Face feature privacy protection method and system, electronic equipment and storage medium

By using the spatiotemporal chaos model and key parameters in face recognition technology to process face feature data and generate chaotic and encryption sequences, the problem of encryption technology affecting recognition performance is solved, and efficient privacy protection and balance of recognition effects is achieved.

CN118982877APending Publication Date: 2024-11-19CHINA TELECOM CORP LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410993026.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

When the prior art applies encryption technology to face feature data, the face recognition rate and recognition time performance decrease, affecting the effect of face recognition.

Method used

By obtaining the key parameters and face feature vectors, the key parameters are input to the space-time chaos model for iterative generation and uniform transformation processing, a chaotic sequence is obtained, and the chaotic sequence is extracted according to the key parameters to generate a chaotic sequence and encryption The sequence is followed by permutation and encryption transformation of the face feature vector to obtain the face feature ciphertext data.

Benefits of technology

While not affecting the efficiency of face recognition, it improves encryption performance, enhances the unpredictability and encryption performance of chaotic sequences, and provides better privacy protection effects.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118982877A_ABST
    Figure CN118982877A_ABST
Patent Text Reader

Abstract

The invention discloses a face feature privacy protection method and system, electronic equipment and a storage medium. The method comprises the following steps: acquiring a key parameter and a face feature vector; inputting the key parameter into a spatiotemporal chaos model for iterative generation and uniform transformation processing to obtain a chaos sequence; performing extraction processing on the chaos sequence according to the key parameter to obtain a scrambling sequence and an encryption sequence; performing replacement processing on the face feature vector according to the scrambling sequence to obtain a replacement feature vector; and performing encryption transformation processing on the replacement feature vector according to the encryption sequence to obtain face feature ciphertext data. According to the embodiment of the invention, the encryption performance of the face features can be improved while the face recognition efficiency is not affected, and the method can be widely applied to the technical field of information security.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of information security technology, and in particular to a method, system, electronic device and storage medium for protecting the privacy of facial features. Background Art

[0002] Face recognition technology is widely used and can be applied to various identity authentication systems. Therefore, the security requirements for face recognition technology are constantly increasing. In the feature recognition process, there are many ways to attack the face recognition system. In related technologies, there is a way to directly apply encryption technology to face feature data. However, in actual applications, it is found that directly introducing data encryption technology may lead to a decrease in face recognition rate and recognition time performance, affecting the effect of face recognition.

[0003] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose a facial feature privacy protection method, system, electronic device and storage medium, which can improve encryption performance without affecting face recognition efficiency.

[0005] To achieve the above purpose, one aspect of an embodiment of the present application proposes a method for protecting the privacy of facial features, the method comprising:

[0006] Get key parameters and face feature vector;

[0007] Inputting the key parameters into the spatiotemporal chaos model for iterative generation and uniform transformation processing to obtain a chaotic sequence;

[0008] Extracting the chaotic sequence according to the key parameter to obtain a scrambled sequence and an encrypted sequence;

[0009] Performing a permutation process on the facial feature vector according to the scrambled sequence to obtain a permuted feature vector;

[0010] The replacement feature vector is encrypted and transformed according to the encryption sequence to obtain facial feature ciphertext data.

[0011] In some embodiments, the step of inputting the key parameters into a spatiotemporal chaos model for iterative generation and uniform transformation to obtain a chaotic sequence comprises the following steps:

[0012] Initializing the spatiotemporal chaos model according to the key parameters to obtain an initialized model;

[0013] Iteratively processing the initialization model according to the dimension of the facial feature vector to obtain an iterative sequence;

[0014] The iterative sequence is subjected to transient transformation processing to obtain a chaotic sequence.

[0015] In some embodiments, performing transient transformation processing on the iterative sequence to obtain a chaotic sequence comprises the following steps:

[0016] Performing binary format conversion processing on the iterative sequence to obtain a first conversion sequence;

[0017] Performing product and binary format conversion processing on the iteration sequence and the first conversion sequence to obtain a product sequence;

[0018] The product sequence is divided and XORed bit by bit to obtain a chaotic sequence.

[0019] In some embodiments, extracting the chaotic sequence according to the key parameter to obtain a scrambled sequence and an encrypted sequence comprises the following steps:

[0020] Obtaining scrambling control parameters and encryption control parameters from the key parameters;

[0021] Performing format conversion and state value extraction processing on the chaotic sequence according to the scrambling control parameter to obtain a scrambled sequence;

[0022] The chaotic sequence is subjected to bit value extraction processing according to the encryption control parameter to obtain an encryption sequence.

[0023] In some embodiments, performing format conversion and state value extraction processing on the chaotic sequence according to the scrambling control parameter to obtain a scrambled sequence includes the following steps:

[0024] Performing floating point number format conversion processing on each grid state value in the chaotic sequence to obtain a second conversion sequence;

[0025] Performing a lattice state value extraction process on the second conversion sequence according to the scrambling control parameter to obtain an extraction sequence;

[0026] The extraction sequence is multiplied and rounded according to the dimension of the facial feature vector to obtain a scrambled sequence.

