A data encryption method, device and related equipment

Abstract

The application discloses a data encryption method and device and related equipment. The method comprises the following steps: obtaining a to-be-encrypted data packet, the to-be-encrypted data packet containing a plurality of physiological index data of a target user in a same time period; determining initial feature vectors of the physiological index data contained in the to-be-encrypted data packet; performing nonlinear transformation on each initial feature vector to obtain a transformed feature vector corresponding to each initial feature vector; determining a correlation feature and global information of each physiological index based on the transformed feature vector corresponding to each initial feature vector; and encrypting the global information based on the correlation feature and encrypting the to-be-encrypted data packet based on a user private key. The application encrypts the global information based on the correlation feature, can obtain the correlation of each index without decrypting the original data, and can guarantee the privacy of the original data.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical health, and in particular to a data encryption method and device and related equipment. BACKGROUND

[0002] With the popularity of wearable devices and home health monitoring devices, personal health data collection is becoming more and more convenient, and various physiological indicator data such as blood pressure, blood sugar, electrocardiogram, and weight are widely collected and applied. However, traditional medical data encryption usually adopts an independent encryption mode, that is, each physiological indicator data of a user is encrypted separately. Since each physiological indicator data is encrypted separately, when subsequent data is accessed to determine the correlation between each physiological indicator of the user, all physiological indicator data needs to be decrypted, and each physiological indicator data decrypted at the same time is obtained, so as to determine the correlation between each physiological indicator of the user. Obviously, this encryption and decryption method is troublesome and easy to expose the original health data of the user.

[0003] In addition, the traditional encryption algorithm generates a key through a fixed algorithm and performs encryption, and the randomness of the key generation is low and easy to be cracked. SUMMARY

[0004] The main purpose of the present application is to provide a data encryption method, device and related equipment, which aims to solve the problem that the traditional encryption algorithm generates a key through a fixed algorithm and is easy to be cracked.

[0005] To achieve the above purpose, the present application provides a data encryption method, comprising:

[0006] obtaining a to-be-encrypted data packet, the to-be-encrypted data packet containing a plurality of physiological indicator data of a target user in a same time period;

[0007] determining an initial feature vector of each physiological indicator data contained in the to-be-encrypted data packet;

[0008] performing nonlinear transformation on each initial feature vector to obtain a transformed feature vector corresponding to each initial feature vector;

[0009] determining a correlation feature between each physiological indicator and global information of the to-be-encrypted data packet based on the transformed feature vector corresponding to each initial feature vector;

[0010] encrypting the global information based on the correlation feature between each physiological indicator to obtain a first ciphertext, and encrypting the to-be-encrypted data packet based on a private key of the target user to obtain a second ciphertext.

[0011] In the embodiment of the present application, each initial feature vector is nonlinearly transformed based on the following method:

[0012]

[0013] in, For the first The initial feature vector of each physiological indicator for The weight parameters, for The bias term, It is the hyperbolic tangent function. For the first Transformed feature vectors corresponding to each physiological indicator.

[0014] In this embodiment of the application, determining the correlation features between the various physiological indicators based on the transformed feature vectors corresponding to each initial feature vector includes:

[0015] Determine the relationship matrix between the transformed feature vectors corresponding to each initial feature vector, and use the relationship matrix as the correlation feature between the various physiological indicators.

[0016] In this embodiment of the application, the relationship matrix is ​​determined based on the following method:

[0017] Determine the Pearson correlation coefficient between each pair of transformed eigenvectors, and obtain the relationship matrix based on each Pearson correlation coefficient; or

[0018] Determine the attention score of each transformed feature vector relative to the other transformed feature vectors, and obtain the relationship matrix based on each attention score; or

[0019] Determine the Euclidean distance between each pair of transformed eigenvectors, and obtain the relation matrix based on each Euclidean distance; or

[0020] The cosine distance between each pair of transformed eigenvectors is determined, and the relationship matrix is ​​obtained based on each cosine distance.

[0021] In this embodiment of the application, the global information of the data packet to be encrypted is determined based on the following method:

[0022] F(V1, ..., Vn) = +

[0023] in, For the first Transformed feature vectors corresponding to each physiological indicator For the first The weights of the transformed feature vectors corresponding to each physiological indicator. The correlation information between the physiological indicators is represented by δ, which is a correlation strength adjustment coefficient, k≤n, and F(V1, …, Vn) represents global information of the data packet to be encrypted.

[0024] In the embodiment of the present application, the global information is encrypted based on the correlation characteristics between the physiological indicators to obtain first ciphertext, including:

[0025] Determining a first anchor point of the global information;

[0026] Encrypting the first anchor point based on the correlation characteristics between the physiological indicators to obtain the first ciphertext.

[0027] In the embodiment of the present application, the first anchor point is determined based on the following method:

[0028] A1 = H(F(V1, …, Vn) || r)

[0029] Wherein, A1 represents the first anchor point, H represents a hash operation, F(V1, …, Vn) represents the global information of the data packet to be encrypted, r represents a random number or noise, and || represents a connection operation.

[0030] In the embodiment of the present application, the global information is encrypted based on the following method:

[0031] C1 = Enc(A1, R)

[0032] Wherein, C1 represents the first ciphertext, A1 represents the first anchor point, R represents a correlation matrix, and Enc represents an encryption algorithm.

[0033] In the embodiment of the present application, the second ciphertext is determined based on the following method:

[0034] C2 = Enc(PKu, D)

[0035] Wherein, C2 represents the second ciphertext, PKu represents a user private key, D represents each physiological indicator data contained in the data packet to be encrypted, and Enc represents an encryption algorithm.

