A security anti-counterfeiting method based on double anti-counterfeiting codes

Abstract

The application provides a security anti-counterfeiting method based on a double anti-counterfeiting code, belongs to the field of anti-counterfeiting technology, and aims to solve the problems of weak anti-copying, anti-tampering and anti-transferring ability and difficulty in covering product whole life cycle tracking in related technologies. The method extracts product physical and space-time characteristics and generates a fusion feature vector, generates a double code based on the fusion feature vector, binds and stores the double code and space-time information, and verifies in layers. The method can improve the anti-copying, anti-tampering, anti-transferring and anti-quantum cracking ability in the whole life cycle, and takes into account the verification accuracy and scene adaptability.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of anti-counterfeiting technology, and in particular to a security anti-counterfeiting method based on double anti-counterfeiting codes. BACKGROUND

[0002] With the rapid development of commodity economy, anti-counterfeiting technology plays an increasingly important role in protecting consumer rights and interests, maintaining market order, etc., and is widely used in food, medicine, luxury goods and other fields. Among them, two-dimensional code anti-counterfeiting, due to its low cost and easy identification, has become one of the current mainstream anti-counterfeiting methods. By setting a two-dimensional code on the product and storing product information, combined with encryption algorithms, authenticity verification is achieved.

[0003] Existing two-dimensional code anti-counterfeiting technology relies on single static physical characteristics (such as surface texture, fixed pattern) to extract information, generates independent explicit or implicit codes, and only realizes double code binding through simple information association (such as explicit code storing implicit code position). At the same time, the space-time information mostly uses ordinary precision time stamp and location data, which is not deeply integrated with product features. Meanwhile, during the verification process, a fixed threshold is mostly used, without considering the influence of product life cycle, material differences and environmental changes on features, and lacking effective detection means for AI counterfeit features and carrier tampering.

[0004] The above existing technology has obvious defects: first, the feature extraction is easily affected by product deformation and environmental fluctuations, resulting in large feature deviation and weak anti-copying ability; second, the double code association is loose, the encryption level is low, and there is a lack of anti-quantum attack design, with insufficient anti-tampering ability; third, the space-time information is weakly bound with product features, with poor chain relationship stability and weak anti-transfer ability; fourth, the verification precision and scene adaptability are low, with easy misjudgment or omission, which is difficult to meet the high security level anti-counterfeiting demand, and a new security anti-counterfeiting method is needed to solve the above problems. SUMMARY

[0005] The present application provides a security anti-counterfeiting method based on double anti-counterfeiting codes, which can improve the anti-copying, anti-tampering and anti-transfer ability of the anti-counterfeiting method through multi-dimensional feature fusion, double code deep association, chain stable binding and hierarchical precise verification, while considering the verification accuracy and scene adaptability.

[0006] The application provides a security anti-counterfeiting method based on double anti-counterfeiting codes. The method includes the following steps: extracting physical features and space-time features of a product, the physical features including core invariant features and dynamic response features that dynamically change with the environment, correcting feature deviations caused by product deformation through nonlinear deformation field modeling, calculating deformation confidence, determining environmental change intensity in combination with temperature and humidity changes of the environment where the product is located, and dynamically adjusting the weight of the core invariant features and the dynamic response features according to the environmental change intensity and the deformation confidence; the space-time features include sub-millimeter-level spatial coordinates, nanosecond-level time stamps in the product production stage, and multi-source space-time data of each node in the circulation link, and after the multi-source space-time data is fused and calibrated, the fused physical features are fused to generate a fusion feature vector; generating an explicit two-dimensional code and an implicit two-dimensional code based on the fusion feature vector, the explicit two-dimensional code adopting a double-layer structure of a basic layer and an additional layer, the basic layer storing a product unique identifier, the additional layer storing feature evolution prediction factors generated based on a core feature aging model and an environmental response coefficient and a hash feature digest of the implicit two-dimensional code; the implicit two-dimensional code is generated based on Logistic chaotic mapping and adopts a double-layer structure of a basic layer and a dynamic layer, the basic layer storing a product unique identifier, a core feature original hash, and generation parameters of the explicit two-dimensional code, and the dynamic layer embedding an environmental response code segment encrypted based on a TorusLWE lattice password, the environmental response code segment being generated from real-time environmental parameters and an implicit code key; associating and binding the explicit two-dimensional code, the implicit two-dimensional code, and the space-time information of the product, encoding the time stamp and the spatial identifier of the product production and circulation to generate a space-time combination code, calculating the hash value of the fusion feature vector, the hash value of the explicit two-dimensional code, the hash value of the implicit two-dimensional code, and the hash value of the space-time combination code, and making the hash values satisfy algebraic topological homology group constraints and bitwise XOR chain constraints, forming a chain association relationship and storing the chain association relationship in a main side chain architecture alliance chain; performing hierarchical verification on the generated explicit two-dimensional code and implicit two-dimensional code, verifying the core invariant features on the user side and combining AI forgery identification, and using a first matching threshold adjusted based on a product life cycle logarithmic decay model; verifying the total physical features and the chain association relationship on the professional side, combining damage detection, and using a second matching threshold adjusted based on a life cycle logarithmic decay model and a material correction coefficient, the first matching threshold being smaller than the second matching threshold.

[0007] By using the above technical solution, the feature extraction accuracy is improved through nonlinear deformation correction and multi-source space-time fusion, the safety of the double codes is strengthened by combining chaotic mapping and quantum-resistant encryption, the chain stability is enhanced by using homology group constraints and main side chain storage, and the verification accuracy is improved by hierarchical verification and AI detection, thereby comprehensively solving the problems of weak anti-copying, anti-tampering, and anti-transferring ability and low verification accuracy in the prior art.

[0008] Further, the feature deviation caused by the product deformation through the nonlinear deformation field modeling includes: constructing a B-spline control grid of the product surface, collecting displacement vectors of key feature points of the product, and fitting a deformation field matrix of a cubic B-spline basis function through a least square method; based on an inverse matrix of the deformation field matrix, mapping the coordinates of the deformed product feature points back to an initial reference coordinate system to obtain equivalent initial coordinates, and correcting the deformation deviation; the deformation field matrix of the cubic B-spline basis function is fitted by collecting displacement vectors of more than 100 key feature points on the product surface through an optical flow method, and the constructed B-spline control grid is a 3*3*3 three-dimensional control grid; the equivalent initial coordinates are used to generate a fusion feature vector, and a hash value of the fusion feature vector is used in subsequent algebraic topology homology group constraints of a chain association relationship, wherein a 2-order boundary operator image set is used to ensure that the chain association relationship remains stable in the overall association structure when the local features of the product change slightly due to environmental fluctuations.