[0027] In some embodiments, performing bit value extraction processing on the chaotic sequence according to the encryption control parameter to obtain an encrypted sequence comprises the following steps:

[0028] Performing bit value extraction processing on each grid state value of the chaotic sequence according to the encryption control parameter to obtain an extracted bit value;

[0029] The extracted bit values ​​are combined to obtain an encrypted sequence.

[0030] In some embodiments, performing encryption transformation processing on the replacement feature vector according to the encryption sequence to obtain the face feature ciphertext data includes the following steps:

[0031] Performing binary format conversion processing on the replacement feature vector to obtain a plaintext sequence;

[0032] The plaintext sequence and the encrypted sequence are subjected to an XOR operation according to an encryption transformation function to obtain ciphertext data of facial features.

[0033] To achieve the above-mentioned purpose, another aspect of the embodiment of the present application provides a facial feature privacy protection system, the system comprising:

[0034] The first module is used to obtain key parameters and face feature vectors;

[0035] The second module is used to input the key parameters into the spatiotemporal chaos model for iterative generation and uniform transformation processing to obtain a chaotic sequence;

[0036] The third module is used to extract the chaotic sequence according to the key parameter to obtain a scrambled sequence and an encrypted sequence;

[0037] A fourth module is used to perform a permutation process on the facial feature vector according to the scrambling sequence to obtain a permuted feature vector;

[0038] The fifth module is used to perform encryption transformation processing on the replacement feature vector according to the encryption sequence to obtain facial feature ciphertext data.

[0039] In some embodiments, the second module is used to input the key parameters into the spatiotemporal chaos model for iterative generation and uniform transformation processing to obtain a chaotic sequence, including:

[0040] The first unit is used to initialize the spatiotemporal chaos model according to the key parameters to obtain an initialized model;

[0041] The second unit is used to iteratively process the initialization model according to the dimension of the facial feature vector to obtain an iterative sequence;

[0042] The third unit is used to perform transient transformation processing on the iterative sequence to obtain a chaotic sequence.

[0043] In some embodiments, the third unit is used to perform transient transformation processing on the iterative sequence to obtain a chaotic sequence, including:

[0044] A first subunit is used to perform binary format conversion processing on the iterative sequence to obtain a first conversion sequence;

[0045] A second subunit is used to perform product and binary format conversion processing on the iteration sequence and the first conversion sequence to obtain a product sequence;

[0046] The third subunit is used for dividing the product sequence and performing XOR operation on each bit to obtain a chaotic sequence.

[0047] In some embodiments, the third module is used to extract the chaotic sequence according to the key parameter to obtain a scrambled sequence and an encrypted sequence, including:

[0048] A fourth unit, configured to obtain a scrambling control parameter and an encryption control parameter from the key parameter;

[0049] A fifth unit is used to perform format conversion and state value extraction processing on the chaotic sequence according to the scrambling control parameter to obtain a scrambled sequence;

[0050] The sixth unit is used to perform bit value extraction processing on the chaotic sequence according to the encryption control parameter to obtain an encrypted sequence.

[0051] In some embodiments, the fifth unit is used to perform format conversion and state value extraction processing on the chaotic sequence according to the scrambling control parameter to obtain a scrambled sequence, including:

[0052] A fourth subunit is used to perform floating point number format conversion processing on each grid state value in the chaotic sequence to obtain a second conversion sequence;

[0053] a fifth subunit, configured to perform a lattice state value extraction process on the second conversion sequence according to the scrambling control parameter to obtain an extraction sequence;

[0054] The sixth subunit is used to multiply and round the extraction sequence according to the dimension of the facial feature vector to obtain a scrambled sequence.

[0055] In some embodiments, the sixth unit is used to perform bit value extraction processing on the chaotic sequence according to the encryption control parameter to obtain an encrypted sequence, including:

[0056] A seventh subunit, configured to perform bit value extraction processing on each grid state value of the chaotic sequence according to the encryption control parameter to obtain an extracted bit value;

[0057] The eighth subunit is used to perform combination processing on the extracted bit values ​​to obtain an encrypted sequence.

[0058] In some embodiments, the fifth module is used to perform encryption transformation processing on the replacement feature vector according to the encryption sequence to obtain facial feature ciphertext data, including the following steps:

[0059] The seventh unit is used to perform binary format conversion processing on the replacement feature vector to obtain a plaintext sequence;

[0060] The eighth unit is used to perform an XOR operation on the plaintext sequence and the encrypted sequence according to the encryption transformation function to obtain facial feature ciphertext data.

[0061] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application provides an electronic device, the electronic device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the above-mentioned method when executing the computer program.

[0062] To achieve the above objective, another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described above is implemented.