[0036] In the embodiment of the present application, the data encryption method further includes:

[0037] Determining a second anchor point based on the first anchor point, the institutional characteristics, and the time effectiveness characteristics;

[0038] Determining a third anchor point based on the second anchor point and the biological characteristics of the target user;

[0039] Encrypting the third anchor point based on an attribute-based encryption algorithm to obtain third ciphertext.

[0040] In the embodiments of the present application, the second anchor point is obtained based on the following method:

[0041] A2 = H (A1||S||t)

[0042] wherein A2 represents the second anchor point, A1 represents the first anchor point, H represents a hash operation, S represents an institution feature requiring authorization, t represents an authorization period, and || represents a connection operation.

[0043] In the embodiments of the present application, the third anchor point is obtained based on the following method:

[0044] A3 = H (A2||M)

[0045] wherein A3 represents the third anchor point, A2 represents the second anchor point, H represents a hash operation, and M represents a biological feature of a target user.

[0046] In the embodiments of the present application, the third ciphertext is obtained based on the following method:

[0047] C3 = ABE (P, A3)

[0048] wherein C3 represents the third ciphertext, ABE represents an attribute-based encryption algorithm, P represents an access policy in the ABE, and A3 represents the third anchor point.

[0049] The present application also provides a data encryption device, comprising:

[0050] an acquisition module configured to acquire a data packet to be encrypted, wherein the data packet to be encrypted contains a plurality of physiological index data of a target user in a same time period;

[0051] a processing module configured to determine an initial feature vector of each physiological index data contained in the data packet to be encrypted;

[0052] performing a nonlinear transformation on each initial feature vector to obtain a transformed feature vector corresponding to each initial feature vector;

[0053] determining a correlation feature between the plurality of physiological indexes and global information of the data packet to be encrypted based on the transformed feature vector corresponding to each initial feature vector;

[0054] encrypting the global information based on the correlation feature between the plurality of physiological indexes to obtain a first ciphertext, and encrypting the data packet to be encrypted based on a private key of the target user to obtain a second ciphertext.

[0055] In the embodiments of the present application, the processing module is configured to perform a nonlinear transformation on each initial feature vector based on the following manner:

[0056]

[0057] in, For the first The initial feature vector of each physiological indicator for The weight parameters, for The bias term, It is the hyperbolic tangent function. For the first Transformed feature vectors corresponding to physiological indicators.

[0058] In this embodiment of the application, the processing module is further configured to:

[0059] Determine the relationship matrix between the transformed feature vectors corresponding to each initial feature vector, and use the relationship matrix as the correlation feature between the various physiological indicators.

[0060] In this embodiment of the application, the processing module is configured to determine the relationship matrix based on the following method:

[0061] Determine the Pearson correlation coefficient between each pair of transformed eigenvectors, and obtain the relationship matrix based on each Pearson correlation coefficient; or

[0062] Determine the attention score of each transformed feature vector relative to the other transformed feature vectors, and obtain the relationship matrix based on each attention score; or

[0063] Determine the Euclidean distance between each pair of transformed eigenvectors, and obtain the relation matrix based on each Euclidean distance; or

[0064] The cosine distance between each pair of transformed eigenvectors is determined, and the relationship matrix is ​​obtained based on each cosine distance.

[0065] In this embodiment of the application, the processing module is configured to determine the global information of the data packet to be encrypted based on the following method:

[0066] F(V1, ..., Vn) = +

[0067] in, For the first Transformed feature vectors corresponding to each physiological indicator For the first The weights of the transformed feature vectors corresponding to each physiological indicator. δ represents the correlation information between various physiological indicators, δ is the correlation strength adjustment coefficient, k≤n, and F(V1,……,Vn) represents the global information of the data packet to be encrypted.

[0068] In the embodiments of the present application, the processing module is further configured to:

[0069] determine a first anchor point of the global information;

[0070] encrypt the first anchor point based on the correlation characteristics between the physiological indicators to obtain the first ciphertext.

[0071] In the embodiments of the present application, the processing module is configured to determine the first anchor point based on the following manner:

[0072] A1 = H(F(V1,..., Vn) || r)

[0073] wherein A1 represents the first anchor point, H represents the hash operation, F(V1,..., Vn) represents the global information of the data packet to be encrypted, r represents a random number or noise, and || represents the connection operation.

[0074] In the embodiments of the present application, the processing module is configured to encrypt the global information based on the following manner:

[0075] C1 = Enc(A1, R)

[0076] wherein C1 represents the first ciphertext, A1 represents the first anchor point, R represents the correlation matrix, and Enc represents the encryption algorithm.

[0077] In the embodiments of the present application, the processing module is configured to determine the second ciphertext based on the following manner:

[0078] C2 = Enc(PKu, D)

[0079] wherein C2 represents the second ciphertext, PKu represents the user private key, D represents the physiological indicator data contained in the data packet to be encrypted, and Enc represents the encryption algorithm.

[0080] In the embodiments of the present application, the processing module is configured to:

[0081] determine a second anchor point based on the first anchor point, the institutional characteristics, and the time characteristics;

[0082] determine a third anchor point based on the second anchor point and the biological characteristics of the target user;

[0083] encrypt the third anchor point based on the attribute-based encryption algorithm to obtain a third ciphertext.

[0084] In the embodiments of the present application, the processing module is configured to obtain the second anchor point based on the following manner:

[0085] A2 = H(A1 || S || t)

[0086] wherein A2 represents the second anchor point, A1 represents the first anchor point, H represents a hash operation, S represents an institution feature requiring authorization, t represents an authorization period, and || represents a connection operation.

