Blockchain-based anti-counterfeiting marketing method and system for commodities

Abstract

The application relates to the technical field of blockchains, and relates to a commodity anti-counterfeiting marketing method and system based on a blockchain, which comprises the following steps: obtaining a target commodity, confirming commodity unique codes and commodity key information based on the target commodity, performing abstract operation on the commodity unique codes to obtain a digital identity hash value, binding the digital identity hash value with the commodity key information to obtain first binding information, writing the first binding information into a pre-constructed blockchain distributed ledger to obtain commodity evidence data, confirming a user preference feature vector based on a code scanning time in interaction behavior data, a code scanning frequency in the interaction behavior data, a stay duration in the interaction behavior data, an interface clicking behavior in the interaction behavior data and consumer regional information in the interaction behavior data, confirming target marketing content based on a user preference label, and completing commodity anti-counterfeiting marketing. The application can improve the anti-counterfeiting reliability and authenticity identification accuracy of commodities.

Description

Technical Field

[0001] This invention relates to the field of blockchain technology, and in particular to a blockchain-based method and system for anti-counterfeiting marketing of goods. Background Technology

[0002] With the accelerated development of the digital economy, product traceability, anti-counterfeiting, and digital marketing have gradually become important means of corporate competition.

[0003] Currently, mainstream anti-counterfeiting and marketing methods mainly include QR code traceability, serial number verification, RFID tag identification, and dedicated anti-counterfeiting labels. In recent years, some companies have also adopted centralized servers to record product circulation information, allowing consumers to obtain information such as the product's production batch, distribution points, and promotional activities pushed by the brand after scanning the code.

[0004] While the above methods can achieve product anti-counterfeiting and marketing, traditional QR codes and serial numbers are easily copied, forged, or cloned in batches. Centralized servers are more likely to be tampered with, resulting in low reliability of anti-counterfeiting measures. Product information is mostly stored in databases built by enterprises themselves, lacking a public, credible, and tamper-proof mechanism, making it difficult for consumers to verify the authenticity of the data. Therefore, how to improve the reliability of product anti-counterfeiting measures and the accuracy of authenticity identification has become an urgent problem to be solved. Summary of the Invention

[0005] This invention provides a blockchain-based anti-counterfeiting marketing method and a computer-readable storage medium, the main purpose of which is to improve the reliability of anti-counterfeiting measures and the accuracy of authenticity identification of products.

[0006] To achieve the above objectives, this invention provides a blockchain-based anti-counterfeiting marketing method, comprising:

[0007] Obtain the target product and, based on the target product, identify its unique code and key information.

[0008] Perform a digest operation on the unique product code to obtain the digital identity hash value;

[0009] The digital identity hash value is bound to key product information to obtain the first binding information;

[0010] Write the first binding information into a pre-built blockchain distributed ledger to obtain product evidence data;

[0011] The QR code label is identified based on the digital identity hash value, and the QR code label is physically bound to the target product to obtain the labeled product;

[0012] Receive a scan request, and confirm the product's evidence data based on the scan request and the product label;

[0013] A visual display interface was created based on the product's certificate data.

[0014] The interactive behavior data of the visual display interface is collected by using pre-built tracking technology. The interactive behavior data includes: scanning time, scanning frequency, dwell time, interface click behavior and consumer geographic information.

[0015] Based on the scanning time, scanning frequency, dwell time, interface click behavior, and consumer geographic information in the interaction behavior data, a user preference feature vector is identified.

[0016] The user preference feature vector is analyzed using a pre-built user preference analysis model to obtain user preference labels;

[0017] Based on user preference tags, target marketing content is identified, and anti-counterfeiting marketing of products is completed.

[0018] Optionally, the step of performing a digest operation on the unique product code to obtain a digital identity hash value includes:

[0019] Obtain product production batch information, perform standard processing on the product production batch information, and obtain processed batch information;

[0020] Perform a hash operation on the batch information to obtain the batch hash value;

[0021] Once the hash timestamp is identified, the unique product code, batch hash value, and hash timestamp are concatenated to obtain the concatenated information.

[0022] Salt values ​​are added to the spliced ​​information to obtain security processing information;

[0023] Perform a hash operation on the security processing information to obtain preliminary hash information;

[0024] Perform a hash digest operation on the initial hash information to obtain the digital identity hash value.

[0025] Optionally, the step of adding a salt value to the spliced ​​information to obtain security processing information includes:

[0026] Obtain environmental parameters, including: system timestamp, network latency, and geolocation code;

[0027] Obtain device fingerprint information, which includes: processor identifier, browser fingerprint code, and communication module identifier;

[0028] A multidimensional feature vector is constructed based on the system timestamp, network latency, geolocation code, processor identifier, browser fingerprint code, and communication module identifier in the environmental parameters;

[0029] The salt value weight vector is determined based on the multidimensional feature vector;

[0030] Dynamic salt values ​​are generated based on multidimensional feature vectors and salt weight vectors.

[0031] Based on the splicing information and dynamic salt values, multiple salt value fragments and multiple insertion points were identified.

[0032] Multiple salt value fragments are inserted into the splicing information at multiple insertion points to obtain salted spliced ​​data;

[0033] Perturb the spliced ​​data from multiple salted segments to obtain security processing information.

[0034] Optionally, determining the salt value weight vector based on the multi-dimensional feature vector includes:

[0035] Acquire multiple sets of historical data, including historical environmental parameters and historical device fingerprint information. The historical environmental parameters include historical system timestamps, historical network latency, and historical geolocation codes. The historical device fingerprint information includes historical processor identifiers, historical browser fingerprint codes, and historical communication module identifiers.

[0036] Perform the following operation on each of the multiple sets of historical data:

[0037] Historical multidimensional feature vectors were identified based on historical system timestamps, historical network latency, historical geolocation codes, historical processor identifiers, historical browser fingerprint codes, and historical communication module identifiers from historical environmental parameters in historical data.

[0038] By summarizing the historical multidimensional feature vectors, we obtain the historical multidimensional feature vector set;

[0039] A salt value weighting model was identified based on a historical multidimensional feature vector set.

[0040] The salt weighting model is used to analyze the multidimensional feature vectors to obtain the salt weighting vector.

[0041] Optionally, the step of determining the salt value weight model based on the historical multidimensional feature vector set includes:

[0042] The historical multidimensional feature vector set is sampled to obtain the training vector set, which includes: A historical multidimensional feature vector;

[0043] based on The historical multidimensional feature vectors confirm that Each salt value weight vector corresponds one-to-one with the historical multidimensional feature vectors.

[0044] Based on the training vector set A historical multidimensional feature vector, The salt value weight vector and the pre-constructed weight model confirm the first model;

[0045] The training vector set is removed from the historical multidimensional feature vector set to obtain the updated historical multidimensional feature vector set;

[0046] The number of vectors in the updated historical multidimensional feature vector set is determined, where the number of vectors is the number of historical multidimensional feature vectors in the updated historical multidimensional feature vector set.

[0047] Compare the number of vectors with a preset threshold. If the number of vectors is greater than the threshold, update the historical multidimensional feature vector set as the historical multidimensional feature vector set, use the first model as the weight model, and return to the step of sampling the historical multidimensional feature vector set until the number of vectors is less than or equal to the threshold. Then, use the first model as the salt value weight model.

[0048] Optionally, the step of identifying multiple salt value segments and multiple insertion points based on splicing information and dynamic salt values ​​includes:

[0049] Obtain the total length of the splicing information, and calculate the baseline segment length based on the total data length and the preset number of target segments;

[0050] Multiple insertion points were identified based on the baseline segment length and the total data length.

[0051] The dynamic salt value is segmented based on the baseline segment length to obtain multiple initial salt value segments;

[0052] For each of the multiple initial salt value segments, perform the following operation:

[0053] Extract the first and last characters from the initial salt value segment;

[0054] Perform an XOR operation between the first character and the last character to obtain the basic perturbation value;

[0055] The length adjustment amount is obtained by performing a modulo operation between the basic disturbance value and the preset adjustment modulus;

[0056] Based on the length adjustment amount, the initial salinity fragment is length-adjusted to obtain the salinity fragment;

[0057] Summarize the salinity fragments to obtain multiple salinity fragments.

[0058] Optionally, the perturbation of multiple salted spliced ​​data segments to obtain security processing information includes:

[0059] Feature extraction is performed on the concatenated data with salts to obtain field length features, data entropy features, fragment distribution features, total number of characters in the data, and character data, where the character data includes multiple characters.

[0060] The first splicing factor is obtained by concatenating the field length feature, data entropy value feature, and fragment distribution feature.

[0061] Perform a hash operation on the first concatenation factor to obtain the structural feature perturbation factor;

[0062] The digit flip rate is calculated based on the character data and the total number of characters in the data. The calculation formula is as follows:

[0063] ,

[0064] in, Indicates the digit flip rate. Indicates the total number of characters in the data. This represents the first character among multiple characters in character data. One character, This represents the first character among multiple characters in character data. One character, Represents a counting function;

[0065] The character change gradient is calculated based on the total number of characters and the character data. The calculation formula is as follows:

[0066] ,

[0067] in, Represents the gradient of character changes. Indicates taking the absolute value;

[0068] The second concatenation factor is obtained by concatenating the digit flip rate and the character change gradient.

[0069] Perform a hash operation on the second concatenation factor to obtain the associated feature perturbation factor;

[0070] Get the latest hash low-order block and the current cumulative number of transactions on the chain;

[0071] Determine if the current cumulative number of transactions on the chain is odd. If the current cumulative number of transactions on the chain is not odd, then use the preset zero value as the exponent of the cumulative number of transactions.

