A distributed storage method of digital image data

Abstract

The application discloses a kind of distributed storage methods of digital image data, belong to data storage technical field, by adopting cluster server to build including main storage node and edge storage node Distributed storage system, by main storage node, using fragmentation encryption mode is encrypted to digital image data Processing, obtain the digital image data after encryption processing and multiple fragmentation encryption keys, by main storage node, the digital image data after encryption processing is randomly transmitted to two first edge storage nodes, and each fragmentation encryption key is transmitted to different second edge storage node, can effectively realize decentralization and double backup storage, greatly improve the safe storage of digital image data.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of data storage, and particularly relates to a distributed storage method for digital image data. BACKGROUND

[0002] Digital image data refers to image information captured, processed, stored and transmitted in a digital manner. These data can be photos, videos, medical images, satellite images and various forms, which usually exist in the form of digital files and can be operated and processed through computers or other electronic devices. With the continuous development of digital image technology, the amount of digital image data shows an explosive growth. Although the traditional centralized storage method can manage data centrally, it has the problem of poor security. SUMMARY

[0003] The application provides a distributed storage method for digital image data to solve the problem of low storage security performance in the prior art.

[0004] A distributed storage method for digital image data, comprising:

[0005] A cluster server is used to build a distributed storage system; wherein the distributed storage system comprises a main storage node and an edge storage node;

[0006] The main storage node obtains a data image data storage request and verifies the data image data storage request to obtain a request verification result; wherein the request verification result includes verification pass or verification fail; the data image data storage request includes patient information and digital image data;

[0007] The main storage node uses a fragmentation encryption method to encrypt the digital image data to obtain encrypted digital image data and a plurality of fragmentation encryption keys;

[0008] The main storage node randomly transmits the encrypted digital image data to two first edge storage nodes, and transmits each fragmentation encryption key to different second edge storage nodes;

[0009] The first edge storage node returns a data storage address, and the second edge storage node returns a key storage address, and the main storage node stores the patient information, the data storage address and the key storage address in association.

[0010] Further, the cluster server is used to build a distributed storage system, comprising:

[0011] Based on the cluster server, the sum of the communication distances between each server and all other servers is determined;

[0012] According to the sum of communication distances between each server and all other servers, the server with the minimum sum of communication distances is determined as the master storage node, and the other servers are determined as edge storage nodes.

[0013] Further, the data image data storage request is obtained by the master storage node, and the data image data storage request is verified to obtain a request verification result, including:

[0014] The data image data storage request is obtained by the master storage node, and the data image data storage request is verified to obtain a request verification result, including:

[0015] The name, gender, and ID number in the to-be-stored patient information are network-verified to obtain a basic verification result; wherein the basic verification result includes verification success or verification failure;

[0016] When the basic verification result is verification failure, it is determined that the request verification result is verification failure;

[0017] When the basic verification result is verification success, the examination information and examination sequence information are subjected to a missing verification to obtain a missing verification result; wherein the missing verification result includes verification success or verification failure;

[0018] When the missing verification result is verification success, it is determined that the request verification result is verification success, otherwise it is determined that the request verification result is verification failure.

[0019] Further, the digital image data is encrypted by the master storage node using a fragmentation encryption method to obtain encrypted digital image data and a plurality of fragmentation encryption keys, including:

[0020] The digital image data is encrypted using a symmetric encryption algorithm to obtain encrypted digital image data and a corresponding symmetric encryption key;

[0021] Based on the symmetric encryption key, a fragmentation processing polynomial is generated, and a plurality of fragmentation encryption keys are obtained according to the fragmentation processing polynomial.