[0009] By adopting the above technical solutions, the feature deviation caused by the product nonlinear deformation is accurately corrected, the specific implementation of the deformation field modeling and the role of the 2-order boundary operator image set are determined, and the accuracy of the fusion feature vector and the stability of the chain association relationship are further improved.

[0010] Further, the fusion calibration of the multi-source spatio-temporal data includes: the multi-source spatio-temporal data includes Beidou high-precision positioning data, 5G base station triangulation positioning data, and inertial navigation data, and an extended Kalman filtering algorithm is used to filter and denoise the multi-source spatio-temporal data; based on the filtered multi-source spatio-temporal data, optimal spatial coordinates and optimal time stamps are calculated to complete the spatio-temporal data fusion calibration.

[0011] By adopting the above technical solutions, the multi-source data complementation and the filtering algorithm are used to eliminate the spatio-temporal data noise, the spatio-temporal information accuracy is improved, and high-quality data basis is provided for the deep binding of the feature-double code-spatio-temporal.

[0012] Further, the generation of the implicit two-dimensional code based on the Logistic chaotic mapping includes: calculating the mean value of each dimension value of the fusion feature vector, performing a modulo operation on the mean value to obtain an initial value of the Logistic chaotic mapping; the initial value is iterated for a preset number of times and the transient value is discarded, and the iteration result is selected to generate 128-bit encryption parameters of the implicit two-dimensional code, and the fusion feature vector is encrypted by combining a TorusLWE lattice encryption to generate the implicit two-dimensional code.

[0013] By adopting the above technical solutions, the sensitivity of the chaotic mapping and the security of the anti-quantum encryption are used to deeply bind the encryption parameters of the implicit two-dimensional code and the product features, and the anti-copying and anti-cracking capabilities of the implicit two-dimensional code are greatly improved.

[0014] Further, the hash value satisfies an algebraic topological homology group constraint, which includes: making the hash value of the fusion feature vector, the hash value of the explicit two-dimensional code, the hash value of the implicit two-dimensional code, and the hash value of the space-time combined code satisfy the homology group constraint of "fusion feature vector hash value-explicit two-dimensional code hash value-implicit two-dimensional code hash value-space-time combined code hash value e 2-order boundary operator image set", and ensuring the topological stability of the chain association relationship.

[0015] By adopting the above technical solution, the association rigidity between the hash values is strengthened by the algebraic topological constraint, and even if there is a slight fluctuation in local information, the overall structure of the chain relationship is still stable, and the tamper resistance is improved.

[0016] Further, the chain association relationship is stored in a consortium chain of a main side chain architecture, which includes: the main side chain architecture includes a main chain and multiple side chains, the side chains are split according to the circulation links and store the chain relationship fragments of the corresponding links, a Merkle tree is constructed for the chain relationship fragments of each side chain, and a root hash is calculated; the root hash and the chain relationship of the product production and retail terminal nodes are stored in the main chain to form a hierarchical evidence storage consortium chain.

[0017] By adopting the above technical solution, hierarchical and efficient storage of the chain relationship is realized, the data amount of the main chain is reduced, the storage and query efficiency is improved, and the data integrity of the side chain is ensured by the Merkle tree, which facilitates the whole life cycle traceability.

[0018] Further, the user-end verification combined with AI forgery identification includes: the user end collects key dimension data of product core invariant features, and calculates the entropy value of the feature vector; if the entropy value is lower than a preset natural feature entropy lower limit, it is determined that the suspected AI-generated forged features trigger professional end deep verification.

[0019] By adopting the above technical solution, AI forgery detection is added on the basis of rapid verification at the user end, false features generated by AI are identified in a timely manner, the risk of counterfeit products passing the preliminary verification is reduced, and the verification comprehensiveness is improved.

[0020] Further, the professional end verification combined with damage detection includes: the professional end collects continuity and integrity indicators of the product surface microtexture, calculates the continuity coefficient of the microtexture direction angle and the integrity coefficient of the gray value; if the continuity coefficient is lower than a preset continuity threshold or the integrity coefficient is lower than a preset integrity threshold, it is determined that the product carrier is tampered with or transferred.

[0021] By adopting the above technical solution, the professional end verifies from two dimensions of features and carriers to accurately identify the carrier tampering or transfer situation, and further improves the verification accuracy in high-security scenarios.

[0022] Further, the dynamic adjustment of the weights of the core invariant features and the dynamic response features comprises: setting the initial value of the core invariant feature weight as 0.7 and the initial value of the dynamic response feature weight as 0.3, adjusting the weights based on the normalized value of the environmental change intensity, when the environmental change intensity tends to 1, the core invariant feature weight is reduced to 0.2 and the dynamic response feature weight is increased to 0.8; taking the deformation confidence as a weight correction factor to perform secondary correction on the adjusted weights, and when the deformation confidence is lower than a preset threshold, the proportion of the core invariant feature weight is increased.

[0023] By adopting the above technical solution, the feature weights are adaptively adjusted according to the environment and the deformation state, so that the fusion feature vector can consider both stability and sensitivity in different scenarios, and the adaptability of feature extraction is improved.

[0024] Further, the generation of the environment response code segment comprises: collecting the temperature and humidity parameters of the environment where the product is located and the current nanosecond-level timestamp in real time to form an environment parameter set; and based on a TorusLWE lattice encryption algorithm, the environment parameter set is encrypted by using a preset implicit code key to generate the environment response code segment.

[0025] By adopting the above technical solution, the environment response code segment dynamically changes with the real-time environment and has quantum-resistant security properties, so that the copied static code cannot match the real-time environment parameters, and the anti-transferring capability is improved.

[0026] In summary, the present application at least has the following beneficial effects:

[0027] 1. A multi-dimensional fusion dual anti-counterfeiting security method is provided, which significantly improves the anti-copying, anti-tampering and anti-transferring capabilities.

[0028] 2. By nonlinear deformation correction and quantum-resistant encryption, the feature and double code security are strengthened to adapt to complex application scenarios.

[0029] 3. By hierarchical verification and AI detection, the verification convenience and accuracy are balanced to meet different security level requirements.