[0087] In the embodiments of the present application, the processing module is configured to obtain the third anchor point based on the following manner:

[0088] A3 = H(A2||M)

[0089] wherein A3 represents the third anchor point, A2 represents the second anchor point, H represents a hash operation, and M represents a biological feature of the target user.

[0090] In the embodiments of the present application, the processing module is configured to obtain the third ciphertext based on the following method:

[0091] C3 = ABE(P, A3)

[0092] wherein C3 represents the third ciphertext, ABE represents an attribute-based encryption algorithm, P represents an access policy in the ABE, and A3 represents the third anchor point.

[0093] The embodiments of the present application also propose a computer readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the data encryption method of any of the above embodiments.

[0094] The embodiments of the present application also propose a computing device comprising a processor, wherein the processor has a computer program stored thereon, and the computer program is executed to implement the data encryption method of any of the above embodiments.

[0095] In the embodiments of the present application, when encrypting the personal health data of the target user, the original health data is encrypted by the private key of the target user, which can fully guarantee the security of the original health data. In addition, the correlation features and global information of each physiological indicator data are determined based on the initial feature vector data of each physiological indicator data in the same time period, and the global information is encrypted by the correlation features as the key. The global information includes the original features of each physiological indicator and the correlation between each physiological indicator. Therefore, when the original features or correlation of each physiological indicator of the user need to be obtained subsequently, the global information can be decrypted by the correlation features as the key, without decrypting the original data, further strengthening the protection of the original health data. Moreover, the randomness of the key based on the correlation features between each physiological indicator is much higher than the key generated by the traditional fixed algorithm, which makes it difficult for attackers to predict the key through pattern analysis or brute force cracking, greatly reducing the risk of key leakage. Furthermore, the key changes dynamically with each physiological indicator, so even if a single key is cracked, it cannot be reused for other data or scenarios, effectively resisting replay attacks and batch cracking. Attached Figure Description

[0096] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0097] Figure 1 This is a flowchart illustrating the steps of a data encryption method in one embodiment of this application;

[0098] Figure 2 This is a block diagram of a data encryption device according to an embodiment of this application;

[0099] Figure 3 This is a block diagram of a computer-readable storage medium in one embodiment of this application;

[0100] Figure 4 This is a block diagram of a computing device according to one embodiment of this application.

[0101] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0102] The principles and spirit of this application will now be described with reference to several exemplary embodiments. It should be understood that these embodiments are provided merely to enable those skilled in the art to better understand and implement this application, and are not intended to limit the scope of this application in any way. Rather, these embodiments are provided to make this application more thorough and complete, and to fully convey the scope of this application to those skilled in the art.

[0103] Those skilled in the art will understand that embodiments of this application can be implemented as a system, device, method, or computer program product. Therefore, this application can be specifically implemented in the following forms: entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0104] According to the embodiments of this application, a data encryption method, apparatus and related equipment are proposed.

[0105] In this article, it is important to understand that any number of elements in the accompanying figures is for illustrative purposes and not for limitation, and any naming is for distinction only and has no limiting meaning.

[0106] The principles and spirit of this application will be explained in detail below with reference to several representative embodiments.

[0107] Exemplary method

[0108] As Figure 1 shown, the embodiment of the present application proposes a data encryption method, comprising the following steps S100-S500:

[0109] S100: obtaining a to-be-encrypted data packet, the to-be-encrypted data packet containing a plurality of physiological index data of a target user in a same time period.

[0110] In the embodiment of the present application, the data in the to-be-encrypted data packet is personal health data of the target user, and a to-be-encrypted data packet contains a plurality of physiological index data, such as blood pressure data, blood glucose data, blood type data, electrocardiogram data, heart rate data, etc. Each physiological index data contained in the to-be-encrypted data packet is personal health data of the target user in a same time period or under a same time stamp.

[0111] S200: determining an initial feature vector of each physiological index data contained in the to-be-encrypted data packet.

[0112] In the embodiment of the present application, the initial feature vector of each physiological index data contained in a to-be-encrypted data packet can be determined based on the type of each physiological index data.

[0113] For example, in the embodiment of the present application, the to-be-encrypted data packet includes blood pressure data, blood glucose data, blood type data, electrocardiogram data, and heart rate data.

[0114] For numerical physiological index data, the numerical value of the physiological index data can be taken as its initial feature vector.

[0115] For example, blood pressure data and blood glucose data are both numerical data, and when obtaining the initial feature vector, the numerical value of the blood pressure data and the blood glucose data can be taken as the respective corresponding initial feature vectors.

[0116] For example, the blood pressure data of the target user is 120 / 80, and the blood glucose data is 5.5, so the initial feature vector of the blood pressure data is [120, 80], and the initial feature vector of the blood glucose data is [5.5].

[0117] For physiological indicators containing category information, the initial feature vector can be obtained by encoding.

[0118] For example, blood type data is a physiological indicator containing category information, including A type, B type, AB type, and O type, and one-hot encoding can be used to encode A type, B type, AB type, and O type as 1000, 000, 0010, 0001, as the initial feature vector corresponding to each blood type.

[0119] Assuming the target user's blood type is A, the initial feature vector of the blood type data would be 1000.

[0120] For fluctuating physiological indicators, frequency domain features are extracted as their initial feature vectors.

[0121] For example, electrocardiogram (ECG) data is a fluctuating physiological indicator. When obtaining the initial feature vector of ECG data, frequency domain features can be extracted from the ECG data as the initial feature vector.

