CN117455312A - Power grid smart supply chain quality detection method and system based on blockchain technology - Google Patents

Abstract

The invention relates to a power grid smart supply chain quality detection method and system based on blockchain technology. It constructs a supply chain quality detection blockchain based on blockchain technology, and builds a data access system for the detection mechanism to integrate real-time material quality The detection data is integrated with the blockchain; the supply chain quality detection blockchain network uses smart contract programming language to construct the first smart contract, the second smart contract and the third smart contract; the first smart contract is used to achieve prediction model, the second smart contract is used to implement the identification model, and the third smart contract is used to implement the matching correction model; the competent department obtains the detection results through the user-side supply chain quality detection blockchain network. The invention realizes the authenticity and credibility of supply chain data, automated quality management and feedback mechanism, and improves the quality and efficiency of the power grid supply chain.

Description

Power grid smart supply chain quality detection method and system based on blockchain technology

Technical field

The invention relates to the field of data management, and in particular to a power grid smart supply chain quality detection method based on blockchain technology.

Background technique

As the demand for materials in the power industry increases day by day, the timeliness and accuracy of the results of material quality testing are increasingly urgent. In the past two years, blockchain technology has attracted great attention from large domestic and foreign institutions and mainstream companies because of its characteristics of openness, transparency, non-tampering, and traceability. There is huge room for growth in the application market when combined with business, and there is no Technology, trade barriers and policy restrictions. The application and exploration of new technologies with high security and reliability in the actual business scenarios of testing institutions has practical guiding significance for establishing and improving testing institutions’ good psychological identity and credibility among the public. Therefore, developing safe and credible quality inspection business applications, and uploading quality inspection process data, quality inspection results, quality inspection reports and other information to the chain for certificate storage, can effectively solve the problem of fidelity of information such as inspection reports under the traditional model of some quality inspection business links. Problems such as weak strength, low mutual trust, and difficulty in handling complaints and disputes are very necessary.

Contents of the invention

In order to solve the above problems, the purpose of the present invention is to provide a power grid smart supply chain quality detection method and system based on blockchain technology, realize the authenticity and credibility of supply chain data, automated quality management and feedback mechanism, and improve the power grid Supply chain quality and efficiency.

In order to achieve the above objects, the present invention adopts the following technical solutions:

A power grid smart supply chain quality inspection method based on blockchain technology, including the following steps:

Step S1: Construct a supply chain quality inspection blockchain based on blockchain technology, and build a data access system for the inspection agency to integrate real-time material quality inspection data with the blockchain;

Step S2: Use smart contract programming language to construct the first smart contract, the second smart contract and the third smart contract; the first smart contract is used to implement the prediction model, and the first smart contract accepts detection items, detection parameters and actual The test value is used as input, the prediction model is called for prediction, and the prediction result is returned to the caller; the second smart contract is used to implement the identification model, accepts the detection order number as input, calls the identification model for identification, and obtains the batch Pre-report; the third smart contract is used to implement the matching correction model, accepts formal detection results and pre-reports as input, and calls the matching correction model to perform matching correction;

Step S3: According to the data access system, connect the real-time material quality detection data to the supply chain quality detection blockchain, and call the first smart contract to generate a pre-report;

Step S4: Feed back the test results and availability information of the material categories that are judged to be qualified in the pre-report to the competent department. The competent department can use the pre-report to carry out relevant material warehousing and requisition work in advance;

Step S5: When the testing agency completes the formal testing, it generates formal testing results, connects the formal testing results to the blockchain, and calls the second smart contract to identify the batch of pre-reports based on the testing order number;

Step S6: Call the third smart contract to complete and correct the pre-report data based on the formal test results. If the material category judged to be qualified in the pre-report is corrected, the corrected data will be fed back to the competent department for correction and completed based on the formal test results. Warehouse and receive all materials of this batch.