[0030] It should be understood that the content described in the summary section is not intended to limit the key or important features of the embodiments of the present application, nor to limit the scope of the present application. Other features of the present application will become apparent through the following description. BRIEF DESCRIPTION OF DRAWINGS

[0031] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent by describing in detail the following embodiments with reference to the attached drawings. In the drawings, the same or similar reference numerals refer to the same or similar elements, and:

[0032] Figure 1An exemplary operating environment in which embodiments of the present application can be implemented is shown.

[0033] Figure 2 A flowchart of a security anti-counterfeiting method based on a dual anti-counterfeiting code in embodiments of the present application is shown. DETAILED DESCRIPTION

[0034] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0035] In addition, the term “and / or” in this document is only to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent the three cases of A alone, A and B together, and B alone. In addition, the character “ / ” in this document generally represents an “or” relationship between the front and rear associated objects.

[0036] The present application provides a security anti-counterfeiting method based on a dual anti-counterfeiting code, which can improve the anti-copying, anti-tampering, and anti-transferring capabilities, balance the verification accuracy and anti-quantum security, adapt to product deformation, complex environment, and other scenes, help high-security anti-counterfeiting, and ensure the reliability of the whole life cycle traceability.

[0037] Figure 1 An exemplary operating environment in which embodiments of the present application can be implemented is shown.

[0038] Reference Figure 1 The operating environment includes a full-link macro hardware system supporting the implementation of the security anti-counterfeiting method based on a dual anti-counterfeiting code, which covers four core links of feature collection, data processing, evidence storage and transmission, and verification interaction. The hardware devices in each link realize data interaction and cooperation through wired (such as Ethernet) or wireless (such as 5G, WiFi) communication methods, form a complete closed loop from original data collection to final anti-counterfeiting verification, and ensure the stable landing of core functions such as nonlinear deformation correction, multi-source space-time fusion, anti-quantum encryption, main side chain evidence storage, and hierarchical verification.

[0039] The first part of the running environment is a feature collection and preprocessing device cluster, which includes a high-resolution industrial camera (more than 12 million pixels, supporting sub-millimeter spatial resolution), a portable spectrometer, a three-dimensional scanner, a Beidou / 5G dual-mode positioning module, a nanosecond-level high-precision clock module, a temperature and humidity sensor (accuracy ±0.1℃ / ±1%RH), and a deformation detection sensor. Among them, the high-resolution industrial camera and the portable spectrometer are used to collect physical features such as product surface microtexture and material spectrum, the three-dimensional scanner captures more than 100 key feature point displacement vectors through the optical flow method to support nonlinear deformation modeling, the Beidou / 5G dual-mode positioning module and the nanosecond-level clock module cooperate to obtain sub-millimeter-level spatial coordinates and nanosecond-level timestamps, and the temperature and humidity sensor and the deformation detection sensor collect environmental parameters and product deformation status in real time. All collection devices are connected to subsequent data processing devices through data interfaces to transmit raw feature data to the data processing end for preprocessing.

[0040] The second part of the running environment is a data processing and encryption computing device cluster, mainly composed of high-performance data processing servers and secure encryption devices. The high-performance data processing server is equipped with more than 16-core CPU and GPU acceleration module, used to run extended Kalman filter algorithm (realize multi-source spatio-temporal data fusion denoising), Logistic chaotic mapping algorithm (determine the initial value of the implicit two-dimensional code), LSTM-Transformer hybrid model (risk prediction), etc., while supporting edge-cloud collaborative computing, can issue lightweight model to edge device and receive parameter update; The secure encryption device includes anti-quantum encryption chip (supports TorusLWE lattice cryptography operation) and secure storage module (encrypted hard disk / trusted execution environment TEE), the former is used to realize anti-quantum encryption of dynamic layer of implicit two-dimensional code at hardware level, the latter is used to store sensitive data such as implicit code key and chaotic mapping parameters. The cluster interacts with feature collection devices and blockchain storage devices through communication links, receives raw data and outputs processed fusion feature vectors, double-code parameters and other core data.

[0041] The third part of the running environment is a blockchain storage and communication device cluster, including main chain node servers (not less than 3, distributed deployment), side chain node servers (split and deployed according to the storage, transportation and other circulation links), distributed storage devices (such as HDFS distributed file system) and communication transmission devices; the main chain node server stores the chain relationship of product production / retail terminal nodes and the Merkle root hash of each side chain, runs PBFT and other consortium chain consensus mechanisms to ensure data consistency, the side chain node server stores the chain relationship fragment of the corresponding circulation link and constructs the Merkle tree to calculate the root hash, the distributed storage device is used to store the feature hash and chain relationship history version of each node; the communication transmission device includes an Internet of Things gateway and a LAN / WAN communication module, the Internet of Things gateway accesses the circulation node sensing device and realizes low-delay data transmission (delay ≤100 ms), the LAN / WAN communication module ensures the communication stability between blockchain nodes and between blockchain and other devices, the cluster is connected to the data processing device to obtain chain relationship data, and provides storage query services for the verification interaction device.

[0042] The fourth part of the running environment is a circulation link sensing and edge computing device cluster, which is composed of circulation node sensing devices and edge computing terminals; the circulation node sensing device includes an RFID card reader and a barcode scanner, which are used to collect circulation node identification, node environmental parameter and other information, and the edge computing terminal is an embedded server or an industrial panel with a CPU of 4 cores or more, which is deployed with a lightweight model (such as a lightweight EKF model and a SPONGENT-256 hash algorithm) optimized by federated learning, can locally calculate edge chain fragments and only upload fragment data to the blockchain storage device, thereby reducing the amount of raw data transmission, and the cluster is connected to the blockchain storage device and the data processing device through the Internet of Things gateway to realize real-time uploading of circulation data and synchronization of lightweight calculation results.

[0043] The fifth part of the running environment is a hierarchical verification terminal device cluster, which is divided into user-end verification devices and professional-end verification devices; the user-end verification device is a smart phone equipped with a camera with a pixel of more than 12 million and NFC function, which supports explicit two-dimensional code scanning and lightweight AI forgery identification (such as feature entropy calculation), can quickly complete core invariant feature matching and suspected forgery early warning; the professional-end verification device includes a special terminal integrated with a high-precision code scanner and a computing terminal equipped with an AI acceleration module, the high-precision code scanner is used to collect product surface microtexture to detect carrier continuity and integrity, and the computing terminal runs full-amount feature matching algorithm and chain association relationship verification logic, and can also generate an AR visualization layer to assist in presenting the verification result, the cluster is connected to the blockchain storage device through wireless communication to query chain relationship data to complete verification judgment.