[0122] For physiological indicator data that is in sequence type, it can be converted into a fixed-length feature vector.

[0123] For example, heart rate is a physiological indicator of sequence type. When determining the initial feature vector of heart rate data, it can be converted into a fixed-length vector based on a recurrent neural network (RNN or Transformer) as the initial feature vector.

[0124] S300: Perform a nonlinear transformation on each initial eigenvector to obtain the transformed eigenvector corresponding to each initial eigenvector.

[0125] In step S200, the initial feature vectors corresponding to each physiological indicator data contained in the data packet to be encrypted are obtained. In step S300, a nonlinear transformation can be performed based on the initial feature vectors corresponding to each physiological indicator data to obtain the transformed feature vectors corresponding to each initial feature vector.

[0126] In this embodiment of the application, each initial feature vector can be nonlinearly transformed based on the following formula (1):

[0127] (1)

[0128] in, For the first The initial feature vector of each physiological indicator for The weight parameters, for The bias term, It is the hyperbolic tangent function. For the first Transformed feature vectors corresponding to physiological indicators.

[0129] S400: Based on the transformed feature vectors corresponding to each initial feature vector, determine the correlation features and global information between the various physiological indicators.

[0130] In this embodiment of the application, when determining the correlation features of each physiological indicator data, the relationship matrix between the transformed feature vectors corresponding to each initial feature vector can be used as the correlation feature between the various physiological indicator data.

[0131] In the embodiments of this application, the relationship matrix can be determined based on the following methods 1)-4):

[0132] Method 1)

[0133] The Pearson correlation coefficient between each pair of transformed eigenvectors is determined, and the relationship matrix is ​​obtained based on each Pearson correlation coefficient.

[0134] Method 2)

[0135] Each transformed feature vector is determined with respect to the attention scores of other transformed feature vectors, and the relationship matrix is ​​obtained based on each attention score.

[0136] Method 3)

[0137] The Euclidean distance between each pair of transformed eigenvectors is determined, and the relationship matrix is ​​obtained based on each Euclidean distance.

[0138] Method 4)

[0139] The cosine distance between each pair of transformed eigenvectors is determined, and the relationship matrix is ​​obtained based on each cosine distance.

[0140] Any of the methods described in 1-4 above can be used to determine the relationship matrix between the transformed eigenvectors corresponding to each initial eigenvector. The relationship matrix can represent the correlation between each transformed eigenvector. Since each transformed eigenvector is obtained by nonlinear transformation of each initial eigenvector, the relationship matrix can also represent the correlation between each initial eigenvector, and thus represent the correlation characteristics of each physiological indicator data.

[0141] In this embodiment of the application, when determining the global information of the data packet to be encrypted based on the transformed feature vectors corresponding to each initial feature vector, it can be determined based on the following formula (2):

[0142] F(V1, ..., Vn) = + (2)

[0143] in, For the first Transformed feature vectors corresponding to each physiological indicator For the first The weights of the transformed feature vectors corresponding to each physiological indicator. The correlation information between the physiological indicators is represented by δ, which is a correlation strength adjustment coefficient, k≤n, and F(V1,..., Vn) represents global information of the data packet to be encrypted.

[0144] In combination with the above formulas (1) and (2), wherein, is a linear combination part, and is based on Linear weighting is performed to capture the linear relationship between the physiological indicators, and the tanh function is used to process the nonlinear relationship between the physiological indicators. The correlation information of the physiological indicators is added. The correlation strength is adjusted. Based on formulas (1) and (2), the initial feature vector of each physiological indicator and the corresponding transformed feature are inputted, F(V1,..., Vn) is obtained after nonlinear transformation, F(V1,..., Vn) contains not only the feature information of each physiological indicator, but also the correlation information between the physiological indicators, that is, F(V1,..., Vn) contains the global information of the data packet to be encrypted.

[0145] In addition, the value of k in the above formula can be determined based on actual conditions. For example, if the physiological indicators include blood pressure data, blood glucose data, blood type data, electrocardiogram data, and heart rate data, and each physiological indicator has correlation, k can be n, that is, the correlation between all physiological indicators is added. For example, if the data packet to be encrypted includes a physiological indicator that has no correlation with other physiological indicators, the indicator can not be considered when adding the correlation of the physiological indicators, and k is less than n. For example, in addition to blood pressure data, blood glucose data, blood type data, electrocardiogram data, and heart rate data, the data packet to be encrypted also includes height. Obviously, the height data has no correlation with the blood pressure data, blood glucose data, blood type data, electrocardiogram data, and heart rate data. At this time, the height indicator is not considered when calculating

[0146] S500: Based on the correlation characteristics between the physiological indicators, the global information is encrypted to obtain first ciphertext, and the data packet to be encrypted is encrypted based on a target user private key to obtain second ciphertext.

[0147] In an embodiment of the present application, the first ciphertext can be obtained based on the following steps S510-S520:

[0148] S510: Determine the first anchor point of the global information.

[0149] In an embodiment of the present application, the first anchor point of the global information can be determined based on the following formula (3):

[0150] ​A1 = H(F(V1,..., Vn) || r) (3):

[0151] Wherein, A1 represents the first anchor point, H represents the hash operation, F(V1,..., Vn) represents the global information of the data packet to be encrypted, r represents the random number or noise, and || represents the connection operation.

[0152] In the embodiment of the application, the hash operation based on the global information of the data packet to be encrypted can obtain the first anchor point, and the first anchor point can be regarded as a digest of the global information.