[0072] If the current cumulative number of transactions on the chain is odd, then the preset single value will be used as the cumulative transaction number index.

[0073] The third concatenation factor is obtained by concatenating the latest hash low-order block with the cumulative transaction count index.

[0074] Perform a hash operation on the third concatenation factor to obtain the on-chain dynamic perturbation factor;

[0075] The structural feature perturbation factor, the correlation feature perturbation factor, and the on-chain dynamic perturbation factor are concatenated to obtain the fourth concatenation factor.

[0076] Perform a hash operation on the fourth concatenation factor to obtain the final perturbation factor;

[0077] Once the perturbation timestamp is identified, the perturbation timestamp, the final perturbation factor, and the multiple salted data segments are concatenated to obtain the perturbation data.

[0078] The perturbation data is hashed to obtain security processing information.

[0079] Optionally, the step of using pre-built tracking technology to collect interactive behavior data from the visual display interface to obtain interactive behavior data includes:

[0080] The visualization interface is pre-embedded using the event tracking technology to obtain the event tracking interface and the event tracking collector. The event tracking collector includes: page lifecycle collector, touch event collector and geographic information collector.

[0081] The page lifecycle collector is used to collect information from the event tracking interface, including scanning time, interface dwell time, and interface exit time.

[0082] The touch event collector is used to monitor the embedded interface and obtain the click coordinate sequence and control identifier;

[0083] The location of consumers can be obtained by using a geographic information collector to capture the location of the embedded interface.

[0084] The scanning time, screen dwell time, screen exit time, click coordinate sequence, control identifiers, and consumer geographic information are packaged to obtain an interactive behavior data package.

[0085] The interaction behavior data is obtained by parsing and storing the interaction behavior data packets using a pre-built data receiving server.

[0086] Optionally, the step of determining the user preference feature vector based on the scanning time, scanning frequency, dwell time, interface click behavior, and consumer geographic information in the interaction behavior data includes:

[0087] Time features are extracted from the scanning time in the interactive behavior data to obtain a time period feature vector;

[0088] Statistical processing is performed on the scanning frequency in the interactive behavior data to obtain a frequency statistical feature vector;

[0089] The dwell time in the interaction behavior data is segmented to obtain the duration distribution feature vector;

[0090] Behavioral analysis is performed on interface click behavior in interactive behavior data to obtain click behavior feature vectors;

[0091] Geographically encode the consumer geographic information in the interaction behavior data to obtain a geographic feature vector;

[0092] Based on the time period feature vector, frequency statistics feature vector, duration distribution feature vector, click behavior feature vector, and regional feature vector, the weights of the time period feature, frequency statistics feature, duration distribution feature, click behavior feature, and regional feature are determined.

[0093] Construct a user preference feature vector based on the time period feature vector, frequency statistics feature vector, duration distribution feature vector, click behavior feature vector, geographic feature vector, time period feature weight, frequency statistics feature weight, duration distribution feature weight, click behavior feature weight, and geographic feature weight.

[0094] To achieve the above objectives, the present invention also provides a blockchain-based anti-counterfeiting marketing system, comprising:

[0095] The evidence storage data acquisition module is used to acquire the target product, confirm the unique code and key information of the product based on the target product, perform a digest operation on the unique code of the product to obtain the digital identity hash value, bind the digital identity hash value with the key information of the product to obtain the first binding information, and write the first binding information into the pre-built blockchain distributed ledger to obtain the product evidence storage data.

[0096] The display interface confirmation module is used to confirm the QR code label based on the digital identity hash value, and physically bind the QR code label to the target product to obtain the labeled product. It receives the scanning request, confirms the product storage data based on the scanning request and the labeled product, and confirms the visual display interface based on the product storage data.

[0097] The preference vector calculation module is used to collect interactive behaviors from the visual display interface using pre-built tracking technology to obtain interactive behavior data. The interactive behavior data includes: scanning time, scanning frequency, dwell time, interface click behavior, and consumer geographic information. Based on the scanning time, scanning frequency, dwell time, interface click behavior, and consumer geographic information in the interactive behavior data, the user preference feature vector is determined.

[0098] The anti-counterfeiting marketing strategy module is used to analyze user preference feature vectors using a pre-built user preference analysis model, obtain user preference tags, identify target marketing content based on user preference tags, and complete product anti-counterfeiting marketing.

[0099] To address the above problems, the present invention also provides an electronic device, the electronic device comprising:

[0100] A memory that stores at least one instruction; and a processor that executes the instructions stored in the memory to implement the blockchain-based anti-counterfeiting marketing method described above.

[0101] To address the aforementioned issues, the present invention also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in an electronic device to implement the aforementioned blockchain-based anti-counterfeiting marketing method.

[0102] To address the problems described in the background art, this invention obtains a target product, identifies its unique code and key information, and establishes a unique digital identity for the product, linking it to its core attributes to form a data foundation for anti-counterfeiting and marketing. Then, a digest operation is performed on the unique product code to obtain a digital identity hash value. This invention utilizes a cryptographic hash function to transform the product identifier into an irreversible unique digital fingerprint, ensuring the immutability and uniqueness of the identity information. The digital identity hash value is then bound to the key product information to obtain the first binding information. Thus, this invention constructs a complete digital twin by strongly linking the product's digital identity to its physical attributes, providing a complete digital twin for the entire supply chain. This provides a basis for traceability, improving the anti-counterfeiting reliability and authenticity identification accuracy of goods. The first binding information is written into a pre-built blockchain distributed ledger to obtain product evidence data. It is evident that this embodiment of the invention, by leveraging the distributed storage and consensus mechanism of blockchain, achieves permanent, transparent, and tamper-proof evidence storage of product information, establishing a reliable traceability foundation. Based on the digital identity hash value, a QR code label is confirmed, and the QR code label is physically bound to the target product to obtain a labeled product. This embodiment of the invention, by attaching a digital identity to a product with a conveniently identifiable physical carrier, opens up a connection channel between offline entities and online data. It receives scanning requests and, based on the scanning request and the labeled product, confirms the product evidence data. This embodiment of the invention... By responding to consumers' scanning behavior, the system retrieves and verifies product information from the blockchain network in real time, completing the anti-counterfeiting authentication process. This improves the reliability of anti-counterfeiting measures and the accuracy of authenticity identification. A visual display interface is then established based on the product's stored evidence data. This embodiment of the invention transforms on-chain evidence data into intuitive and user-friendly front-end display content, enhancing consumers' information access experience and trust. Pre-built tracking technology is used to collect interactive behavior data from the visual display interface, including scanning time, scanning frequency, dwell time, interface click behavior, and consumer geographic information. This embodiment of the invention seamlessly collects multi-dimensional user behavior data during the anti-counterfeiting query process, enabling consumer insights and precise marketing. Providing authentic and abundant analytical materials improves the reliability of product anti-counterfeiting and the accuracy of authenticity identification. Based on scanning time, scanning frequency, dwell time, interface click behavior, and consumer geographic information from interaction behavior data, user preference feature vectors are identified. This invention quantifies multi-dimensional behavioral data into structured feature vectors, accurately depicting user interests and consumption potential. A pre-built user preference analysis model is used to analyze the user preference feature vectors, resulting in user preference tags. This invention achieves intelligent and refined segmentation of user groups by applying machine learning models for in-depth mining and classification of feature vectors.Based on user preference tags, the target marketing content is identified, and product anti-counterfeiting marketing is completed. It is evident that this embodiment of the invention transforms the anti-counterfeiting query scenario into an efficient marketing touchpoint by simultaneously pushing customized marketing information to users while completing anti-counterfeiting verification. This achieves the dual value of anti-counterfeiting and promotion, improving the reliability of product anti-counterfeiting and the accuracy of authenticity identification. Therefore, this invention can improve the reliability of product anti-counterfeiting and the accuracy of authenticity identification. Attached Figure Description

[0103] Figure 1 A schematic flowchart of a blockchain-based anti-counterfeiting marketing method for goods provided in an embodiment of the present invention;

[0104] Figure 2 A functional module diagram of a blockchain-based anti-counterfeiting marketing system provided in an embodiment of the present invention;

[0105] Figure 3 This is a schematic diagram of the structure of an electronic device that implements the blockchain-based anti-counterfeiting marketing method for goods, according to an embodiment of the present invention.

[0106] Explanation of reference numerals in the attached figures:

[0107] 10. Electronic device; 11. Processor; 12. Memory; 13. Bus.

[0108] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0109] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0110] This application provides a blockchain-based anti-counterfeiting marketing method for goods. The executing entity of the blockchain-based anti-counterfeiting marketing method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the blockchain-based anti-counterfeiting marketing method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0111] Reference Figure 1 The diagram shown is a flowchart illustrating a blockchain-based anti-counterfeiting marketing method according to an embodiment of the present invention. In this embodiment, the blockchain-based anti-counterfeiting marketing method includes:

[0112] S1. Obtain the target product and identify its unique code and key information based on it.

[0113] For example, Xiao Zhang is an employee of a product marketing company. He needs to implement anti-counterfeiting measures for a certain product and market it. Therefore, Xiao Zhang obtains the target product, its barcode, production serial number, product photo, production time, production batch number, and distributor information. The target product refers to the product for which anti-counterfeiting marketing is required. The product barcode is the product's unique code, and the production serial number, product photo, production time, production batch number, and distributor information are the product's key information. The product photo refers to a photograph of the target product, and the production time refers to the time the target product was produced in the factory.

[0114] S2. Perform a digest operation on the unique code of the product to obtain the digital identity hash value, and bind the digital identity hash value with the key information of the product to obtain the first binding information.