[0044] Each part of the hardware device works together, the feature acquisition device provides the original data basis, the data processing device completes the core algorithm operation and data encryption, the block chain storage device guarantees the chain relationship cannot be tampered with and is traceable, the circulation perception device realizes the full life cycle data supplement, the verification terminal device completes the final anti-fake verification, and together they constitute a macro device environment supporting the efficient and stable operation of the "a security anti-fake method based on double anti-fake codes".

[0045] The embodiment of the application discloses a security anti-fake method based on double anti-fake codes.

[0046] Figure 2 The flowchart of the security anti-fake method based on double anti-fake codes in the embodiment of the application is shown.

[0047] Referring to Figure 2 , the method specifically comprises the following steps:

[0048] S1: Extracting physical features and space-time features of the product.

[0049] The physical features include core invariant features and dynamic response features that dynamically change with the environment. The feature deviation caused by product deformation is corrected by nonlinear deformation field modeling, the deformation confidence is calculated, the environmental change intensity is determined in combination with the temperature and humidity change of the environment where the product is located, and the weight of the core invariant features and the dynamic response features is dynamically adjusted according to the environmental change intensity and the deformation confidence. The space-time features include sub-millimeter level spatial coordinates, nanosecond level time stamps in the product production stage, and multi-source space-time data of each node in the circulation link. After the multi-source space-time data is fused and calibrated, it is fused with the weighted physical features to generate a fusion feature vector.

[0050] In the method of this step, the correction of the feature deviation caused by product deformation by nonlinear deformation field modeling includes constructing a B-spline control grid of the product surface, collecting displacement vectors of key feature points of the product, and fitting a deformation field matrix of a cubic B-spline basis function by the least square method. , wherein is a parameter variable, is a node vector value, is a 0th B-spline basis function (1 in the interval , and 0 otherwise). The fitting process of the deformation field matrix is realized by the least square method, and the objective function is , wherein is the initial coordinate vector of the i th feature point, is the displacement vector thereof, is the number of feature points ​Based on the inverse matrix of the deformation field matrix, the coordinates of the deformed product feature points are mapped back to the initial reference coordinate system to obtain equivalent initial coordinates, thus correcting the deformation deviation. The deformation field matrix of the cubic B-spline basis function is fitted using the optical flow method by collecting displacement vectors from more than 100 key feature points on the product surface, and the constructed B-spline control mesh is... A three-dimensional control mesh; the equivalent initial coordinates are used to generate a fused feature vector, the hash value of which is subsequently used to participate in the algebraic topological homology group constraint of the chain association relationship, wherein the second-order boundary operator image set is used to ensure that the chain association relationship maintains the stability of the overall association structure when the local features of the product undergo minor changes due to environmental fluctuations.

[0051] The fusion calibration of multi-source spatiotemporal data includes BeiDou high-precision positioning data, 5G base station triangulation positioning data, and inertial navigation data. An extended Kalman filter algorithm is used to filter and denoise the multi-source spatiotemporal data. The state equation of the extended Kalman filter is: The observation equation is ,in for The state vector at any given time (containing spatial coordinates and timestamp). To control the input, and These are process noise and observation noise, respectively (both following a Gaussian distribution). and These are the state transition function and the observation function, respectively. During the filtering process, prediction is first performed using the state equation. Prior state at time and prior covariance Combined with observed values Calculate Kalman gain (in For the observation matrix, To observe the noise covariance, the posterior state is finally updated. and posterior covariance The optimal spatial coordinates and timestamps are calculated based on the filtered multi-source spatiotemporal data to complete the spatiotemporal data fusion calibration.

[0052] The dynamic adjustment of the weights for core invariant features and dynamic response features includes setting the initial weight of the core invariant features to 0.7 and the initial weight of the dynamic response features to 0.3, and adjusting the weights based on the normalized value of the environmental change intensity. The normalization formula is ,in The change in temperature This represents the change in humidity. and These are the preset maximum temperature change threshold and maximum humidity change threshold, respectively. The weighting adjustment formula is as follows: ,in As the core invariant feature weights, As dynamic response feature weights, when the intensity of environmental change... As the value approaches 1, the weight of the core invariant feature decreases to 0.2, while the weight of the dynamic response feature increases to 0.8; the deformation confidence level is... As a weighting correction factor, the deformation confidence is calculated using the condition number of the deformation field matrix. (in The condition number of the deformation field matrix is ​​denoted as . (The maximum condition number threshold is used as a preset threshold). The adjusted weights are then further corrected using the following formula: , When the deformation confidence level When the weight is below a preset threshold, the weight ratio of the core invariant features is increased.

[0053] When fusing weighted physical features with spatiotemporal features to generate a fused feature vector, the physical feature vector is first... (in For core invariant eigenvectors, (Dynamic response feature vector) and spatiotemporal feature vector (Including optimal spatial coordinates and optimal timestamp) are dimensionally aligned, and then vectors are concatenated to form a fused feature vector. The semicolon indicates a vertical splicing operation.

[0054] S2: Generate explicit and implicit QR codes based on the fused feature vectors.

[0055] The explicit QR code adopts a two-layer structure of a base layer and an additional layer. The base layer stores the product's unique identifier, while the additional layer stores the feature evolution prediction factor generated based on the core feature aging model and environmental response coefficients, as well as the hash feature summary of the implicit QR code. The calculation of the feature evolution prediction factor is based on the core feature aging model, which uses an exponential decay function to describe the change trend of the core feature over time. The mathematical expression is as follows: ,in for The core feature value predicted at time 1. The initial core invariant eigenvalues ​​(core invariant features collected from the product manufacturing stage) Extracted from ( ) The core characteristic is the aging coefficient (set according to the material characteristics of the product, such as paper products). Heaven, metal products sky), The duration from product production to the present moment. and These are the environmental response coefficients for temperature and humidity (obtained from a material environmental response database, such as for plastic materials). ), and These are the current environment and the standard environment, respectively. The temperature and humidity differences; the hash feature digest of the hidden QR code is calculated using the SPHINCS+ quantum-resistant hash algorithm, the formula is as follows: ,in This is the base layer data for the hidden QR code. For Torus LWE lattice basis parameters (ring) polynomial degree Modulus The implicit QR code is generated based on Logistic chaotic mapping and adopts a two-layer structure of a base layer and a dynamic layer. The base layer stores the product's unique identifier, the original hash of the core feature, and the generation parameters of the explicit QR code. The original hash of the core feature is the core invariant feature. The hash value is calculated using the following formula: The generation parameters of the explicit QR code include the data length of the base layer and the update cycle of the feature evolution prediction factor of the additional layer; the dynamic layer embeds an environmental response code segment encrypted based on Torus LWE lattice cryptography, which is generated by real-time environmental parameters and the implicit code key.

