Identity verification data processing method based on edge computing

Abstract

The invention discloses an identity verification data processing method based on edge computing. The method comprises the following steps: determining a target user tag corresponding to a user identity by receiving a user identity verification request sent by current terminal equipment; according to the user tag and the user parameter, accurate identity verification can be carried out, and the verification accuracy is improved; furthermore, by establishing a target node at the cloud and backing up the user identity data, distributed calculation can be carried out by utilizing an edge calculation node, the calculation pressure of the cloud is reduced, and meanwhile, after the user identity data is backed up to the target node, identity verification calculation can be carried out in the target node, and the verification efficiency is improved; through obtaining the target user identifier in the target node and performing verification, identity verification can be quickly performed, search and calculation time can be reduced, an identity verification result can be fed back in time, and it is ensured that the user can quickly know whether verification succeeds or not.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to an identity authentication data processing method based on edge computing. Background Art

[0002] In modern computing and network systems, user identity authentication is an important means to ensure system security and user privacy. Traditional user identity authentication methods usually rely on centralized cloud computing, which has at least the following defects: in high-concurrency situations, a large number of users simultaneously authenticate their identities, which will cause excessive computing pressure on the cloud server, thus affecting the response speed and stability of the system;

[0003] At the same time, in traditional methods, user identity data is usually stored in a centralized database. When identity authentication is performed, it is necessary to search in a large amount of data, which leads to inefficient data search and increased verification time.

[0004] Therefore, researchers believe that the use of distributed methods based on edge computing for storage and verification of user identity authentication is more advantageous than traditional centralized cloud computing; however, how to improve the efficiency of user identity authentication and ensure the accuracy of user identity authentication is a problem that needs to be solved urgently. Summary of the invention

[0005] The purpose of the present invention is to provide an identity authentication data processing method based on edge computing, which solves the above-mentioned technical problems pointed out in the prior art.

[0006] The present invention provides an identity authentication data processing method based on edge computing, comprising the following steps:

[0007] Receive a user identity authentication request sent by the current terminal device, and determine a current target user tag according to the user identity authentication request;

[0008] Establishing a target node on the current cloud according to the target user tag; backing up the user identity data corresponding to the target user tag to the target node;

[0009] The target user identifier corresponding to the current target user tag is obtained in the target node; verification is performed according to the target user identifier and the user parameters of the user identity authentication request to obtain a verification result; and finally, based on the verification result, the user identity authentication result is fed back to the current terminal device.

[0010] Preferably, the verification is performed according to the target user identifier and the user parameters of the user identity authentication request to obtain a verification result, including the following steps:

[0011] Encode the target user ID through a hash function to obtain a target hash value;

[0012] Encode the user parameters through a hash function to obtain a verification hash value;

[0013] Calculate the cosine function of the target hash value and the verification hash value;

[0014] When the cosine function is 1, the verification result is a successful verification; when the cosine function is not 1, the verification result is a failed verification.

[0015] Preferably, the step of establishing a target node on the current cloud according to the target user tag includes the following steps:

[0016] Establishing a plurality of first nodes; marking each of the first nodes to obtain a first node mark;

[0017] During initialization, a target space is first constructed; a mapping function f of the target space is constructed; based on the mapping function, the first node mark is mapped to the target space to obtain the first node coordinates corresponding to each of the first node marks;

[0018] Constructing a node position set X={x1, x2, x3, ...xi} of the current target space based on all the first node coordinates; wherein xi is the first node coordinate of the i-th first node;

[0019] Initialize iteration parameters; the iteration parameters include an iteration counter and a maximum iteration threshold; the iteration number of the iteration counter is initially 0;

[0020] A search is performed based on the iteration parameter and the node position set X to obtain a target node.