[0063] The embodiments of the present application include at least the following beneficial effects: the present application provides a method, system, electronic device and storage medium for protecting the privacy of facial features. The scheme obtains key parameters and facial feature vectors; inputs the key parameters into a spatiotemporal chaos model for iterative generation and uniform transformation processing to obtain a chaotic sequence, which can obtain a chaotic sequence with higher complexity and enhance the unpredictability of the chaotic sequence; in addition, the scheme extracts and processes the chaotic sequence according to the key parameters respectively to obtain a scrambled sequence and an encrypted sequence, which can generate a scrambled sequence at a lower computational cost, reduce the time-consuming operations and system iterations in the encryption process to reduce the impact on recognition efficiency; furthermore, the scheme permutes the facial feature vector according to the scrambled sequence to obtain a permuted feature vector; performs encryption transformation processing on the permuted feature vector according to the encryption sequence to obtain facial feature ciphertext data, and can perform chaotic stream encryption on the scrambled facial feature vector through the encryption sequence, which improves encryption performance and has a better privacy protection effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 This is a flow chart of a facial feature privacy protection method provided in an embodiment of the present application;

[0065] Figure 2 yes Figure 1 Flow chart of step S102 in FIG.

[0066] Figure 3 yes Figure 2 Flow chart of step S203 in FIG.

[0067] Figure 4 yes Figure 1 Flow chart of step S103 in FIG.

[0068] Figure 5 yes Figure 4 Flow chart of step S402 in FIG.

[0069] Figure 6 yes Figure 4 Flow chart of step S403 in FIG.

[0070] Figure 7 This is a flow chart of a face registration module provided in an embodiment of the present application;

[0071] Figure 8 This is a flow chart of a face recognition module provided in an embodiment of the present application;

[0072] Fig. 9 It is a structural schematic diagram of a facial feature privacy protection system provided in an embodiment of the present application;

[0073] Fig.10 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0074] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are only examples of systems and methods consistent with some aspects of the embodiments of the present application as detailed in the attached claims.

[0075] It is understood that the terms "first", "second", etc. used in this application can be used to describe various concepts in this article, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another concept. For example, without departing from the scope of the embodiment of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination".

[0076] The terms "at least one", "multiple", "each", "any", etc. used in this application, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0077] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0078] Before describing the embodiments of the present application in detail, some nouns and terms involved in the embodiments of the present application are first described. The nouns and terms involved in the embodiments of the present application are subject to the following explanations.

[0079] 1) Artificial Intelligence (AI) is an important driving force for the new round of scientific and technological revolution and industrial transformation. It is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. Artificial Intelligence is an important part of the intelligent discipline. It attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Artificial Intelligence is a very broad science, including robots, language recognition, image recognition, natural language processing, expert systems, machine learning, computer vision, etc.

[0080] 2) Face recognition is a biometric technology that identifies people based on their facial features. It uses a camera or camcorder to collect images or video streams containing faces, automatically detects and tracks faces in images, and then performs facial recognition on the detected faces. It is also commonly called portrait recognition or facial recognition.

[0081] 3) Coupled Map Lattice (CML): A classic spatiotemporal chaos model, it is a complex dynamical system discretized in both time and space. Coupled Map Lattice is simple and easy to calculate, and is often used in chaos cryptography.

[0082] 4) 2D Coupled Map Lattice (2DCML): The one-dimensional coupled map lattice is extended to the two-dimensional coupled map lattice.

[0083] 5) Piecewise Logistic Map (PLM): a nonlinear mapping with more complex dynamic behavior than the logical chaotic mapping.

[0084] Face recognition technology is widely used and can be applied to various identity authentication systems. Therefore, the security requirements for face recognition technology are constantly increasing. In the feature recognition process, there are many attack methods, such as forging face features, tampering with the extraction module, tampering with the face feature database, etc. to destroy the face recognition system, making it easy for illegal users to pass the identity authentication or access control system. There are different technical solutions for different attack methods, such as liveness detection technology to solve the attack method of forging face features, and data encryption technology can solve the problem of tampering with the face feature database, protecting the security and privacy leakage of face feature data. At present, the privacy protection method for face features is still developing, and there are still many bottlenecks and difficulties in the widespread application of privacy protection methods for face features. In the related technology, there are many problems in directly applying data encryption technology to face feature data, which may cause the face recognition rate and recognition time performance to decrease, affecting the effect of face recognition. At present, the common protection methods for face feature data are scrambling encryption or numerical transformation, but there is still a situation where the efficiency of the face recognition process is low.

[0085] For example, Logistic chaotic mapping is a classic one-dimensional nonlinear mapping, and its chaotic sequence has the characteristics of sensitivity to initial conditions and pseudo-randomness. Therefore, a scrambled encryption method for facial feature vectors is designed in combination with chaos theory to achieve privacy protection of facial features while ensuring that the accuracy of face recognition is not affected. However, in practical applications, it is found that low-dimensional chaotic mapping is affected by computer calculation accuracy, causing the chaotic orbit to become periodic. At the same time, the chaotic sequence generated by Logistic chaotic mapping often has uneven value distribution, which affects its security. The consumption of computing resources required to generate the scrambled sequence will also affect the time performance of the face recognition process.