[0056] In this step, generating an implicit QR code based on a Logistic chaotic mapping includes calculating the mean value of each dimension of the fused feature vector. Include Dimensions (such as) (covering weighted physical and spatiotemporal characteristics), with values ​​for each dimension as follows: The formula for calculating the mean is: The initial value of the Logistic chaotic mapping is obtained by performing a modulo operation on the mean. The modulo operation is as follows: Ensure initial values Then, through a linear transformation, it is mapped to the effective iteration interval of the Logistic mapping [0.1, 0.9], i.e. The iterative formula for the Logistic chaotic mapping is: ,in For control parameters (range of values) Take this place To ensure strong chaotic characteristics, the initial value is iterated a preset number of times (e.g., 1000 times), and transient values ​​are discarded (the results of the first 100 iterations are discarded to avoid the influence of initial value fluctuations). The results of iterations from the 101st to the 1000th are selected, and a 128-bit binary number is extracted from them as the 128-bit encryption parameter of the implicit QR code. The fused feature vector is then encrypted using a Torus LWE lattice cipher. During the encryption process, the fused feature vector... As explicit Hidden key To obtain from discrete Gaussian distribution Sampling dimensional vector Public key From the ring Uniformly distributed sampling on the above, error term from Sampling, ciphertext ,in , This represents the vector inner product operation, generating an implicit QR code.

[0057] The generation of the environmental response code segment includes real-time acquisition of temperature and humidity parameters of the product's environment, as well as the current nanosecond-level timestamp, and temperature parameters. (unit: ), humidity parameters (Unit: %RH), nanosecond-level timestamp (Unit: ns), forming a set of environmental parameters. Based on the TorusLWE lattice cryptography algorithm, the set of environmental parameters is encrypted using a preset implicit key, which is the TorusLWE encryption key mentioned above. During encryption, the environmental parameter set is first... Convert to a ring plaintext (Mapping the parameter values ​​to a linear transformation) of (range), then generate ciphertext according to the TorusLWE encryption process. , ,in For the newly sampled public key portion, For the error term of the new sampling, the ciphertext This is the environmental response code segment, a dynamic layer that embeds a hidden QR code.

[0058] S3: Associate and bind the explicit QR code and implicit QR code with the product's spatiotemporal information.

[0059] The product's production and distribution timestamps and spatial identifiers are encoded to generate a spatiotemporal combination code. The product production timestamp is... (Production stage timestamp collected by nanosecond high-precision clock module in S1, unit: ns), and the time stamp of each node in the circulation link is ( The number of circulation nodes, such as storage and transportation nodes) and the production stage space identifier is (S1 sub-millimeter level space coordinates, unit: mm), and the circulation node space identifier is (Beidou dual-mode positioning data of each node). When encoding the space-time combined code, first construct the space-time vector

[0060] , and then generate the space-time combined code through Base64 encoding and hash mapping , the formula is , wherein is the TorusLWE lattice basis parameter (ring , polynomial degree , modulus ), and SPHINCS+ is a quantum-resistant hash algorithm. Calculate the hash values of the fusion feature vector, the explicit two-dimensional code, the implicit two-dimensional code, and the space-time combined code, and the hash value of the fusion feature vector is (S1 generated fusion feature vector), the hash value of the explicit two-dimensional code is ( The splicing data of the basic layer and the additional layer of the explicit two-dimensional code), the hash value of the implicit two-dimensional code is ( The splicing data of the basic layer and the dynamic layer of the implicit two-dimensional code), and the hash value of the space-time combined code is ; make the above hash values satisfy the algebraic topological homology group constraint and the chain constraint relationship of bitwise XOR, and the bitwise XOR constraint is ( Bitwise XOR operation), which ensures the direct association between hash values; form a chain association relationship and store it in the alliance chain of the main side chain architecture.

[0061] In the product circulation process, the node feature information of each circulation node (storage, transportation, and distribution node) is obtained in real time, and the node feature information includes the circulation node identifier ID, the node operation timestamp (nanosecond level), the node environment parameters (temperature , humidity ), and the product local feature data collected by the node device (such as the product packaging integrity feature collected by the storage node); calculate the hash value of the node feature information ( TorusLWE lattice basis parameter); and the node feature hash Hash superposition operation is performed on the current stored chain association relationship, and the chain association relationship is updated: To ensure that the updated chain relationship still satisfies the algebraic topological homology group constraint The order boundary operator image set); the updated chain association relationship is synchronized to the side chain of the corresponding circulation link (such as a warehouse side chain and a transportation side chain), and the root hash of the side chain Merkle tree is updated, and the new root hash is synchronized to the main chain, realizing dynamic updating and full-link notarization of the chain relationship of the circulation link.

[0062] In the method of the present step, the hash value satisfying the algebraic topological homology group constraint includes making the hash value of the fusion feature vector, the hash value of the explicit two-dimensional code, the hash value of the implicit two-dimensional code, and the hash value of the space-time combination code satisfy the constraint relationship of "fusion feature vector hash value-explicit two-dimensional code hash value-implicit two-dimensional code hash value-space-time combination code hash value The homology group constraint of the order boundary operator image set ensures the topological stability of the chain association relationship. In the algebraic topological homology group, the chain complex is defined as Wherein is The order chain group (here, the integer chain group ), is The order boundary operator; the image set of the 2-order boundary operator The image set of the 2-order boundary operator , represents a set of 1-order chains obtained by mapping all 2-order chains through the boundary operator. The four hash values are mapped into 2-order chain elements: , The constraint relationship can be represented as That is ( The kernel of the 2-order boundary operator), and ( The 3-order boundary operator) constitute the 2-order homology group This constraint ensures the equivalence of the chain relationship in the topological structure - even if the local hash value changes due to a small disturbance, the overall association structure remains stable.

