Method for payment security authentication of commodity supply chain platform based on biometric authentication

Abstract

The application relates to the field of payment security technology, in particular to a commodity supply chain platform payment security authentication method based on biological feature authentication. The method obtains biological feature vectors of a sending party and a receiving party as reference vectors; according to the size and fluctuation of elements at the same position in the reference vectors of each party, reference average vectors and the confidence degree of each position element in the reference average vectors are obtained; the specified position of the elements that need to be reserved in the reference average vectors is determined based on the confidence degree; the biological feature fusion vector is obtained according to the elements at the specified position after binaryzation, and then the real-time encryption key and the real-time decryption key are obtained, and the commodity supply chain platform is subjected to payment security authentication. The biological feature fusion vector is obtained, the stability of the key is effectively improved, the leakage of the key in the transmission process is avoided, and the accuracy and efficiency of the payment security authentication of the commodity supply chain platform are effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of payment security, in particular to a commodity supply chain platform payment security authentication method based on biometric authentication. BACKGROUND

[0002] With the digital upgrading of commodity supply chain platforms, the secure transmission and authentication of full-link data (including commodity traceability information, inter-enterprise transaction credentials, user identity, etc.) has become a core link to protect commercial trust. Especially in multi-agent collaborative scenarios (such as manufacturers, logistics, and sales terminals), data needs to be transferred across multiple entities, facing the three threats of man-in-the-middle attacks, data tampering, and privacy leakage. Therefore, full-link data needs to be encrypted to ensure its security.

[0003] To improve the security of encryption, existing methods combine the uniqueness of the biometric features (such as fingerprints, faces, and irises, etc.) of the sender and the receiver into the secret key encryption, i.e., combining full-link data encryption and authentication, generating and encrypting the secret key based on the biometric features of the sender and the receiver, reducing the risk of secret key transmission, and improving the security of full-link data transmission and authentication. However, in actual situations, biometric features have benign fluctuations, and when the biometric features of the sender and the receiver are fused, the fluctuations of the biometric features of both parties will be added up, which may cause the benign fluctuations to exceed the limit, resulting in secret key recognition failure and affecting the stability and accuracy of payment security authentication. SUMMARY

[0004] To solve the technical problem of secret key recognition failure due to the fusion of the biometric features of the sender and the receiver, which causes the benign fluctuations of the biometric features to exceed the limit, and affects the stability and accuracy of payment security authentication, the present application aims to provide a commodity supply chain platform payment security authentication method based on biometric authentication, and the technical solution adopted is as follows:

[0005] The present application provides a commodity supply chain platform payment security authentication method based on biometric authentication, which includes the following steps:

[0006] The biometric feature vectors of the sender and the receiver are obtained multiple times, each serving as a reference vector;

[0007] According to the size and fluctuation of the same position elements in each party's reference vector, the reference average vector of each party and the confidence degree of each position element in the reference average vector are obtained;

[0008] The specified positions of the elements that need to be retained in the reference average vectors of the sender and the receiver are determined based on the confidence degree; and the biometric feature fusion vector is obtained based on the elements at the specified positions in the reference average vectors of the sender and the receiver after binarization.

[0009] Based on the real-time reference vector of the biological feature fusion vector, the sender and the receiver, the real-time encryption key of the sender and the real-time decryption key of the receiver are obtained, and the payment security authentication of the commodity supply chain platform is performed.

[0010] Further, the method for obtaining the reference average vector is:

[0011] For any one of the sender and the receiver, the mean value of the elements at the same position in all the reference vectors of the party is taken as the reference element at the corresponding position in the vector.

[0012] The vector composed of the reference elements is taken as the reference average vector of the party; wherein the reference average vector and the elements in the reference vector have the same number.

[0013] Further, the method for obtaining the confidence degree is:

[0014] For any position element in the reference average vector of any party, the difference between the position element and the preset binary threshold is taken as the first trust analysis value of the position element.

[0015] The standard deviation of the elements at the same position as the position element in all the reference vectors of the party is taken as the second trust analysis value of the position element.