[0115] In detail, the process of performing a digest operation on the unique product code to obtain a digital identity hash value includes:

[0116] Obtain product production batch information, perform standard processing on the product production batch information, and obtain processed batch information;

[0117] Perform a hash operation on the batch information to obtain the batch hash value;

[0118] Once the hash timestamp is identified, the unique product code, batch hash value, and hash timestamp are concatenated to obtain the concatenated information.

[0119] Salt values ​​are added to the spliced ​​information to obtain security processing information;

[0120] Perform a hash operation on the security processing information to obtain preliminary hash information;

[0121] Perform a hash digest operation on the initial hash information to obtain the digital identity hash value.

[0122] It should be explained that product production batch information refers to information related to the batch in which the target product was produced. For example, product production information might be: Production Date: November 24, 2025, 11:11:11 AM; Shelf Life: 6 months; Production Quantity: 500 units. Standardizing the product production batch information means organizing it into a uniform format. For instance, if the product production information is: Production Date: November 24, 2025, 11:11:11 AM; Shelf Life: 6 months; Production Quantity: 500 units, then after standardizing the product production batch information, the processed batch information would be 2025-11-24T11:11:11,180,500. Processed batch information refers to the standardized product production batch information. Performing a hash operation on the processed batch information means using a preliminary algorithm to process the processed batch information, thereby generating a fixed-length string related to the processed batch information. Optionally, MD4 can be used as the preliminary algorithm. The fixed-length string related to the batch processing information is the batch hash value. The hash timestamp refers to the total number of seconds from 08:00:00 Beijing time on January 1, 1970, to the moment the hash timestamp is confirmed. For example, if the confirmed hash timestamp is 11:11:11 Beijing time on November 24, 2025, then the hash timestamp is 1763965871.

[0123] For example, if the product unique code is 6901234567892, the batch hash value is d41d8cd98f00b204e9800998ecf8427e, and the hash timestamp is 1763965871, then concatenating the product unique code, batch hash value, and hash timestamp will result in the concatenated information: 6901234567892d41d8cd98f00b204e9800998ecf84271763965871.

[0124] It should be understood that the secure processing information refers to the concatenated information after salting. The method for hashing the secure processing information is the same as the method for hashing the batch processing information, and will not be repeated here. The preliminary hash information refers to the secure processing information after hashing. The hash digest operation on the preliminary hash information refers to processing the preliminary hash information using an intermediate algorithm to obtain a fixed-length string related to the preliminary hash information. Optionally, MD5 is used as the intermediate algorithm, and the fixed-length string related to the preliminary hash information is the digital identity hash value.

[0125] Specifically, the process of adding a salt value to the spliced ​​information to obtain secure processing information includes:

[0126] Obtain environmental parameters, including: system timestamp, network latency, and geolocation code;

[0127] Obtain device fingerprint information, which includes: processor identifier, browser fingerprint code, and communication module identifier;

[0128] A multi-dimensional feature vector is constructed based on the system timestamp, network latency, geolocation code, processor identifier, browser fingerprint, and communication module identifier in the environmental parameters. The multi-dimensional feature vector is shown below:

[0129] ,

[0130] in, Represents a multidimensional feature vector. This represents the system timestamp in the environment parameters. This indicates network latency in the environmental parameters. This indicates the geographic location code in the environmental parameters. This indicates the processor identifier in the device fingerprint information. This refers to the browser's fingerprint code within the device's fingerprint information. This indicates the communication module identifier in the device fingerprint information;

[0131] The salt value weight vector is determined based on the multidimensional feature vector;

[0132] Dynamic salt values ​​are generated based on multidimensional feature vectors and salt weight vectors, as shown below:

[0133] ,

[0134] in, Indicates dynamic salt value, Represents a hash function. Represents the salt weight vector. Indicates a splicing operation;

[0135] Based on the splicing information and dynamic salt values, multiple salt value fragments and multiple insertion points were identified.

[0136] Multiple salt value fragments are inserted into the splicing information at multiple insertion points to obtain salted spliced ​​data;

[0137] Perturb the spliced ​​data from multiple salted segments to obtain security processing information.

[0138] It should be explained that environmental parameters refer to parameters related to the operating environment in which the salting operation is performed. These parameters include: system timestamp, network latency, and geolocation code. The system timestamp is the timestamp at the moment the salting operation is performed. Network latency is the round-trip time between the device performing the salting operation and the reference server (such as a time server or authentication server). The geolocation code is the digital code indicating the physical location of the device performing the salting operation. Device fingerprint information refers to information related to the device performing the salting operation. This includes: processor identifier, browser fingerprint code, and communication module identifier. The processor identifier is the CPU model of the device performing the salting operation. The browser fingerprint code is a digital digest generated based on the browser characteristics of the device performing the salting operation. The communication module identifier is the MAC address of the network communication hardware in the device performing the salting operation. Inserting multiple salt value fragments into the concatenated information at multiple insertion points means sequentially inserting multiple salt value fragments into the concatenated information according to their corresponding insertion points. The salted concatenated data refers to the concatenated information with multiple salt value fragments inserted. Multidimensional feature vectors are vectors used to characterize environmental parameters and device fingerprint information.

[0139] Specifically, the determination of the salt value weight vector based on the multi-dimensional feature vector includes:

[0140] Acquire multiple sets of historical data, including historical environmental parameters and historical device fingerprint information. The historical environmental parameters include historical system timestamps, historical network latency, and historical geolocation codes. The historical device fingerprint information includes historical processor identifiers, historical browser fingerprint codes, and historical communication module identifiers.

[0141] Perform the following operation on each of the multiple sets of historical data:

[0142] Historical multidimensional feature vectors were identified based on historical system timestamps, historical network latency, historical geolocation codes, historical processor identifiers, historical browser fingerprint codes, and historical communication module identifiers from historical environmental parameters in historical data.

[0143] By summarizing the historical multidimensional feature vectors, we obtain the historical multidimensional feature vector set;

[0144] A salt value weighting model was identified based on a historical multidimensional feature vector set.

[0145] The salt weighting model is used to analyze the multidimensional feature vectors to obtain the salt weighting vector.

[0146] It should be explained that historical data refers to data recorded in the past when salting operations were performed. Historical data includes: historical environmental parameters and historical device fingerprint information. Among them, historical environmental parameters refer to parameters related to the operating environment in which the salting operation was performed, which are recorded in the past. Historical environmental parameters include: historical system timestamp, historical network latency, and historical geolocation code. The historical system timestamp refers to the timestamp of the moment when the salting operation was performed, the historical network latency refers to the round-trip time between the device performing the salting operation and the reference server (such as a time server or authentication server), which is recorded in the past. The historical geolocation code refers to the digital code of the physical location of the device performing the salting operation, which is recorded in the past. Historical device fingerprint information refers to information recorded historically related to devices that performed salting operations. This information includes: historical processor identifier, historical browser fingerprint code, and historical communication module identifier. The historical processor identifier refers to the CPU model of the device that historically performed the salting operation. The historical browser fingerprint code is a digital digest generated based on the browser characteristics of the device that performed the salting operation. The historical communication module identifier is the MAC address of the network communication hardware in the device that historically performed the salting operation. The historical multidimensional feature vector set is a collection of multiple historical multidimensional feature vectors. These vectors characterize historical environmental parameters and historical device fingerprint information.

[0147] It should be understood that the method for identifying historical multidimensional feature vectors based on historical system timestamps, historical network latency, historical geolocation codes, historical processor identifiers, historical browser fingerprints, and historical communication module identifiers in historical environmental parameters from historical data is the same as the method for constructing multidimensional feature vectors based on system timestamps, network latency, geographical location codes, processor identifiers, browser fingerprints, and communication module identifiers in environmental parameters, and will not be elaborated further here.

[0148] It is understood that the analysis of multidimensional feature vectors using the salt value weight model refers to: inputting the multidimensional feature vectors into the salt value weight model, and using the salt value weight model to analyze and obtain the salt value weight vector. The salt value weight vector is a vector used to characterize the weight ratio of each component element in the multidimensional feature vector during the dynamic salt value generation process. For detailed steps of analyzing and obtaining the salt value weight vector using the salt value weight model, please refer to the following embodiments.

[0149] In detail, the salt value weighting model determined based on the historical multidimensional feature vector set includes:

[0150] The historical multidimensional feature vector set is sampled to obtain the training vector set, which includes: A historical multidimensional feature vector;

[0151] based on The historical multidimensional feature vectors confirm that Each salt value weight vector corresponds one-to-one with the historical multidimensional feature vectors.

[0152] Based on the training vector set A historical multidimensional feature vector, The salt value weight vector and the pre-constructed weight model confirm the first model;

[0153] The training vector set is removed from the historical multidimensional feature vector set to obtain the updated historical multidimensional feature vector set;

[0154] The number of vectors in the updated historical multidimensional feature vector set is determined, where the number of vectors is the number of historical multidimensional feature vectors in the updated historical multidimensional feature vector set.

[0155] Compare the number of vectors with a preset threshold. If the number of vectors is greater than the threshold, update the historical multidimensional feature vector set as the historical multidimensional feature vector set, use the first model as the weight model, and return to the step of sampling the historical multidimensional feature vector set until the number of vectors is less than or equal to the threshold. Then, use the first model as the salt value weight model.