[0021] Preferably, the searching and acquiring the target node based on the iteration parameter and the node position set X comprises the following steps:

[0022] The coordinates of the center point of all the node position sets are obtained as the initial position D, and the fitness R corresponding to each of the first node coordinates is calculated using a preset fitness calculation function f(x);

[0023] Select the fitness R with the largest fitness value among all the fitness R as the first fitness;

[0024] Add 1 to the iteration number of the iteration counter to obtain the current iteration number;

[0025] The target node is obtained by performing screening and iterative processing based on the current number of iterations and the first fitness;

[0026] Preferably, the step of performing screening and iterative processing according to the current number of iterations and the first fitness to obtain the target node comprises the following steps:

[0027] Determine whether the current iteration number is 1; if so, use the first fitness as the candidate fitness; if not, determine whether the candidate fitness is greater than or equal to the candidate fitness generated by the previous iteration; if so, screen out the candidate fitness generated by the previous iteration; if not, screen out the candidate fitness generated by the current iteration;

[0028] Further determine whether the number of iterations is greater than or equal to the maximum iteration threshold; if so, output the first node coordinate corresponding to the current candidate fitness as the target node; if not, then according to the current number of iterations t and the maximum iteration threshold t max Calculate and obtain the iteration factor α;

[0029] Calculate and obtain the search step length A based on the iteration factor α;

[0030] The calculation method of the search step length A is:

[0031] A = 2α × p-α; where p is a random number between 0 and 1;

[0032] Obtain a random number T; wherein 0≤random number T≤1; determine whether the random number T is less than 0.5; if so, determine whether the absolute value of the search step length A is less than 1; if so, update the coordinates of the initial position according to the first position update function to obtain an updated first coordinate W1; if not, update the coordinates of the initial position according to the second position update function to obtain an updated second coordinate W2; if the random number T is greater than or equal to 0.5, update the coordinates of the initial position according to the third position update function to obtain an updated third coordinate W3;

[0033] The node coordinates are mutated based on the updated first coordinates, the updated second coordinates, or the updated third coordinates to obtain mutated node coordinates, the mutated node coordinates are used as the first node coordinates, and the above operation is returned until the target node is output.

[0034] Preferably, the iteration factor α is calculated as follows:

[0035]

[0036] Preferably, the updated first coordinate W1 is calculated as follows:

[0037]

[0038] The updated second coordinate W2 is calculated as follows:

[0039]

[0040] The updated third coordinate W3 is calculated as follows:

[0041]

[0042] Where D is the current initial position; X * (R) is the coordinate of the node with the highest current fitness; A is the search step; K is the update position; X rand (R) is the node coordinate corresponding to any random fitness; e bl is the function parameter;

[0043] Preferably, the calculation method of the mutated node coordinates is:

[0044] X'=X i (t)+F(WX i (t)); W∈(W1, W2, W3);

[0045] Where, X i (t) is the first node coordinate of the current iteration; W is the updated first coordinate or the updated second coordinate or the updated third coordinate;

[0046] The present invention also provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the above-mentioned authentication data processing method based on edge computing

[0047] The present invention also provides a storage medium, which includes a stored program, wherein when the program is running, the device where the readable storage medium is located is controlled to execute the above-mentioned identity authentication data processing method based on edge computing.

[0048] Compared with the prior art, the embodiments of the present invention have at least the following technical advantages:

[0049] By analyzing the above-mentioned identity authentication data processing method based on edge computing provided by the present invention, it can be known that in specific applications, the target user tag (such as account number, user name, etc.) corresponding to the user identity is clarified by receiving the user identity authentication request sent by the current terminal device; according to the user tag and user parameters (such as password, etc.), accurate identity authentication can be performed to improve the accuracy of verification;

[0050] Furthermore, the technical solution adopted in the embodiment of the present invention can use the edge computing node to perform distributed computing by establishing a target node in the cloud and backing up the user identity data, thereby reducing the computing pressure on the cloud. At the same time, after backing up the user identity data to the target node, identity authentication calculation can be performed in the target node to improve the verification efficiency; by obtaining the target user identification in the target node and performing verification, identity authentication can be performed quickly, reducing the search and calculation time, and the identity authentication result can be fed back in time to ensure that the user can quickly know whether the verification is successful;