[0016] The product of the negative correlation result of the first trust analysis value and the second trust analysis value is normalized to obtain the confidence degree of the position element.

[0017] Further, the method for obtaining the specified position is:

[0018] The element positions in the reference average vectors of the sender and the receiver are labeled with the same rule to obtain the labels of each element position in the reference average vectors of the sender and the receiver; wherein the labels of the same element positions in the reference average vectors of the sender and the receiver are the same.

[0019] When the confidence degree is greater than the preset confidence degree threshold, the corresponding position elements in the reference average vector are reserved, the labels of the reserved element positions in the reference average vectors of the sender and the receiver are determined, and each label set is constructed.

[0020] The intersection of the label sets of the sender and the receiver is taken as the common label set.

[0021] The element positions corresponding to the labels in the common label set in the reference average vector are all taken as the specified positions.

[0022] Further, the method for obtaining the biological feature fusion vector is:

[0023] The vectors constructed by binarizing the elements at the specified positions in the reference average vectors of the sender and the receiver are both target vectors;

[0024] The target vectors are both encrypted and compressed to obtain the feature vectors of the sender and the receiver;

[0025] The vector obtained by performing a bitwise XOR operation on the feature vectors of the sender and the receiver is taken as a biometric feature fusion vector.

[0026] Further, the method for obtaining the feature vectors is as follows:

[0027] For any target vector, the target vector is divided into multiple local vectors, each local vector is subjected to BCH encoding, a specified vector of each local vector after encoding is obtained, and a locking parameter of each local vector is constructed;

[0028] All the specified vectors are uniformly mapped through a hash algorithm to obtain the feature vector of the target vector after encryption and compression.

[0029] Further, the method for obtaining the real-time encryption key is as follows:

[0030] The vector constructed by binarizing the elements at the specified positions in the real-time reference vector of the sender is taken as the effective feature vector of the sender;

[0031] The effective feature vector of the sender is divided according to the division manner of the target vector, and the data in each local effective feature vector of the sender is restored in combination with the locking parameter of each local vector to obtain the de-blurred effective feature vector of the sender;

[0032] The de-blurred effective feature vector of the sender is converted into a vector with the same encryption length as the biometric feature fusion vector through a hash algorithm, which is taken as the specified feature vector of the sender;

[0033] The data obtained by performing an OR operation on the data in the specified feature vector of the sender and the biometric feature fusion vector is taken as the real-time encryption key of the sender.

[0034] Further, the method for obtaining the real-time decryption key is as follows:

[0035] The vector constructed by binarizing the elements at the specified positions in the real-time reference vector of the receiver is taken as the effective feature vector of the receiver;

[0036] The effective feature vector of the receiver is divided according to the division manner of the target vector, and the data in each local effective feature vector of the receiver is restored in combination with the locking parameter of each local vector to obtain the de-blurred effective feature vector of the receiver;

[0037] The receiver's deblurred effective feature vector is converted into a vector with the same length as the biometric feature fusion vector by a hash algorithm, as the receiver's specified feature vector.

[0038] The data obtained by performing an OR operation on the receiver's specified feature vector and the data in the biometric feature fusion vector is used as the receiver's real-time decryption key.

[0039] Further, the elements in the reference vector are all normalized data.

[0040] Further, the element binarization method is as follows:

[0041] When the element is greater than the preset binarization threshold, the corresponding element is set to 1.

[0042] When the element is less than or equal to the preset binarization threshold, the corresponding element is set to 0.

[0043] The present application has the following advantages:

