished by different colors, shapes or icons, and combined with dynamic special effects display, so that users can more easily understand and distinguish various types of information when viewing, effectively avoiding the redundancy of information display, and improving the pertinence and efficiency of information use.

[0082] In a preferred embodiment of the present invention, in the above-mentioned blockchain-based automobile supply chain traceability method, the visual representation function of the data type includes: for production data D production, design the visual effect of dynamic growth of the bar chart, the performance function is Among them, P is the current production progress, Q is the total production target; for the service life D lifetime , design the visual effect of the progress bar, and use color changes to reflect the remaining life. The performance function is A(D lifetime )=Progress_Bar(R)·C(R), where R is the remaining service life, and the function C(R) indicates adjusting the color according to the proportion of the remaining service life; for maintenance information D maintenance , the design uses timeline animation to display maintenance information, and the performance function is A(D maintenance )=Timeline_Animation(R t ), where R t For the time and information of the latest maintenance; for inventory information D inventory , the design uses pie charts to display various inventory statuses and dynamically updates them. The performance function is A(D inventory )=Pie_Chart(Stock_Distribution).

[0083] Its technical effect is: by designing different dynamic visualization functions for production data, service life, maintenance information and inventory information, the intuitiveness and understanding of data display are enhanced, the timeline and relevance of information display are improved, real-time dynamic feedback of data status is achieved, and the user experience of information display is improved. At the same time, it provides efficient and accurate support for decision-making in supply chain management, allowing suppliers to better grasp the production and inventory status and make timely adjustments and optimizations.

[0084] In a preferred embodiment of the present invention, in the above-mentioned blockchain-based automobile supply chain tracing method, the time-varying dynamic special effect function is Among them, T is the special effect period, and E is the special effect amplitude used to control the intensity of the dynamic effect.

[0085] Its technical effect is: the introduction of dynamic special effects functions of time changes makes the displayed data more vivid and eye-catching by periodically presenting visual changes within time T, allowing users to intuitively perceive data changes and status updates on the information display interface, helping users to quickly capture key information and make timely adjustments or decisions, enhancing the hierarchy and dynamics of data display, making the data change process more natural and smooth, and making the system interface more attractive by presenting different visual effects at different time points.

[0086] Please refer to Figure 2The second embodiment of the present invention provides a blockchain-based automobile supply chain traceability method, which is applied to an e-commerce platform, and includes: accessing the blockchain through a smart contract to obtain the production data of auto parts; controlling data access rights through a smart contract, displaying basic data to consumers, and using proprietary data internally by authorized supply chain partners and e-commerce platforms; when auto parts are traded, verifying the authenticity of the auto parts through a smart contract; after the transaction is completed, transferring the traceability through a smart contract and uploading the transaction information to the chain; if the status of the auto parts is damaged or abnormal, uploading the damage record to the blockchain through a smart contract, and triggering the after-sales service process; using augmented reality technology to display the production data, service life, maintenance information and inventory information of auto parts in real time; analyzing the performance of the parts through a machine learning algorithm, and performing monitoring and fault warning.

[0087] In a preferred embodiment of the present invention, in the above-mentioned blockchain-based automobile supply chain tracing method, the performance of the accessories is analyzed by a machine learning algorithm to monitor and warn of faults, including: standardizing the production data of the automobile accessories to obtain a standardized input data set x t ; For performance monitoring and fault prediction, a deep learning model based on long short-term memory network is established, including input layer, LSTM layer, fully connected layer and output layer; the input layer receives the standardized input data set x t ; For each time t, the state update formula of the LSTM layer includes the input gate i t =σ(W i x t +U i h t-1 +b i ), indicating the extent to which LSTM adopts the candidate state information generated by the current input at time t, and the forget gate f t =σ(W f x t +U f h t-1 +b f ), controls the proportion of the LSTM layer to retain or forget the past state at time t, and the output gate o t =σ(W o x t +U o h t-1 +b o ), controls how much information the cell state passes to the hidden state after the activation function, the candidate state Represents the new candidate information generated by LSTM at time t based on the current input and the previous hidden state, cell state Record long-term dependency information and hide status It represents the output result of LSTM for the current input, including long-term and short-term memory information, where σ is the activation function, W and U are weight matrices, and b is the bias term; the calculation formula of the fully connected layer is S=w s ·h T +b s , where w s is the weight vector, b s is a bias term; the output layer outputs a performance score S and a failure probability P, and the calculation formula of the failure probability P is: Among them, w p is the weight used for fault prediction, b p is a bias term; when the fault probability P exceeds the fault threshold θ, a fault warning is triggered; a time-based performance decay function S is used t =S 0 exp(-αg), predicting the performance degradation of the component over time, where S 0 is the initial performance score, α is the attenuation coefficient, and g is the usage time of the accessory. The fault information and performance data are uploaded to the blockchain through smart contracts.