[0086] In view of this, a facial feature privacy protection method, system, electronic device and storage medium are provided in the embodiments of the present application. The scheme obtains key parameters and facial feature vectors; inputs the key parameters into a spatiotemporal chaos model for iterative generation and uniform transformation processing to obtain a chaotic sequence, which can obtain a chaotic sequence with higher complexity and enhance the unpredictability of the chaotic sequence; in addition, the scheme extracts and processes the chaotic sequence according to the key parameters respectively to obtain a scrambled sequence and an encrypted sequence, and can generate a scrambled sequence at a lower computational cost, thereby reducing the time-consuming operations and system iterations in the encryption process to reduce the impact on recognition efficiency; furthermore, the scheme permutes the facial feature vector according to the scrambled sequence to obtain a permuted feature vector; performs encryption transformation processing on the permuted feature vector according to the encryption sequence to obtain facial feature ciphertext data, and can perform chaotic stream encryption on the scrambled facial feature vector through the encryption sequence, thereby improving encryption performance and having a better privacy protection effect.

[0087] The embodiments of the present application can be applied to encryption scenarios of facial feature data, such as facial feature databases, and can further improve the security of facial feature databases and prevent facial feature data from being tampered with in accordance with the security requirements of facial feature data and the requirements of facial recognition performance. At the same time, the facial recognition rate should not be affected by the encryption method, and the impact of the encryption method on the time performance of the facial recognition process should be minimized as much as possible, so as to balance the performance and security of facial recognition. While the security and revocability of the facial feature database are met, the performance of facial recognition is improved.

[0088] A method for protecting the privacy of facial features provided in an embodiment of the present application relates to the field of information security technology. A method for protecting the privacy of facial features provided in an embodiment of the present application can be applied to a terminal, can be applied to a server, or can be software running in a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and a car terminal, etc., but is not limited to this; the server side can be configured as an independent physical server, or a server cluster or distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network; the software can be an application that implements a method for protecting the privacy of facial features, etc., but is not limited to the above forms.

[0089] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0090] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0091] Figure 1 is an optional flow chart of a facial feature privacy protection method provided in an embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S105.

[0092] Step S101, obtaining key parameters and face feature vectors;

[0093] Step S102, inputting the key parameters into the spatiotemporal chaos model for iterative generation and uniform transformation processing to obtain a chaotic sequence;

[0094] Step S103, extracting the chaotic sequence according to the key parameter to obtain a scrambled sequence and an encrypted sequence;

[0095] Step S104, performing a permutation process on the facial feature vector according to the scrambling sequence to obtain a permuted feature vector;

[0096] Step S105, performing encryption transformation processing on the replacement feature vector according to the encryption sequence to obtain facial feature ciphertext data.

[0097] In the steps S101 to S105 shown in the embodiment of the present application, by obtaining the key parameters and the face feature vector, the key parameters are input into the spatiotemporal chaos model for iterative generation and uniform transformation processing to obtain a chaotic sequence. Among them, the spatiotemporal chaos model adopts a two-dimensional coupled image lattice (2DCML) model, through which a sequence is iteratively generated, and then the generated sequence is uniformly transformed to obtain a chaotic sequence. A chaotic sequence, also known as a chaotic time series, is a type of irregular motion that occurs in a certain system. The discrete state of chaos is often manifested as a chaotic time series. A chaotic time series is a time series with chaotic characteristics generated by a chaotic model. The chaotic time series contains rich dynamic information of the system. Then, the chaotic sequence is extracted according to the key parameters, and a scrambled sequence and an encrypted sequence are obtained by extracting the control parameters of different sequences in the key parameters. Then, the face feature vector is permuted according to the scrambled sequence to obtain a permuted feature vector; finally, the permuted feature vector is encrypted and transformed according to the encryption sequence to obtain face feature ciphertext data, and the face feature ciphertext data is saved in the face feature database. The embodiment of the present application can utilize the characteristics of more uniform distribution of the generated chaotic sequence values ​​to make the method of generating the scrambled sequence simpler and have a better scrambling effect, and can reduce the computational complexity of the scrambled sequence to improve the efficiency of face recognition. In addition, the encryption sequence is generated to perform encryption transformation on the scrambled face feature vector, which has high encryption performance and can improve the encryption performance without affecting the efficiency of face recognition.

[0098] In step S101 of some embodiments, firstly, a key parameter and a facial feature vector are obtained, and the key parameter is Key (x0, μ, N, ε, M, k, H), where x0 is the initial value of the segmented Logistic Map (PLM), μ is the control parameter of the PLM chaotic map, N is the total number of segments of the PLM map, ε is the coupling strength of the spatiotemporal chaotic model, M is the number of iterations of the PLM, k is the control parameter of the scrambled sequence, and H is the control parameter of the encryption sequence. The key parameter is used to complete the initialization of the spatiotemporal chaotic model and iteratively generate chaotic sequences, scrambled sequences, and encryption sequences. The facial feature vector can be obtained by obtaining a facial image through a camera or other shooting device and extracting features from the facial image, or it can be obtained by other methods, such as obtaining it from a facial feature library, but is not limited to this.

[0099] See also Figure 2 In step S102 of some embodiments, the key parameters are input into the spatiotemporal chaos model for iterative generation and uniform transformation to obtain a chaotic sequence, including the following steps:

[0100] Step S201, initializing the spatiotemporal chaos model according to the key parameters to obtain an initialized model;

[0101] Step S202, iteratively processing the initialization model according to the dimension of the facial feature vector to obtain an iterative sequence;

[0102] Step S203, performing transient transformation processing on the iterative sequence to obtain a chaotic sequence.