[0051] Specifically, by performing distributed computing at edge computing nodes, the computing pressure on the cloud can be effectively reduced, especially when a large number of users are performing identity authentication at the same time; by distributed computing and rapid search for target user identification, the efficiency of identity authentication can be significantly improved and user waiting time can be reduced; by precise hash value verification, the accuracy of identity authentication can be ensured and the possibility of misjudgment can be reduced; by distributed computing and hash value verification, the security of identity authentication can be improved to prevent malicious attacks and data leakage;

[0052] Through technical means such as distributed computing, fast search and precise verification, the efficiency and accuracy of user identity authentication are significantly improved, while the computing pressure on the cloud is reduced and the security of cloud data is enhanced. Especially when processing a large number of user identity authentication requests, it can effectively cope with high concurrent authentication needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 A schematic diagram of the main process of an identity authentication data processing method based on edge computing;

[0054] Figure 2 A schematic diagram of the operational flow of establishing a target node in an identity authentication data processing method based on edge computing. DETAILED DESCRIPTION

[0055] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] The present invention is further described in detail below through specific embodiments in conjunction with the accompanying drawings.

[0057] like Figure 1 As shown, the present invention proposes an identity authentication data processing method based on edge computing, comprising the following steps:

[0058] Step S10: receiving a user identity authentication request sent by the current terminal device, and determining a current target user tag according to the user identity authentication request;

[0059] It should be noted that, when the above-mentioned current terminal device sends a user identity authentication request, it will mark the user tag that currently needs to be authenticated according to the attribute information of the user identity authentication request (the attribute information of the user identity authentication request generally includes a user tag, a user parameter, etc.) (the user tag can be understood as the user's account, user name, etc., and correspondingly, the user parameter can be understood as the account password, etc.);

[0060] Step S20: establishing a target node on the current cloud according to the target user tag; backing up the user identity data corresponding to the target user tag to the target node;

[0061] The target node mentioned above refers to the "container" for verification calculation when the current user identity authentication request is subsequently executed to perform verification calculation operations;

[0062] It should be noted that the above-mentioned nodes refer to edge computing nodes when performing authentication operations on user authentication requests, and edge computing nodes can be used as independent computing units;

[0063] The above-mentioned embodiment of the present application establishes an independent computing unit edge computing node according to the target user tag, and backs up the user identity data corresponding to the target user tag to the target node (the target node is the above-mentioned edge computing node), and processes the user identity authentication request of the current user in the target node, which can prevent excessive computing pressure on the cloud when a large number of users are authenticated at the same time, and at the same time can improve the efficiency of identity authentication.

[0064] Step S30: obtaining the target user identifier corresponding to the current target user tag in the target node; performing verification based on the target user identifier and the user parameters of the user identity authentication request to obtain a verification result; and finally feeding back the user identity authentication result to the current terminal device based on the verification result.

[0065] Specifically, the above verification (i.e., user parameter verification) obtains the verification result by means of hash value verification; specifically: the target user identification is encoded through a hash function to obtain a target hash value, and the user parameters are encoded through a hash function to obtain a verification hash value; the cosine function of the target hash value and the verification hash value is calculated; when the cosine function is 1, the verification result obtained is a successful verification; when the cosine function is not 1, the verification result obtained is a failed verification (or unsuccessful verification).

[0066] It should be noted that the above embodiment of the present application is to search from the target node to obtain the target user identifier corresponding to the current target user tag after the target node is retrieved, thereby avoiding the data search pressure caused by searching for the target user identifier corresponding to the target user tag among all user identifiers, improving the search efficiency, and thus further improving the speed of user identity authentication;

[0067] In further operations, verification is performed through the target user identifier and the user parameters in the user identity authentication request to determine whether the identity authentication is successful; specifically, when the verification result is successful, it proves that the identity authentication is successful, and the current terminal device can access the information on the current cloud according to the node of the current terminal device; when the verification result is unsuccessful, it proves that the identity authentication has failed, and the result of the identity authentication failure will be fed back to the current terminal device.