Further, the step S1 is specifically:

Define the data structure of material quality testing data, including material name, batch number, production date, testing results, and testing time fields;

Define a smart contract on the blockchain to store and manage material quality inspection data;

The testing agency builds a data access system to upload real-time material quality testing data to the blockchain network. The data access system uses digital signature technology to verify and encrypt the data:

First calculate the hash value of the input data, then call the signHash function to sign the hash value using the sender's private key, and store the signature result in the signatures map;

Based on the verifySignature function, it accepts the signer's address, data and signature as parameters, and uses the signer's public key to verify the validity of the signature;

Then call the signHash function to take a hash value as a parameter and use the sender's private key to sign the hash value. The signature result is returned in the form of a byte array; call the verifyHash function to accept a hash value, signature and signer. The address is used as a parameter, and the signer's public key is used to verify the validity of the signature; the ecdsaSign function is called to sign the hash value and the signer, and the r, s and v values of the signature are returned; where the r value is the One part, the s value is another part of the signature, and the v value represents the recovery ID of the signer's public key;

The hash value and signature are verified based on the ecdsaVerify function, and the validity of the signature is returned;

The testing agency uploads real-time material quality testing data to the smart contract on the blockchain through the data access system;

The smart contract will store each uploaded data on the blockchain in the form of a transaction and ensure the non-tamperability and transparency of the data.

Further, the details of the first smart contract are as follows:

A smart contract named QualityPredictionContract is declared based on Solidity. In the contract, a structure TestResult is defined to store detection parameters and prediction results. The structure contains two fields: detection parameters parameters and prediction results;

A mapping testResults is used to store historical test data. The key of the map is the project name, and the value is the TestResult structure array, which is used to store the historical test data of the project;

The addTestData function is used to add historical test data to testResults, accepts the project name, detection parameters and prediction results as parameters, and stores them under the corresponding project name;

The predictQuality function is used to call the smart contract of the prediction model to make predictions, accepts the project name and detection parameters as parameters, and returns the prediction results.

Further, the prediction model is called for prediction, as follows:

First, a smart contract named LogisticRegressionModel is defined, which contains a logistic regression model. The model parameters include intercept, coefficient coef1 of parameter 1, and coefficient coef2 of parameter 2. The prediction function predict accepts parameter 1 and parameter 2 as input, and Returns the prediction result true or false. In the prediction function, the sigmoid function and exponential function are used to calculate the prediction result;

Next, the QualityPredictionContract smart contract was modified, a constructor was added to receive the address of the LogisticRegressionModel smart contract, and the logisticRegressionModel was initialized in the constructor; a structure TestResult was also defined to store detection parameters and prediction results, and use mapping testResults to store historical test data;

In the QualityPredictionContract smart contract, the addTestData function is added to add historical test data, and the function is modified to add an actualValue parameter to store the actual test value. The predictQuality function is also added to call logisticRegressionModel for prediction. And store the prediction results in testResults.

Further, the logistic regression model is specifically:

There are n detection parameters x1, x2, ..., xn, and corresponding quality level labels y, y=1 means qualified, y=0 means unqualified;

The logistic regression model is:

hθ(x) = g(θ^T * x)

Among them, θ is the parameter vector of the model, x is the input feature vector;

g(z) is a logistic function whose formula is:

g(z) = 1 / (1 + e^(-z))

where z is the input parameter;

The prediction results of the model are:

If hθ(x) >= 0.5, predict y = 1; if hθ(x) < 0.5, predict y = 0.

Further, the second smart contract accepts the detection order number as input, calls the identification model for identification, and retrieves the pre-report of the corresponding order number in the blockchain based on the identification result, as follows:

A contract named ReportStorage is defined, which contains a reports mapping to store the pre-report corresponding to the detection order number. A function named setReport is defined to set the pre-report corresponding to the detection order number. At the same time, it also A function named getReport is defined to obtain the pre-report corresponding to the detection order number;

A contract named DetectionModel is defined, which contains a reportStorageAddress variable to store the address of the ReportStorage contract. It also defines a function named detectAndGenerateReport to identify single numbers and return pre-reports;

In the detectAndGenerateReport function, the order number recognition model is first called for identification, and then the getReportFromStorage function is called to obtain the pre-report of the corresponding order number. According to the ReportStorage contract address stored in reportStorageAddress, the getReport function of the ReportStorage contract is called to obtain the pre-report of the corresponding order number. , and finally return the pre-report.

Further, the third smart contract includes a contract named MatchingModel. The contract defines a mapping named matchedAddresses for storing matching correction results. The contract includes a public function named match for converting specific The key and address are matched and stored in the map; a matchedStorage is also defined, which is used to call the match correction model; in addition, there is a public view function named getMatchedAddress, which is used to obtain the match correction address corresponding to a specific key.