[0103] In step S201 of some embodiments, the spatiotemporal chaos model is initialized according to the key parameters. The spatiotemporal chaos model adopts a 2DCML model. The mathematical expression of the 2DCML model is as follows:

[0104]

[0105] In the formula, y i,j n+1 It represents the state value of the grid in the i-th row and j-th column at the time of n+1; i=1,2,…,R,j=1,2,…,L,the model size is R×L,R=L=8,ε is the coupling strength, the value range is (0,1), f(y) is the local function, and f(y) selects PLM chaotic mapping. The mathematical expression of PLM chaotic mapping is as follows:

[0106]

[0107] In the formula, the value range of xn+1 is (0,1), μ represents the control parameter of the chaotic mapping, and its value range is (0,4), and N represents the total number of segments of the PLM mapping, which is usually an even number. The spatiotemporal chaotic model is initialized by obtaining the initial value x0 of the PLM mapping from the key parameter to obtain the initialization model.

[0108] In step S202 of some embodiments, the dimension value of the facial feature vector is obtained, and the initialization model is iterated according to the dimension value, wherein the spatiotemporal chaos model is iterated in the time dimension, and the number of iterations depends on the dimension of the facial feature vector. In a specific embodiment, the dimension of the facial feature vector is 512, and the initial iteration number M is obtained from the key parameter, and the PLM chaotic mapping is iterated M times, and then the PLM chaotic mapping is iterated R×L times to obtain the initial state value y i,j 0. Then y i,j 0 and ε are input to initialize the model and iterate 512 times, resulting in an iterative sequence Y of length 512. n ={y 1,1 n ,y 1,2 n …y 8,8n}, where n = 1, 2,…, 512.

[0109] See also Figure 3 In step S203 of some embodiments, the performing of transient transformation processing on the iterative sequence to obtain a chaotic sequence includes the following steps:

[0110] Step S301, performing binary format conversion processing on the iterative sequence to obtain a first conversion sequence;

[0111] Step S302, performing product and binary format conversion processing on the iteration sequence and the first conversion sequence to obtain a product sequence;

[0112] Step S03, dividing the product sequence and performing XOR operation on each bit to obtain a chaotic sequence.

[0113] In the embodiment of the present application, it is necessary to use transient transformation to transform the generated iterative sequence to obtain a chaotic sequence with uniform distribution in order to address the disadvantage of uneven distribution of the chaotic sequence iteratively generated by the 2DCML model. The first conversion sequence is obtained by converting the iterative sequence into a binary format. The first conversion sequence is a sequence constructed according to the binary format of the iterative sequence. Specifically, the iterative sequence is represented in binary by determining the number of bits of the iterative sequence with computer precision. That is, each lattice state value in the iterative sequence needs to be converted into a binary format for subsequent processing. The operation performed on the sequence is the operation performed on the lattice state value in the sequence. Take the first lattice state value y in the iterative sequence as 1,1 1 as an example, y 1,1 1∈(0,1), the first grid state value y represented in binary 1,1 The expression of 1 is u=0.u1…u A u A+1 u A+2 …u 2A , where A represents half of the precision of the fixed-point number in the computer. Then, according to half of the precision of the fixed-point number in the computer, each grid state value of the iterative sequence represented by binary is segmented and swapped to obtain the first conversion sequence. The first grid state value expression of the first conversion sequence is v=0.u A+1 u A+2 …u 2A u1…u AThen, the iteration sequence and the first conversion sequence are multiplied and converted to binary format. Specifically, each grid state value in the iteration sequence in binary format is multiplied with each grid state value in the first conversion sequence in binary format to obtain a product result, and the product result is converted to binary format to obtain a product sequence. For example, the expression of the first grid state value of the product sequence is t=u×v=0.t1t2…t 2A t 2A+1 …t 4A Finally, the state value of each grid of the binary sequence of the product sequence is evenly divided into the front and rear parts and the chaotic sequence is obtained by bitwise XOR operation. The expression of each grid state value of the chaotic sequence is o = 0. (t1 XOR t 2A+1 )(t2 XOR t 2A+2 )…(t 2A XOR t 4A ). Since the fixed-point number precision of the computer is 2A, the product sequence only retains the first 2A digits after the decimal point, and the last 2A digits are discarded as transient data, and transient data has good random properties. Therefore, the embodiment of the present application can make the generated chaotic sequence have better randomness by performing an XOR operation with the transient data, thereby obtaining a new transient homogenized chaotic sequence.

[0114] See also Figure 4 In step S103 of some embodiments, the extraction process of the chaotic sequence according to the key parameter to obtain a scrambled sequence and an encrypted sequence includes the following steps:

[0115] Step S401, obtaining a scrambling control parameter and an encryption control parameter from the key parameter;

[0116] Step S402, performing format conversion and state value extraction processing on the chaotic sequence according to the scrambling control parameter to obtain a scrambled sequence;

[0117] Step S403: extracting bits from the chaotic sequence according to the encryption control parameter to obtain an encryption sequence.

