E-commerce commodity traceability management system based on big data

Abstract

The application belongs to the technical field of commodity traceability, and provides an e-commerce commodity traceability management system based on big data, which comprises the following steps: calling historical traceability records of e-commerce commodities from a production end to a consumption end full link, combing adjacent link correlation pairs in a natural flow sequence of production, storage, logistics, sales and after-sales, performing hash value and associated document number consistency verification, evaluating the credibility of the historical traceability records, and screening out credible historical records with high credibility; for the commodities corresponding to the credible historical records, quantifying the difference amplitude of different commodity characteristics, and identifying abnormal characteristics in the commodity characteristics; based on the abnormal characteristics in the commodity characteristics, the time length of the commodity full link flow in the e-commerce commodity traceability process is obtained, and the difference amplitude of the commodity characteristics is subjected to correlation analysis. The application not only strengthens the e-commerce commodity quality control capability, but also improves the industry compliance level and consumer trust through full-process traceability.

Description

Technical Field

[0001] This invention belongs to the field of product traceability technology, specifically a big data-based e-commerce product traceability management system. Background Technology

[0002] With the rapid development of the e-commerce industry, the commodity circulation chain is becoming increasingly complex. From the production end to the consumption end, it needs to go through multiple links such as warehousing, logistics, and sales. Consumers' demand for product quality traceability is becoming more and more urgent. Accurate and reliable traceability management has become the core demand of quality control in the e-commerce industry.

[0003] Existing e-commerce product traceability systems mostly rely on data recording by a single entity, lacking cross-link data collaboration and consistency verification mechanisms. Traceability data is easily tampered with and forged, resulting in insufficient credibility of traceability records. At the same time, existing systems mostly only realize the simple input and display of product circulation information, making it difficult to use big data technology to conduct in-depth analysis of traceability data. They cannot accurately identify abnormal product characteristics, nor can they effectively link the factors of the entire circulation chain to investigate the causes of anomalies. Consequently, they cannot take targeted risk control and after-sales handling measures, which not only affects the protection of consumer rights but also restricts the standardized and intelligent development of traceability management in the e-commerce industry.

[0004] To address this, the present invention provides an e-commerce product traceability management system based on big data. Summary of the Invention

[0005] In order to overcome the shortcomings of the prior art, at least one technical problem raised in the background art is solved.

[0006] The technical solution adopted by this invention to solve its technical problem is: Trustworthy Analysis Module: Retrieves historical traceability records of e-commerce products from the production end to the consumption end, sorts them into adjacent links according to the natural flow order of production, warehousing, logistics, sales and after-sales, performs consistency verification of hash value and related document number, evaluates the trustworthiness of historical traceability records, and filters out trustworthy historical records with high trustworthiness. Anomaly Attribute Recognition Module: For products corresponding to trusted historical records, quantifies the difference in characteristics among different products and identifies abnormal characteristics among the product characteristics; Analysis and processing module: Based on the abnormal characteristics of the product, obtain the total product circulation time in the e-commerce product traceability process, and perform correlation analysis with the difference in product characteristics to determine whether the total circulation time is the cause of the abnormal characteristics of e-commerce products.

[0007] As a further aspect of the present invention: the process of verifying the consistency between the hash value and the associated document number is as follows: Collect a number of historical traceability records and uniformly enter them into the traceability system built on the e-commerce multi-party alliance chain to construct a traceable dataset; The process is sorted according to the actual flow path of production, warehousing, logistics, sales and after-sales service. The corresponding consortium blockchain block information for each link is extracted. The block header contains the hash value of the previous link, the link identifier and traceability code binding information, and the block body records the operation time, operator and related document number. For any historical traceability record, select any adjacent links to construct a link association pair. After the data of the next link in the link association pair is generated, the hash value of the next link in the link association pair is recorded by the first link block header in the sequence after the next link in the link association pair in the consortium blockchain. If the hash values ​​of the preceding and following links and the associated document number are all consistent in a link association pair, then the corresponding link association pair is recorded as a trusted link association pair; otherwise, the corresponding link association pair is recorded as an untrusted link association pair.

[0008] As a further aspect of the present invention: the process of filtering out highly reliable historical records is as follows: The credibility of historical traceability records is determined by analyzing and processing trusted association pairs. If the credibility of a historical traceability record is greater than or equal to the credibility threshold, the corresponding historical traceability record will be recorded as a credible historical record; otherwise, the corresponding historical traceability record will be recorded as an untrustworthy historical record, and the traceability information will become invalid.