[0068] The above-mentioned embodiment of the present application clarifies the target user tag (such as account number, user name, etc.) corresponding to the user identity by receiving the user identity authentication request sent by the current terminal device; according to the user tag and user parameters (such as password, etc.), accurate identity authentication can be performed to improve the accuracy of verification; further, by establishing a target node in the cloud and backing up the user identity data, it is possible to use the edge computing node for distributed computing to reduce the computing pressure on the cloud. At the same time, after backing up the user identity data to the target node, the identity authentication calculation can be performed in the target node to improve the verification efficiency; by obtaining the target user identifier in the target node and performing verification, the identity authentication can be quickly performed, the search and calculation time can be reduced, and the identity authentication result can be fed back in time to ensure that the user can quickly know whether the verification is successful;

[0069] The above-mentioned embodiments of the present application can effectively reduce the computing pressure of the cloud by performing distributed computing on edge computing nodes, especially when a large number of users are performing identity authentication at the same time; through distributed computing and rapid search for target user identification, the efficiency of identity authentication can be significantly improved and the user waiting time can be reduced; through precise hash value verification, the accuracy of identity authentication can be ensured and the possibility of misjudgment can be reduced; through distributed computing and hash value verification, the security of identity authentication can be improved to prevent malicious attacks and data leakage;

[0070] Through technical means such as distributed computing, fast search and precise verification, the efficiency and accuracy of user identity authentication are significantly improved, while the computing pressure on the cloud is reduced and the security of cloud data is enhanced. Especially when processing a large number of user identity authentication requests, it can effectively cope with high concurrent authentication needs.

[0071] Specifically, Figure 2 As shown, in step S20, a target node is established on the current cloud according to the target user tag, including the following operation steps:

[0072] Step S21: establishing a plurality of first nodes; marking each of the first nodes to obtain a first node mark;

[0073] Step S22: during initialization, first construct a target space (the target space is a two-dimensional space or a three-dimensional space); construct a mapping function f of the target space; based on the mapping function, map the first node mark to the target space to obtain the first node coordinates corresponding to each of the first node marks; it should be noted that the target space constructed during the initialization operation is empty, and then the first node mark is mapped to the target space using the preset mapping function f to obtain the final target space, thereby obtaining the first node coordinates corresponding to the first node mark;

[0074] Step S23: constructing a node position set X={x1, x2, x3, ...xi} of the current target space based on all the first node coordinates; wherein xi is the first node coordinate of the i-th first node;

[0075] Step S24: Initialize iteration parameters (the iteration parameters mentioned here are search parameters required in subsequent operations); the iteration parameters include an iteration counter and a maximum iteration number threshold; the iteration number of the iteration counter is initially 0;

[0076] Step S25: Search and obtain the target node based on the iteration parameter and the node position set X.

[0077] It should be noted that the above-mentioned embodiment of the present application lays the foundation for subsequent spatial mapping and searching by establishing multiple first nodes and marking them; further, by constructing a target space (two-dimensional or three-dimensional), a specific physical or abstract space is provided for node mapping and searching, and a mapping function is used to map the first node mark to the target space, and the specific position of each node in the target space is determined to obtain the first node coordinates; by collecting the coordinates of all first nodes, a node position set is constructed to provide basic data for subsequent search operations; by initializing iteration parameters (including an iteration counter and a maximum number threshold), the iteration process is controlled to avoid infinite loops or excessive iterations; the iteration parameters and the node position set are used to search, and the search efficiency is improved through iteration and optimization algorithms to ensure that the target node is found within a reasonable time.