Further, the matching correction model is as follows:

Obtain historical information about a batch of products, including test items, test parameters and actual test values, and perform preprocessing to build a training data set;

A matching correction model is built based on the random forest model and trained based on the training data set. During the training process, we use the product's various detection items and detection parameters as features, and the actual test values as labels;

The trained model is optimized through cross-validation to obtain the final matching correction model.

A power grid smart supply chain quality detection system based on blockchain technology, including a detection mechanism, a data access system, a supply chain quality detection blockchain network and a user terminal; the detection mechanism transmits real-time material information through the data access system Quality inspection data is integrated with the blockchain; the supply chain quality inspection blockchain network uses smart contract programming language to construct the first smart contract, the second smart contract and the third smart contract; the first smart contract is used to implement Prediction model, the first smart contract accepts detection items, detection parameters and actual test values as input, calls the prediction model to make predictions, and returns the prediction results to the caller; the second smart contract is used to implement the identification model, accepting The detection order number is used as input, the identification model is called to identify, and the pre-report of the batch is obtained; the third smart contract is used to implement the matching and correction model, accepts the formal detection results and pre-report as input, and calls the matching and correction model to perform matching and correction. ; The competent authorities access the supply chain quality inspection blockchain network through the user terminal to obtain the inspection results.

Furthermore, the user terminal is also equipped with a testing fee management module, which adjusts and sets the testing fee benchmark value according to the testing items, testing institutions, material categories, and testing level conditions. At the same time, the testing fee is automatically calculated by correlating the testing plan and the content of the testing project. At the same time, for the testing fees of unqualified products, summarize the testing status and testing amount information, generate a testing fee payment notification letter, send it to the email address provided by the supplier, push the testing fee payment information to the supplier’s to-do list, and Send the payment of testing fees to the supplier's contact person via text message, and set up an early warning function for information about overdue testing fees. For suppliers who have not submitted payment vouchers for testing fees, notification messages can be sent regularly and repeatedly.

The invention has the following beneficial effects:

1. This invention realizes the authenticity and credibility of supply chain data, automated quality management and feedback mechanism, and improves the quality and efficiency of the power grid supply chain;

2. This invention stores data such as pre-reports and detection results on the blockchain to ensure data security and non-tamperability. These data can be easily accessed through smart contracts to perform operations such as matching and correction;

3. The present invention encapsulates low-complexity prediction models directly through smart contracts, while high-complexity identification models and matching correction models are used through calls. The more complex the code in the smart contract, the higher the fuel cost required for execution. Encapsulating low-complexity prediction models directly in smart contracts can reduce the complexity of smart contracts, reduce execution costs, and improve the execution efficiency of smart contracts. High-complexity identification models and matching correction models can be used as callable external services. , can realize the decoupling of smart contracts and external models, and flexibly update and replace the identification model and matching correction model without modifying the code of the smart contract, which improves scalability and flexibility.

Description of the drawings

Figure 1 is a flow chart of the method of the present invention;

Figure 2 is a schematic diagram of the system architecture in an embodiment of the present invention.

Detailed ways

The present invention will be further described in detail below in conjunction with the accompanying drawings and specific examples:

Referring to Figure 1, in this embodiment, a power grid smart supply chain quality detection method based on blockchain technology is provided, including the following steps:

Step S1: Construct a supply chain quality inspection blockchain based on blockchain technology, and build a data access system for the inspection agency to integrate real-time material quality inspection data with the blockchain;

Step S2: Use smart contract programming language to construct the first smart contract, the second smart contract and the third smart contract; the first smart contract is used to implement the prediction model, and the first smart contract accepts detection items, detection parameters and actual The test value is used as input, the prediction model is called for prediction, and the prediction result is returned to the caller; the second smart contract is used to implement the identification model, accepts the detection order number as input, calls the identification model for identification, and obtains the batch Pre-report; the third smart contract is used to implement the matching correction model, accepts formal detection results and pre-reports as input, and calls the matching correction model to perform matching correction;

Step S3: According to the data access system, connect the real-time material quality detection data to the supply chain quality detection blockchain, and call the first smart contract to generate a pre-report;

Step S4: Feed back the test results and availability information of the material categories that are judged to be qualified in the pre-report to the competent department. The competent department can use the pre-report to carry out relevant material warehousing and requisition work in advance;

Step S5: When the testing agency completes the formal testing, it generates formal testing results, connects the formal testing results to the blockchain, and calls the second smart contract to identify the batch of pre-reports based on the testing order number;

Step S6: Call the third smart contract to complete and correct the pre-report data based on the formal test results. If the material category judged to be qualified in the pre-report is corrected, the corrected data will be fed back to the competent department for correction and completed based on the formal test results. Warehouse and receive all materials of this batch.