[0009] As a further aspect of the present invention: the process of determining the credibility of historical traceability records is as follows: The credibility of historical traceability records is determined by the percentage of credible association pairs among all links in the historical traceability records.

[0010] As a further aspect of the present invention: the process for obtaining the difference range of the product characteristics is as follows: Extract e-commerce products of the same category corresponding to trusted historical records and obtain the actual feature values ​​of the consumer when receiving the product; The difference between the actual feature value and the preset standard feature value is calculated, and the absolute value is then compared with the preset standard feature value to obtain the difference range of the current product characteristics.

[0011] As a further aspect of the present invention: the process of identifying abnormal characteristics in the product characteristics is as follows: If the difference in product characteristics is greater than or equal to the difference threshold, the corresponding product characteristic will be recorded as an abnormal characteristic.

[0012] As a further aspect of the present invention: the process of obtaining the entire product flow time during the e-commerce product traceability process is as follows: Obtain the warehousing time, logistics time, and pre-sales time, and sum them up to get the total end-to-end processing time.

[0013] As a further aspect of the present invention: the process of obtaining warehousing time, logistics time, and pre-sales time is as follows: From the operation time recorded in the consortium blockchain, extract the product's production completion time, warehousing entry time, warehousing exit time, logistics pickup time, logistics delivery completion time, and sales delivery time. Subtract the warehousing exit time from the warehousing entry time to obtain the warehousing duration. Subtract the logistics delivery completion time from the logistics pickup time to obtain the logistics duration. Subtract the sales delivery time from the logistics delivery completion time to obtain the pre-sales duration.

[0014] As a further aspect of the present invention: the process of determining whether the end-to-end processing time is the cause of abnormal characteristics of e-commerce products is as follows: Correlation analysis was conducted between the total supply chain duration and the differences in product characteristics to identify abnormal correlation values; If the abnormality correlation value is greater than or equal to the abnormality correlation value threshold, then the end-to-end processing time is the cause of the abnormal characteristics of the e-commerce product; otherwise, the end-to-end processing time is not the cause of the abnormal characteristics of the e-commerce product.

[0015] As a further aspect of the present invention: the process of determining the abnormal correlation value is as follows: The abnormal correlation value is calculated by taking the absolute value of the Pearson correlation coefficient formula.

[0016] The beneficial effects of this invention are as follows: 1. This invention relies on consortium blockchain technology to perform dual verification of the hash value and associated document number on the entire product traceability record, accurately filtering out reliable historical records, ensuring the authenticity and reliability of traceability data from the source, and eliminating interference from invalid traceability information; 2. This invention quantifies the difference between the actual characteristics and standard characteristics of a product, enabling precise identification of abnormal product features. By conducting correlation analysis between the entire supply chain duration and abnormal features, the causes of abnormalities are identified, and targeted measures such as suspending outbound inspection and after-sales handling are taken to effectively reduce the risk of delivering defective products. At the same time, all handling actions are recorded in the consortium blockchain, which not only strengthens the e-commerce product quality control capabilities but also improves industry compliance and consumer trust through full-process traceability. Attached Figure Description

[0017] The invention will now be further described with reference to the accompanying drawings.

[0018] Figure 1 This is a system block diagram of the e-commerce product traceability management system based on big data, according to an embodiment of the present invention. Figure 2 This is a flowchart illustrating the steps of the e-commerce product traceability management method based on big data, according to an embodiment of the present invention. Detailed Implementation

[0019] To make the technical means, creative features, objectives and effects of this invention easier to understand, the invention will be further described below in conjunction with specific embodiments.