[0078] The embodiment of the present invention needs to establish a node first, and then verify the current user identity authentication request in the node; the embodiment of the present invention also screens and optimizes each established node in the subsequent processing process to obtain the target node; after the embodiment of the present invention is completed, the target node needs to be further used as a sample to perform machine learning model training to further establish an intelligent model;

[0079] Generally speaking, samples are the basis of machine learning models. Through a large number of training samples, the model can learn potential laws and features, thereby improving its prediction and decision-making capabilities.

[0080] The "target node" in the embodiment of the present application is the sample for subsequent machine learning model training and processing. However, this sample is not collected here, but established according to the target user label; in essence, it is still a search for the optimal node, but a new node is created, and an optimal node is searched from the multiple nodes initially established. The coordinates of the multiple nodes initially established are subsequently mutated to increase the population size, thereby obtaining a globally optimal target node. Through the above scheme, more forms of target nodes can be obtained, thereby enhancing the sample diversity of the subsequent machine learning model.

[0081] Specifically, in step S25, searching and acquiring the target node based on the iteration parameter and the node position set X includes the following steps:

[0082] Step S251: obtaining the center point coordinates of all the node position sets as the initial position D, and using a preset fitness calculation function f(x) to calculate and obtain the fitness R corresponding to each of the first node coordinates;

[0083] Step S252: selecting the fitness R with the largest fitness value among all the fitness R as the first fitness;

[0084] It should be noted that the above application first initializes and preliminarily screens the center point coordinates of all node position sets as the initial position to determine the initial starting point of the optimization; the fitness R corresponding to each first node coordinate is calculated to evaluate the quality of each first node position; the fitness R with the largest fitness value is selected as the first fitness, and the current optimal node position is preliminarily screened out;

[0085] Step S253: adding 1 to the iteration number of the iteration counter to obtain the current iteration number;

[0086] Step S254: performing screening and iterative processing according to the current number of iterations and the first fitness to obtain a target node;

[0087] It should be noted that the above-mentioned embodiment of the present application obtains the center point coordinates of the node position set as the initial position to ensure that the optimization process starts from a reasonable starting point and avoids deviations caused by extreme values, and uses a preset fitness calculation function to calculate the fitness of each node, evaluates the advantages and disadvantages of each node position, and provides a basis for subsequent screening and optimization; by selecting the node with the largest fitness value, the current optimal node position is preliminarily screened out to ensure that the optimization process starts from the optimal point; by increasing the number of iteration counters, the iteration process is controlled to avoid infinite loops and ensure that the optimization process is completed within a reasonable time; the combination of fitness and number of iterations is used to ensure the accuracy of the screening process and improve the accuracy of the final target node.

[0088] Specifically, in step S254, the target node is obtained by screening and iterating according to the current number of iterations and the first fitness, including the following operation steps:

[0089] Step S2541: determine whether the current iteration number is 1; if so, use the first fitness as the candidate fitness; if not, determine whether the candidate fitness is greater than or equal to the candidate fitness generated in the previous iteration; if so, filter out the candidate fitness generated in the previous iteration (i.e., retain the current candidate fitness); if not, filter out the candidate fitness generated in the current iteration (i.e., retain the candidate fitness generated in the previous iteration);

[0090] It should be noted that the above-mentioned application determines whether there are previous results that need to be compared by judging whether it is the first iteration. If it is the first iteration, the first fitness is used as the candidate fitness and as the initial reference point; if not, the current fitness is compared with the fitness of the previous iteration; if the current fitness is better than the previous one, the current fitness is retained; otherwise, the previous fitness is retained.

[0091] Step S2542: further determine whether the number of iterations is greater than or equal to the maximum iteration threshold; if so, output the first node coordinate corresponding to the current candidate fitness as the target node; if not, according to the current number of iterations t and the maximum iteration threshold t max Calculate and obtain the iteration factor α;

[0092] The iteration factor α is calculated as:

[0093]

[0094] It should be noted that the above application determines whether the number of iterations is greater than or equal to the maximum threshold: if so, the current optimal first node coordinates are output as the final target node; if not, the iteration continues, and the iteration factor α is calculated based on the current number of iterations.