[0088] Its technical effects are: using a deep learning model based on long short-term memory network to effectively capture the time series characteristics of accessory performance data. The design of LSTM input gate, forget gate, output gate, cell state and hidden state can retain past state information, while flexibly adjusting the newly input data, so as to accurately predict the changes in accessory performance and potential failures. Through the automated early warning mechanism, in the event of accessory failure or performance degradation, the fault information is uploaded to the blockchain through smart contracts, and the after-sales service process is automatically triggered, reducing the steps of manual intervention and ensuring the transparency and non-tamperability of fault information. Through the design of a time-based performance decay function, the performance degradation trend of automotive accessories over time can be accurately predicted to help optimize the maintenance and replacement time points of accessories.

[0089] Please refer to Figure 3 The third embodiment of the present invention provides a blockchain-based automobile supply chain traceability method, which is applied to consumers and includes: inputting a traceability code and querying basic data of automobile accessories with access rights through the blockchain; when using the automobile accessories, if a fault occurs, detecting the fault status of the automobile accessories; performing a difference analysis between the fault status and the blockchain data, and judging whether the status of the automobile accessories is damaged or abnormal based on the analysis results, triggering a corresponding after-sales service process; uploading the detection results and maintenance information to the blockchain through a smart contract; scanning the automobile accessories through augmented reality technology, and displaying the production data, service life, maintenance information and inventory information of the scanned automobile accessories in real time.

[0090] Specifically, using augmented reality technology, consumers can scan accessories to view the current detection status, difference analysis results, and judgment information of the accessories in real time, such as "the temperature is out of the normal range, and immediate repair is recommended". The AR interface intuitively superimposes this information on the accessories to help consumers understand the status of the accessories. Color coding (for example: red for abnormal, green for normal) is used to intuitively display the status of each detection dimension, and the dynamic risk index is displayed in combination with the size of the difference degree value DDD.

[0091] In a preferred embodiment of the present invention, in the above-mentioned blockchain-based automobile supply chain tracing method, the difference analysis between the fault status and the blockchain data, and judging whether the status of the automobile parts is damaged or abnormal according to the analysis results, includes: comparing the function The fault status is analyzed differently from the blockchain data, where: The fault status data of the auto parts detected by consumers in the i-th dimension, is the basic data of auto parts in the i-th dimension extracted from the blockchain, Δ i is the allowable deviation range of various parameters within the normal use range of the accessories, including temperature, wear degree, pressure, etc., i is a different detection dimension, including temperature, wear, mechanical stress and other dimensions, i = 1, 2, ..., n, p is the sensitivity, which is used to enhance the impact of large deviations, usually 2; if the difference degree F exceeds the threshold, usually 1, then the state of the automotive accessories is judged to be damaged or abnormal.

[0092] The technical effect is: by comparing the fault status of auto parts detected by consumers with the basic data extracted from the blockchain, the difference analysis can be carried out to effectively identify whether the parts are beyond the normal use range. By using the parameter deviation range and combining sensitivity, the accurate judgment of abnormal situations can be ensured, the fault status can be monitored in real time, and the status of the parts can be quickly judged as damaged or abnormal, and the after-sales service process can be triggered, which promotes intelligent decision-making and resource optimization, and improves the safety and reliability of the overall supply chain.

[0093] In a preferred embodiment of the present invention, the above-mentioned automobile supply chain tracing method based on blockchain further includes: establishing a risk index model Predict possible future failures, where w i is a weight coefficient used to highlight certain factors that have a greater impact on the life of accessories, such as temperature, wear, etc. R is a comprehensive risk index used to evaluate the overall health status of accessories. When the comprehensive risk index R exceeds the threshold, a preventive fault warning is triggered.

[0094] Its technical effect is: predicting possible future failures through the risk index model, improving the prediction ability and preventing potential failures from occurring; weighting the key factors that affect the life of automotive parts through weight coefficients to achieve accurate risk assessment.