[0156] It should be explained that sampling the historical multidimensional feature vector set refers to randomly sampling the historical multidimensional feature vector set, and the training vector set refers to the set obtained after sampling the historical multidimensional feature vector set. The phrase "based on..." The historical multidimensional feature vectors confirm that Each salt value weight vector refers to: [the following is a list of weights] For each historical multidimensional feature vector, the following operation is performed: The historical multidimensional feature vector is input into a preset salt value weight calculation model to obtain the salt value weight vector corresponding to that historical multidimensional feature vector. Finally, the salt value weight vectors are summed to obtain... A salt value weight vector. The salt value weight calculation model operates as follows: First, the multi-dimensional feature vectors are normalized to obtain normalized feature vectors. Then, based on the normalized feature vectors, the correlation index between each feature dimension and historical salt value changes is calculated to obtain a feature correlation vector. Next, the importance of each feature dimension is quantized and mapped according to the feature correlation vector to obtain a feature contribution vector. Finally, a salt value weight vector consistent with the input dimensions is generated based on the feature contribution vector. The above is based on the training vector set... A historical multidimensional feature vector, The salt weight vectors and the pre-constructed weight model confirm that the first model refers to: utilizing the salt weight vectors in the training vector set... Historical multidimensional feature vectors and The first model is obtained by training a weight model using salt value weight vectors. This weight model is essentially a supervised learning-based regression model, employing a convolutional neural network as its basic structure. It learns the mapping relationship between historical multidimensional feature vectors and their corresponding salt value weight vectors through training. During training, the model takes historical multidimensional feature vectors as input and their corresponding salt value weight vectors as output. A loss function (such as mean squared error) is used to calculate the difference between the predicted and actual results. Backpropagation and gradient descent are used to continuously update the network parameters, enabling the model to automatically extract key patterns from the feature vectors and output corresponding weights. In the usage phase, the multidimensional feature vector to be processed is input into the trained convolutional neural network. After calculations through convolutional layers, activation functions, and fully connected layers, the network outputs a weight vector corresponding to the multidimensional feature vector. This weight vector is the salt value weight vector. The first model refers to the model that utilizes the salt value weight vector from the training vector set. Historical multidimensional feature vectors and The weighted model is trained using 10 salt-weighted vectors. The quantity threshold is a value set manually by the staff of the product marketing company; it is optional, with a quantity threshold of 3. The salt-weighted model refers to the first model trained when the number of vectors is less than or equal to the quantity threshold.

[0157] For example, if the historical multidimensional feature vector set is C1, C2, C3, C4, C5, and the training vector set is C2, C3, then the updated historical multidimensional feature vector set obtained after training the vector set from the historical multidimensional feature vector set is C1, C4, C5.

[0158] Specifically, the identification of multiple salt value fragments and multiple insertion points based on splicing information and dynamic salt values ​​includes:

[0159] Obtain the total length of the splicing information, and calculate the baseline segment length based on the total data length and the preset number of target segments;

[0160] Multiple insertion points were identified based on the baseline segment length and the total data length.

[0161] The dynamic salt value is segmented based on the baseline segment length to obtain multiple initial salt value segments;

[0162] For each of the multiple initial salt value segments, perform the following operation:

[0163] Extract the first and last characters from the initial salt value segment;

[0164] Perform an XOR operation between the first character and the last character to obtain the basic perturbation value;

[0165] The length adjustment amount is obtained by performing a modulo operation between the basic disturbance value and the preset adjustment modulus;

[0166] Based on the length adjustment amount, the initial salinity fragment is length-adjusted to obtain the salinity fragment;

[0167] Summarize the salinity fragments to obtain multiple salinity fragments.

[0168] It should be explained that the total data length refers to the number of characters contained in the concatenated information, and the formula for calculating the baseline segment length is as follows: ,in, Indicates the reference segment length. Indicates the total length of the data. Indicates the number of target segments. This indicates rounding down. The target number of segments is a value manually set by the marketing company's staff based on the total length of the spliced ​​information. For example, if the total length of the spliced ​​information is less than or equal to 128, the target number of segments is 3; if the total length of the spliced ​​information is greater than 128 but less than or equal to 512, the target number of segments is 5; and if the total length of the spliced ​​information is greater than or equal to 512, the target number of segments is 8.

[0169] For example, if the total length of the data is 256 characters and the baseline segment length is 64 characters, then the multiple insertion points determined based on the baseline segment length and the total length of the data are: the 64th character, the 128th character, the 192nd character, and the 256th character.

[0170] Understandably, segmenting the dynamic salt value based on the baseline segment length means: using the baseline segment length as the step size, starting from the position of the first character of the dynamic salt value, sequentially slicing it into fixed-length segments, continuously segmenting the dynamic salt value until all dynamic salt values ​​are segmented. The initial salt value segment refers to the segmented dynamic salt value.

[0171] For example, if the initial salt value fragment is: ss11234fdsaasdf12341, then the first character extracted from the initial salt value fragment is 's' and the last character is '1'.

[0172] It should be understood that the XOR operation between the first and last characters refers to: converting the first and last characters into their corresponding character codes, performing an XOR operation on the two character codes, and obtaining the calculation result, which is the basic perturbation value. The modulo operation between the basic perturbation value and the preset adjustment modulus refers to using the basic perturbation value as the dividend and the adjustment modulus as the divisor, performing a modulo operation, and obtaining the remainder after dividing the basic perturbation value by the adjustment modulus. The remainder after dividing the basic perturbation value by the adjustment modulus is the length adjustment amount. The length adjustment of the initial salt value segment based on the length adjustment amount refers to: performing a corresponding length change operation on the initial salt value segment according to the magnitude of the length adjustment amount: when the length adjustment amount is greater than zero, appending a corresponding number of random characters to the end of the initial salt value segment to increase the segment length; when the length adjustment amount is zero, the initial salt value segment remains unchanged. The adjustment modulus is a value manually set by the marketing company's staff based on the required anti-counterfeiting level of the product. For example, if the required anti-counterfeiting level is high, the adjustment modulus is 5; if the required anti-counterfeiting level is medium, the adjustment modulus is 4; and if the required anti-counterfeiting level is low, the adjustment modulus is 3. The salt value segment refers to the initial salt value segment after length adjustment.

[0173] Specifically, the process of perturbing multiple segments of salted spliced ​​data to obtain security processing information includes:

[0174] Feature extraction is performed on the concatenated data with salts to obtain field length features, data entropy features, fragment distribution features, total number of characters in the data, and character data, where the character data includes multiple characters.

[0175] The first splicing factor is obtained by concatenating the field length feature, data entropy value feature, and fragment distribution feature.

[0176] Perform a hash operation on the first concatenation factor to obtain the structural feature perturbation factor;

[0177] The digit flip rate is calculated based on the character data and the total number of characters in the data. The calculation formula is as follows:

[0178] ,

[0179] in, Indicates the digit flip rate. Indicates the total number of characters in the data. This represents the first character among multiple characters in character data. One character, This represents the first character among multiple characters in character data. One character, Represents a counting function;

[0180] The character change gradient is calculated based on the total number of characters and the character data. The calculation formula is as follows:

[0181] ,

[0182] in, Represents the gradient of character changes. Indicates taking the absolute value;

[0183] The second concatenation factor is obtained by concatenating the digit flip rate and the character change gradient.

[0184] Perform a hash operation on the second concatenation factor to obtain the associated feature perturbation factor;

[0185] Get the latest hash low-order block and the current cumulative number of transactions on the chain;

[0186] Determine if the current cumulative number of transactions on the chain is odd. If the current cumulative number of transactions on the chain is not odd, then use the preset zero value as the exponent of the cumulative number of transactions.

[0187] If the current cumulative number of transactions on the chain is odd, then the preset single value will be used as the cumulative transaction number index.

[0188] The third concatenation factor is obtained by concatenating the latest hash low-order block with the cumulative transaction count index.

[0189] Perform a hash operation on the third concatenation factor to obtain the on-chain dynamic perturbation factor;

[0190] The structural feature perturbation factor, the correlation feature perturbation factor, and the on-chain dynamic perturbation factor are concatenated to obtain the fourth concatenation factor.

[0191] Perform a hash operation on the fourth concatenation factor to obtain the final perturbation factor;

[0192] Once the perturbation timestamp is identified, the perturbation timestamp, the final perturbation factor, and the multiple salted data segments are concatenated to obtain the perturbation data.

[0193] The perturbation data is hashed to obtain security processing information.

[0194] It should be explained that the feature extraction performed on multi-segment salted concatenated data refers to content analysis of the multi-segment salted concatenated data to extract quantifiable and computable statistical features. Field length feature is a parameter used to describe the length information of each field (i.e., each data block) in the multi-segment salted concatenated data. Data entropy feature is a statistical quantity representing the randomness, complexity, or uncertainty of data. It is usually calculated using Shannon entropy from information theory. Fragment distribution feature is a parameter used to describe the arrangement of different fragments in the multi-segment salted concatenated data. Total number of characters in the data refers to the count value of all characters contained in the multi-segment salted concatenated data. Character data consists of multiple characters arranged in their original order, and includes multiple characters, where characters are a collective term for letters, numbers, and symbols in electronic computers or radio communications. The latest hash low-order block refers to the last 32 bits of the most recently generated block in the blockchain service network, and the current cumulative number of transactions on the chain refers to the total number of transactions recorded on the blockchain in its current state. The digit flip rate reflects the frequency of data changes. A higher digit flip rate indicates more frequent data changes. The digit flip rate measures the proportion of adjacent characters in a set of character data that transform (from one character to another). A higher digit flip rate indicates a larger proportion of adjacent characters transforming, meaning the data changes frequently; conversely, a lower digit flip rate indicates less frequent data changes. The character change gradient reflects the degree of difference between adjacent characters in a set of character data. A larger character change gradient indicates a greater degree of difference between adjacent characters. Optionally, zero is "0", and a single value is "1".