[0153] In addition, when the hash operation is performed to obtain the first anchor point, the global information F(V1,..., Vn) is also connected with the random noise or noise r, so that the randomness of the hash input can be increased, so that even for the same global information vector, the first anchor point generated each time is also different, thereby helping to improve the security of encryption when subsequent encryption is performed based on the first anchor point, and preventing replay attacks.

[0154] S520: encrypting the first anchor point based on the correlation characteristics between the physiological indicators to obtain the first ciphertext.

[0155] In the embodiment of the application, the first anchor point can represent the digest of the global information of the data packet to be encrypted, and the correlation matrix can represent the correlation characteristics between the physiological indicator data, so when the global information is encrypted based on the correlation characteristics between the physiological indicators, the first anchor point can be encrypted based on the correlation matrix.

[0156] In the embodiment of the application, the first anchor point can be encrypted based on the correlation matrix based on the following formula (4):

[0157] C1 = Enc(A1, R) (4)

[0158] Wherein, C1 represents the first ciphertext, A1 represents the first anchor point, R represents the correlation matrix, and Enc represents the encryption algorithm.

[0159] In the embodiment of the application, after obtaining each initial feature vector, the method further includes: encrypting the data packet to be encrypted based on the private key of the target user to obtain a second ciphertext.

[0160] In the embodiment of the application, the second ciphertext can be determined based on the following formula (5):

[0161] C2 = Enc(PKu, D) (5)

[0162] Wherein, C2 represents the second ciphertext, PKu represents the user private key, D is the original data of each physiological index contained in the data packet to be encrypted, and Enc represents an encryption algorithm such as symmetric encryption, asymmetric encryption, and hash encryption.

[0163] Wherein, D is the original data of each physiological index of the data packet to be encrypted, for example, the data packet D to be encrypted includes blood pressure data, blood glucose data, blood type data, electrocardiogram data, and heart rate data.

[0164] In the embodiments of the present application, the original data of each physiological index data is encrypted using the private key of the target user to obtain the second ciphertext C2, and the second ciphertext can only be decrypted by the private key of the target user, thereby protecting the privacy of the original health data of the target user.

[0165] In addition, based on the initial feature vector data of each physiological index data in the same time period, the associated features and global information of each physiological index data are determined, and the global information is encrypted with the associated features as the key. The global information includes the original features of each physiological index and the association between each physiological index. Therefore, when the associated information of each physiological index of the user is needed in the subsequent process, the global information can be obtained by decrypting with the associated features as the key, without decrypting the original data, thereby further strengthening the protection of the original health data. Moreover, the randomness of the key based on the associated features between each physiological index is much higher than that of the key generated by the traditional fixed algorithm, and it is difficult for attackers to predict the key through pattern analysis or brute force cracking, thereby greatly reducing the risk of key leakage. Moreover, the key changes dynamically with each physiological index, so even if a single key is cracked, it cannot be reused for other data or scenarios, effectively resisting replay attacks and batch cracking.

[0166] In the embodiments of the present application, the data encryption method further includes the following steps S610-S630:

[0167] S610: determining a second anchor point based on the first anchor point, the institutional feature, and the time feature.

[0168] In the embodiments of the present application, the second anchor point is obtained based on the following formula (6):

[0169] A2 = H (A1||S||t) (6)

[0170] Wherein, A2 represents the second anchor point, A1 represents the first anchor point, H represents the hash operation, S represents the institutional feature that needs to be authorized, t represents the authorization period, and || represents the connection operation.

[0171] In the embodiments of the present application, the first anchor point A1 can be obtained based on the above step S520, S represents the authorized institution features such as the ID, number and the like of the authorized medical institution, and the authorized medical institution represents an institution that can access the data packet to be encrypted, and the authorized period represents a time period during which the data packet to be encrypted can be accessed.

[0172] S620: determining a third anchor point based on the second anchor point and the biological feature of the target user.

[0173] In the embodiments of the present application, the third anchor point is obtained based on the following formula (7):

[0174] A3 = H (A2||M) (7)

[0175] Wherein, A3 represents the third anchor point, A2 represents the second anchor point, H represents the hash operation, and M represents the biological feature of the target user.

[0176] In the embodiments of the present application, the biological feature of the target user can be unique information such as fingerprint information, voice information, iris information and face information.

[0177] S630: encrypting the third anchor point based on the attribute-based encryption algorithm to obtain third ciphertext.

[0178] In the embodiments of the present application, the third ciphertext is obtained based on the following formula (8):

[0179] C3 = ABE (P, A3) (8)

[0180] Wherein, C3 represents the third ciphertext, ABE represents the attribute-based encryption algorithm, P represents the access policy in ABE, and A3 represents the third anchor point.

[0181] In the embodiments of the present application, the third ciphertext is obtained based on the attribute-based encryption algorithm, and only when the attribute of the decrypted user satisfies the access policy corresponding to P, the decrypted user can use the corresponding key (A3) to decrypt the third ciphertext C3.

[0182] In the embodiments of the present application, the first anchor point contains the global information of each physiological index data contained in the data packet to be encrypted, the second anchor point introduces the authorized institution features and the authorized period based on the first anchor point, and the third anchor point introduces the biological feature of the decrypted user based on the second anchor point, so that the global information, the authorized institution permission, the authorized time period and the biological feature of the user can be comprehensively used to perform more detailed permission control on the health data of the target user.

[0183] Exemplary device

[0184] As Figure 2As shown, the present exemplary embodiment proposes a data encryption apparatus 100, which in the embodiment of the present application comprises:

[0185] The acquisition module 110 is configured to acquire a data packet to be encrypted, wherein the data packet to be encrypted contains a plurality of physiological index data of a target user in a same time period.