[0022] Further, based on the symmetric encryption key, the fragmentation processing polynomial is generated as:

[0023] The symmetric encryption key is converted to a decimal number, and the fragmentation processing polynomial is constructed according to the converted decimal number as:

[0024] f(x) = s + a1x + a2x 2 +…+a k x k

[0025] wherein f(x) represents the dependent variable, x represents the independent variable, k represents the order of the polynomial, a1, a2, …, ak represent the coefficients of the polynomial, and s represents a decimal number. k respectively represent the 1st, 2nd, …, kth different fragmentation processing polynomial coefficients, and s represents a decimal number.

[0026] Further, the plurality of fragmented encryption keys are obtained according to the fragmentation processing polynomial, comprising:

[0027] The converted decimal number is divided into at least 2k key fragments, and each key fragment is input into the fragmentation processing polynomial to obtain a target dependent variable corresponding to each key fragment;

[0028] For any one key fragment, the key fragment and the target dependent variable form a fragmented encryption key, and a plurality of fragmented encryption keys are obtained.

[0029] Further, the digital image data after encryption processing is randomly transmitted to two first edge storage nodes through the main storage node, and each fragmented encryption key is transmitted to a different second edge storage node, comprising:

[0030] Two first edge storage nodes are randomly determined through the main storage node, the digital image data after encryption processing is randomly transmitted to the two first edge storage nodes, and the remaining edge storage nodes are set as second edge storage nodes; wherein the number of second edge storage nodes is greater than 2k;

[0031] 2k second edge storage nodes are randomly determined, and each fragmented encryption key is transmitted to a different second edge storage node.

[0032] Further, it further comprises:

[0033] Obtaining a data query request input by a user; wherein the data query request at least includes one item of patient information;

[0034] According to the data query request, the main storage node is used to find the corresponding target patient information, target data storage address and target key storage address;

[0035] According to the target data storage address and the target key storage address, the encrypted digital image data and the fragmented encryption key are obtained, and the encrypted transmission is performed through the public key of the user equipment.

[0036] Further, while obtaining the data query request input by the user, it further comprises:

[0037] Collect network traffic features, and adopt a pre-deployed deep learning model to detect the network traffic features to obtain a network security detection result; wherein the network security detection result includes network security or network intrusion;

[0038] When the network security detection result is network intrusion, a network security protection operation is performed to ensure the storage security of digital image data.

[0039] Further, the pre-deployment method of the deep learning model comprises:

[0040] A uniform initialization strategy is adopted to initialize a population of the algorithm; wherein each individual in the population is composed of all or part of the hyperparameters of the deep learning model;

[0041] The population is sequentially subjected to exploration stage space search, development stage space search, surrounding stage space search and escape stage space search to obtain the population after multi-stage space search;

[0042] It is judged whether the population after multi-stage space search meets the iteration end condition, if yes, the optimal individual is selected from the population after multi-stage space search, and the optimal individual is preset to the deep learning model, otherwise the step of multi-stage search is returned.

[0043] The application provides a distributed storage method of digital image data, which comprises the following steps: constructing a distributed storage system comprising a main storage node and an edge storage node by using a cluster server; encrypting the digital image data by using a fragmentation encryption method through the main storage node to obtain the encrypted digital image data and a plurality of fragmentation encryption keys; and transmitting the encrypted digital image data to two first edge storage nodes and transmitting each fragmentation encryption key to different second edge storage nodes through the main storage node, so that the decentralization and double backup storage can be effectively realized, and the safe storage of the digital image data is greatly improved. BRIEF DESCRIPTION OF DRAWINGS

[0044] The accompanying drawings, which are incorporated into and form part of the specification, illustrate embodiments consistent with the present application and, together with the specification, serve to explain the principles of the present application.

[0045] Figure 1 A flowchart of the distributed storage method of digital image data provided by the embodiment of the present application.

[0046] Figure 2 A flowchart of the pre-deployment method of the deep learning model provided by the embodiment of the present application.

[0047] The specific embodiments of the present application have been shown and described in the above drawings and text, and will be described in more detail in the following. These drawings and text are not intended to limit the scope of the inventive concept in any way, but to illustrate the inventive concept to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0048] Exemplary embodiments will be described in detail herein with reference to the attached drawings. The same or similar components are denoted by the same or similar reference numerals throughout the drawings and text. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the present application as detailed in the appended claims.