[0095] A fourth embodiment of the present invention provides a blockchain-based automobile supply chain tracing system, comprising:

[0096] The data collection module is used to collect the production data of automobile parts, classify the collected production data, and store it in the database;

[0097] The traceability code generation and management module is used to generate a unique traceability code for each auto part as the unique identifier of the part on the blockchain, and associate the traceability code with the production data;

[0098] Data encryption and smart contract module, which is used to encrypt proprietary data, upload it to the blockchain through smart contracts, and set data access permissions;

[0099] The status monitoring module is used to record the change information to the blockchain through smart contracts if the accessories are damaged or the transaction changes;

[0100] Augmented reality module, used to scan accessories in real time, obtain traceability codes, and display relevant information in real time in a visual form;

[0101] Machine learning analysis and fault warning module, which is used to predict and warn the status of auto parts through deep learning models;

[0102] Risk assessment and decision support module, which is used to provide optimization suggestions and decision support for suppliers and e-commerce platforms based on blockchain data and prediction models;

[0103] The blockchain storage and access control module is used to store production data, transaction information, maintenance records and status updates. It uses smart contracts to control data access permissions. Basic data is open to consumers, and proprietary data is only authorized for supply chain partners and internal use.

[0104] The computer program product of the blockchain-based automobile supply chain traceability method and device provided in the embodiments of the present invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the method in the previous method embodiment. The specific implementation can be found in the method embodiment, which will not be repeated here.

[0105] Specifically, the storage medium can be a general storage medium, such as a mobile disk, a hard disk, etc. When the computer program on the storage medium is run, the above-mentioned blockchain-based automobile supply chain traceability method can be executed, thereby comprehensively improving the intelligent level of automobile parts traceability management, fault detection and after-sales service through the immutability of blockchain technology, combined with the data visualization display of augmented reality technology and the intelligent analysis of machine learning.

[0106] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0107] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A blockchain-based automotive supply chain traceability method, applied to suppliers, characterized in that: include: Collect production data of auto parts, classify and store them in the database; Generating a unique traceability code for each of the automotive parts; Classify the production data of the automotive parts according to the importance and sensitivity of the data, including proprietary data and basic data; The proprietary data and the basic data are processed separately, associated with a unique traceability code, and uploaded to the blockchain through a smart contract; If a car part is damaged, abnormal, or updated, the status and time will be uploaded and recorded through the smart contract; Through augmented reality technology, production data, service life, maintenance information and inventory information are displayed in real time.

2. The automobile supply chain tracing method based on blockchain according to claim 1 is characterized in that: The processing of the proprietary data and the basic data respectively, associating with the unique traceability code, and uploading to the blockchain through the smart contract includes: Use D proprietary Indicates proprietary data, wherein the proprietary data includes at least one of material formula, process parameters, and supplier internal process; Use D basic Indicates basic data, wherein the basic data includes at least one of production date, batch number, and quality inspection data; Hash the proprietary data to generate a proprietary data hash value Among them, d i is the i-th production parameter in the proprietary data, w i is the weighting coefficient of different production parameters, H(·) is the hash function; Associating the unique traceability code with the proprietary data hash value and uploading it to the blockchain through a smart contract; The unique traceability code is associated with the basic data and uploaded to the blockchain through a smart contract.

3. The automobile supply chain tracing method based on blockchain according to claim 1 is characterized in that: The real-time display of production data, service life, maintenance information and inventory information by augmented reality technology includes: Capturing an image of the auto part by a camera and identifying the corresponding unique traceability code; Invoke the smart contract to retrieve production data, service life, maintenance information and inventory information related to the unique traceability code from the blockchain; The data retrieved from the blockchain is presented in a visual form based on the user’s perspective and actions; The basic model of dynamic visual effects of visualization is defined as V(t,D)=A(D)·F(t), where V(t,D) is the visual effect displayed at time t, A(D) is the visual expression function of the data type, and F(t) is the dynamic special effects function of time change.