[0186] The processing module 120 is configured to determine an initial feature vector of each physiological index data contained in the data packet to be encrypted.

[0187] The processing module 120 is configured to determine an initial feature vector of each physiological index data contained in the data packet to be encrypted.

[0188] The processing module 120 is configured to determine an initial feature vector of each physiological index data contained in the data packet to be encrypted.

[0189] The processing module 120 is configured to determine an initial feature vector of each physiological index data contained in the data packet to be encrypted.

[0190] In the embodiment of the present application, the processing module 120 is configured to perform nonlinear transformation on each initial feature vector based on the following manner:

[0191]

[0192] wherein, is the initial feature vector of the i-th physiological index, is a weight parameter of the i-th physiological index, is a bias term of the i-th physiological index, is a hyperbolic tangent function, is the transformed feature vector corresponding to the i-th physiological index. In the embodiment of the present application, the processing module 120 is further configured to: determine a relationship matrix between the transformed feature vectors corresponding to each initial feature vector, and take the relationship matrix as the correlation feature between the physiological indexes.

[0193] In the embodiment of the present application, the processing module 120 is further configured to:

[0194] determine a relationship matrix between the transformed feature vectors corresponding to each initial feature vector, and take the relationship matrix as the correlation feature between the physiological indexes.

[0195] In the embodiment of the present application, the processing module 120 is configured to determine the relationship matrix based on the following manner:

[0196] determine a Pearson correlation coefficient between each two transformed feature vectors respectively, and obtain the relationship matrix based on each Pearson correlation coefficient; or​​

[0197] Determine the attention score of each transformed feature vector relative to other transformed feature vectors, and obtain the relationship matrix based on each attention score; or

[0198] Determine the Euclidean distance between each pair of transformed eigenvectors, and obtain the relation matrix based on each Euclidean distance; or

[0199] The cosine distance between each pair of transformed eigenvectors is determined, and the relationship matrix is ​​obtained based on each cosine distance.

[0200] In this embodiment of the application, the processing module 120 is configured to determine the global information of the data packet to be encrypted based on the following method:

[0201] F(V1, ..., Vn) = +

[0202] in, For the first Transformed feature vectors corresponding to each physiological indicator For the first The weights of the transformed feature vectors corresponding to each physiological indicator. δ represents the correlation information between various physiological indicators, δ is the correlation strength adjustment coefficient, k≤n, and F(V1,……,Vn) represents the global information of the data packet to be encrypted.

[0203] In this embodiment of the application, the processing module 120 is further configured to:

[0204] Determine the first anchor point of the global information;

[0205] The first anchor point is encrypted based on the correlation characteristics between the various physiological indicators to obtain the first ciphertext.

[0206] In this embodiment of the application, the processing module 120 is configured to determine the first anchor point based on the following method:

[0207] A1 = H(F(V1,...,Vn) || r)

[0208] Where A1 represents the first anchor point, H represents the hash operation, F(V1, ..., Vn) represents the global information of the data packet to be encrypted, r represents a random number or noise, and || represents the connection operation.

[0209] In this embodiment of the application, the processing module 120 is configured to encrypt the global information in the following manner:

[0210] C1 = Enc(A1, R)

[0211] Wherein, C1 represents a first cipher text, A1 represents a first anchor point, R represents a correlation matrix, and Enc represents an encryption algorithm.

[0212] In the embodiment of the present application, the processing module 120 is configured to determine the second cipher text based on the following manner:

[0213] C2 = Enc(PKu, D)

[0214] Wherein, C2 represents a second cipher text, PKu represents a user private key, D is each physiological index data contained in a data packet to be encrypted, and Enc represents an encryption algorithm.

[0215] In the embodiment of the present application, the processing module 120 is configured to:

[0216] determine a second anchor point based on the first anchor point, an institution feature, and a time limit feature;

[0217] determine a third anchor point based on the second anchor point and a biological feature of the target user;

[0218] encrypt the third anchor point based on an attribute-based encryption algorithm to obtain a third cipher text.

[0219] In the embodiment of the present application, the processing module 120 is configured to obtain the second anchor point based on the following manner:

[0220] A2 = H(A1||S||t)

[0221] Wherein, A2 represents a second anchor point, A1 represents a first anchor point, H represents a hash operation, S represents an institution feature to be authorized, t represents an authorization time limit, and || represents a connection operation.

[0222] In the embodiment of the present application, the processing module 120 is configured to obtain the third anchor point based on the following manner:

[0223] A3 = H(A2||M)

[0224] Wherein, A3 represents a third anchor point, A2 represents a second anchor point, H represents a hash operation, and M represents a biological feature of the target user.

[0225] In the embodiment of the present application, the processing module 120 is configured to obtain the third cipher text based on the following method:

[0226] C3 = ABE(P, A3)

[0227] Wherein, C3 represents a third cipher text, ABE represents an attribute-based encryption algorithm, P represents an access policy in the ABE, and A3 represents a third anchor point.

[0228] The specific encryption manner of each module of the data encryption device in each embodiment can refer to each embodiment of the encryption method, which will not be described here.