[0049] Embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0050] As Figure 1 shown, an embodiment of the present application provides a distributed storage method for digital image data, comprising:

[0051] S101, a distributed storage system is constructed by using a cluster server; wherein the distributed storage system comprises a main storage node and an edge storage node;

[0052] By constructing a distributed storage system by using a cluster server, not only the data storage capacity can be effectively improved, but also the decentralized processing can be realized, and the data security storage capacity can be improved.

[0053] S102, a data image data storage request is obtained by the main storage node, and the data image data storage request is verified to obtain a request verification result; wherein the request verification result comprises verification pass or verification fail; the data image data storage request comprises patient information and digital image data;

[0054] In order to ensure that the stored data is valid, the data image data storage request needs to be verified first, so as to avoid data recording error or omission.

[0055] S103, the digital image data is encrypted by using a fragmentation encryption method by the main storage node, to obtain the digital image data after encryption processing and a plurality of fragmentation encryption keys;

[0056] By obtaining the digital image data after encryption processing and the plurality of fragmentation encryption keys, the key acquisition degree can be increased, even if an illegal intruder obtains a part of the data or the key, it is also impossible to decrypt, so as to effectively ensure the security of the algorithm.

[0057] S104, transmitting the digital image data after encryption processing to two first edge storage nodes randomly through the main storage node, and transmitting each fragmented encryption key to different second edge storage nodes;

[0058] For any patient corresponding digital image data, backup processing is carried out, which can effectively guarantee the safety of data, resist network attack and physical attack, and transmit each fragmented encryption key to different second edge storage nodes, which can increase the difficulty of obtaining fragmented encryption key, and the public key of the second edge storage node is used for encryption transmission in the transmission process, avoiding the acquisition of fragmented encryption key, the system complexity is increased by several times, and the data security can be effectively improved.

[0059] S105, return the data storage address through the first edge storage node and the key storage address through the second edge storage node, and store the patient information, the data storage address and the key storage address through the main storage node.

[0060] When the association storage is carried out, the data can be encrypted, when the user normally accesses, the decryption and the acquisition of related data are carried out, so as to realize the double encryption mechanism.

[0061] In the embodiment of the application, a cluster server is used to construct a distributed storage system, which comprises:

[0062] Based on the cluster server, the sum of communication distances between each server and all other servers is determined;

[0063] According to the sum of communication distances between each server and all other servers, the server with the minimum sum of communication distances is determined as the main storage node, and the other servers are determined as edge storage nodes.

[0064] Since the main storage node needs to communicate with other edge storage nodes, the server with the minimum sum of communication distances is determined as the main storage node, so as to improve the data storage and reading efficiency.

[0065] In the embodiment of the application, the data image data storage request is obtained through the main storage node, and the data image data storage request is verified to obtain a request verification result, comprising:

[0066] The data image data storage request is obtained through the main storage node, and the data image data storage request is verified to obtain a request verification result, comprising:

[0067] The name, gender and ID number in the to-be-stored patient information are network-verified to obtain a basic verification result; wherein the basic verification result comprises verification success or verification failure;

[0068] When the basic verification result is a verification failure, then the request verification result is determined to be a verification failure;

[0069] When the basic verification result is a verification success, then the missing verification is performed on the check information and the check sequence information, and a missing verification result is obtained; wherein the missing verification result includes a verification success or a verification failure;

[0070] When the missing verification result is a verification success, then the request verification result is determined to be a verification success, otherwise the request verification result is determined to be a verification failure.