[0095] Step S2543: Calculate and obtain the search step length A based on the iteration factor α;

[0096] The calculation method of the search step length A is:

[0097] A = 2α × p-α; where p is a random number between 0 and 1;

[0098] Explanation: The above application calculates the search step length A based on the iteration factor α, and adjusts the search step length to search for the optimal solution faster.

[0099] Step S2544: Obtain a random number T (0≤random number T≤1); determine whether the random number T is less than 0.5; if so, determine whether the absolute value of the search step A is less than 1; if so, update the coordinates of the initial position according to the first position update function to obtain an updated first coordinate W1; if not, update the coordinates of the initial position according to the second position update function to obtain an updated second coordinate W2; if the random number T is greater than or equal to 0.5, update the coordinates of the initial position according to the third position update function to obtain an updated third coordinate W3;

[0100] The updated first coordinate W1 is calculated as follows:

[0101]

[0102] The updated second coordinate W2 is calculated as follows:

[0103]

[0104] The updated third coordinate W3 is calculated as follows:

[0105]

[0106] Where D is the current initial position; X * (R) is the coordinate of the node with the highest current fitness; A is the search step; K is the update position; X rand (R) is the node coordinate corresponding to any random fitness; e bl is the function parameter;

[0107] It should be noted that the above-mentioned application introduces randomness to avoid local interference. Specifically, combined with the idea of ​​guiding population optimization with adaptive inertia weight in the particle swarm optimization algorithm, this paper introduces an adaptive strategy into the position update formula to speed up the convergence of the algorithm.

[0108] Step S2545: mutating the node coordinates based on the updated first coordinates, the updated second coordinates, or the updated third coordinates to obtain mutated node coordinates (mutated node coordinates or second node coordinates), using the mutated node coordinates as the first node coordinates and returning to the above operation until the target node is output;

[0109] The calculation method of the mutated node coordinates is as follows:

[0110] X'=X i (t)+F(WX i (t)); W∈(W1, W2, W3);

[0111] Where, X i (t) is the first node coordinate of the current iteration; W is the updated first coordinate or the updated second coordinate or the updated third coordinate;

[0112] It should be noted that the above embodiment of the present application mutates the node coordinates based on the updated coordinates, increases diversity through the mutation operation, and further avoids the local optimum;

[0113] It should be noted that, in the above-mentioned embodiment of the present application, at the first iteration, the first fitness is used as the initial reference point to provide a benchmark for subsequent iterations; at the non-first iteration, by comparing the current fitness with the fitness of the previous iteration, a better fitness is dynamically screened out to ensure that the optimization process gradually approaches the optimal solution; further, by judging whether the number of iterations reaches the maximum threshold, it is determined whether to terminate the iteration to avoid an infinite loop. When the maximum number of iterations is not reached, the iteration factor is calculated, which provides a basis for calculating the subsequent search step length;

[0114] It calculates the search step size and dynamically adjusts the search step size according to the current iteration factor and random number to ensure the flexibility and diversity of the search process. Adjusting the search step size helps to speed up the convergence of the algorithm and avoid falling into the local optimum. By introducing random numbers, the search process is prevented from falling into the local optimum and the diversity of the search is increased. According to different conditions (random numbers and search step sizes), different position update functions are selected to update the coordinates of the initial position to ensure the flexibility and diversity of the search process. Mutation is performed based on the updated coordinates to increase the diversity of node coordinates and further avoid local optimum. Then the mutated node coordinates are used as the new first node coordinates, and iteration continues to gradually optimize the node position and approach the optimal solution.

[0115] The above-mentioned embodiments of the present application form a complete node optimization process through dynamic screening, termination condition control, flexible step size adjustment, introduction of randomness and increased diversity, thereby improving the efficiency and accuracy of node optimization; through reasonable screening, flexible step size adjustment and introduction of randomness, it can effectively deal with complex node optimization problems and gradually find the optimal target node.