[0195] It is understood that the methods for concatenating field length features, data entropy features, and fragment distribution features, the methods for concatenating digit flip rate and character change gradient, the methods for concatenating the latest hash low-order block and the cumulative transaction count index, the methods for concatenating structural feature perturbation factors, correlation feature perturbation factors, and on-chain dynamic perturbation factors, and the methods for concatenating perturbation timestamps, final perturbation factors, and multi-segment salted concatenated data are all the same as the methods for concatenating product unique codes, batch hash values, and hash timestamps, and will not be repeated here. The first concatenation factor refers to the data obtained by concatenating the field length feature, data entropy value feature, and fragment distribution feature. The second concatenation factor refers to the data obtained by concatenating the digit flip rate and character change gradient. The third concatenation factor refers to the data obtained by concatenating the latest hash low-order block and the cumulative transaction count index. The fourth concatenation factor refers to the data obtained by concatenating the structural feature perturbation factor, the association feature perturbation factor, and the on-chain dynamic perturbation factor. The perturbation data refers to the data obtained by concatenating the perturbation timestamp, the final perturbation factor, and the multi-segment salted concatenation data. The determination of the perturbation timestamp means that the timestamp of the hash operation on the fourth concatenation factor is used as the perturbation timestamp.

[0196] It should be understood that the methods for hashing the first concatenation factor, the second concatenation factor, the third concatenation factor, the fourth concatenation factor, and the perturbation data are all the same as the method for hashing the batch processing information, and will not be repeated here. The associated feature perturbation factor refers to the first concatenation factor after hashing; the on-chain dynamic perturbation factor refers to the second concatenation factor after hashing; the final perturbation factor refers to the third concatenation factor after hashing; the structural feature perturbation factor refers to the fourth concatenation factor after hashing; and the security processing information refers to the perturbation data after hashing.

[0197] S3. Write the first binding information into the pre-built blockchain distributed ledger to obtain the product evidence data, confirm the QR code label based on the digital identity hash value, and physically bind the QR code label to the target product to obtain the labeled product.

[0198] It should be explained that writing the first binding information into the pre-built blockchain distributed ledger means: submitting the first binding information to the deployed blockchain service network, verifying the first binding information through nodes in the blockchain service network, and packaging and writing the first binding information into a new block after successful verification. Verification of the first binding information involves multiple nodes in the blockchain service network checking its legality, including verifying whether the data format of the first binding information conforms to blockchain requirements and whether there are duplicate records of the first binding information in the blockchain. A new block refers to a data block newly generated by the blockchain service network. The blockchain service network is the blockchain distributed ledger. Product evidence data refers to the first binding information written into the blockchain distributed ledger.

[0199] Understandably, identifying the QR code label based on the digital identity hash value means: generating corresponding QR code encoding data from the digital identity hash value, and converting the QR code encoding data into a QR code graphic using a QR code generation method. The QR code graphic is the QR code label. Optionally, a QR code generator can be used as the QR code generation method. Physically binding the QR code label to the target product means: pasting the QR code label onto the target product. The labeled product refers to the target product that has completed the physical binding.

[0200] S4. Receive the scanning request, confirm the product's certificate data based on the scanning request and the product label, and confirm the visual display interface based on the product's certificate data.

[0201] It should be explained that receiving a scan request refers to receiving an access request sent by a mobile terminal after scanning a QR code label. The mobile terminal refers to the user's mobile phone. Confirming product evidence data based on the scan request and the product label means querying the digital identity hash value and first binding information corresponding to the QR code label in the blockchain distributed ledger, based on the QR code label of the product included in the scan request. The digital identity hash value and first binding information corresponding to the QR code label constitute the product evidence data. Confirming a visual display interface based on the product evidence data means generating a graphic and text display page that can be displayed on the mobile terminal based on the product evidence data. This graphic and text display page is the visual display interface, and it is used to present basic product information, traceability information, or production information.

[0202] S5. Use pre-built tracking technology to collect interactive behavior data from the visual display interface. The interactive behavior data includes: scanning time, scanning frequency, dwell time, interface click behavior, and consumer geographic information. Based on the scanning time, scanning frequency, dwell time, interface click behavior, and consumer geographic information in the interactive behavior data, the user preference feature vector is identified.

[0203] In detail, the method of using pre-built tracking technology to collect interactive behavior data from the visual display interface to obtain interactive behavior data includes:

[0204] The visualization interface is pre-embedded using the event tracking technology to obtain the event tracking interface and the event tracking collector. The event tracking collector includes: page lifecycle collector, touch event collector and geographic information collector.

[0205] The page lifecycle collector is used to collect information from the event tracking interface, including scanning time, interface dwell time, and interface exit time.

[0206] The touch event collector is used to monitor the embedded interface and obtain the click coordinate sequence and control identifier;

[0207] The location of consumers can be obtained by using a geographic information collector to capture the location of the embedded interface.

[0208] The scanning time, screen dwell time, screen exit time, click coordinate sequence, control identifiers, and consumer geographic information are packaged to obtain an interactive behavior data package.

[0209] The interaction behavior data is obtained by parsing and storing the interaction behavior data packets using a pre-built data receiving server.

[0210] It should be explained that the aforementioned use of event tracking technology to pre-embed data collection points in the visual display interface refers to: pre-implanting code for data collection in various pages, buttons, controls, nodes, etc., within the visual display interface using event tracking technology. During the operation of the visual display interface, user-triggered events are automatically recorded. Furthermore, the method of pre-implanting data collection code in various pages, buttons, controls, event nodes, etc., within the visual display interface using event tracking technology is existing technology and will not be elaborated upon here. Event tracking technology refers to the technology for collecting user behavior data in the field of electronic information technology. An event tracking interface refers to a visual display interface that has undergone event tracking processing. The event tracking collector is a data collection module used to actively collect events during the operation of the event tracking interface. It includes a page lifecycle collector, a touch event collector, and a geographic information collector. The page lifecycle collector is used to monitor and record key lifecycle events during the operation of the event tracking interface. These key lifecycle events include: scan time, interface dwell time, and interface exit time. Scan time refers to the time when the mobile terminal user scans the QR code; interface dwell time refers to the span of time the mobile terminal user stays on the event tracking interface; and interface exit time refers to the time when the mobile terminal user closes the event tracking interface. For example, if the mobile terminal user scans a QR code at 11:11:01 and closes the event tracking interface at 11:12:03, the scan time is 11:11:01, the interface dwell time is 1 minute 02 seconds, and the interface exit time is 11:12:03. Collecting information from the event tracking interface using the page lifecycle collector refers to using the page lifecycle collector to collect the key lifecycle events of the event tracking interface.

[0211] Understandably, the touch event collector is a module used to record user touch behavior on the event tracking interface. Touch behavior includes: click coordinate sequences and control identifiers. The click coordinate sequence refers to a set of coordinate points ordered by time generated when a user on a mobile terminal continuously performs touch operations on the event tracking interface. Control identifiers are unique identifiers used to identify interactive controls such as buttons, icons, links, and images on the event tracking interface. Monitoring the event tracking interface using the touch event collector means collecting touch behavior on the event tracking interface. The geographic information collector is a module that uses the mobile terminal's positioning function to obtain the user's location information. Obtaining the location of the event tracking interface using the geographic information collector means obtaining the location information of the mobile terminal accessing the event tracking interface; this location information is the consumer's geographic location information.

[0212] It should be understood that packaging the scanning time, interface dwell time, interface exit time, click coordinate sequence, control identifier, and consumer geographic information refers to encapsulating these data. Furthermore, the method of encapsulating these data is existing technology and will not be elaborated upon here. The interactive behavior data packet refers to the data packet obtained after packaging the scanning time, interface dwell time, interface exit time, click coordinate sequence, control identifier, and consumer geographic information. Parsing and storing the interactive behavior data packet using a pre-built data receiving server means: using the data receiving server to identify and format the data fields in the interactive behavior data packet and write them into a database. Optionally, an IDC server can be used as the data receiving server. Interactive behavior data refers to the interactive behavior data packet stored on the data receiving server.

[0213] Specifically, the process of identifying user preference feature vectors based on scanning time, scanning frequency, dwell time, interface click behavior, and consumer geographic information from interaction behavior data includes:

[0214] Time features are extracted from the scanning time in the interactive behavior data to obtain a time period feature vector;

[0215] Statistical processing is performed on the scanning frequency in the interactive behavior data to obtain a frequency statistical feature vector;

[0216] The dwell time in the interaction behavior data is segmented to obtain the duration distribution feature vector;

[0217] Behavioral analysis is performed on interface click behavior in interactive behavior data to obtain click behavior feature vectors;

[0218] Geographically encode the consumer geographic information in the interaction behavior data to obtain a geographic feature vector;

[0219] Based on the time period feature vector, frequency statistics feature vector, duration distribution feature vector, click behavior feature vector, and regional feature vector, the weights of the time period feature, frequency statistics feature, duration distribution feature, click behavior feature, and regional feature are determined.

[0220] A user preference feature vector is constructed based on the time period feature vector, frequency statistics feature vector, duration distribution feature vector, click behavior feature vector, geographic feature vector, time period feature weight, frequency statistics feature weight, duration distribution feature weight, click behavior feature weight, and geographic feature weight. The user preference feature vector is shown below:

[0221] ,

[0222] in, Represents the user preference feature vector. Indicates the weight of time period features. Indicates time period characteristics, Indicates the weight of frequency statistical features. Indicates frequency statistical characteristics, Represents the weights of the duration distribution features. Indicates the characteristics of duration distribution. This indicates the weight of click behavior features. This indicates the characteristics of click behavior. Indicates the weight of regional characteristics. Indicates regional characteristics, This indicates dot product.