[0071] In the embodiment of the application, the digital image data is encrypted by the master storage node using a fragmentation encryption mode, and encrypted digital image data and a plurality of fragmentation encryption keys are obtained, including:

[0072] The digital image data is encrypted using a symmetric encryption algorithm, and encrypted digital image data and a corresponding symmetric encryption key are obtained;

[0073] The fragmentation processing polynomial is generated based on the symmetric encryption key, and a plurality of fragmentation encryption keys are obtained according to the fragmentation processing polynomial.

[0074] In the embodiment of the application, the fragmentation processing polynomial generated based on the symmetric encryption key is:

[0075] The symmetric encryption key is converted into a decimal number (for example, when using the advanced encryption standard algorithm, 11 rounds of keys are required, the 11 rounds of keys can be arranged in order, and then converted into a decimal number), and the fragmentation processing polynomial is constructed according to the converted decimal number:

[0076] f(x)=s+a1x+a2x 2 +…+a k x k

[0077] Wherein, f(x) represents the dependent variable, x represents the independent variable, k represents the order of the polynomial, a1, a2, …, a k respectively represent the 1st, 2nd, …, kth different fragmentation processing polynomial coefficients, and s represents the decimal number.

[0078] In the embodiment of the application, the plurality of fragmentation encryption keys are obtained according to the fragmentation processing polynomial, including:

[0079] The converted decimal number is divided into at least 2k key fragments, and each key fragment is brought into the fragmentation processing polynomial to obtain a target dependent variable corresponding to each key fragment;

[0080] For any one key fragment, the key fragment and the target dependent variable form a fragmented encryption key, and a plurality of fragmented encryption keys are obtained.

[0081] By obtaining a plurality of fragmented encryption keys, only k+1 fragmented encryption keys are obtained during decryption, the fragmented processing polynomial is reconstructed, the decryption of the symmetric encryption key is realized, and the decryption of the digital image data is realized.

[0082] In the embodiment of the application, the digital image data after encryption processing is randomly transmitted to two first edge storage nodes by the main storage node, and each fragmented encryption key is transmitted to different second edge storage nodes, comprising:

[0083] The two first edge storage nodes are randomly determined by the main storage node, the digital image data after encryption processing is randomly transmitted to the two first edge storage nodes, and the remaining edge storage nodes are set as second edge storage nodes; wherein the number of second edge storage nodes is greater than 2k;

[0084] 2k second edge storage nodes are randomly determined, and each fragmented encryption key is transmitted to different second edge storage nodes.

[0085] In the embodiment of the application, it also comprises:

[0086] The data query request input by the user is obtained; wherein the data query request comprises at least one item of patient information;

[0087] According to the data query request, the corresponding target patient information, target data storage address and target key storage address are found by the main storage node;

[0088] According to the target data storage address and the target key storage address, the encrypted digital image data and the fragmented encryption key are obtained, and the encrypted transmission is carried out through the public key of the user equipment.

[0089] According to the target data storage address, the encrypted digital image data can be obtained, and according to the target key storage address, at least k+1 fragmented encryption keys can be obtained, after the encrypted digital image data and at least k+1 fragmented encryption keys are transmitted to the user equipment, data decryption and viewing can be realized, thereby realizing comprehensive data security protection.

[0090] In the embodiment of the application, while obtaining the data query request input by the user, it also comprises:

[0091] Network traffic features are collected, and a pre-deployed deep learning model is used to detect the network traffic features to obtain a network security detection result; wherein the network security detection result comprises network security or network intrusion;

[0092] When the network security detection result network is invaded, a network security protection operation is performed to ensure the storage security of the digital image data.

[0093] The network security protection operation can be to block the user IP for a certain period of time to prohibit the user from accessing the data. If the number of attacks is too large, the port can be blocked for a certain period of time, so that data leakage can be avoided.