4. The automobile supply chain tracing method based on blockchain according to claim 3 is characterized in that: The visual representation functions of the data types include: For production data D production , design the visual effect of dynamic growth of the bar chart, the performance function is Among them, P is the current production progress and Q is the total production target; For service life D lifetime , design the visual effect of the progress bar, and use color changes to reflect the remaining life. The performance function is A(D lifetime )=Progress_Bar(R)·C(R), where R is the remaining service life, and the function C(R) represents adjusting the color according to the proportion of the remaining service life; For maintenance information D maintenance , the design uses timeline animation to display maintenance information, and the performance function is A(D maintenance )=Timeline_Animation(R t ), where R t The time and information of the most recent maintenance; For inventory information D inventory , the design uses pie charts to display various inventory statuses and dynamically updates them. The performance function is A(D inventory )=Pie_Chart(Stock_Distribution).

5. The automobile supply chain tracing method based on blockchain according to claim 3 is characterized in that: The time-varying dynamic special effect function is: Among them, T is the special effect period, and E is the special effect amplitude used to control the intensity of the dynamic effect.

6. A blockchain-based automobile supply chain tracing method, applied to an e-commerce platform, characterized in that: include: Access blockchain through smart contracts to obtain production data of auto parts; Control data access rights through smart contracts, display basic data to consumers, and use proprietary data internally by authorized supply chain partners and e-commerce platforms; When auto parts are traded, the authenticity of the auto parts is verified through smart contracts; After the transaction is completed, the transaction information is uploaded to the chain through smart contract transfer and traceability; If the status of the auto parts is damaged or abnormal, the damage record will be uploaded to the blockchain through the smart contract, and the after-sales service process will be triggered; Through augmented reality technology, the production data, service life, maintenance information and inventory information of auto parts can be displayed in real time; The performance of accessories is analyzed through machine learning algorithms for monitoring and fault warning.

7. The automobile supply chain tracing method based on blockchain according to claim 6 is applied to an e-commerce platform, characterized in that: The analysis of the performance of the accessories by machine learning algorithms to monitor and provide fault warnings includes: The production data of the automobile parts is standardized to obtain a standardized input data set x t ; For performance monitoring and fault prediction, a deep learning model based on long short-term memory network is established, including input layer, LSTM layer, fully connected layer and output layer; The input layer receives the normalized input dataset x t ; For each time t, the state update formula of the LSTM layer includes the input gate i t =σ(W i x t +U i h t-1 +b i ), forget gate f t =σ(W f x t +U f h t-1 +b f ), output gate o t =σ(W o x t +U o h t-1 +b o ), cell status Hidden State Among them, σ is the activation function, W and U are weight matrices, and b is the bias term; The calculation formula of the fully connected layer is S=w s ·h T +b s , where w s is the weight vector, b s is the bias term; The output layer outputs the performance score S and the failure probability P. The calculation formula of the failure probability P is: Among them, w p is the weight used for fault prediction, b p is the bias term; When the failure probability P exceeds the failure threshold θ, a failure warning is triggered; Adopting the time-based performance decay function S t =S0·exp(-αg), predicting the performance degradation of accessories over time, where S0 is the initial performance score, α is the decay coefficient, and g is the usage time of the accessories; Upload fault information and performance data to the blockchain through smart contracts.

8. A blockchain-based automobile supply chain traceability method, applied to consumers, characterized in that: include: Enter the traceability code and query the basic data of auto parts with access rights through the blockchain; When using auto parts, if a fault occurs, the fault state of the auto parts is detected; Perform differential analysis on the fault status and blockchain data, and determine whether the status of the auto parts is damaged or abnormal based on the analysis results, triggering the corresponding after-sales service process; Upload test results and repair information to the blockchain through smart contracts; Scan auto parts through augmented reality technology to display the production data, service life, maintenance information and inventory information of the scanned auto parts in real time.

9. The automobile supply chain tracing method based on blockchain according to claim 8 is characterized in that: The difference analysis between the fault status and the blockchain data and judging whether the status of the auto parts is damaged or abnormal according to the analysis results include: By comparing the function The fault status is analyzed differently from the blockchain data, where: The fault status data of the auto parts detected by consumers in the i-th dimension, is the basic data of auto parts in the i-th dimension extracted from the blockchain, Δ i is the allowable deviation range of various parameters within the normal use range of the accessories, i is the different detection dimensions, and p is the sensitivity; If the difference degree F exceeds the threshold, the state of the automobile accessory is determined to be damaged or abnormal.

10. The automobile supply chain tracing method based on blockchain according to claim 8 is characterized in that: Also includes: By building a risk index model Predict possible future failures, where w i is the weight coefficient, R is the comprehensive risk index, and when the comprehensive risk index R exceeds the threshold, a preventive fault warning is triggered.

Images