[0020] Example 1 Please see Figure 1 As shown in the embodiment of the present invention, the e-commerce product traceability management system based on big data includes the following modules: Trustworthy Analysis Module: Retrieves historical traceability records of e-commerce products from the production end to the consumption end, sorts them into adjacent links according to the natural flow order of production, warehousing, logistics, sales and after-sales, performs consistency verification of hash value and related document number, evaluates the trustworthiness of historical traceability records, and filters out trustworthy historical records with high trustworthiness. Collect a number of historical traceability records, which consist of details of product production batches, warehouse entry and exit ledgers, logistics trajectory details, sales order vouchers, after-sales return and exchange records, etc., and uniformly enter them into the traceability system built on the e-commerce multi-party alliance chain to construct a traceable dataset; The process is sorted according to the actual flow path of production, warehousing, logistics, sales and after-sales service. The corresponding consortium blockchain block information for each link is extracted. The block header contains the hash value of the previous link, the link identifier and traceability code binding information. The block body records the operation time, the operator, and the associated document number (order number, logistics waybill number, outbound order). For any historical traceability record, select any adjacent links to construct a link association pair. After the data of the next link in the link association pair is generated, the hash value of the next link in the link association pair is recorded in the first block header of the link association pair in the consortium blockchain. It should be noted that the block header of each stage only records the hash value of the previous stage to anchor the link. When the block of the next stage is generated, its block header will synchronously record the hash value of the current stage. If the hash value of the preceding stage, the hash value of the following stage, and the associated document number are all consistent in a stage association pair, then the corresponding stage association pair is recorded as a trusted association pair. If the hash value of the previous stage and the hash value of the next stage in a stage association pair are inconsistent with the associated document number, then the corresponding stage association pair will be recorded as an untrusted association pair. It should be noted that the following situations are possible when the hash values ​​of the preceding and following stages and the associated document numbers in a stage-related pair are inconsistent: the hash values ​​of the preceding and following stages are the same, but the associated document numbers are different; the hash values ​​of the preceding and following stages are inconsistent, but the associated document numbers are the same; the hash values ​​of the preceding and following stages are inconsistent, but the associated document numbers are different. The credibility of historical traceability records is obtained by statistically analyzing the percentage of credible association pairs among all links in the historical traceability records. A credibility threshold is set. If the credibility of a historical traceability record is greater than or equal to the credibility threshold, the corresponding historical traceability record is recorded as a trusted historical record. If the credibility of a historical traceability record is less than the credibility threshold, the corresponding historical traceability record is recorded as an untrustworthy historical record, and the traceability information becomes invalid. It should be noted that by anchoring the links of each link through the blockchain structure, the immutability and continuity of the traceability records are ensured, providing a reliable data base for subsequent anomaly analysis, distinguishing between credible and untrustworthy historical records and failure scenarios, avoiding the use of false or fragmented traceability data as the basis for subsequent work, reducing the risk of misjudgment, ensuring the seriousness and practicality of the traceability system, and facilitating rapid traceability and accountability in the event of subsequent disputes. Anomaly Attribute Recognition Module: For products corresponding to trusted historical records, quantifies the difference in characteristics among different products and identifies abnormal characteristics among the product characteristics; Extract e-commerce products of the same category corresponding to trusted historical records and obtain the actual feature values ​​of the consumer when receiving the product; The difference between the actual feature value and the preset standard feature value is calculated, and the absolute value is then compared with the preset standard feature value to obtain the difference range of the current product characteristics. It should be noted that the standard feature values ​​were set by those skilled in the art based on historical experience; If the difference in product characteristics is greater than or equal to the difference threshold, the corresponding product characteristic will be recorded as an abnormal characteristic. If the difference in product characteristics is less than the difference threshold, the corresponding product characteristic is recorded as a normal characteristic. For example, the battery health of a digital product is 100% when it leaves the factory, but when the consumer receives it, the battery health is displayed as 85%, with a difference of 15%. If the difference threshold is set to 10%, then the product characteristic is determined to be abnormal. It should be noted that by identifying abnormal characteristics in trusted historical records, interference from untrusted data can be avoided, the accuracy of abnormal characteristic judgment can be improved, and misjudgment of normal products and omission of problematic products can be avoided. Analysis and processing module: Based on the abnormal characteristics of the product, obtain the total product circulation time in the e-commerce product traceability process, and perform correlation analysis with the difference in product characteristics to determine whether the total circulation time is the cause of the abnormal characteristics of e-commerce products. From the operation time recorded in the consortium blockchain, extract the product's production end time, warehousing entry time, warehousing exit time, logistics pickup time, logistics delivery completion time, and sales delivery time. Subtract the warehousing exit time from the warehousing entry time to obtain the warehousing duration. Subtract the logistics delivery completion time from the logistics pickup time to obtain the logistics duration. Subtract the sales delivery time from the logistics delivery completion time to obtain the pre-sales duration. The total time for the entire supply chain is obtained by summing the warehousing time, logistics time, and pre-sales time. Using the Pearson correlation coefficient formula: The absolute value is used to calculate the anomaly correlation value. In the formula, This indicates the quantity of sampled goods, selecting samples of goods from the same category and batch that contain abnormal characteristics. For the first The end-to-end circulation time of a sample product For the first The magnitude of the abnormal characteristics of each sample product; If the abnormal correlation value is greater than or equal to the abnormal correlation value threshold, then the end-to-end processing time is the cause of the abnormal characteristics of e-commerce products. If the abnormal correlation value is less than the abnormal correlation value threshold, then the end-to-end circulation time is not the cause of the abnormal characteristics of e-commerce products. The analysis should then turn to other potential factors, which include, but are not limited to, temperature and humidity. Based on the fact that the end-to-end circulation time is the cause of abnormal characteristics of e-commerce products, and based on the traceability code of the consortium blockchain, all products in the same batch whose end-to-end circulation time exceeds the threshold are investigated. For products that have not been delivered to consumers, the outbound and delivery processes are suspended, and the target characteristics are re-examined. For delivered products, after-sales processing is initiated based on the degree of difference. For products with differences exceeding the safety threshold, recall and replacement are carried out. For products that do not exceed the threshold, an abnormality explanation and compensation plan are provided simultaneously. All processing actions are recorded to the consortium blockchain to ensure traceability. It should be noted that by quantifying the correlation through the Pearson correlation coefficient and formulating a tiered disposal plan based on the correlation analysis results, the risks of e-commerce operations can be reduced while balancing efficiency and compliance. The disposal actions are recorded in the consortium blockchain to strengthen the risk management capabilities of the entire chain and provide data for subsequent optimization of the circulation process, thereby continuously improving the level of e-commerce supply chain management. The technical solution of this invention is as follows: Retrieve historical traceability records of e-commerce products from production to consumption; organize adjacent links into pairs according to the natural flow sequence of production, warehousing, logistics, sales, and after-sales service; verify the consistency of hash values ​​and associated document numbers; assess the credibility of historical traceability records; and select highly credible historical records. For products corresponding to credible historical records, quantify the differences in different product characteristics and identify abnormal characteristics. Based on these abnormal characteristics, obtain the total flow time of the product during the e-commerce product traceability process and perform correlation analysis with the differences in product characteristics to determine whether the total flow time is the cause of abnormal characteristics of e-commerce products. This invention leverages consortium blockchain technology to perform dual verification of the entire product traceability record using hash values ​​and associated document numbers. This accurately filters out reliable historical records, ensuring the authenticity and reliability of traceability data from the source and eliminating interference from invalid traceability information. It quantifies the difference between actual and standard product characteristics, enabling precise identification of abnormal product features. By analyzing the correlation between the entire supply chain duration and abnormal characteristics, it clarifies the causes of anomalies and implements targeted measures such as suspending outbound inspections and after-sales handling, effectively reducing the risk of delivering defective goods. Simultaneously, all actions are recorded on the consortium blockchain, strengthening e-commerce product quality control capabilities and enhancing industry compliance and consumer trust through end-to-end traceability.