[0118] In step S401 of some embodiments, the key parameters include scrambling control parameters and encryption control parameters, wherein the scrambling control parameters are used to generate a scrambling sequence, and the encryption control parameters are used to generate an encryption sequence. In the embodiment of the present application, a pseudo-random generator can be used to generate the scrambling control parameters and the encryption control parameters, respectively. By generating a scrambling sequence and an encryption sequence, the embodiment of the present application can scramble and encrypt the facial feature vector, thereby improving the privacy protection effect of the facial features.

[0119] See also Figure 5In step S402 of some embodiments, the format conversion and state value extraction processing of the chaotic sequence according to the scrambling control parameter to obtain the scrambled sequence includes the following steps:

[0120] Step S501, performing floating point number format conversion processing on each grid state value in the chaotic sequence to obtain a second conversion sequence;

[0121] Step S502, performing a lattice state value extraction process on the second conversion sequence according to the scrambling control parameter to obtain an extraction sequence;

[0122] Step S503, multiplying and rounding the extracted sequence according to the dimension of the facial feature vector to obtain a scrambled sequence.

[0123] In step S501 of some embodiments, a chaotic sequence is obtained by performing transient transformation processing on the iterative sequence. The chaotic sequence is in binary format and needs to be converted into a floating point format for subsequent processing. By performing floating point format conversion processing on each grid state value in the chaotic sequence, subsequent calculation processing is facilitated.

[0124] In step S502 of some embodiments, the second conversion sequence is subjected to a lattice state value extraction process according to a scrambling control parameter, wherein the scrambling control parameter has a value range of (1, R×L), and R×L represents the size of the spatiotemporal chaos model. The scrambling control parameter is set to k, and the kth data of each lattice state value is extracted from the chaotic sequence to obtain an extraction sequence.

[0125] In step S503 of some embodiments, the dimension value of the facial feature vector is obtained, and each sequence element of the extracted sequence is multiplied according to the dimension value, and rounded down to obtain a new scrambled sequence, wherein the rounding down uses the floor function, that is, taking the maximum integer not greater than the specified value, and the specified value can be the dimension value. The embodiment of the present application converts the chaotic sequence into a floating point format by scrambling control parameters, and extracts the state value and the facial feature vector dimension for multiplication and rounding, and finally obtains the scrambled sequence, which can make the generated scrambled sequence have good performance, and the generation of the scrambled sequence by scrambling the chaotic sequence with the scrambling control parameters can make the method of generating the scrambled sequence simpler and have a better scrambling effect, reduce the computational complexity of the scrambled sequence, and ensure the efficiency of face recognition.

[0126] See also Figure 6 In step S403 of some embodiments, the bit value extraction processing of the chaotic sequence according to the encryption control parameter to obtain the encryption sequence includes the following steps:

[0127] Step S601, performing bit value extraction processing on each grid state value of the chaotic sequence according to the encryption control parameter to obtain an extracted bit value;

[0128] Step S602, combining the extracted bit values ​​to obtain an encrypted sequence.

[0129] In step S601 of some embodiments, an encryption control parameter is obtained, and the encryption control parameter is set to H. H bits are extracted from the first H values ​​of each lattice state value of the chaotic sequence to obtain an extracted bit value, which is a numerical value corresponding to the bit extracted according to the encryption control parameter.

[0130] In step S602 of some embodiments, the extracted bit values ​​are combined in the extraction order to obtain a combined encryption sequence, which is used to encrypt the scrambled facial feature vector. In the embodiment of the present application, the encryption sequence is generated by encrypting the control parameters, and the scrambled facial feature vector can be further encrypted with chaotic flow, thereby improving the encryption effect of facial feature privacy protection.

[0131] In step S104 of some embodiments, the facial feature vector is permuted according to the scrambling sequence to obtain a permuted feature vector, wherein the value of the facial feature vector can be exchanged according to the scrambling sequence. Specifically, the value of the i-th feature point of the facial feature vector and the D-th feature point are permuted. i +1 feature point value exchange, i is a positive integer, D i is the value of the i-th element in the scrambled sequence, that is, the exchange subscript of each element in the facial feature vector is obtained from the scrambled sequence, so that the value of the facial feature vector is scrambled according to the exchange subscript to obtain the scrambled permutation feature vector.

[0132] In step S105 of some embodiments, performing encryption transformation processing on the replacement feature vector according to the encryption sequence to obtain ciphertext data of facial features includes the following steps:

[0133] Performing binary format conversion processing on the replacement feature vector to obtain a plaintext sequence;

[0134] The plaintext sequence and the encrypted sequence are subjected to an XOR operation according to an encryption transformation function to obtain ciphertext data of facial features.

[0135] In the embodiment of the present application, the scrambled face feature vector, that is, the permuted feature vector, is converted into a binary format to obtain a plaintext sequence, wherein the plaintext sequence is composed of a basic plaintext unit m of 8 bits each. i , i = 1, 2, ..., 8. It can be imagined that here the encryption sequence is also composed of key streams k for every 8 bits i, i = 1, 2, ..., 8, and then perform XOR operation on the plaintext sequence and the encrypted sequence according to the encryption transformation function to obtain the ciphertext sequence, that is, the face feature ciphertext data. The expression of the encryption transformation function is as follows:

[0136] c=(m8 XOR k1)(m7 XOR k2)(m6 XOR k3)(m5 XOR k4)(m4 XOR k5)(m3 XOR k6)(m2

[0137] XOR k7)(m1 XOR k8);

[0138] In the formula, c represents the face feature ciphertext data. The encryption transformation function in the embodiment of the present application is a stream cipher method based on Latin square design, which can improve the effect of data encryption, thereby storing the encrypted face feature ciphertext data in the database to prevent privacy leakage of face data and data tampering.