[0063] The chain association relationship is stored in the alliance chain of the main side chain architecture, which includes the main chain and multiple side chains. The side chains are split according to the circulation links (such as warehouse side chains, transportation side chains, and distribution side chains), and each side chain stores the chain relationship fragment of the corresponding link: the warehouse side chain stores the (warehouse space-time combination code hash), (warehouse stage fusion feature vector hash) and node operation record hash; the transportation side chain stores , Etc. Build a Merkle tree for each side chain and calculate the root hash. Take the transportation side chain as an example, and the chain relationship fragment set is The number of fragments for the transportation link), the Merkle tree construction steps are: 1) generate leaf nodes If is odd, supplement to make the number of nodes even; 3) generate non-leaf nodes, and calculate the hash value of adjacent leaf nodes according to , and calculate the hash value of adjacent leaf nodes according to (the Merkle root hash of the transportation side chain). Store the root hash and the chain relationship of the product production and retail terminal nodes in the main chain. The production node data stored in the main chain includes (the production phase fusion feature vector hash), (the production phase explicit two-dimensional code hash), (the production phase implicit two-dimensional code hash), and the retail terminal node data includes , and store the Merkle root hash of each side chain , forming a hierarchical evidence storage consortium chain - the side chain stores link-level detail data, and the main chain stores key node data and root hash, which not only reduces the storage pressure of the main chain, but also ensures the integrity of the side chain data through the Merkle root hash.

[0064] S4: Perform hierarchical verification on the generated explicit two-dimensional code and implicit two-dimensional code.

[0065] The core of the user-end verification is to verify the invariant features and combine AI forgery identification, and the first matching threshold is adjusted based on the product life cycle logarithmic decay model. The core of the product life cycle logarithmic decay model is to dynamically adjust the matching threshold according to the time from production to verification, so as to adapt to the natural aging of the core invariant features over time. Let the initial value of the first matching threshold be (based on the feature matching accuracy when the product is shipped, such as , indicating that the initial feature matching), the product production time is (converted from nanosecond-level timestamp to days in S1, unit: days), the current verification time is (system time at the time of user-end verification, unit: days), the product preset life cycle is (set according to product type, such as days for pharmaceuticals, days for luxury goods), and the decay coefficient is (control the decay rate of the threshold, based on a large amount of product aging data statistics, such as ), then the first matching threshold calculation formula is , wherein ​The threshold is a natural logarithmic function, ensuring that it decays slowly over the lifespan and avoiding misjudgments due to normal aging. Professional verification of all physical features and chain relationships is performed, and combined with damage detection, a second matching threshold is adopted based on the logarithmic decay model of the lifespan and the material correction coefficient. The first matching threshold is less than the second matching threshold.

[0066] In this step, the user-side verification combined with AI forgery detection includes collecting key dimension data of the product's core invariant features from the user-side. The key dimensions of these core invariant features include inflection points of the product's surface texture and material spectral characteristics. A stable dimension (such as) ), forming feature vectors ,in For the first The feature values ​​of each dimension (such as texture inflection point spacing and spectral peak intensity) are used to calculate the entropy value of the feature vector. The entropy value is calculated using the Shannon entropy formula. First, the probability distribution of each feature value is statistically analyzed. (Based on a probability library of natural features of similar products stored locally on the user's device), then calculate the Shannon entropy. ,in Let the entropy be a logarithmic function with base 2. Reflecting the randomness of feature vectors—natural product features have higher entropy values, while AI-generated fake features have lower entropy values ​​due to their strong regularity; if the entropy value is lower than the preset lower limit of natural feature entropy values. (Based on statistical settings of 100,000+ natural product characteristics, such as...) If the result is not found, it is determined to be a suspected AI-generated forgery feature, triggering in-depth verification by professionals.

[0067] Professional-grade verification combined with damage detection includes professionally acquired data on the continuity and integrity of microtextures on the product surface. Microtexture continuity is measured using an angular continuity coefficient, while integrity is measured using a grayscale integrity coefficient. Data is collected from the product surface. Uniformly distributed micro-texture sampling points (e.g.) Record the micro-texture orientation angle of each sampling point. (Angle with the horizontal direction, unit: ) and grayscale value To calculate the continuity coefficient of the microtexture orientation angle, first calculate the variance of the orientation angle. (in (This is the mean of the direction angles), then define the continuity coefficient. ,in The maximum permissible variance is preset (e.g.) (Based on the product's original micro-texture test settings). The closer to 1 indicates that the micro-texture direction is more continuous, without obvious breakage or tampering; the integrity coefficient of the gray value is calculated, and the standard micro-texture gray value vector stored in the product production stage is obtained , and the total deviation of the gray value is calculated , and the integrity coefficient is defined, wherein is the maximum gray value, The closer to 1 indicates that the gray value is more consistent with the original state, without wear or tampering; if the continuity coefficient is lower than a preset continuity threshold (such as ) or the integrity coefficient is lower than a preset integrity threshold (such as , it is determined that the product carrier is tampered or transferred.

[0068] The second matching threshold calculation of the professional end needs to superimpose the material correction coefficient, and the material correction coefficient is set to (according to the product material characteristics, such as metal material , paper material , the more stable the material is , the closer to 1), and the initial value of the second matching threshold is (higher than the initial value of the first matching threshold, such as , the second matching threshold calculation formula is , to ensure , to meet the higher accuracy verification requirements of the professional end; when verifying the full amount of physical features of the professional end, the cosine similarity between the full amount of physical feature vectors (acquired in real time, including core invariant features and dynamic response features) and the original physical feature vectors stored in the production stage (wherein • is the inner product of the vector, is the L2 norm) is calculated, if and the chain association relationship verification is passed (that is, is established, and the hash value meets the algebraic topological homology group constraint), it is determined that the verification is passed.

[0069] It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all expressed as a series of action combinations, but those skilled in the art should know that the application is not limited by the action sequence described, because according to the embodiments of the application, certain steps can be adopted in other order or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the application.