[0021] Example 2 Based on the same inventive concept as the big data-based e-commerce product traceability management system in the foregoing embodiments, such as Figure 2 As shown, this application provides a method for e-commerce product traceability management based on big data, wherein the method specifically includes the following steps: Step 1: Retrieve the historical traceability records of e-commerce products from the production end to the consumption end, sort them out into adjacent links according to the natural flow order of production, warehousing, logistics, sales and after-sales, verify the consistency of hash value and related document number, evaluate the credibility of historical traceability records, and select the reliable historical records with high credibility. Step 2: For products corresponding to trusted historical records, quantify the differences in characteristics among different products and identify abnormal characteristics among the product characteristics; Step 3: Based on the abnormal characteristics of the product, obtain the total product circulation time in the e-commerce product traceability process and conduct correlation analysis with the difference in product characteristics to determine whether the total circulation time is the cause of the abnormal characteristics of e-commerce products.

[0022] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A big data-based e-commerce product traceability management system, characterized by: include: Trustworthy Analysis Module: Retrieves historical traceability records of e-commerce products from the production end to the consumption end, sorts them into adjacent links according to the natural flow order of production, warehousing, logistics, sales and after-sales, performs consistency verification of hash value and related document number, evaluates the trustworthiness of historical traceability records, and filters out trustworthy historical records with high trustworthiness. Anomaly Attribute Recognition Module: For products corresponding to trusted historical records, quantifies the difference in characteristics among different products and identifies abnormal characteristics among the product characteristics; Analysis and processing module: Based on the abnormal characteristics of the product, obtain the total product circulation time in the e-commerce product traceability process, and perform correlation analysis with the difference in product characteristics to determine whether the total circulation time is the cause of the abnormal characteristics of e-commerce products.