[0229] In the embodiments of the present application, when encrypting the personal health data of the target user, the original health data is encrypted by the private key of the target user, which can fully guarantee the security of the original health data. In addition, based on the initial feature vector data of each physiological indicator data in the same time period, the associated features and global information of each physiological indicator data are determined, and the global information is encrypted by the associated features as the key. The global information includes the original features of each physiological indicator and the correlation between each physiological indicator. Therefore, when the original features or correlation of each physiological indicator of the user need to be obtained subsequently, the global information can be decrypted by the associated features as the key, without decrypting the original data, which further strengthens the protection of the original health data. Moreover, the randomness of the key based on the associated features between each physiological indicator is much higher than that of the key generated by the traditional fixed algorithm, so it is difficult for attackers to predict the key through pattern analysis or brute force cracking, which greatly reduces the risk of key leakage. Moreover, the key changes dynamically with each physiological indicator, so even if a single key is cracked, it cannot be reused for other data or scenarios, effectively resisting replay attacks and batch cracking.

[0230] Exemplary medium

[0231] After introducing the method, medium and system of the exemplary embodiments of the present application, next, with reference to Figure 3 The computer-readable storage medium of the exemplary embodiments of the present application is described with reference to Figure 3The computer-readable storage medium shown is an optical disc 70, on which a computer program (i.e., a program product) is stored. When the computer program is run by a processor, it implements the steps described in the above method implementation, such as: acquiring a data packet to be encrypted, the data packet containing multiple physiological indicator data of a target user within the same time period; determining the initial feature vectors of each physiological indicator data contained in the data packet to be encrypted; performing a nonlinear transformation on each initial feature vector to obtain a transformed feature vector corresponding to each initial feature vector; determining the correlation features between the physiological indicators and the global information of the data packet to be encrypted based on the transformed feature vectors corresponding to each initial feature vector; encrypting the global information based on the correlation features between the physiological indicators to obtain a first ciphertext; and encrypting the data packet to be encrypted based on the target user's private key to obtain a second ciphertext. The specific implementation methods of each step will not be repeated here. It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical and magnetic storage media, which will not be elaborated here.

[0232] Exemplary computing device

[0233] After introducing the methods, systems, and media of exemplary embodiments of this application, the following references are made. Figure 4 Computing devices according to exemplary embodiments of this application.

[0234] Figure 4 A block diagram is shown of an exemplary computing device 80 suitable for implementing embodiments of the present application. The computing device 80 may be a computer system or a server. Figure 4 The computing device 80 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0235] like Figure 4 As shown, the components of the computing device 80 may include, but are not limited to: one or more processors or processing units 801, system memory 802, and bus 803 connecting different system components (including system memory 802 and processing unit 801).

[0236] The computing device 80 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computing device 80, including volatile and non-volatile media, removable and non-removable media.

[0237] The system memory 802 can include computer system readable media in the form of volatile memory, such as random-access memory (RAM) 8021 and / or cache memory 8022. The computing device 80 can further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, a ROM 8023 can be used for reading a stable, non- volatile, magnetic Figure 4 media, often referred to as a "hard disk drive" (HDD). Although not shown in Figure 4 the computing device 80, it should be appreciated that a disk drive, optical drive and the like can also be used. Additionally, it should be appreciated that a computer program product can be tangibly embodied in an information carrier, such as in a non-transitory machine-readable storage medium. The computer program product contains computer instructions that, when executed, can monitor and / or control the operation of the computing device 80. The computer program product can be delivered to a user or a customer of the computing device 80 via a communication channel, such as a communication network and / or a wireless link.

[0238] A program / utility 8025 having a set (at least one) of program modules 8024, can be stored in, for example, system memory 802 and implemented or accessed by the processing unit(s) 801. It is appreciated that each of the program modules 8024 includes or can be associated with a computer program product having instructions that, when executed by the processing unit(s) 801, can perform the functions and / or methods described in the embodiments of the present application. The program / utility 8025 can include, but is not limited to, for example, an operating system, one or more applications, other program modules, and program data.

[0239] The computing device 80 can also communicate with one or more external devices 804 such as a keyboard, a pointing device, a display, etc. via I / O interface 805. Further, the computing device 80 can communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via network adapter 806. As Figure 4 illustrated, the network adapter 806 can be communicatively coupled to the other modules of the computing device 80 (such as the processing unit(s) 801, etc.) via a bus 803. It should be appreciated that the computing device 80 can be a general purpose computing device, such as a personal computer, a laptop computer, a handheld computer, a workstation, a network computer, another type of special purpose computing device, or the like. Figure 4 It should be appreciated that the computing device 80 can be connected to other types of devices, systems, and / or networks via the bus 803 or another bus. For example, the computing device 80 can be connected to a wireless communication network, a wired communication network, or the like.

[0240] The processing unit 801 performs various function applications and data processing by running programs stored in the system memory 802, such as obtaining a to-be-encrypted data packet containing a plurality of physiological index data of a target user in a same time period, determining an initial feature vector of each physiological index data contained in the to-be-encrypted data packet, performing nonlinear transformation on each initial feature vector to obtain a transformed feature vector corresponding to each initial feature vector, determining a correlation feature between the plurality of physiological indexes and global information of the to-be-encrypted data packet based on the transformed feature vector corresponding to each initial feature vector, encrypting the global information based on the correlation feature between the plurality of physiological indexes to obtain a first ciphertext, and encrypting the to-be-encrypted data packet based on a private key of the target user to obtain a second ciphertext. The specific implementation of each step will not be repeated here. It should be noted that although several units / modules or sub-units / sub-modules of the operation device are mentioned in the foregoing detailed description, such division is merely exemplary and not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into a plurality of units / modules.

[0241] In the description of the present application, it should be noted that the terms "first", "second", "third" are only for the purpose of description and cannot be understood or implied as indicating or implying relative importance.