In this embodiment, step S1 is specifically:

Define the data structure of material quality testing data, including material name, batch number, production date, testing results, and testing time fields;

Define a smart contract on the blockchain to store and manage material quality inspection data;

The testing agency builds a data access system to upload real-time material quality testing data to the blockchain network. The data access system uses digital signature technology to verify and encrypt the data:

First calculate the hash value of the input data, then call the signHash function to sign the hash value using the sender's private key, and store the signature result in the signatures map;

Based on the verifySignature function, it accepts the signer's address, data and signature as parameters, and uses the signer's public key to verify the validity of the signature;

Then call the signHash function to take a hash value as a parameter and use the sender's private key to sign the hash value. The signature result is returned in the form of a byte array; call the verifyHash function to accept a hash value, signature and signer. The address is used as a parameter, and the signer's public key is used to verify the validity of the signature; the ecdsaSign function is called to sign the hash value and the signer, and the r, s and v values of the signature are returned; where the r value is the One part, the s value is another part of the signature, and the v value represents the recovery ID of the signer's public key;

The hash value and signature are verified based on the ecdsaVerify function, and the validity of the signature is returned;

The testing agency uploads real-time material quality testing data to the smart contract on the blockchain through the data access system;

The smart contract will store each uploaded data on the blockchain in the form of a transaction and ensure the non-tamperability and transparency of the data.

Further, the details of the first smart contract are as follows:

A smart contract named QualityPredictionContract is declared based on Solidity. In the contract, a structure TestResult is defined to store detection parameters and prediction results. The structure contains two fields: detection parameters parameters and prediction results;

A mapping testResults is used to store historical test data. The key of the map is the project name, and the value is the TestResult structure array, which is used to store the historical test data of the project;

The addTestData function is used to add historical test data to testResults, accepts the project name, detection parameters and prediction results as parameters, and stores them under the corresponding project name;

The predictQuality function is used to call the smart contract of the prediction model to make predictions, accepts the project name and detection parameters as parameters, and returns the prediction results.

In this embodiment, the prediction model is called for prediction, as follows:

First, a smart contract named LogisticRegressionModel is defined, which contains a logistic regression model. The model parameters include intercept, coefficient coef1 of parameter 1, and coefficient coef2 of parameter 2. The prediction function predict accepts parameter 1 and parameter 2 as input, and Returns the prediction result true or false. In the prediction function, the sigmoid function and exponential function are used to calculate the prediction result;

Next, the QualityPredictionContract smart contract was modified, a constructor was added to receive the address of the LogisticRegressionModel smart contract, and the logisticRegressionModel was initialized in the constructor; a structure TestResult was also defined to store detection parameters and prediction results, and use mapping testResults to store historical test data;

In the QualityPredictionContract smart contract, the addTestData function is added to add historical test data, and the function is modified to add an actualValue parameter to store the actual test value. The predictQuality function is also added to call logisticRegressionModel for prediction. And store the prediction results in testResults.

In this embodiment, the logistic regression model is specifically:

There are n detection parameters x1, x2, ..., xn, and corresponding quality level labels y, y=1 means qualified, y=0 means unqualified;

The logistic regression model is:

hθ(x) = g(θ^T * x)

Among them, θ is the parameter vector of the model, x is the input feature vector;

g(z) is a logistic function and its formula is:

g(z) = 1 / (1 + e^(-z))

where z is the input parameter;

The prediction results of the model are:

If hθ(x) >= 0.5, predict y = 1; if hθ(x) < 0.5, predict y = 0.