[0223] It needs to be explained that the feature extraction of various fields in the interactive behavior data refers to: First, extracting time features from the scanning time. The original scanning times (e.g., "2025-11-29-08:12:31", "2025-11-29-20:33:10", "2025-11-30-08:11:02", "2025-11-30-08:55:21") are parsed one by one to extract the hour information "8, 20, 8, 8". A 24-dimensional statistical vector is then constructed according to the 0-23 hour range. For example, if a user scans the code 3 times at 8:00, once at 20:00, and 0 times at other times, the resulting hour vector is "". The hourly vector is the time period feature vector. The statistical processing of the scanning frequency in the interaction behavior data refers to: summing and statistically analyzing the number of scans per day over 7 consecutive days (e.g., "3, 1, 0, 4, 2, 0, 1"): total scans = 11, average daily scans = 1.57, maximum daily scans = 4, minimum daily scans = 0, thus forming a frequency statistical feature vector. The segmentation of dwell time in the interaction behavior data refers to: segmenting the dwell time (e.g., "2.2 seconds, 5.6 seconds, 11.7 seconds, 1.3 seconds, 3.5 seconds, 0.8 seconds, 15.2 seconds") into preset intervals, such as "0–3 seconds", "3–10 seconds", and "more than 10 seconds", and counting the number of each segment: 0–3 seconds has 3 occurrences (2.2, 1.3, 0.8 seconds), 3–10 seconds has 2 occurrences (5.6, 3.5 seconds), and more than 10 seconds has 2 occurrences (11.7, 15.2 seconds). If a proportional form is used, the corresponding duration distribution feature vector is " The aforementioned behavioral analysis of interface click behavior in interactive behavior data refers to: performing behavioral analysis on interface click behavior, and statistically analyzing the click location IDs recorded by the tracking points (e.g., "banner_01, tab_goods, tab_goods, tab_coupon, banner_02, tab_goods, detail_button") according to interface modules. For example, if the page is divided into 5 categories such as "banner area, product area, coupon area, details area, and other areas", the corresponding click count results are: 2 times for the banner area (banner_01, banner_02), 3 times for the product area (tab_goods×3), 1 time for the coupon area, 1 time for the details area, and 0 times for the other areas. The resulting click behavior feature vector is then "". The aforementioned geocoding of consumer geographic information in interactive behavior data refers to: encoding the original geographic text (e.g., "Hefei High-tech Zone, Anhui Province") according to national standard administrative divisions: provincial code "34", city code "3401", and district code "340104", forming a geographic feature vector. ".

[0224] It is understood that determining the weights of time-period features, frequency statistics features, duration distribution features, click behavior features, and geographic features based on time-period feature vectors, frequency statistics feature vectors, duration distribution feature vectors, click behavior features, and geographic features means: according to a preset weight allocation rule, assigning weights to the time-period feature vectors, frequency statistics feature vectors, duration distribution feature vectors, click behavior feature vectors, and geographic features to obtain the weights of time-period features, frequency statistics feature vectors, duration distribution feature vectors, click behavior features, and geographic features. The weight allocation rule is as follows: Time-period features reflect the stability of user behavior and have moderate importance, which can be set to 0.2; frequency statistics features directly reflect user activity and have high importance, which can be set to 0.3; duration distribution features reflect the depth of user attention to content and have high importance, which can be set to 0.25; click behavior features reflect the user's immediate interest preferences and have the highest importance, which can be set to 0.15; geographic features are used to distinguish regional differences and have relatively low importance, which can be set to 0.1. The time period feature weight is a coefficient used to reflect the degree of influence of time period features on user preference results. The frequency statistics feature weight is a coefficient used to reflect the degree of influence of frequency statistics features on user preference results. The duration distribution feature weight is a coefficient used to reflect the degree of influence of duration distribution features on user preference results. The click behavior feature weight is a coefficient used to reflect the degree of influence of click behavior features on user preference results. The geographic feature weight is a coefficient used to reflect the degree of influence of geographic features on user preference results.

[0225] S6. Analyze the user preference feature vector using a pre-built user preference analysis model to obtain user preference labels.

[0226] It should be explained that the user preference analysis model uses a deep neural network as its core structure. It is trained using historical user preference feature vectors and historical user preference labels, enabling the model to learn the mapping relationship between user preference feature vectors and corresponding user preference labels. During the training phase, the model uses historical user preference feature vectors as input and manually compiled user preference labels as output. The network parameters are continuously adjusted through backpropagation, gradually bringing the model's predictions closer to the true labels. In the usage phase, the user preference feature vector to be analyzed is input into the trained user preference analysis model. The model internally processes the input user preference feature vector using the learned mapping relationship and outputs the label with the highest confidence as the final user preference label. The user preference labels include: high-frequency scanning users, deep browsing users, and users active within a specific time period.

[0227] S7. Identify target marketing content based on user preference tags and complete product anti-counterfeiting marketing.

[0228] It should be explained that the identification of target marketing content based on user preference tags means: if the user preference tag is a high-frequency QR code scanning user, then the preset first marketing content will be used as the target marketing content; if the user preference tag is a deep browsing user, then the preset second marketing content will be used as the target marketing content; if the user preference tag is a user active during a specific time period, then the preset third marketing content will be used as the target marketing content. Here, the first marketing content refers to pushing periodic check-in activities, points accumulation rewards, continuous QR code scanning incentive tasks, and new product launch notifications or short-term coupons to such users; the second marketing content refers to pushing in-depth content marketing materials to such users, such as product comparison guides, limited-time discount details pages, member-exclusive content, or brand story special pages; and the third marketing content refers to accurately targeting such users during their active time periods with time-limited coupons, hourly lucky draws, and limited-time flash sale reminders.

[0229] For example, when the target marketing content is pushed to the user's mobile device, the user receives personalized marketing content, and Xiao Zhang completes the anti-counterfeiting marketing for the product.

[0230] To address the problems described in the background art, this invention obtains a target product, identifies its unique code and key information, and establishes a unique digital identity for the product, linking it to its core attributes to form a data foundation for anti-counterfeiting and marketing. Then, a digest operation is performed on the unique product code to obtain a digital identity hash value. This invention utilizes a cryptographic hash function to transform the product identifier into an irreversible unique digital fingerprint, ensuring the immutability and uniqueness of the identity information. The digital identity hash value is then bound to the key product information to obtain the first binding information. Thus, this invention constructs a complete digital twin by strongly linking the product's digital identity to its physical attributes, providing a complete digital twin for the entire supply chain. This provides a basis for traceability, improving the anti-counterfeiting reliability and authenticity identification accuracy of goods. The first binding information is written into a pre-built blockchain distributed ledger to obtain product evidence data. It is evident that this embodiment of the invention, by leveraging the distributed storage and consensus mechanism of blockchain, achieves permanent, transparent, and tamper-proof evidence storage of product information, establishing a reliable traceability foundation. Based on the digital identity hash value, a QR code label is confirmed, and the QR code label is physically bound to the target product to obtain a labeled product. This embodiment of the invention, by attaching a digital identity to a product with a conveniently identifiable physical carrier, opens up a connection channel between offline entities and online data. It receives scanning requests and, based on the scanning request and the labeled product, confirms the product evidence data. This embodiment of the invention... By responding to consumers' scanning behavior, the system retrieves and verifies product information from the blockchain network in real time, completing the anti-counterfeiting authentication process. This improves the reliability of anti-counterfeiting measures and the accuracy of authenticity identification. A visual display interface is then established based on the product's stored evidence data. This embodiment of the invention transforms on-chain evidence data into intuitive and user-friendly front-end display content, enhancing consumers' information access experience and trust. Pre-built tracking technology is used to collect interactive behavior data from the visual display interface, including scanning time, scanning frequency, dwell time, interface click behavior, and consumer geographic information. This embodiment of the invention seamlessly collects multi-dimensional user behavior data during the anti-counterfeiting query process, enabling consumer insights and precise marketing. Providing authentic and abundant analytical materials improves the reliability of product anti-counterfeiting and the accuracy of authenticity identification. Based on scanning time, scanning frequency, dwell time, interface click behavior, and consumer geographic information from interaction behavior data, user preference feature vectors are identified. This invention quantifies multi-dimensional behavioral data into structured feature vectors, accurately depicting user interests and consumption potential. A pre-built user preference analysis model is used to analyze the user preference feature vectors, resulting in user preference tags. This invention achieves intelligent and refined segmentation of user groups by applying machine learning models for in-depth mining and classification of feature vectors.Based on user preference tags, the target marketing content is identified, and product anti-counterfeiting marketing is completed. It is evident that this embodiment of the invention transforms the anti-counterfeiting query scenario into an efficient marketing touchpoint by simultaneously pushing customized marketing information to users while completing anti-counterfeiting verification. This achieves the dual value of anti-counterfeiting and promotion, improving the reliability of product anti-counterfeiting and the accuracy of authenticity identification. Therefore, this invention can improve the reliability of product anti-counterfeiting and the accuracy of authenticity identification.

[0231] like Figure 2 The diagram shown is a functional block diagram of a blockchain-based anti-counterfeiting marketing system provided in an embodiment of the present invention.

[0232] The blockchain-based anti-counterfeiting marketing system 100 described in this invention can be installed in an electronic device. Depending on the functions implemented, the blockchain-based anti-counterfeiting marketing system 100 may include a data acquisition module 101, a display interface confirmation module 102, a preference vector calculation module 103, and an anti-counterfeiting marketing strategy module 104. The module described in this invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.