2. The e-commerce product traceability management system based on big data according to claim 1, characterized in that: The process of verifying the consistency between the hash value and the associated document number is as follows: Collect a number of historical traceability records and uniformly enter them into the traceability system built on the e-commerce multi-party alliance chain to construct a traceable dataset; The process is sorted according to the actual flow path of production, warehousing, logistics, sales and after-sales service. The corresponding consortium blockchain block information for each link is extracted. The block header contains the hash value of the previous link, the link identifier and traceability code binding information, and the block body records the operation time, operator and related document number. For any historical traceability record, select any adjacent links to construct a link association pair. After the data of the next link in the link association pair is generated, the hash value of the next link in the link association pair is recorded by the first link block header in the sequence after the next link in the link association pair in the consortium blockchain. If the hash values ​​of the preceding and following links and the associated document number are all consistent in a link association pair, then the corresponding link association pair is recorded as a trusted link association pair; otherwise, the corresponding link association pair is recorded as an untrusted link association pair.

3. The e-commerce product traceability management system based on big data according to claim 2, characterized in that: The process of filtering out highly reliable historical records is as follows: The credibility of historical traceability records is determined by analyzing and processing trusted association pairs. If the credibility of a historical traceability record is greater than or equal to the credibility threshold, the corresponding historical traceability record will be recorded as a credible historical record; otherwise, the corresponding historical traceability record will be recorded as an untrustworthy historical record, and the traceability information will become invalid.

4. The e-commerce product traceability management system based on big data according to claim 3, characterized in that: The process of determining the credibility of historical traceability records is as follows: The credibility of historical traceability records is determined by the percentage of credible association pairs among all links in the historical traceability records.

5. The e-commerce product traceability management system based on big data according to claim 3, characterized in that: The process for obtaining the difference in the product characteristics is as follows: Extract e-commerce products of the same category corresponding to trusted historical records and obtain the actual feature values ​​of the consumer when receiving the product; The difference between the actual feature value and the preset standard feature value is calculated, and the absolute value is then compared with the preset standard feature value to obtain the difference range of the current product characteristics.

6. The e-commerce product traceability management system based on big data according to claim 5, characterized in that: The process of identifying abnormal characteristics in product features is as follows: If the difference in product characteristics is greater than or equal to the difference threshold, the corresponding product characteristic will be recorded as an abnormal characteristic.

7. The e-commerce product traceability management system based on big data according to claim 1, characterized in that: The process of obtaining the entire product circulation time in the e-commerce product traceability process is as follows: Obtain the warehousing time, logistics time, and pre-sales time, and sum them up to get the total end-to-end processing time.

8. The e-commerce product traceability management system based on big data according to claim 7, characterized in that: The process of obtaining warehousing time, logistics time, and pre-sales time is as follows: From the operation time recorded in the consortium blockchain, extract the product's production completion time, warehousing entry time, warehousing exit time, logistics pickup time, logistics delivery completion time, and sales delivery time. Subtract the warehousing exit time from the warehousing entry time to obtain the warehousing duration. Subtract the logistics delivery completion time from the logistics pickup time to obtain the logistics duration. Subtract the sales delivery time from the logistics delivery completion time to obtain the pre-sales duration.

9. The e-commerce product traceability management system based on big data according to claim 7, characterized in that: The process of determining whether the end-to-end processing time is the cause of abnormal characteristics of e-commerce products is as follows: Correlation analysis was conducted between the total supply chain duration and the differences in product characteristics to identify abnormal correlation values; If the abnormality correlation value is greater than or equal to the abnormality correlation value threshold, then the end-to-end processing time is the cause of the abnormal characteristics of the e-commerce product; otherwise, the end-to-end processing time is not the cause of the abnormal characteristics of the e-commerce product.

10. The e-commerce product traceability management system based on big data according to claim 9, characterized in that: The process for determining the abnormal correlation value is as follows: The abnormal correlation value is calculated by taking the absolute value of the Pearson correlation coefficient formula.

Images