Further, the second smart contract accepts the detection order number as input, calls the identification model for identification, and retrieves the pre-report of the corresponding order number in the blockchain based on the identification result, as follows:

A contract named ReportStorage is defined, which contains a reports mapping to store the pre-report corresponding to the detection order number. A function named setReport is defined to set the pre-report corresponding to the detection order number. At the same time, it also A function named getReport is defined to obtain the pre-report corresponding to the inspection order number;

A contract named DetectionModel is defined, which contains a reportStorageAddress variable to store the address of the ReportStorage contract. It also defines a function named detectAndGenerateReport to identify single numbers and return pre-reports;

In the detectAndGenerateReport function, the order number recognition model is first called for identification, and then the getReportFromStorage function is called to obtain the pre-report of the corresponding order number. According to the ReportStorage contract address stored in reportStorageAddress, the getReport function of the ReportStorage contract is called to obtain the pre-report of the corresponding order number. , and finally return the pre-report.

Further, the third smart contract includes a contract named MatchingModel. The contract defines a mapping named matchedAddresses for storing matching correction results. The contract includes a public function named match for converting specific The key and address are matched and stored in the map; a matchedStorage is also defined, which is used to call the match correction model; in addition, there is a public view function named getMatchedAddress, which is used to obtain the match correction address corresponding to a specific key.

Further, the matching correction model is as follows:

Obtain historical information about a batch of products, including test items, test parameters and actual test values, and perform preprocessing to build a training data set;

A matching correction model is built based on the random forest model and trained based on the training data set. During the training process, we use the product's various detection items and detection parameters as features, and the actual test values as labels;

The trained model is optimized through cross-validation to obtain the final matching correction model.

Referring to Figure 2, in this embodiment, a power grid smart supply chain quality detection system based on blockchain technology is also provided, including a detection mechanism, a data access system, a supply chain quality detection blockchain network and a user terminal; so The testing agency integrates real-time material quality testing data with the blockchain through the data access system; the supply chain quality testing blockchain network uses smart contract programming language to construct the first smart contract, the second smart contract and the third smart contract. Smart contract; the first smart contract is used to implement the prediction model. The first smart contract accepts detection items, detection parameters and actual test values as input, calls the prediction model to make predictions, and returns the prediction results to the caller; so The second smart contract is used to implement the identification model, accepts the detection order number as input, calls the identification model for identification, and obtains the pre-report of the batch; the third smart contract is used to implement the matching correction model, accepts the formal detection results and The pre-report is used as input, and the matching correction model is called to perform matching correction; the competent department accesses the supply chain quality inspection blockchain network through the user terminal to obtain the test results.

In this embodiment, the user terminal is also equipped with a testing fee management module, which adjusts and sets the testing fee benchmark value according to the testing items, testing institutions, material categories, and testing level conditions. At the same time, it automatically calculates the testing fee by correlating the testing plan and testing project content. The amount of the fee, and for the testing fees of unqualified products, summarize the testing status and testing amount information, generate a testing fee payment notification letter, send it to the email address provided by the supplier, and push the testing fee payment information to the supplier's to-do list. The payment of testing fees will be sent to the supplier's contact person via text message, and an early warning function will be set up for information on overdue testing fees. For suppliers who have not submitted payment vouchers for testing fees, notification messages can be sent regularly and repeatedly.

Those skilled in the art will understand that embodiments of the present application may be provided as methods, systems, or computer program products. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment that combines software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each process and/or block in the flowchart illustrations and/or block diagrams, and combinations of processes and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing device to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing device produce a use A device for realizing the functions specified in a process or processes in a flowchart and/or a block or blocks in a block diagram.

These computer program instructions may also be stored in a computer-readable memory that causes a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction means, the instructions The device implements the functions specified in a process or processes in the flowchart and/or in a block or blocks in the block diagram.

These computer program instructions may also be loaded onto a computer or other programmable data processing device, causing a series of operating steps to be performed on the computer or other programmable device to produce computer-implemented processing, thereby executing on the computer or other programmable device. Instructions provide steps for implementing the functions specified in a process or processes of a flowchart diagram and/or a block or blocks of a block diagram.