[0094] As shown in the figure, the pre-deployment method of the deep learning model comprises: Figure 2

[0095] S201, a uniform initialization strategy is used to initialize a population of an algorithm; each individual in the population is composed of all or part of the hyperparameters of the deep learning model;

[0096] For the dth dimension parameter, the parameter is randomly generated between the upper limit and the lower limit x 1,d ; wherein x 1,d represents the dth dimension parameter of the initial individual;

[0097] Based on the initial individual, the subsequent individual is generated as:

[0098]

[0099] wherein x n,d represents the dth dimension parameter of the nth individual, n = 1, 2, …, M, M represents the total number of individuals to be generated, rand1 represents a random number between (0, 1), x n+1,d represents the dth dimension parameter of the n+1th individual, γ d,min represents the lower limit of the dth dimension parameter, γ d,max represents the upper limit of the dth dimension parameter, and α represents a partition parameter, which is generally set to (γ d,min + γ d,max ) / 2.

[0100] By improving the initialization method, the initial training can make all individuals more uniformly distributed in the solution space, effectively improve the convergence ability and convergence speed of the algorithm, and compared with the chaotic mapping method, the data distribution is more uniform, avoiding the technical problem of poor local distribution of chaotic mapping.

[0101] It should be noted that the population can also be initialized by using a random initialization strategy.

[0102] S202, the population is sequentially subjected to exploration stage space search, development stage space search, surrounding stage space search, and escape stage space search, to obtain the population after multi-stage space search; ​

[0103] S202.1, Exploration phase space search, including:

[0104]

[0105] in, Let represent the m-th individual during the t-th training iteration, where m = 1, 2, ..., M, and M represents the total number of individuals in the population. `rand2` represents a random number between (0, 1), and `rand3` represents a random number between (0, 1). Indicates except Random individuals other than those mentioned above This refers to the individual after the spatial search in the exploration phase.

[0106] By exploring the spatial search phase, information from two individuals can be combined to improve the algorithm's ability to explore local areas and find a better location within its search range.

[0107] S202.2, Spatial search during the development phase, including:

[0108] Based on the population after the spatial search in the exploration phase, the loss function value corresponding to each individual is obtained. After arranging all individuals in ascending order of their loss function values, the weight coefficients corresponding to the individuals used for information interaction are obtained from the sorted order:

[0109]

[0110] in, This represents the weight coefficient corresponding to the i-th individual after sorting during the t-th training process.

[0111] Based on the weight coefficients corresponding to the individuals used for information interaction, the useful information of the population is obtained as follows:

[0112]

[0113] in, This represents useful information about the population. The dimensions are the same as those of other individuals. This represents the i-th individual after sorting.

[0114] Useful information of the population Based on this, the first update quantity and the second update quantity are determined as follows:

[0115]

[0116] in, Indicates the first update quantity The d-th dimension parameter follows (0, Cov) i) with a total dimensionality of D, Cov i denotes an intermediate parameter, T denotes a transpose, denotes with a scalar product, denotes a second update quantity, denotes an optimal individual in the t-th training process, denotes an individual after a k-th exploration stage space search, k = 1, 2, …, M.

[0117] The individual after the k-th exploration stage space search is updated as:

[0118]

[0119] wherein, denotes an individual after a development stage space search

[0120] The relationship between individuals is represented by establishing a probability model, which effectively improves the search ability and local convergence of the algorithm. Then by introducing a normal distribution, useful information can be learned more effectively, supplemented by learning the information of the best individual, which not only guarantees the local search ability of the algorithm, but also effectively avoids the algorithm from falling into a local optimum too early.

[0121] S202.3, the surrounding stage space search, comprising:

[0122]

[0123] β = (b-a)*rand4*e (tmax-t) / tmax

[0124] wherein, denotes an individual after a h-th development stage space search, denotes an individual after a surrounding stage space search β denotes an adaptive adjustment parameter, a denotes a first constant (set to 0.5 in this embodiment), b denotes a second constant (set to 1 in this embodiment), rand4 denotes a random number between (0, 1), and tmax denotes a preset maximum training number.