[0233] The evidence storage data acquisition module 101 is used to acquire the target product, confirm the unique code and key information of the product based on the target product, perform a digest operation on the unique code of the product to obtain a digital identity hash value, bind the digital identity hash value with the key information of the product to obtain the first binding information, and write the first binding information into a pre-built blockchain distributed ledger to obtain the product evidence storage data.

[0234] The display interface confirmation module 102 is used to confirm the QR code label based on the digital identity hash value, and physically bind the QR code label to the target product to obtain the labeled product, receive the scanning request, confirm the product storage data based on the scanning request and the labeled product, and confirm the visual display interface based on the product storage data.

[0235] The preference vector calculation module 103 is used to collect interactive behaviors of the visual display interface using pre-built tracking technology to obtain interactive behavior data. The interactive behavior data includes: scanning time, scanning frequency, dwell time, interface click behavior, and consumer geographic information. Based on the scanning time, scanning frequency, dwell time, interface click behavior, and consumer geographic information in the interactive behavior data, the user preference feature vector is determined.

[0236] The anti-counterfeiting marketing strategy module 104 is used to analyze user preference feature vectors using a pre-built user preference analysis model to obtain user preference tags, identify target marketing content based on user preference tags, and complete product anti-counterfeiting marketing.

[0237] In detail, the modules in the blockchain-based anti-counterfeiting marketing system 100 described in this embodiment of the invention employ the same methods as described above. Figure 1 The same technical means are used in the blockchain-based anti-counterfeiting marketing method described in the article, and it can produce the same technical effect, so it will not be repeated here.

[0238] like Figure 3 The diagram shown is a structural schematic of an electronic device that implements a blockchain-based anti-counterfeiting marketing method for goods, according to an embodiment of the present invention.

[0239] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as a blockchain-based anti-counterfeiting marketing method program.

[0240] The memory 11 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device 1. Furthermore, the memory 11 includes both internal storage units and external storage devices of the electronic device 1. The memory 11 can be used not only to store application software and various types of data installed on the electronic device 1, such as the code of a blockchain-based anti-counterfeiting marketing method program, but also to temporarily store data that has been output or will be output.

[0241] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., blockchain-based anti-counterfeiting marketing methods) and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0242] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0243] Figure 3 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0244] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0245] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device 1 and other electronic devices.

[0246] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device 1 and to display a visual user interface.

[0247] The blockchain-based anti-counterfeiting marketing method program stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When run in the processor 10, it can achieve the following:

[0248] Obtain the target product and, based on the target product, identify its unique code and key information.

[0249] Perform a digest operation on the unique product code to obtain the digital identity hash value;

[0250] The digital identity hash value is bound to key product information to obtain the first binding information;

[0251] Write the first binding information into a pre-built blockchain distributed ledger to obtain product evidence data;

[0252] The QR code label is identified based on the digital identity hash value, and the QR code label is physically bound to the target product to obtain the labeled product;

[0253] Receive a scan request, and confirm the product's evidence data based on the scan request and the product label;

[0254] A visual display interface was created based on the product's certificate data.

[0255] The interactive behavior data of the visual display interface is collected by using pre-built tracking technology. The interactive behavior data includes: scanning time, scanning frequency, dwell time, interface click behavior and consumer geographic information.

[0256] Based on the scanning time, scanning frequency, dwell time, interface click behavior, and consumer geographic information in the interaction behavior data, a user preference feature vector is identified.

[0257] The user preference feature vector is analyzed using a pre-built user preference analysis model to obtain user preference labels;

[0258] Based on user preference tags, target marketing content is identified, and anti-counterfeiting marketing of products is completed.

[0259] Specifically, the processor 10's implementation method for the above instructions can be found in [reference needed]. Figures 1 to 3 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0260] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0261] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following:

[0262] Obtain the target product and, based on the target product, identify its unique code and key information.

[0263] Perform a digest operation on the unique product code to obtain the digital identity hash value;

[0264] The digital identity hash value is bound to key product information to obtain the first binding information;

[0265] Write the first binding information into a pre-built blockchain distributed ledger to obtain product evidence data;

[0266] The QR code label is identified based on the digital identity hash value, and the QR code label is physically bound to the target product to obtain the labeled product;

[0267] Receive a scan request, and confirm the product's evidence data based on the scan request and the product label;

[0268] A visual display interface was created based on the product's certificate data.

[0269] The interactive behavior data of the visual display interface is collected by using pre-built tracking technology. The interactive behavior data includes: scanning time, scanning frequency, dwell time, interface click behavior and consumer geographic information.

[0270] Based on the scanning time, scanning frequency, dwell time, interface click behavior, and consumer geographic information in the interaction behavior data, a user preference feature vector is identified.

[0271] The user preference feature vector is analyzed using a pre-built user preference analysis model to obtain user preference labels;

[0272] Based on user preference tags, target marketing content is identified, and anti-counterfeiting marketing of products is completed.

[0273] In the embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and actual implementations may have other classification methods.