[0044] The present application first obtains the reference average vector of each party and the confidence degree of each position element in the reference average vector according to the size and fluctuation of the same position elements in the reference vector of each party, accurately determines the data corresponding to the biometric features of the sender and the receiver, and accurately reflects the confidence degree of the data corresponding to the biometric features, which is beneficial to accurately screening the data corresponding to the locally stable features with reference significance in the sender and the receiver, and preparing for the stable and accurate fusion of the biometric features of the sender and the receiver; then determines the specified position of the elements that need to be retained in the reference average vector of the sender and the receiver based on the confidence degree, accurately determines the element position that can be fused to generate a shared key in the sender and the receiver, and then constructs a vector according to the binarization of the elements in the specified position of the reference average vector of the sender and the receiver, obtains a biometric feature fusion vector, accurately determines the shared key of the sender and the receiver, effectively avoids the situation that the shared key is not accurately recognized due to the fluctuation of the biometric features, effectively avoids the risk of the key in the transmission process, and improves the stability and security of data transmission; in order to accurately and in real time authenticate the payment security of the commodity supply chain platform, the real-time encryption key of the sender and the real-time decryption key of the receiver are accurately obtained in real time based on the biometric feature fusion vector and the real-time reference vector of the sender and the receiver, so that the payment security of the commodity supply chain platform is accurately and efficiently authenticated, the user experience is effectively improved, and the commodity supply chain platform is widely applied and popularized. BRIEF DESCRIPTION OF DRAWINGS

[0045] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description only constitute some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort.

[0046] Figure 1 A schematic flow chart of a commodity supply chain platform payment security authentication method based on biometric authentication provided by an embodiment of the present application is shown in

[0047] Figure 2 A system structure diagram of a commodity supply chain platform payment security authentication system based on biometric authentication provided by an embodiment of the present application is shown in

[0048] Figure 3 A schematic diagram of a computer device provided by an embodiment of the present application is shown in DETAILED DESCRIPTION

[0049] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined purpose, the commodity supply chain platform payment security authentication method based on biometric authentication according to the present application, its specific implementation, structure, features and effects are described in detail as follows in combination with the drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0050] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0051] The specific scheme of the commodity supply chain platform payment security authentication method based on biometric authentication provided by the present application is specifically described below in combination with the drawings. Embodiment 1

[0052] The present application proposes a commodity supply chain platform payment security authentication method based on biometric authentication, please refer to Figure 1 , which shows a schematic flow chart of a commodity supply chain platform payment security authentication method based on biometric authentication provided by an embodiment of the present application. The method comprises the following steps:

[0053] Step S1: Obtain the biometric feature vector of the sender and the receiver multiple times, both as reference vectors.

[0054] Specifically, the embodiment takes a sender and a receiver in a commodity supply chain platform as an example for analysis, and the subsequent sender and receiver are all the sender and receiver in the above. In addition, known biometric features include fingerprints, faces, irises, and palm prints, and the embodiment takes fingerprints as an example for analysis, and the subsequent biometric features are all assumed to be fingerprints. In order to ensure the security of the data transmitted by the sender to the receiver, the embodiment encrypts the data through the biometric features of the sender and the receiver, because the biometric features are unique, and the biometric feature authentication is combined in the data transmission process, which effectively improves the security of data transmission.

[0055] In order to accurately analyze the biometric features of the sender and the receiver, the embodiment obtains the fingerprint images of the sender and the receiver multiple times when the sender and the receiver register the commodity supply chain platform. The embodiment sets that three fingerprint images need to be obtained when each user registers the commodity supply chain platform, and the implementer can set the number of fingerprint images obtained by each user when registering according to the actual situation, which is not limited here. Each user's fingerprint image when registering is of the same finger. The fingerprint images of the sender and the receiver are input into the trained neural network or a special fingerprint feature extraction model to obtain the biometric feature vector corresponding to each fingerprint image, that is, the biometric feature vectors of the sender and the receiver are obtained multiple times. In order to better describe, the biometric feature vectors of the sender and the receiver obtained multiple times are all used as reference vectors. It should be noted that the elements in the reference vector are all normalized data, and each reference vector is a 512-dimensional floating-point number array. The method of obtaining the biometric feature vector through the neural network or the special fingerprint feature extraction model is a known technology, and will not be described here.

[0056] Step S2: According to the size and fluctuation of the same position elements in each party's reference vector, obtain each party's reference average vector and the confidence degree of each position element in the reference average vector.