[0116] In summary, the present invention proposes an identity authentication data processing method based on edge computing, which clarifies the target user tag corresponding to the user identity by receiving the user identity authentication request sent by the current terminal device; according to the user tag and user parameters, accurate identity authentication can be performed to improve the accuracy of verification; further, by establishing a target node in the cloud and backing up the user identity data, the edge computing node can be used for distributed computing to reduce the computing pressure on the cloud; at the same time, after backing up the user identity data to the target node, the identity authentication calculation can be performed in the target node to improve the verification efficiency; by obtaining the target user identifier in the target node and performing verification, the identity authentication can be performed quickly, the search and calculation time can be reduced, and the identity authentication result can be fed back in time to ensure that the user can quickly know whether the verification is successful;

[0117] Specifically, in the process of establishing the target node, by establishing multiple first nodes and marking them, a foundation is laid for subsequent spatial mapping and searching; further, by constructing a target space (two-dimensional or three-dimensional), a specific physical or abstract space is provided for node mapping and searching, and a mapping function is used to map the first node mark to the target space, determine the specific position of each node in the target space, and obtain the first node coordinates; by collecting the coordinates of all first nodes, a node position set is constructed to provide basic data for subsequent search operations; by initializing iteration parameters (including iteration counters and maximum number thresholds), the iteration process is controlled to avoid infinite loops or excessive iterations; by using iteration parameters and node position sets to search, the search efficiency is improved through iteration and optimization algorithms to ensure that the target node is found within a reasonable time;

[0118] In the specific implementation process, by obtaining the center point coordinates of the node position set as the initial position, it is ensured that the optimization process starts from a reasonable starting point to avoid deviations caused by extreme values, and the fitness of each node is calculated using the preset fitness calculation function to evaluate the pros and cons of each node position, providing a basis for subsequent screening and optimization; by selecting the node with the largest fitness value, the current optimal node position is preliminarily screened out to ensure that the optimization process starts from the optimal point; by increasing the number of iteration counters, the iteration process is controlled to avoid infinite loops and ensure that the optimization process is completed within a reasonable time; by combining fitness and the number of iterations, the accuracy of the screening process is ensured and the accuracy of the final target node is improved;

[0119] In the specific iterative process, a complete node optimization process is formed through dynamic screening, termination condition control, flexible step size adjustment, introduction of randomness and increased diversity, which improves the efficiency and accuracy of node optimization. Through reasonable screening, flexible step size adjustment and introduction of randomness, it can effectively deal with complex node optimization problems and gradually find the optimal target node.

[0120] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. A person skilled in the art may modify the technical solutions described in the above embodiments, or replace part or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for processing identity authentication data based on edge computing, characterized in that: The steps are as follows: Receive a user identity authentication request sent by the current terminal device, and determine a current target user tag according to the user identity authentication request; Establishing a target node on the current cloud according to the target user tag; backing up the user identity data corresponding to the target user tag to the target node; Obtaining a target user identifier corresponding to the current target user tag in the target node; Verification is performed according to the target user identifier and the user parameters of the user identity verification request to obtain a verification result; and finally, based on the verification result, the user identity verification result is fed back to the current terminal device.

2. A method for processing identity authentication data based on edge computing according to claim 1, characterized in that: The step of performing verification according to the target user identifier and the user parameters of the user identity verification request to obtain a verification result includes the following steps: Encode the target user ID through a hash function to obtain a target hash value; Encode the user parameters through a hash function to obtain a verification hash value; Calculate the cosine function of the target hash value and the verification hash value; When the cosine function is 1, the verification result is a successful verification; when the cosine function is not 1, the verification result is a failed verification.