[0125] In the early stage of algorithm iteration, a larger adaptive adjustment parameter is used to generate a new solution to increase the diversity of the population. As the number of iterations increases, the algorithm will gradually tend to the optimal solution, so the influence of the new solution needs to be gradually reduced to realize the surrounding search of the optimal position and improve the convergence precision of the algorithm.

[0126] S202.4, the escape stage space search, comprising:

[0127]

[0128] wherein N(0,1) represents a standard Gaussian distribution function, represents the dth dimension parameter of the individual after the qth surrounding stage space search, represents the dth dimension parameter of the individual after the escape stage space search

[0129] By introducing the Gaussian distribution, the mutation ability of the individual can be improved, the individual has a certain probability to escape from the original position, the algorithm can be effectively avoided from falling into a local optimal solution, and the search ability of the algorithm is improved.

[0130] Optionally, after each search, each individual can be subjected to boundary crossing processing, so as to ensure the effectiveness of the algorithm.

[0131] S203, judge whether the population after the multi-stage space search meets the iteration end condition, if yes, select the optimal individual from the population after the multi-stage space search, and preset the deep learning model with the optimal individual, otherwise return to the step of the multi-stage search.

[0132] The pre-deployment method of the deep learning model provided by the embodiment of the application can effectively improve the hyperparameter optimization speed, avoid the algorithm from falling into a local optimal solution, finally improve the network intrusion detection capability, and improve the data security protection effect.

[0133] Those skilled in the art will understand that the embodiments of the application can be provided as a method, a system, or a computer program product. Therefore, the application can adopt a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the application can adopt the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer usable program code.

[0134] The application is described with reference to flowcharts and / or block diagrams of the method, device (system), and computer program product according to the embodiments of the application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the computer or other programmable data processing devices produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one flow or multiple flows and / or blocks Figure 1 The device that implements the functions specified in one block or multiple blocks.

[0135] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the Figure 1 function specified in the flow or flows and / or blocks Figure 1 of the block or blocks.

[0136] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the Figure 1 function specified in the flow or flows and / or blocks Figure 1 of the block or blocks.

[0137] Those of ordinary skill in the art can understand that all or part of the steps of the above-mentioned facts and methods can be completed by programs instructing relevant hardware, and the programs involved or the programs mentioned can be stored in a computer-readable storage medium. When the program is executed, it includes the following steps: at this time, the corresponding method steps are derived, and the storage medium can be ROM / RAM, a magnetic disc, an optical disc, etc.

[0138] The above detailed description of the specific embodiments of the present application further illustrates the purposes, technical solutions and beneficial effects of the present application. It should be understood that the above description is only a specific embodiment of the present application and is not used to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A distributed storage method for digital image data, characterized in that, include: A distributed storage system is constructed using clustered servers; wherein the distributed storage system includes a main storage node and edge storage nodes; The system obtains data image data storage requests through the primary storage node and verifies the data image data storage requests to obtain a request verification result; wherein, the request verification result includes verification passed or verification failed; the data image data storage request includes patient information and digital image data; The digital image data is encrypted using a fragmented encryption method on the main storage node to obtain the encrypted digital image data and multiple fragmented encryption keys. The encrypted digital image data is randomly transmitted from the main storage node to two first edge storage nodes, and each fragmented encryption key is transmitted to a different second edge storage node. The data storage address is returned through the first edge storage node and the key storage address is returned through the second edge storage node. The patient information, data storage address and key storage address are associated and stored through the main storage node. The digital image data is encrypted using a fragmented encryption method on the main storage node, resulting in encrypted digital image data and multiple fragmented encryption keys, including: For digital image data, a symmetric encryption algorithm is used to encrypt it, resulting in encrypted digital image data and the corresponding symmetric encryption key; Based on the symmetric encryption key, a fragmentation processing polynomial is generated, and multiple fragmentation encryption keys are obtained according to the fragmentation processing polynomial. Based on the aforementioned symmetric encryption key, the fragmentation processing polynomial is generated as follows: The symmetric encryption key is converted into a decimal number, and the fragmentation polynomial is constructed based on the converted decimal number as follows: in, Indicates the dependent variable. Indicates the independent variable. k Denotes the order of a polynomial. , ,…, They represent the 1st, 2nd, ..., k Different fragmentation processing of polynomial coefficients s Represents a decimal number; Multiple fragmented encryption keys are obtained based on the fragmentation processing polynomial, including: The converted decimal number is divided into at least 2k key fragments, and each key fragment is substituted into the fragmentation processing polynomial to obtain the target dependent variable corresponding to each key fragment; For any given key fragment, combine the key fragment with the target dependent variable to form a fragmented encryption key, resulting in multiple fragmented encryption keys.