[0139] The following is a detailed description of the embodiments of the present invention with reference to specific application examples:

[0140] The embodiments of the present application are applied to the scenario of facial feature privacy protection. They can be applied to systems using facial recognition technology to protect the privacy information of users and prevent facial feature data from being tampered with, which may affect the security and stability of the system. They can also be applied to different facial recognition technologies, suitable for different facial feature extraction technologies and the characteristics of facial feature vectors, and are specifically applied to facial recognition scenarios such as security monitoring and recognition, facial access control, and identity authentication. Specifically, in facial recognition scenarios, a facial registration module is used to collect and protect facial feature data, and a facial recognition module is used to identify and verify faces. Please refer to Figure 7 When a user registers, the user's face image is collected after identity authentication, and then the face is detected by the face detection model. After the face image is detected, the face features are extracted, and the initialized chaotic sequence is iteratively generated after initialization through the spatiotemporal chaos model. The initialized chaotic sequence is subjected to a uniform transformation to obtain the final chaotic sequence. The scrambled sequence and the encrypted sequence are generated according to the final chaotic sequence, and the extracted face feature vector is scrambled according to the scrambled sequence, and then the scrambled face features are encrypted with the encryption sequence, and the encrypted ciphertext data is stored in the face feature database. When the user performs face authentication, please refer to Figure 8, collect and process the face image of the user who needs to be authenticated, detect the face image through the face detection model, extract the face features, and initialize the spatiotemporal chaos model, iteratively generate the chaotic sequence and perform uniform changes on the chaotic sequence to generate the scrambled sequence and the decryption sequence. Obtain the ciphertext data by reading the face feature database and decrypt it according to the decryption sequence, scramble the decrypted authentication face feature vector according to the scrambled sequence and convert it into the original face feature vector format, calculate the Euclidean distance between the decrypted face feature vector and the extracted face feature vector, judge and return the recognition result. The embodiment of the present application is based on the characteristics of the face feature vector, and performs privacy protection based on a high-dimensional spatiotemporal chaos model, which improves the shortcomings of small key space and short period, reduces the problem of insufficient security of encrypted face feature data caused by uneven probability density distribution of chaotic sequences, thereby improving the problem that the relevant privacy protection methods cannot well protect the face feature data from being tampered with, thereby causing the system to suffer losses due to data tampering. The chaotic sequence generated by the embodiment of the present application has higher complexity, which enhances the unpredictability of the chaotic sequence, and combines with the stream encryption transformation function designed based on Latin square to improve the security of the face feature database. The model has good time performance and generates a more evenly distributed and more secure chaotic sequence at a lower computational cost. In order to ensure the performance of the face recognition module, a scrambled sequence is generated by a pseudo-random number generator with low computational complexity. The encryption scheme reduces the impact of recognition efficiency by minimizing the time-consuming operations and system iterations during the encryption process. The encryption method does not affect the matching success rate of the original face recognition module, and improves encryption performance without affecting the face recognition efficiency.

[0141] See also Fig. 9 The embodiment of the present application also provides a facial feature privacy protection system, which can implement the above facial feature privacy protection method, and the system includes:

[0142] The first module 901 is used to obtain key parameters and face feature vectors;

[0143] The second module 902 is used to input the key parameters into the spatiotemporal chaos model for iterative generation and uniform transformation processing to obtain a chaotic sequence;

[0144] The third module 903 is used to extract the chaotic sequence according to the key parameter to obtain a scrambled sequence and an encrypted sequence;

[0145] The fourth module 904 is used to perform a permutation process on the face feature vector according to the scrambling sequence to obtain a permuted feature vector;

[0146] The fifth module 905 is used to perform encryption transformation processing on the replacement feature vector according to the encryption sequence to obtain facial feature ciphertext data.

[0147] It can be understood that the contents of the above method embodiments are all applicable to the present system embodiments, the functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0148] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned facial feature privacy protection method when executing the computer program. The electronic device can be any smart terminal including a tablet computer, a car computer, etc.

[0149] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0150] See also Fig.10 , Fig.10 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0151] The processor 1001 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0152] The memory 1002 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1002 can store an operating system and other applications. When the technical solution provided in the embodiments of this specification is implemented by software or firmware, the relevant program code is stored in the memory 1002, and the processor 1001 calls and executes the face feature privacy protection method of the embodiment of this application;

[0153] Input / output interface 1003, used to implement information input and output;

[0154] The communication interface 1004 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WI FI, Bluetooth, etc.);

[0155] A bus 1005 , which transmits information between various components of the device (e.g., the processor 1001 , the memory 1002 , the input / output interface 1003 , and the communication interface 1004 );

[0156] The processor 1001 , the memory 1002 , the input / output interface 1003 and the communication interface 1004 are connected to each other in communication within the device via the bus 1005 .