[0274] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0275] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0276] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0277] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1.A blockchain-based anti-counterfeiting marketing method for a commodity, characterized in that, The method comprises: acquiring a target commodity, and confirming a commodity unique code and commodity key information based on the target commodity, wherein the commodity key information comprises a production serial number, a product photo, a production time, a production batch number, and a distributor; performing a digest operation on the commodity unique code to obtain a digital identity hash value; wherein the digest operation on the commodity unique code to obtain the digital identity hash value comprises: acquiring commodity production batch information, performing standard processing on the commodity production batch information to obtain processed batch information; performing a hash operation on the processed batch information to obtain a batch hash value; confirming a hash timestamp, and concatenating the commodity unique code, the batch hash value, and the hash timestamp to obtain concatenated information; adding a salt value to the concatenated information to obtain security processing information; performing a hash operation on the security processing information to obtain preliminary hash information; performing a hash digest operation on the preliminary hash information to obtain the digital identity hash value; wherein the adding of the salt value to the concatenated information to obtain the security processing information comprises: acquiring environmental parameters, wherein the environmental parameters comprise a system timestamp, a network delay, and a geographic location code; acquiring device fingerprint information, wherein the device fingerprint information comprises a processor identifier, a browser fingerprint code, and a communication module identifier; constructing a multi-dimensional feature vector based on the system timestamp in the environmental parameters, the network delay in the environmental parameters, the geographic location code in the environmental parameters, the processor identifier in the device fingerprint information, the browser fingerprint code in the device fingerprint information, and the communication module identifier in the device fingerprint information; confirming a salt value weight vector based on the multi-dimensional feature vector; generating a dynamic salt value based on the multi-dimensional feature vector and the salt value weight vector; confirming a plurality of salt value segments and a plurality of insertion points based on the concatenated information and the dynamic salt value; inserting the plurality of salt value segments into the concatenated information according to the plurality of insertion points to obtain salted concatenated data; perturbing the plurality of salted concatenated data to obtain the security processing information; binding the digital identity hash value with the commodity key information to obtain first binding information; writing the first binding information into a pre-constructed blockchain distributed ledger to obtain commodity evidence data; confirming a two-dimensional code label based on the digital identity hash value, and physically binding the two-dimensional code label with the target commodity to obtain a labeled commodity; receiving a code scanning request, and confirming the commodity evidence data based on the code scanning request and the labeled commodity; confirming a visual display interface based on the commodity evidence data; collecting interaction behavior data by using a pre-constructed burying point technology to interact with the visual display interface, wherein the interaction behavior data comprises a code scanning time, a code scanning frequency, a stay duration, an interface clicking behavior, and consumer regional information; confirming a user preference feature vector based on the code scanning time in the interaction behavior data, the code scanning frequency in the interaction behavior data, the stay duration in the interaction behavior data, the interface clicking behavior in the interaction behavior data, and the consumer regional information in the interaction behavior data; analyzing the user preference feature vector by using a pre-constructed user preference analysis model to obtain a user preference label; confirming target marketing content based on the user preference label, and completing commodity anti-counterfeiting marketing. 2.The blockchain-based anti-counterfeiting marketing method of goods according to claim 1, characterized in that, The salt value weight vector is confirmed based on the multi-dimensional feature vector, and the method comprises the steps of: obtaining a plurality of sets of historical data, wherein the historical data comprises historical environment parameters and historical device fingerprint information, the historical environment parameters comprise a historical system timestamp, a historical network delay and a historical geographic location code, and the historical device fingerprint information comprises a historical processor identifier, a historical browser fingerprint code and a historical communication module identifier; performing the following operations on each set of historical data in the plurality of sets of historical data: confirming a historical multi-dimensional feature vector based on the historical system timestamp in the historical environment parameters in the historical data, the historical network delay in the historical environment parameters in the historical data, the historical geographic location code in the historical environment parameters in the historical data, the historical processor identifier in the historical device fingerprint information in the historical data, the historical browser fingerprint code in the historical device fingerprint information in the historical data and the historical communication module identifier in the historical device fingerprint information in the historical data; aggregating the historical multi-dimensional feature vectors to obtain a historical multi-dimensional feature vector set; confirming a salt value weight model based on the historical multi-dimensional feature vector set; analyzing the multi-dimensional feature vector by using the salt value weight model to obtain a salt value weight vector. 3.The blockchain-based anti-counterfeiting marketing method of commodities according to claim 2, characterized in that, The salt value weight model is confirmed based on the historical multi-dimensional feature vector set, and the method comprises the steps of: The historical multi-dimensional feature vector set is sampled to obtain a training vector set, wherein the training vector set includes: historical multi-dimensional feature vectors; based on The historical multidimensional feature vectors confirm that Each salt value weight vector corresponds one-to-one with the historical multidimensional feature vectors. based on a set of training vectors including a plurality of historical multi-dimensional feature vectors, a plurality of salt value weight vectors, and a pre-constructed weight model to identify a first model; removing a training vector set from the historical multi-dimensional feature vector set to obtain an updated historical multi-dimensional feature vector set; confirming a vector quantity of the updated historical multi-dimensional feature vector set, wherein the vector quantity is the number of historical multi-dimensional feature vectors in the updated historical multi-dimensional feature vector set; comparing the vector quantity with a preset quantity threshold value, if the vector quantity is greater than the quantity threshold value, taking the updated historical multi-dimensional feature vector set as the historical multi-dimensional feature vector set, taking the first model as the weight model, returning to the step of sampling the historical multi-dimensional feature vector set until the vector quantity is less than or equal to the quantity threshold value, and taking the first model as the salt value weight model. 4.The blockchain-based anti-counterfeiting marketing method of commodities according to claim 3, characterized in that, The plurality of salt value segments and the plurality of insertion points are confirmed based on the splicing information and the dynamic salt value, and the method comprises the steps of: obtaining a total data length of the splicing information, calculating a reference segmentation length according to the total data length and a preset target segment quantity; confirming a plurality of insertion points based on the reference segmentation length and the total data length; segmenting the dynamic salt value based on the reference segmentation length to obtain a plurality of initial salt value segments; performing the following operations on each initial salt value segment in the plurality of initial salt value segments: extracting a first character and a last character from the initial salt value segment; performing an exclusive OR operation on the first character and the last character to obtain a basic disturbance value; performing a modulo operation on the basic disturbance value and a preset adjustment modulus to obtain a length adjustment amount; performing length adjustment on the initial salt value segment based on the length adjustment amount to obtain a salt value segment; aggregating the salt value segments to obtain a plurality of salt value segments. 5.The blockchain-based anti-counterfeiting marketing method of commodities according to claim 4, characterized in that, The plurality of salt value segments and the plurality of insertion points are confirmed based on the splicing information and the dynamic salt value, and the method comprises the steps of: performing feature extraction on the plurality of salted splicing data to obtain a field length feature, a data entropy value feature, a segment distribution feature, a total character quantity and character data, wherein the character data comprises a plurality of characters; The field length feature, the data entropy value feature and the segment distribution feature are spliced to obtain a first splicing factor; Hash operation is performed on the first splicing factor to obtain a structure feature disturbance factor; The digit flip rate is calculated according to the character data and the total number of characters, and the calculation formula is as follows: ， wherein, represents the number of digit flips, represents the total number of characters of data, represents the first of a plurality of characters in the character data, represents the first of a plurality of characters in the character data, represents the first of a plurality of characters in the character data, represents the first of a plurality of characters in the character data, represents a counting function; The character change gradient is calculated according to the total number of characters and the character data, and the calculation formula is as follows: ， wherein represents a character change gradient, represents taking the absolute value; The digit flip rate and the character change gradient are spliced to obtain a second splicing factor; Hash operation is performed on the second splicing factor to obtain a correlation feature disturbance factor; The latest hash low-bit block and the cumulative transaction number on the current chain are obtained; It is judged whether the cumulative transaction number on the current chain is odd, if the cumulative transaction number on the current chain is not odd, a preset zero value is taken as the cumulative transaction number index; If the cumulative transaction number on the current chain is odd, a preset single value is taken as the cumulative transaction number index; The latest hash low-bit block and the cumulative transaction number index are spliced to obtain a third splicing factor; Hash operation is performed on the third splicing factor to obtain an on-chain dynamic disturbance factor; The structure feature disturbance factor, the correlation feature disturbance factor and the on-chain dynamic disturbance factor are spliced to obtain a fourth splicing factor; Hash operation is performed on the fourth splicing factor to obtain a final disturbance factor; The disturbance timestamp is confirmed, and the disturbance timestamp, the final disturbance factor and the multi-segment salted splicing data are spliced to obtain disturbance data; Hash operation is performed on the disturbance data to obtain security processing information. 6.The blockchain-based anti-counterfeiting marketing method of commodities according to claim 5, characterized in that, The interactive behavior data is obtained by collecting the interactive behavior of the visual display interface by using the pre-constructed burying point technology, and the interactive behavior data includes: The burying point interface and the burying point collector are obtained by pre-burying the visual display interface by using the burying point technology, wherein the burying point collector includes a page life cycle collector, a touch event collector and a geographic information collector; The scan code time, interface stay time and interface leaving time are obtained by collecting information of the burying point interface by using the page life cycle collector; The click coordinate sequence and the control identifier are obtained by listening to the burying point interface by using the touch event collector; The consumer regional information is obtained by acquiring the position of the burying point interface by using the geographic information collector; The interactive behavior data packet is obtained by packaging the scan code time, the interface stay time, the interface leaving time, the click coordinate sequence, the control identifier and the consumer regional information; The interactive behavior data is obtained by analyzing and storing the interactive behavior data packet by using the pre-constructed data receiving server. 7.The blockchain-based anti-counterfeiting marketing method of commodities according to claim 6, characterized in that, The user preference feature vector is confirmed according to the scan code time in the interactive behavior data, the scan code frequency in the interactive behavior data, the stay time in the interactive behavior data, the interface click behavior in the interactive behavior data and the consumer regional information in the interactive behavior data, and the user preference feature vector includes: The time period feature vector is obtained by performing time feature extraction on the scan code time in the interactive behavior data; The frequency statistical feature vector is obtained by performing statistical processing on the scan code frequency in the interactive behavior data; The time length distribution feature vector is obtained by performing segmentation processing on the stay time in the interactive behavior data; The click behavior feature vector is obtained by performing behavior analysis on the interface click behavior in the interactive behavior data; Geocode the consumer geographical information in the interaction behavior data to obtain a geographical feature vector; confirm the time period feature weight, the frequency statistics feature weight, the time length distribution feature weight, the click behavior feature weight and the geographical feature weight based on the time period feature vector, the frequency statistics feature vector, the time length distribution feature vector, the click behavior feature vector and the geographical feature vector; construct the user preference feature vector according to the time period feature vector, the frequency statistics feature vector, the time length distribution feature vector, the click behavior feature vector, the geographical feature vector, the time period feature weight, the frequency statistics feature weight, the time length distribution feature weight, the click behavior feature weight and the geographical feature weight. 8.A blockchain-based anti-counterfeiting marketing system for commodities, characterized in that, The system comprises: The evidence data acquisition module is used for acquiring a target commodity, confirming a commodity unique code and commodity key information based on the target commodity, wherein the commodity key information comprises a production serial number, a product photo, a production time, a production batch number and a distributor, performing a digest operation on the commodity unique code to obtain a digital identity hash value, wherein the digest operation on the commodity unique code to obtain the digital identity hash value comprises: acquiring commodity production batch information, performing standard processing on the commodity production batch information to obtain processed batch information; performing a hash operation on the processed batch information to obtain a batch hash value; confirming a hash timestamp, splicing the commodity unique code, the batch hash value and the hash timestamp to obtain spliced information; adding a salt value to the spliced information to obtain security processing information; performing a hash operation on the security processing information to obtain preliminary hash information; performing a hash digest operation on the preliminary hash information to obtain the digital identity hash value; wherein the adding of the salt value to the spliced information to obtain the security processing information comprises: acquiring environmental parameters, wherein the environmental parameters comprise a system timestamp, a network delay and a geographic location code; acquiring device fingerprint information, wherein the device fingerprint information comprises a processor identifier, a browser fingerprint code and a communication module identifier; constructing a multi-dimensional feature vector according to the system timestamp in the environmental parameters, the network delay in the environmental parameters, the geographic location code in the environmental parameters, the processor identifier in the device fingerprint information, the browser fingerprint code in the device fingerprint information and the communication module identifier in the device fingerprint information; confirming a salt weight vector based on the multi-dimensional feature vector; generating a dynamic salt value according to the multi-dimensional feature vector and the salt weight vector; confirming a plurality of salt value segments and a plurality of insertion points based on the spliced information and the dynamic salt value; inserting the plurality of salt value segments into the spliced information according to the plurality of insertion points to obtain salted spliced data; perturbing the plurality of salted spliced data to obtain the security processing information, binding the digital identity hash value with the commodity key information to obtain first binding information, writing the first binding information into a pre-constructed blockchain distributed ledger to obtain commodity evidence data; The display interface confirmation module is configured to confirm the two-dimensional code label based on the digital identity hash value, physically bind the two-dimensional code label with the target commodity to obtain a labeled commodity, receive a code scanning request, confirm commodity storage data based on the code scanning request and the labeled commodity, and confirm a visual display interface based on the commodity storage data. The preference vector calculation module is configured to collect interaction behavior data of the visual display interface by using a pre-constructed burying point technology, wherein the interaction behavior data includes scanning time, scanning frequency, stay duration, interface click behavior, and consumer regional information, and to confirm a user preference feature vector based on the scanning time in the interaction behavior data, the scanning frequency in the interaction behavior data, the stay duration in the interaction behavior data, the interface click behavior in the interaction behavior data, and the consumer regional information in the interaction behavior data. The anti-fake marketing strategy module is configured to analyze the user preference feature vector by using a pre-constructed user preference analysis model to obtain a user preference label, confirm target marketing content based on the user preference label, and complete anti-fake marketing of the commodity.

Images