[0057] Specifically, in the existing method, the reference vectors of the sender and the receiver are fused to generate a shared key, but in actual situations, the biometric features, that is, the reference vectors, have benign fluctuations. When the reference vectors of both parties are fused, the fluctuations of the reference vectors of both parties will be accumulated, which may cause the benign fluctuations to exceed the limit, thereby causing the shared key recognition to fail and unable to enable the data to be transmitted safely and stably. In order to avoid the accumulation of benign fluctuations of the shared key generated by fusion exceeding the limit, it is necessary to screen the data, that is, the elements, in the reference vectors of the sender and the receiver, and select elements with higher stability for encoding transmission to generate a shared key, to ensure the stability of the shared key.

[0058] For any one of the sender and the receiver, the same position elements in the reference vector of the party represent the characteristics of the same region, and the more equal the elements of all the reference vectors of the party at the same position are, the more stable the elements at the position are, and the more reference significance the elements have in generating the shared secret key; in order to more accurately analyze the reference significance of the elements at each position in the reference vector, the embodiment constructs a vector composed of the mean values of the elements at the same position in all the reference vectors of the party as the reference average vector of the party, and the elements in the reference average vector have the function of reducing errors, therefore, the elements in the reference average vector have more analysis significance; considering that data transmission in the network needs to be binarized, therefore, the embodiment sets a preset binarization threshold, and the more similar the element at a certain position in the reference average vector is to the preset binarization threshold, the less reference significance the element at the position has, because when the element at the position has a slight fluctuation, it may cause bit flipping, and the credibility is relatively low. Therefore, the embodiment obtains the reference average vector of each party and the confidence degree of each position element in the reference average vector according to the size and fluctuation of the same position elements in the reference vector of each party. The greater the confidence degree is, the more reference significance the corresponding position element in the corresponding reference average vector has, and the more it should be reserved.

[0059] Preferably, in an implementable manner of the embodiment, the method for obtaining the reference average vector is: for any one of the sender and the receiver, the mean value of the same position elements in all the reference vectors of the party is taken as the reference element at the corresponding position in the vector; and the vector composed of the reference elements is taken as the reference average vector of the party; wherein the number of elements in the reference average vector and the reference vector is the same. A certain element in the reference average vector of the party is the mean value of the elements at the same position in the reference vector of the party.

[0060] So far, the reference average vectors of the sender and the receiver are obtained, which prepares for the subsequent accurate acquisition of the fusion elements of the sender and the receiver.

[0061] Preferably, in an implementable manner of the embodiment, the confidence degree obtaining method is: for any position element in the reference average vector of any party, the absolute value of the difference between the position element and the preset binarization threshold is taken as the first trusted analysis value of the position element, the smaller the first trusted analysis value, the less the position element has reference significance, and the lower the trustworthiness. The preset binarization threshold is set to 0.5 in the embodiment, and the implementer can set the size of the preset binarization threshold according to the actual situation, which is not limited here. In order to more accurately analyze the trustworthiness of the position element, and then take the standard deviation of the elements in the same position as the position element in all reference vectors of the party as the second trusted analysis value of the position element, the smaller the second trusted analysis value, the more the position element has reference significance, and the higher the trustworthiness; in order to prepare to represent the trustworthiness of the position element, the embodiment takes the product of the first trusted analysis value and the negative correlation result of the second trusted analysis value as the result of normalization, as the confidence degree of the position element. The embodiment normalizes the product by the norm normalization function; the embodiment takes the reciprocal of the second trusted analysis value as the power of the exponential function with the natural constant as the base, and the output result of the exponential function is the negative correlation result of the second trusted analysis value.

[0062] At this point, the confidence degree of each position element in the reference average vector of the sending party and the receiving party is obtained, which is beneficial to accurately screening the fusion elements of the sending party and the receiving party subsequently.

[0063] Step S3: determining the specified position of the element to be retained in the reference average vector of the sending party and the receiving party based on the confidence degree; and obtaining the biometric feature fusion vector according to the vector constructed by binarizing the elements at the specified position in the reference average vector of the sending party and the receiving party.