[0070] Through the cooperation of the "feature collection-double code generation-chain storage-evidence layer-by-layer verification" full-link technical means, the application can objectively deduce the full-life-cycle high-resilience anti-counterfeiting effect, and the specific logical deduction is as follows:

[0071] 1. Feature acquisition and preprocessing link: precise data foundation supports anti-interference capability

[0072] The technical means of "nonlinear deformation field modeling (B-spline control grid + 3rd order basis function fitting) + multi-source spatio-temporal fusion (Beidou / 5G positioning + extended Kalman filter) + dynamic weight adjustment (environmental change intensity + deformation confidence)" are adopted: nonlinear deformation modeling corrects product wrinkles, extrusion and other complex deformation deviations through inverse matrix mapping, avoiding feature misjudgment caused by deformation; multi-source spatio-temporal fusion eliminates positioning and timestamp errors through filtering and denoising, ensuring sub-millimeter spatial accuracy and nanosecond temporal accuracy; dynamic weight adjustment adapts the weight of core invariant features and dynamic response features to environmental fluctuations and deformation reliability, avoiding the failure of a single feature in extreme environments. The three work together to directly derive: the generated fusion feature vector has the properties of "deformation independence, spatio-temporal precision, and environmental adaptation", providing high-quality data foundation for subsequent double-code generation and chain association, reducing the risk of anti-counterfeiting failure caused by feature interference from the source.

[0073] 2. Double code generation link: encryption and dynamic design strengthen anti-copy and anti-cracking capabilities

[0074] The technical means of "explicit code double-layer structure (basic layer unique identifier + additional layer feature evolution prediction factor) + implicit code chaotic mapping + TorusLWE quantum-resistant encryption + dynamic environmental response code segment" are adopted: the feature evolution prediction factor of explicit code is generated based on the core feature aging model, which can adapt to the natural change of features with life cycle and avoid matching failure caused by aging; implicit code converts the mean value of the fusion feature vector into an encrypted initial value through Logistic chaotic mapping, making the encryption parameters deeply bound to product features and unable to be copied independently; TorusLWE quantum-resistant encryption can resist the cracking risk of traditional encryption by quantum computing; dynamic environmental response code segment changes with real-time temperature and humidity and timestamp, and the code segment copied statically cannot match real-time environmental parameters. The four work together to directly derive: the double two-dimensional code has the properties of "feature binding, quantum-resistant cracking, and dynamic anti-static replication", which eliminates the possibility of counterfeit products through copying two-dimensional code from the generation logic.

[0075] 3. Chain storage link: constraint and hierarchical design guarantee anti-tampering and full-link traceability capability

[0076] Adopting the technical means of "hash bitwise XOR constraint + algebraic topology homology group constraint + main side chain hierarchical storage (Merkle tree) + circulation chain dynamic update": the hash bitwise XOR constraint makes the hash values of the fused features, double codes and space-time combined codes form a rigid association, and single hash tampering will destroy the association; the algebraic topology homology group constraint ensures that local feature fluctuations do not affect the stability of the overall chain structure through a 2-order boundary operator image set; the main side chain hierarchical storage stores the circulation link segment data in the side chain, the key nodes and the root hash in the main chain, which not only reduces the storage pressure of the main chain, but also ensures the integrity of the side chain data through the Merkle tree; the circulation chain dynamic update adds the feature hash of each node to the original chain relationship, completing the full life cycle data. The four work together to directly deduce that the chain association relationship has the properties of "tamper-identifiable, stable structure, and full-link traceable", preventing chain data from being tampered with or broken at the storage level, and realizing the full-link credible traceability of products from production to retail.

[0077] 4. Hierarchical verification link: multi-dimensional detection and dynamic threshold to achieve precise anti-counterfeiting capability

[0078] Adopting the technical means of "user-side AI counterfeit identification (feature entropy value judgment) + professional side damage detection (micro-texture continuity / integrity coefficient) + life cycle logarithmic decay threshold + material correction coefficient": the user side distinguishes natural features from AI-generated counterfeit features through feature entropy value to quickly intercept low-order counterfeits; the professional side judges whether the carrier has been tampered with or transferred through the micro-texture coefficient to identify high-order physical counterfeits; the dynamic threshold adjusts with the life cycle and material characteristics to avoid false positives due to aging or material differences; the hierarchical design of the first / second threshold balances the convenience of the user side and the high precision of the professional side. The four work together to directly deduce that the verification link has the properties of "full coverage of counterfeit types, precision adaptation to scenarios, and low false positive rate", which accurately distinguishes true from false at the verification level, avoiding both missed counterfeit judgments and false positives of genuine products due to environmental or aging factors.

[0079] In summary, the full-link technical means form a logical closed loop of "precise data → safe double code → stable storage → precise verification", which can objectively deduce that the application achieves the core anti-counterfeiting effect of "full life cycle anti-copy, anti-tampering, anti-transfer, and anti-quantum cracking", while considering verification convenience and scenario adaptability, providing reliable technical support for high-security level anti-counterfeiting needs.

[0080] The above description is merely exemplary of the application and of the application of the principles thereof and the application is not limited to the disclosed technical features or combinations thereof. It is intended to be apparent to one skilled in the art that the scope of the disclosure is not limited to the technical solutions formed by the specific combinations of the technical features disclosed above, and also includes other technical solutions formed by the combinations of the technical features disclosed above or their equivalent features without departing from the above disclosed concept. For example, technical solutions formed by the mutual replacement of the above features and technical features with similar functions disclosed in the application (but not limited to) are also included.