3. A method for processing identity authentication data based on edge computing according to claim 2, characterized in that: The step of establishing a target node on the current cloud according to the target user tag includes the following steps: Establishing a plurality of first nodes; marking each of the first nodes to obtain a first node mark; During initialization, a target space is first constructed; a mapping function f of the target space is constructed; based on the mapping function, the first node mark is mapped to the target space to obtain the first node coordinates corresponding to each of the first node marks; Constructing a node position set X={x1, x2, x3, ...xi} of the current target space based on all the first node coordinates; wherein xi is the first node coordinate of the i-th first node; Initialize iteration parameters; the iteration parameters include an iteration counter and a maximum iteration threshold; the iteration number of the iteration counter is initially 0; A search is performed based on the iteration parameter and the node position set X to obtain a target node.

4. A method for processing identity authentication data based on edge computing according to claim 3, characterized in that: The step of searching and acquiring a target node based on the iteration parameter and the node position set X comprises the following steps: The coordinates of the center point of all the node position sets are obtained as the initial position D, and the fitness R corresponding to each of the first node coordinates is calculated using a preset fitness calculation function f(x); Select the fitness R with the largest fitness value among all the fitness R as the first fitness; Add 1 to the iteration number of the iteration counter to obtain the current iteration number; The target node is obtained by performing screening and iterative processing based on the current number of iterations and the first fitness.

5. A method for processing identity authentication data based on edge computing according to claim 4, characterized in that: The step of performing screening and iterative processing according to the current number of iterations and the first fitness to obtain a target node includes the following steps: Determine whether the current iteration number is 1; if so, use the first fitness as the candidate fitness; if not, determine whether the candidate fitness is greater than or equal to the candidate fitness generated by the previous iteration; if so, screen out the candidate fitness generated by the previous iteration; if not, screen out the candidate fitness generated by the current iteration; Further determine whether the number of iterations is greater than or equal to the maximum iteration threshold; if so, output the first node coordinate corresponding to the current candidate fitness as the target node; if not, then according to the current number of iterations t and the maximum iteration threshold t max Calculate and obtain the iteration factor α; Calculate and obtain the search step length A based on the iteration factor α; The calculation method of the search step length A is: A = 2α × p-α; where p is a random number between 0 and 1; Obtain a random number T; wherein 0≤random number T≤1; determine whether the random number T is less than 0.5; if so, determine whether the absolute value of the search step length A is less than 1; if so, update the coordinates of the initial position according to the first position update function to obtain an updated first coordinate W1; if not, update the coordinates of the initial position according to the second position update function to obtain an updated second coordinate W2; if the random number T is greater than or equal to 0.5, update the coordinates of the initial position according to the third position update function to obtain an updated third coordinate W3; The node coordinates are mutated based on the updated first coordinates, the updated second coordinates, or the updated third coordinates to obtain mutated node coordinates, the mutated node coordinates are used as the first node coordinates, and the above operation is returned until the target node is output.

6. A method for processing identity authentication data based on edge computing according to claim 5, characterized in that: The iteration factor α is calculated as:

7. The method for processing identity authentication data based on edge computing according to claim 6, characterized in that: The updated first coordinate W1 is calculated as follows: The updated second coordinate W2 is calculated as follows: The updated third coordinate W3 is calculated as follows: Where D is the current initial position; X * (R) is the coordinate of the node with the highest current fitness; A is the search step; K is the update position; X rand (R) is the node coordinate corresponding to any random fitness; e bl For function parameters.

8. The method for processing identity authentication data based on edge computing according to claim 7, characterized in that: The calculation method of the node coordinates after the mutation is: X'=X i (t)+F(W-X i (t));W∈(W1、W2、W3); Where, X i (t) is the first node coordinate of the current iteration; W is the updated first coordinate or the updated second coordinate or the updated third coordinate.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement an identity authentication data processing method based on edge computing as described in any one of claims 1 to 8.

10. A storage medium, characterized in that: The storage medium includes a stored program, wherein when the program is running, the device where the readable storage medium is located is controlled to execute an identity authentication data processing method based on edge computing as described in any one of claims 1 to 8.

Images