[0064] Specifically, the greater the confidence degree, the more the element at the corresponding position in the corresponding reference average vector has reference significance, and then the position of the element to be retained in the reference average vector of the sending party and the receiving party can be determined based on the confidence degree. In actual situations, the positions of the retained elements in the reference average vectors of the sending party and the receiving party can be different. In order to make the elements with reference significance in the reference average vectors of the sending party and the receiving party fuse to generate a shared secret key, the data transmitted by the two parties can be encrypted and decrypted subsequently, therefore, the position of the element to be retained in the reference average vectors of the sending party and the receiving party needs to be found, which is beneficial to accurately obtaining the shared secret key subsequently. Then, the embodiment first determines the specified position of the element to be retained in the reference average vector of the sending party and the receiving party based on the confidence degree; and then obtains the biometric feature fusion vector, i.e. the shared secret key, according to the vector constructed by binarizing the elements at the specified position in the reference average vector of the sending party and the receiving party.

[0065] Preferably, in one implementation of the embodiment, the method for obtaining the specified position is as follows: the same rule is used to label the element positions in the reference average vectors of the sender and the receiver, and the labels of each element position in the reference average vectors of the sender and the receiver are obtained; wherein the labels of the same element positions in the reference average vectors of the sender and the receiver are the same; wherein the rule for labeling the element positions in the reference average vector is that the element positions in the reference average vector are sequentially labeled as 1, 2, 3, 4, 5, 6…520, 521 from left to right. The embodiment sets the preset confidence threshold to 0.6, and the implementer can set the size of the preset confidence threshold according to the actual situation, which is not limited here. When the confidence degree is greater than the preset confidence threshold, the corresponding element position in the reference average vector is reserved, and then the labels of the reserved element positions in the reference average vectors of the sender and the receiver are determined, which are all constructed into a label set; the intersection of the label sets of the sender and the receiver is taken as a common label set; and then the element positions corresponding to the labels in the common label set in the reference average vector are all taken as the specified positions.

[0066] Preferably, in one implementation of the embodiment, the method for obtaining the biometric fusion vector is as follows: the vectors constructed by binarizing the elements at the specified positions in the reference average vectors of the sender and the receiver are all taken as target vectors; wherein the method for binarizing the elements is as follows: when an element is greater than a preset binarization threshold, the corresponding element is set to 1; and when an element is less than or equal to the preset binarization threshold, the corresponding element is set to 0. In order to ensure the security of the shared secret key, the embodiment further performs fuzzy extraction on the data in the target vectors of the sender and the receiver, that is, the target vectors are all encrypted and compressed to obtain the feature vectors of the sender and the receiver; and then the vector obtained by performing bitwise XOR operation on the feature vectors of the sender and the receiver is taken as the biometric fusion vector. The biometric fusion vector is sent to the sender and the receiver respectively, and is saved by both parties in a secure environment, so as to achieve the purpose that only the biometric features of both parties can encrypt and decrypt the transmitted data.

[0067] Preferably, in one implementation of the present embodiment, the feature vector acquisition method is as follows: for any target vector, the target vector is divided into multiple local vectors, and the number of elements in each local vector is set to 128 in the present embodiment, and the length of each local vector can be set by the implementer according to actual conditions, which is not limited here. It should be noted that for the last local vector, if the number of elements is less than 128, 0 is added at the end. Then each local vector is subjected to BCH (Bose-Chaudhuri-Hocquenghem) encoding, and a BCH check bit with a length of 128 is added to each local vector, wherein the number of error-tolerant bits in BCH encoding is set to 10 in the present embodiment, and the size of the error-tolerant bits can be set by the implementer according to actual conditions, which is not limited here, and then the specified vector after encoding of each local vector is obtained and the locking parameter of each local vector is constructed; in order to improve the data transmission and encryption and decryption efficiency, the present embodiment further unifies the mapping of all specified vectors through a hash algorithm to obtain the feature vector after encryption and compression of the target vector. The length of the feature vector is set to 256 in the present embodiment, that is, the feature vector contains 256 elements, and the length of the feature vector can be set by the implementer according to actual conditions, which is not limited here. The BCH encoding, locking parameter and hash algorithm are all known technologies and will not be described here.