Claims

1. A security method based on a double anti-counterfeit code, characterized in that, The method comprises the following steps: extracting physical features and spatio-temporal features of the product, the physical features including core invariant features and dynamic response features which dynamically change with the environment, correcting feature deviation caused by product deformation through nonlinear deformation field modeling and calculating deformation confidence, determining environmental change intensity in combination with temperature and humidity change of the environment where the product is located, and dynamically adjusting the weight of the core invariant features and the dynamic response features according to the environmental change intensity and the deformation confidence; the spatio-temporal features include sub-millimeter level spatial coordinates of the product production stage, nanosecond level time stamps and multi-source spatio-temporal data of each node in the circulation link, and the multi-source spatio-temporal data is fused and calibrated to generate a fused feature vector in combination with the weighted physical features; generating an explicit two-dimensional code and an implicit two-dimensional code based on the fused feature vector, the explicit two-dimensional code adopting a double-layer structure of a basic layer and an additional layer, the basic layer storing a product unique identifier, the additional layer storing feature evolution prediction factors generated based on a core feature aging model and an environmental response coefficient and a hash feature digest of the implicit two-dimensional code; the implicit two-dimensional code is generated based on Logistic chaotic mapping and adopts a double-layer structure of a basic layer and a dynamic layer, the basic layer storing a product unique identifier, a core feature original hash and generation parameters of the explicit two-dimensional code, and the dynamic layer embedding an environmental response code segment encrypted based on TorusLWE lattice cryptography, the environmental response code segment being generated from real-time environmental parameters and an implicit code key; associating and binding the explicit two-dimensional code, the implicit two-dimensional code and the spatio-temporal information of the product, encoding the time stamp and the spatial identifier of the product production and circulation to generate a spatio-temporal combination code, calculating the hash value of the fused feature vector, the hash value of the explicit two-dimensional code, the hash value of the implicit two-dimensional code and the hash value of the spatio-temporal combination code, and making the hash values satisfy algebraic topological homology group constraints and bitwise XOR chain constraints, forming a chain association relationship and storing the chain association relationship in a main side chain architecture alliance chain; performing hierarchical verification on the generated explicit two-dimensional code and implicit two-dimensional code, verifying the core invariant features on the user side and combining AI forgery identification, and adopting a first matching threshold adjusted based on a product life cycle logarithmic decay model; verifying the full physical features and the chain association relationship on the professional side, combining damage detection, and adopting a second matching threshold adjusted based on a life cycle logarithmic decay model and a material correction coefficient, the first matching threshold being smaller than the second matching threshold.

2. The security method based on a double anticounterfeiting code according to claim 1, characterized in that, The method for correcting feature deviation caused by product deformation through nonlinear deformation field modeling comprises the following steps: constructing a B-spline control grid on the surface of the product, collecting displacement vectors of key feature points of the product, and fitting a deformation field matrix of a cubic B-spline basis function through the least square method; mapping the coordinates of the deformed product feature points back to the initial reference coordinate system based on the inverse matrix of the deformation field matrix to obtain equivalent initial coordinates and correct the deformation deviation. The deformation field matrix of the 3 B-spline basis functions is fitted by collecting displacement vectors of more than 100 key feature points on the product surface through an optical flow method, and a B-spline control grid is constructed as a 3*3*3 three-dimensional control grid; the equivalent initial coordinates are used to generate a fusion feature vector, and a hash value of the fusion feature vector is used in subsequent algebraic topology group constraints of a chain association relationship, wherein a 2-order boundary operator image set is used to ensure that the chain association relationship remains stable in the overall association structure when a local feature of the product produces a slight change due to environmental fluctuations.

3. The security method based on a double anticounterfeiting code according to claim 1, characterized in that, The fusion calibration of the multi-source spatio-temporal data includes: The multi-source spatio-temporal data includes Beidou high-precision positioning data, 5G base station triangulation positioning data, and inertial navigation data, and an extended Kalman filtering algorithm is used to filter and denoise the multi-source spatio-temporal data; Based on the filtered multi-source spatio-temporal data, the optimal spatial coordinates and the optimal time stamp are calculated to complete the spatio-temporal data fusion calibration.

4. The security method based on a double anticounterfeiting code according to claim 1, characterized in that, The generation of the implicit two-dimensional code based on the Logistic chaotic mapping includes: The mean value of each dimension of the fusion feature vector is calculated, and the mean value is subjected to a modulo operation to obtain the initial value of the Logistic chaotic mapping; The initial value is iterated for a preset number of times, and the transient value is discarded, and the iteration result is selected to generate 128-bit encryption parameters of the implicit two-dimensional code, and the fusion feature vector is encrypted by combining a TorusLWE lattice encryption, to generate the implicit two-dimensional code.

5. The security method based on a double anticounterfeiting code according to claim 1, characterized in that, The hash value satisfies the algebraic topology group constraint, which includes: The hash values of the fusion feature vector, the explicit two-dimensional code, the implicit two-dimensional code, and the spatio-temporal combination code satisfy the homology group constraint of "fusion feature vector hash value-explicit two-dimensional code hash value-implicit two-dimensional code hash value-spatio-temporal combination code hash value∈2-order boundary operator image set", to ensure the topological stability of the chain association relationship.

6. The security method based on a double anticounterfeiting code according to claim 1, characterized in that, The chain association relationship is stored in a consortium chain of a main side chain architecture, which includes: The main side chain architecture includes a main chain and multiple side chains, and the side chains are split according to the circulation links and store the chain relationship fragments of the corresponding links, and a Merkle tree is constructed for the chain relationship fragments of each side chain, and the root hash is calculated; The root hash and the chain relationship of the product production and retail terminal nodes are stored in the main chain to form a hierarchical evidence storage consortium chain.

7. The security method based on a double anticounterfeiting code according to claim 1, characterized in that, The user end verification combined with AI forgery identification includes: The user end collects key dimension data of the core invariant feature of the product, and calculates the entropy value of the feature vector; If the entropy value is lower than the preset natural feature entropy lower limit, it is determined that the suspected AI generated fake feature triggers professional end deep verification.

8. The security method based on a double anticounterfeiting code according to claim 1, characterized in that, The professional end verification combined with damage detection includes: The professional end collects continuity and integrity indicators of the microtexture on the product surface, calculates the continuity coefficient of the microtexture direction angle and the integrity coefficient of the gray value; If the continuity coefficient is lower than the preset continuity threshold or the integrity coefficient is lower than the preset integrity threshold, it is determined that the product carrier is tampered or transferred.

9. The security method based on a double anticounterfeiting code according to claim 1, characterized in that, The dynamic adjustment of the weights of the core invariant feature and the dynamic response feature includes: The initial value of the core invariant feature weight is set as 0.7, and the initial value of the dynamic response feature weight is set as 0.3; the weights are adjusted based on the normalized value of the environmental change intensity; when the environmental change intensity tends to 1, the core invariant feature weight is reduced to 0.2, and the dynamic response feature weight is increased to 0.8; The deformation confidence is used as a weight correction factor to perform secondary correction on the adjusted weight; when the deformation confidence is lower than a preset threshold, the proportion of the core invariant feature weight is increased.

10. The security method based on a double anticounterfeiting code according to claim 1, characterized in that, The generation of the environment response code segment includes: Real-time collection of temperature and humidity parameters of the environment in which the product is located and a current nanosecond-level timestamp to form an environment parameter set; Based on the TorusLWE lattice encryption algorithm, the environment parameter set is encrypted by using a preset implicit code key to generate the environment response code segment.

Images