2. The distributed storage method for digital image data according to claim 1, characterized in that, A distributed storage system is built using clustered servers, including: Based on the cluster server, determine the total communication distance between each server and all other servers; Based on the total communication distance between each server and all other servers, the server with the smallest total communication distance is identified as the primary storage node, and the other servers are identified as edge storage nodes.

3. The distributed storage method for digital image data according to claim 2, characterized in that, The system obtains data image data storage requests through the primary storage node, verifies the data image data storage requests, and obtains the request verification results, including: The system obtains the data image data storage request through the main storage node, and then obtains the patient information and digital image data to be stored. The name, gender, and ID number of the patient information to be stored are verified online to obtain a basic verification result; wherein, the basic verification result includes verification success or verification failure; If the basic verification result is verification failure, then the verification request result is determined to be verification failed. When the basic verification result is successful, the inspection information and inspection sequence information are subjected to missing verification to obtain a missing verification result; wherein, the missing verification result includes verification success or verification failure. If the missing verification result is successful, the verification request result is determined to be successful; otherwise, the verification request result is determined to be unsuccessful.

4. The distributed storage method for digital image data according to claim 3, characterized in that, The encrypted digital image data is randomly transmitted from the primary storage node to two first edge storage nodes, and each fragmented encryption key is transmitted to a different second edge storage node, including: Two first edge storage nodes are randomly selected from the main storage node, and the encrypted digital image data is randomly transmitted to the two first edge storage nodes. The remaining edge storage nodes are set as second edge storage nodes. The number of second edge storage nodes is greater than 2k. 2,000 second edge storage nodes are randomly selected, and each fragmented encryption key is transmitted to a different second edge storage node.

5. The distributed storage method for digital image data according to claim 4, characterized in that, Also includes: Obtain a data query request input by the user; wherein the data query request includes at least one item from the patient information; Based on the data query request, the corresponding target patient information, target data storage address, and target key storage address are located through the main storage node; Based on the target data storage address and the target key storage address, the encrypted digital image data and the fragmented encryption key are obtained, and then transmitted in encrypted form using the user equipment's public key.

6. The distributed storage method for digital image data according to claim 5, characterized in that, In addition to obtaining the user-input data query request, it also includes: Network traffic characteristics are collected, and a pre-deployed deep learning model is used to detect these characteristics to obtain network security detection results; wherein, the network security detection results include network security or network intrusion. When the network security detection results indicate that the network has been compromised, network security protection operations are performed to ensure the safe storage of digital image data.

7. The distributed storage method for digital image data according to claim 6, characterized in that, Methods for pre-deploying deep learning models include: The population of the algorithm is initialized using a uniform initialization strategy; wherein each individual in the population is composed of all or part of the hyperparameters of the deep learning model; The population is subjected to spatial search in the exploration phase, spatial search in the development phase, spatial search in the encirclement phase, and spatial search in the escape phase in sequence to obtain the population after the multi-stage spatial search. Determine whether the population after the multi-stage spatial search meets the iteration termination condition. If so, select the optimal individual from the population after the multi-stage spatial search and use the optimal individual to preset the deep learning model. Otherwise, return to the multi-stage search step.

Images