[0068] It should be noted that the entire acquisition process of the biometric fusion vector is processed on a trusted execution platform.

[0069] Step S4: Based on the biometric fusion vector, the real-time reference vector of the sender and the receiver, the real-time encryption key of the sender and the real-time decryption key of the receiver are obtained, and the payment security authentication of the commodity supply chain platform is performed.

[0070] Specifically, after the biometric fusion vector of the sender and the receiver, i.e., the shared key, is known, the biometric features of the sender and the receiver, i.e., the reference vectors, are combined to determine the real-time encryption key of the sender and the real-time decryption key of the receiver, which effectively improves the security of the key and further ensures the security and stability of the transmitted data, and improves the accuracy of the payment security authentication of the commodity supply chain platform. Therefore, the present embodiment obtains the real-time encryption key of the sender and the real-time decryption key of the receiver based on the biometric fusion vector, the real-time reference vector of the sender and the receiver, and performs the payment security authentication of the commodity supply chain platform.

[0071] Preferably, in one of the implementable manners of the present embodiment, the method for obtaining the real-time encryption key is as follows: the vector constructed by binarizing the elements at the specified positions in the real-time reference vector of the sender is taken as the effective feature vector of the sender; the effective feature vector of the sender is divided according to the division manner of the target vector, and the data in each local effective feature vector of the sender is restored in combination with the locking parameters of each local vector to obtain the de-blurred effective feature vector of the sender; the de-blurred effective feature vector of the sender is converted into a vector with the same length as the biometric feature fusion vector through a hash algorithm, which is taken as the specified feature vector of the sender; and the data obtained by performing an OR operation on the specified feature vector of the sender and the data in the biometric feature fusion vector is taken as the real-time encryption key of the sender.

[0072] The sender encrypts and transmits the data by using the obtained encryption key.

[0073] Preferably, in one of the implementable manners of the present embodiment, the method for obtaining the real-time decryption key is as follows: the vector constructed by binarizing the elements at the specified positions in the real-time reference vector of the receiver is taken as the effective feature vector of the receiver; the effective feature vector of the receiver is divided according to the division manner of the target vector, and the data in each local effective feature vector of the receiver is restored in combination with the locking parameters of each local vector to obtain the de-blurred effective feature vector of the receiver; the de-blurred effective feature vector of the receiver is converted into a vector with the same length as the biometric feature fusion vector through a hash algorithm, which is taken as the specified feature vector of the receiver; and the data obtained by performing an OR operation on the specified feature vector of the receiver and the data in the biometric feature fusion vector is taken as the real-time decryption key of the receiver.

[0074] The receiver decrypts the received transmission data by using the obtained decryption key.

[0075] It should be noted that the encryption key of the sender and the decryption key of the receiver are the same in the same data transmission.

[0076] In summary, in the present embodiment, the biometric feature vector of the sender and the receiver are both taken as the reference vector; the reference average vector and the confidence degree of each element in the reference average vector are obtained according to the size and fluctuation of the elements at the same positions in the reference vector of each party; the specified positions in the reference average vector where the elements need to be retained are determined based on the confidence degree; the biometric feature fusion vector is obtained according to the vector constructed by binarizing the elements at the specified positions, and then the real-time encryption key and the real-time decryption key are obtained to perform payment security authentication on the commodity supply chain platform. The present application effectively improves the stability of the key by obtaining the biometric feature fusion vector, avoids the leakage of the key in the transmission process, and effectively improves the accuracy and efficiency of the payment security authentication on the commodity supply chain platform. Embodiment 2

[0077] The application further provides a commodity supply chain platform payment security authentication system based on biometric authentication. Figure 2 It shows a structure diagram of a commodity supply chain platform payment security authentication system based on biometric authentication provided by one embodiment of the application, and the system comprises a data acquisition module 10, a confidence degree acquisition module 20, a biometric feature fusion vector acquisition module 30 and a data processing module 40.

[0078] The data acquisition module 10 is used for acquiring the biometric feature vectors of the sender and the receiver multiple times, and the biometric feature vectors are all used as reference vectors.