[0157] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned facial feature privacy protection method is implemented.

[0158] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiments, the functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0159] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0160] The embodiments of the present application provide a method, system, electronic device and storage medium for protecting the privacy of facial features. The scheme obtains key parameters and facial feature vectors; inputs the key parameters into a spatiotemporal chaos model for iterative generation and uniform transformation processing to obtain a chaotic sequence, which can obtain a chaotic sequence with higher complexity and enhance the unpredictability of the chaotic sequence; in addition, the scheme extracts and processes the chaotic sequence according to the key parameters to obtain a scrambled sequence and an encrypted sequence, and can generate a scrambled sequence at a lower computational cost, thereby reducing the time-consuming operations and system iterations in the encryption process to reduce the impact on recognition efficiency; furthermore, the scheme permutes the facial feature vector according to the scrambled sequence to obtain a permuted feature vector; performs encryption transformation processing on the permuted feature vector according to the encryption sequence to obtain facial feature ciphertext data, and can perform chaotic stream encryption on the scrambled facial feature vector through the encryption sequence, thereby improving encryption performance and having a better privacy protection effect.

[0161] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0162] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0163] The system embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0164] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0165] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0166] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0167] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or units, which can be electrical, mechanical or other forms.

[0168] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0169] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0170] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0171] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A method for protecting the privacy of facial features, characterized in that: The method comprises the following steps: Get key parameters and face feature vector; Inputting the key parameters into the spatiotemporal chaos model for iterative generation and uniform transformation processing to obtain a chaotic sequence; Extracting the chaotic sequence according to the key parameter to obtain a scrambled sequence and an encrypted sequence; Performing a permutation process on the facial feature vector according to the scrambled sequence to obtain a permuted feature vector; The replacement feature vector is encrypted and transformed according to the encryption sequence to obtain facial feature ciphertext data.

2. The method according to claim 1, characterized in that The key parameters are input into the spatiotemporal chaos model for iterative generation and uniform transformation processing to obtain a chaotic sequence, comprising the following steps: Initializing the spatiotemporal chaos model according to the key parameters to obtain an initialized model; Iteratively processing the initialization model according to the dimension of the facial feature vector to obtain an iterative sequence; The iterative sequence is subjected to transient transformation processing to obtain a chaotic sequence.

3. The method according to claim 2, characterized in that The step of performing transient transformation processing on the iterative sequence to obtain a chaotic sequence comprises the following steps: Performing binary format conversion processing on the iterative sequence to obtain a first conversion sequence; Performing product and binary format conversion processing on the iteration sequence and the first conversion sequence to obtain a product sequence; The product sequence is divided and XORed bit by bit to obtain a chaotic sequence.

4. The method according to claim 1, characterized in that The extracting process of the chaotic sequence according to the key parameter to obtain a scrambled sequence and an encrypted sequence comprises the following steps: Obtaining scrambling control parameters and encryption control parameters from the key parameters; Performing format conversion and state value extraction processing on the chaotic sequence according to the scrambling control parameter to obtain a scrambled sequence; The chaotic sequence is subjected to bit value extraction processing according to the encryption control parameter to obtain an encryption sequence.

5. The method according to claim 4, characterized in that The step of performing format conversion and state value extraction processing on the chaotic sequence according to the scrambling control parameter to obtain a scrambled sequence comprises the following steps: Performing floating point number format conversion processing on each grid state value in the chaotic sequence to obtain a second conversion sequence; Performing a lattice state value extraction process on the second conversion sequence according to the scrambling control parameter to obtain an extraction sequence; The extraction sequence is multiplied and rounded according to the dimension of the facial feature vector to obtain a scrambled sequence.

6. The method according to claim 4, characterized in that The step of extracting the bit value of the chaotic sequence according to the encryption control parameter to obtain the encrypted sequence comprises the following steps: Performing bit value extraction processing on each grid state value of the chaotic sequence according to the encryption control parameter to obtain an extracted bit value; The extracted bit values ​​are combined to obtain an encrypted sequence.

7. The method according to claim 1, characterized in that The step of performing encryption transformation processing on the replacement feature vector according to the encryption sequence to obtain ciphertext data of facial features comprises the following steps: Performing binary format conversion processing on the replacement feature vector to obtain a plaintext sequence; The plaintext sequence and the encrypted sequence are subjected to an XOR operation according to an encryption transformation function to obtain ciphertext data of facial features.

8. A facial feature privacy protection system, characterized in that: The system comprises: The first module is used to obtain key parameters and face feature vectors; The second module is used to input the key parameters into the spatiotemporal chaos model for iterative generation and uniform transformation processing to obtain a chaotic sequence; The third module is used to extract the chaotic sequence according to the key parameter to obtain a scrambled sequence and an encrypted sequence; A fourth module is used to perform a permutation process on the facial feature vector according to the scrambling sequence to obtain a permuted feature vector; The fifth module is used to perform encryption transformation processing on the replacement feature vector according to the encryption sequence to obtain facial feature ciphertext data.

9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.