The above are only preferred embodiments of the present invention, and are not intended to limit the present invention in other forms. Any skilled person familiar with the art may make changes or modifications to equivalent changes using the technical contents disclosed above. Example. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims (10)

1. A power grid smart supply chain quality detection method based on blockchain technology, which is characterized by including the following steps: Step S1: Construct a supply chain quality inspection blockchain based on blockchain technology, and build a data access system for the inspection agency to integrate real-time material quality inspection data with the blockchain; Step S2: Use smart contract programming language to construct the first smart contract, the second smart contract and the third smart contract; the first smart contract is used to implement the prediction model, and the first smart contract accepts detection items, detection parameters and actual The test value is used as input, the prediction model is called for prediction, and the prediction result is returned to the caller; the second smart contract is used to implement the identification model, accepts the detection order number as input, calls the identification model for identification, and obtains the batch Pre-report; the third smart contract is used to implement the matching correction model, accepts formal detection results and pre-reports as input, and calls the matching correction model to perform matching correction; Step S3: According to the data access system, connect the real-time material quality detection data to the supply chain quality detection blockchain, and call the first smart contract to generate a pre-report; Step S4: Feed back the test results and availability information of the material categories that are judged to be qualified in the pre-report to the competent department. The competent department can use the pre-report to carry out relevant material warehousing and requisition work in advance; Step S5: When the testing agency completes the formal testing, it generates formal testing results, connects the formal testing results to the blockchain, and calls the second smart contract to identify the batch of pre-reports based on the testing order number; Step S6: Call the third smart contract to complete and correct the pre-report data based on the formal test results. If the material category judged to be qualified in the pre-report is corrected, the corrected data will be fed back to the competent department for correction and completed based on the formal test results. Warehouse and receive all materials of this batch. 2. The power grid smart supply chain quality detection method based on blockchain technology according to claim 1, characterized in that the step S1 is specifically: Define the data structure of material quality testing data, including material name, batch number, production date, testing results, and testing time fields; Define a smart contract on the blockchain to store and manage material quality inspection data; The testing agency builds a data access system to upload real-time material quality testing data to the blockchain network. The data access system uses digital signature technology to verify and encrypt the data: First calculate the hash value of the input data, then call the signHash function to sign the hash value using the sender's private key, and store the signature result in the signatures map; Based on the verifySignature function, it accepts the signer's address, data and signature as parameters, and uses the signer's public key to verify the validity of the signature; Then call the signHash function to take a hash value as a parameter and use the sender's private key to sign the hash value. The signature result is returned in the form of a byte array; call the verifyHash function to accept a hash value, signature and signer. The address is used as a parameter, and the signer's public key is used to verify the validity of the signature; the ecdsaSign function is called to sign the hash value and the signer, and the r, s and v values of the signature are returned, where the r value is the One part, the s value is another part of the signature, and the v value represents the recovery ID of the signer's public key; The hash value and signature are verified based on the ecdsaVerify function, and the validity of the signature is returned; The testing agency uploads real-time material quality testing data to the smart contract on the blockchain through the data access system; The smart contract will store each uploaded data on the blockchain in the form of a transaction and ensure the non-tamperability and transparency of the data. 3. The power grid smart supply chain quality detection method based on blockchain technology according to claim 1, characterized in that the first smart contract is as follows: A smart contract named QualityPredictionContract is declared based on Solidity. In the contract, a structure TestResult is defined to store detection parameters and prediction results. The structure contains two fields: detection parameters parameters and prediction results; A mapping testResults is used to store historical test data. The key of the map is the project name, and the value is the TestResult structure array, which is used to store the historical test data of the project; The addTestData function is used to add historical test data to testResults, accepts the project name, detection parameters and prediction results as parameters, and stores them under the corresponding project name; The predictQuality function is used to call the smart contract of the prediction model to make predictions, accepts the project name and detection parameters as parameters, and returns the prediction results. 4. The power grid smart supply chain quality detection method based on blockchain technology according to claim 3, characterized in that the prediction model is called for prediction, specifically as follows: First, a smart contract named LogisticRegressionModel is defined, which contains a logistic regression model. The model parameters include intercept, coefficient coef1 of parameter 1, and coefficient coef2 of parameter 2. The prediction function predict accepts parameter 1 and parameter 2 as input, and Returns the prediction result true or false. In the prediction function, the sigmoid function and exponential function are used to calculate the prediction result; Next, the QualityPredictionContract smart contract was modified, a constructor was added to receive the address of the LogisticRegressionModel smart contract, and the logisticRegressionModel was initialized in the constructor; a structure TestResult was also defined to store detection parameters and prediction results, and use mapping testResults to store historical test data; In the QualityPredictionContract smart contract, the addTestData function is added to add historical test data, and the function is modified to add an actualValue parameter to store the actual test value. The predictQuality function is also added to call logisticRegressionModel for prediction. And store the prediction results in testResults. 