[0079] The confidence degree acquisition module 20 is used for acquiring the reference average vector of each party and the confidence degree of each position element in the reference average vector according to the size and fluctuation of the same position elements in the reference vector of each party.

[0080] The biometric feature fusion vector acquisition module 30 is used for determining the specified positions of the elements that need to be reserved in the reference average vectors of the sender and the receiver based on the confidence degree, and acquiring the biometric feature fusion vector according to the vector constructed by binarizing the elements at the specified positions in the reference average vectors of the sender and the receiver.

[0081] The data processing module 40 is used for acquiring the real-time encryption secret key of the sender and the real-time decryption secret key of the receiver based on the biometric feature fusion vector and the real-time reference vectors of the sender and the receiver, and performing payment security authentication on the commodity supply chain platform.

[0082] It should be noted that the system provided in the above embodiment is only used as an example for the division of the above functional modules, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the commodity supply chain platform payment security authentication system based on biometric authentication and the commodity supply chain platform payment security authentication method based on biometric authentication provided in the above embodiment belong to the same concept, and the specific implementation process is described in the method embodiment, which will not be repeated here. Embodiment 3

[0083] The application further provides a device for payment security authentication of a commodity supply chain platform based on biometric authentication, which comprises a memory and a processor, wherein the memory stores executable program codes, and the processor is used to call and execute the executable program codes to execute the method for payment security authentication of a commodity supply chain platform based on biometric authentication provided in the embodiments. The device can be a chip, an assembly or a module. The chip can comprise a processor and a memory connected to each other. When the processor calls and executes the instructions, the chip can execute the method for payment security authentication of a commodity supply chain platform based on biometric authentication provided in the embodiments.

[0084] In addition, the embodiments of the application also protect a computer device, please refer to Figure 3 The computer device comprises a memory 401, a processor 402 and a computer program 403 stored in the memory 401 and running on the processor 402. When the processor 402 executes the computer program 403, the computer device can execute any of the methods for payment security authentication of a commodity supply chain platform based on biometric authentication introduced above. Embodiment 4

[0085] The embodiments also provide a computer readable storage medium, which stores computer program codes. When the computer program codes run on a computer, the computer can execute the related method steps to implement the method for payment security authentication of a commodity supply chain platform based on biometric authentication provided in the embodiments. Embodiment 5

[0086] The embodiments also provide a computer program product. When the computer program product runs on a computer, the computer can execute the related steps to implement the method for payment security authentication of a commodity supply chain platform based on biometric authentication provided in the embodiments.

[0087] The device, the computer readable storage medium, the computer program product or the chip provided in the embodiments are used to execute the corresponding methods provided above, so the beneficial effects achieved thereby can refer to the beneficial effects of the corresponding methods provided above, which will not be described here again.

[0088] It should be noted that the sequence of the above embodiments of the application is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0089] The various embodiments described in this specification are presented by way of example, and each embodiment is not inherently more important than any other embodiment.

Claims

1. A method for payment security authentication of a commodity supply chain platform based on biometric authentication, characterized in that, The method comprises the following steps: Multiple biological feature vectors of the sender and the receiver are acquired, and each is taken as a reference vector; According to the size and fluctuation of the elements at the same position in each reference vector, a reference average vector of each party and the confidence degree of each element in the reference average vector are obtained; Based on the confidence degree, the specified positions of the elements that need to be reserved in the reference average vectors of the sender and the receiver are determined; and based on the elements at the specified positions in the reference average vectors of the sender and the receiver, a biological feature fusion vector is constructed by binarizing the elements; Based on the biological feature fusion vector, the real-time reference vectors of the sender and the receiver, a real-time encryption key of the sender and a real-time decryption key of the receiver are obtained, and payment security authentication of the commodity supply chain platform is performed; The reference average vector is obtained by the following method: For any one of the sender and the receiver, the mean value of the elements at the same position in all reference vectors of the party is taken as the reference element at the corresponding position in the vector; The vector composed of the reference elements is taken as the reference average vector of the party; wherein the number of elements in the reference average vector and the reference vector is the same; The confidence degree is obtained by the following method: For any one position element in the reference average vector of any one party, the difference between the position element and a preset binarization threshold is taken as the first credible analysis value of the position element; The standard deviation of the elements at the same position as the position element in all reference vectors of the party is taken as the second credible analysis value of the position element; The product of the negative correlation result of the first credible analysis value and the second credible analysis value is normalized to obtain the confidence degree of the position element; The biological feature fusion vector is obtained by the following method: The vector constructed by binarizing the elements at the specified positions in the reference average vectors of the sender and the receiver is taken as the target vector; The target vector is encrypted and compressed to obtain the feature vectors of the sender and the receiver; The vector obtained by performing bitwise XOR operation on the feature vectors of the sender and the receiver is taken as the biological feature fusion vector.