[0242] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, system and unit can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0243] In several embodiments provided in the present application, it should be understood that the disclosed system, system and method can be implemented in other ways. The system embodiments described above are only schematic. For example, the division of the units is only a logical function division, and there can be another division in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some communication interfaces. The coupling or communication connection between systems or units can be electrical, mechanical or in other forms.

[0244] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e. may be located in one place, or may be distributed on multiple network units. Part or all of the units may be selected to achieve the purpose of the embodiment of the present application according to actual needs.

[0245] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit.

[0246] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a non-volatile computer readable storage medium executable by a processor. Based on this understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of software products. The computer software product is stored in a storage medium, including a plurality of instructions for causing a computing device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk, and various media that can store program codes.

[0247] Finally, it should be noted that: the above-described embodiments are merely specific embodiments of the present application, used to illustrate the technical solutions of the present application, and not to limit them. The protection scope of the present application is not limited thereto, although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any skilled person familiar with the technology in the art can modify or easily think of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed by the present application, or make equivalent replacements to some of the technical features; and these modifications, changes or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be limited by the protection scope of the claims.

[0248] In addition, although the operations of the method of the present application are described in a specific order in the accompanying drawings, this does not require or imply that the operations must be performed in that specific order, or that all of the shown operations must be performed to achieve the desired result. Additionally or alternatively, some steps can be omitted, a plurality of steps can be combined into one step, and / or one step can be divided into a plurality of steps.

Claims

1. A data encryption method, comprising: Obtain a data packet to be encrypted, wherein the data packet to be encrypted contains multiple physiological indicator data of the target user within the same time period; Determine the initial feature vectors of each physiological indicator data contained in the data packet to be encrypted; A nonlinear transformation is performed on each initial eigenvector to obtain the transformed eigenvector corresponding to each initial eigenvector. Based on the transformed feature vectors corresponding to each initial feature vector, the correlation features between the various physiological indicators and the global information of the data packet to be encrypted are determined. Based on the correlation characteristics between the various physiological indicators, the global information is encrypted using the correlation characteristics as a key to obtain the first ciphertext, and the data packet to be encrypted is encrypted using the target user's private key to obtain the second ciphertext; The global information of the data packet to be encrypted is determined based on the following method: F(V1,……,Vn )= + in, For the first Transformed feature vectors corresponding to each physiological indicator For the first The weights of the transformed feature vectors corresponding to each physiological indicator. δ represents the correlation information between various physiological indicators, and is the correlation strength adjustment coefficient. For the first The initial feature vectors of the physiological indicators, k≤n, F(V1,……,Vn) represent the global information of the data packet to be encrypted; The step of determining the correlation features between the various physiological indicators based on the transformed feature vectors corresponding to each initial feature vector includes: Determine the relationship matrix between the transformed feature vectors corresponding to each initial feature vector, and use the relationship matrix as the correlation feature between the various physiological indicators.

2. The data encryption method as described in claim 1, wherein each initial feature vector is subjected to a nonlinear transformation based on the following method: in, For the first The initial feature vector of each physiological indicator for The weight parameters, for The bias term, It is the hyperbolic tangent function. For the first Transformed feature vectors corresponding to each physiological indicator For the first The weights of the transformed feature vectors corresponding to each physiological indicator.

3. The data encryption method as described in claim 1, wherein the relation matrix is ​​determined based on the following method: Determine the Pearson correlation coefficient between each pair of transformed eigenvectors, and obtain the relationship matrix based on each Pearson correlation coefficient; or Determine the attention score of each transformed feature vector relative to other transformed feature vectors, and obtain the relationship matrix based on each attention score; or Determine the Euclidean distance between each pair of transformed eigenvectors, and obtain the relation matrix based on each Euclidean distance; or The cosine distance between each pair of transformed eigenvectors is determined, and the relationship matrix is ​​obtained based on each cosine distance.

4. A data encryption device, comprising: The acquisition module is used to acquire the data packet to be encrypted, which contains multiple physiological indicator data of the target user within the same time period; The processing module is used to determine the initial feature vector of each physiological indicator data contained in the data packet to be encrypted; A nonlinear transformation is performed on each initial eigenvector to obtain the transformed eigenvector corresponding to each initial eigenvector. Based on the transformed feature vectors corresponding to each initial feature vector, the correlation features between the various physiological indicators and the global information of the data packet to be encrypted are determined. Based on the correlation characteristics between the various physiological indicators, the global information is encrypted using the correlation characteristics as a key to obtain the first ciphertext, and the data packet to be encrypted is encrypted using the private key of the target user to obtain the second ciphertext. The global information of the data packet to be encrypted is determined based on the following method: F(V1,……,Vn )= + in, For the first Transformed feature vectors corresponding to each physiological indicator For the first The weights of the transformed feature vectors corresponding to each physiological indicator. This represents the correlation information between various physiological indicators. For the first The initial feature vector of each physiological indicator, δ is the correlation strength adjustment coefficient, k≤n, F(V1,……,Vn) represents the global information of the data packet to be encrypted; The step of determining the correlation features between the various physiological indicators based on the transformed feature vectors corresponding to each initial feature vector includes: Determine the relationship matrix between the transformed feature vectors corresponding to each initial feature vector, and use the relationship matrix as the correlation feature between the various physiological indicators.

5. A computer-readable storage medium comprising instructions that, when executed on a computer, cause the computer to perform the data encryption method as described in any one of claims 1-3.

6. A computing device, comprising a processor, wherein a computer program is stored on the processor, the computer program, when executed, implements the data encryption method as described in any one of claims 1-3.

Images