5. The power grid smart supply chain quality detection method based on blockchain technology according to claim 4, characterized in that the logistic regression model is specifically: There are n detection parameters x1, x2, ..., xn, and corresponding quality level labels y, y=1 means qualified, y=0 means unqualified; The logistic regression model is: hθ(x) = g(θ^T * x) Among them, θ is the parameter vector of the model, x is the input feature vector; g(z) is a logistic function whose formula is: g(z) = 1 / (1 + e^(-z)) where z is the input parameter; The prediction results of the model are: If hθ(x) >= 0.5, predict y = 1; if hθ(x) < 0.5, predict y = 0. 6. The power grid smart supply chain quality detection method based on blockchain technology according to claim 1, characterized in that the second smart contract accepts the detection order number as input, calls the identification model for identification, and based on the identification result Retrieve the pre-report of the corresponding order number in the blockchain, as follows: A contract named ReportStorage is defined, which contains a reports mapping to store the pre-report corresponding to the detection order number. A function named setReport is defined to set the pre-report corresponding to the detection order number. At the same time, it also A function named getReport is defined to obtain the pre-report corresponding to the detection order number; A contract named DetectionModel is defined, which contains a reportStorageAddress variable to store the address of the ReportStorage contract. It also defines a function named detectAndGenerateReport to identify single numbers and return pre-reports; In the detectAndGenerateReport function, the order number recognition model is first called for identification, and then the getReportFromStorage function is called to obtain the pre-report of the corresponding order number. According to the ReportStorage contract address stored in reportStorageAddress, the getReport function of the ReportStorage contract is called to obtain the pre-report of the corresponding order number. , and finally return the pre-report. 7. The power grid smart supply chain quality detection method based on blockchain technology according to claim 1, characterized in that the third smart contract includes a contract named MatchingModel, and a contract named matchedAddresses is defined in the contract. Mapping, used to store matching correction results. The contract contains a public function named match, which is used to match specific keys and addresses and store them in the mapping; it also defines a matchedStorage, which is used to call the matching correction model; in addition, There is also a public view function called getMatchedAddress, which is used to obtain the matched corrected address corresponding to a specific key. 8. The power grid smart supply chain quality detection method based on blockchain technology according to claim 7, characterized in that the matching correction model is as follows: Obtain historical information about a batch of products, including test items, test parameters and actual test values, and perform preprocessing to build a training data set; A matching correction model is built based on the random forest model and trained based on the training data set. During the training process, we use the product's various detection items and detection parameters as features, and the actual test values as labels; The trained model is optimized through cross-validation to obtain the final matching correction model. 9. A power grid smart supply chain quality detection system based on blockchain technology, characterized by including a detection mechanism, a data access system, a supply chain quality detection blockchain network and a user end; the detection mechanism passes the data connection The system integrates real-time material quality detection data with the blockchain; the supply chain quality detection blockchain network uses smart contract programming language to construct the first smart contract, the second smart contract and the third smart contract; the third smart contract A smart contract is used to implement the prediction model. The first smart contract accepts detection items, detection parameters and actual test values as input, calls the prediction model to make predictions, and returns the prediction results to the caller; the second smart contract uses To implement the identification model, accept the test order number as input, call the identification model for identification, and obtain the pre-report of the batch; the third smart contract is used to implement the matching correction model, accept the formal test results and pre-report as input, and call The matching correction model is used for matching correction; the competent department accesses the supply chain quality inspection blockchain network through the user terminal to obtain the inspection results. 10. A power grid smart supply chain quality inspection system based on blockchain technology according to claim 9, characterized in that the user terminal is also equipped with a inspection fee management module. According to the inspection items, inspection institutions, and material categories , adjust the testing level conditions and dimension parameters to set the testing fee benchmark value, and automatically calculate the testing fee amount by correlating the testing plan and testing project content. At the same time, for the testing fees of unqualified products, summarize the testing status and testing amount information, and generate testing fee payment notices. Send a letter to the email address provided by the supplier, push the testing fee payment information to the supplier's to-do list, send the testing fee payment to the supplier contact via text message, and set up a request for information on overdue testing fees. The early warning function can regularly and repeatedly send notification messages to suppliers who have not submitted payment vouchers for testing fees.