2. The method of claim 1, wherein the method is characterized by: The specified position is obtained by the following method: The element positions in the reference average vectors of the sender and the receiver are labeled with the same rule to obtain the labels of each element position in the reference average vectors of the sender and the receiver; wherein the labels of the same element positions in the reference average vectors of the sender and the receiver are the same; When the confidence degree is greater than a preset confidence degree threshold, the corresponding position elements in the reference average vector are reserved, the labels of the reserved element positions in the reference average vectors of the sender and the receiver are determined, and each is constructed into a label set; The intersection of the label sets of the sender and the receiver is taken as a common label set; The element positions corresponding to the labels in the common label set in the reference average vector are taken as the specified positions.

3. The method of claim 1, wherein the method further comprises: receiving a request for a payment from a user; and transmitting a payment request to the user, wherein the payment request includes a payment amount and a payment method. The feature vector is obtained by the following method: For any target vector, the target vector is divided into multiple local vectors, each local vector is BCH encoded to obtain the specified vector after encoding of each local vector and the locking parameter of each local vector is constructed; The specified vectors are uniformly mapped by a hash algorithm to obtain the encrypted and compressed feature vectors of the target vector.

4. The payment security authentication method for a commodity supply chain platform based on biometric authentication as described in claim 3, characterized in that, The method for obtaining the real-time encryption key is: A vector constructed by binarizing the elements at the specified positions in the real-time reference vector of the sender is used as the effective feature vector of the sender; The effective feature vector of the sender is divided according to the division mode of the target vector, and the data in each local effective feature vector of the sender is restored in combination with the locking parameters of each local vector to obtain the de-blurred effective feature vector of the sender; The de-blurred effective feature vector of the sender is converted into a vector with the same encryption length as the biometric feature fusion vector by a hash algorithm, which is used as the specified feature vector of the sender; The data obtained by performing an OR operation on the specified feature vector of the sender and the data in the biometric feature fusion vector is used as the real-time encryption key of the sender.

5. The payment security authentication method for a commodity supply chain platform based on biometric authentication as described in claim 3, characterized in that, The method for obtaining the real-time decryption key is: A vector constructed by binarizing the elements at the specified positions in the real-time reference vector of the receiver is used as the effective feature vector of the receiver; The effective feature vector of the receiver is divided according to the division mode of the target vector, and the data in each local effective feature vector of the receiver is restored in combination with the locking parameters of each local vector to obtain the de-blurred effective feature vector of the receiver; The de-blurred effective feature vector of the receiver is converted into a vector with the same encryption length as the biometric feature fusion vector by a hash algorithm, which is used as the specified feature vector of the receiver; The data obtained by performing an OR operation on the specified feature vector of the receiver and the data in the biometric feature fusion vector is used as the real-time decryption key of the receiver.

6. The payment security authentication method for a commodity supply chain platform based on biometric authentication as described in claim 1, characterized in that, The elements in the reference vector are normalized data.

7. The payment security authentication method for a commodity supply chain platform based on biometric authentication as described in claim 1, characterized in that, The method for binarizing the elements is: When an element is greater than a preset binarization threshold, the corresponding element is set to 1; When an element is less than or equal to a preset binarization threshold, the corresponding element is set to 0.

Images