A digital identity access management method and system based on artificial intelligence

Abstract

The present invention belongs to the field of information security technology. A digital identity access management method and system based on artificial intelligence are provided. The method includes: retrieving the associated access information and the first historical access information of the access party according to the first digital identity information of the access party; using the artificial intelligence model to perform preliminary identity verification to obtain the first verification pass value of the access party; screening each assisting node in the blockchain network, and each assisting node performs identity verification on the first digital identity information and the associated access information to obtain the first access similarity index; calculating the second verification pass value according to the first access similarity index and the first verification pass value, and deciding whether to allow the access of the access party according to the second verification pass value. The present invention simultaneously performs identity authentication on the access party based on the digital identity information and the associated access information of the access party, and also performs online auxiliary verification of the identity information based on the blockchain network, which can improve the security of digital identity access management.

Description

Technical Field

[0001] The present invention relates to the field of information security technology, and in particular to an artificial intelligence-based digital identity access management method and system. Background Art

[0002] Digital identity access refers to the online identity used by an individual, organization or electronic device in cyberspace. It involves a series of data and information used to describe or identify a subject. The existing digital identity access management is based on the local identity database to match and verify the identity information of the access party. If the matching verification is passed, that is, there is a template identity information matching the identity information of the access party in the local identity database, the access party is allowed to access the corresponding system.

[0003] The above-mentioned existing digital identity access management method only matches and verifies the identity information of the access party, and lacks synchronous analysis of other additional information, resulting in major security defects in digital identity access management and failing to meet actual needs. Summary of the invention

[0004] In this regard, the present invention provides an artificial intelligence-based digital identity access management method, system, electronic device, computer storage medium and computer program product to solve the above-mentioned technical problems.

[0005] The present invention discloses a digital identity access management method based on artificial intelligence, and the method comprises the following steps: receiving the first digital identity information of an input access party, and retrieving the associated access information and the first historical access information related to the access party according to the first digital identity information; using an artificial intelligence model to perform preliminary identity verification on the first digital identity information, the associated access information and the first historical access information, and obtain a first verification pass value of the access party; determining the number of assisting nodes according to the first verification pass value, and selecting a corresponding number of assisting nodes in a blockchain network according to the number of assisting nodes, and having each of the assisting nodes perform identity verification on the first digital identity information and the associated access information respectively, and obtain a first access similarity index; calculating a second verification pass value according to the first access similarity index and the first verification pass value, and determining whether to allow the access of the access party according to the second verification pass value.

[0006] In some embodiments, retrieving first historical access information involving the access party based on the first digital identity information includes: determining type information of the first digital identity information; wherein the type information includes an account password, an identity sequence code stored in a dedicated identity device, and physiological identity information; determining a first span duration based on the type information, and retrieving first historical access information involving the access party based on the first span duration.

[0007] In some embodiments, determining the first span duration based on the type information includes: if the type information is an account password, setting the first span duration to a first value; if the type information is an identity sequence code stored in a dedicated identity device, setting the first span duration to a second value; if the physiological identity information is an account password, setting the first span duration to a third value; wherein the first value is greater than the second value, and the second value is greater than the third value.

[0008] In some embodiments, the use of an artificial intelligence model to perform preliminary identity verification on the first digital identity information, the associated access information and the first historical access information to obtain a first verification pass value of the access party includes: matching and verifying the first digital identity information with a number of second digital identity information preset in a database, and if there is at least one matching second digital identity information in the matching verification result, calculating a third verification pass value according to a negative correlation relationship based on the number of second digital identity information; inputting the associated access information and the first historical access information of the access party into the artificial intelligence model, and the artificial intelligence model outputting a second access similarity index between the associated access information and the first historical access information; and calculating the first verification pass value of the access party based on the second access similarity index and the third verification pass value.

[0009] In some embodiments, the determining the number of assisting nodes according to the first verification pass value includes: calculating the number of assisting nodes by the following formula: ; In the above formula, is the number of assisting nodes, is the minimum number of assisting nodes; is the first verified passed value, is an average value of all the first verification pass values ​​for digital identity access management of the access party; is the first span duration, is an average value of all the first span durations for performing digital identity access management on the access party.

[0010] In some embodiments, the method of screening a corresponding number of assisting nodes in the blockchain network according to the number of assisting nodes, and having each of the assisting nodes perform identity verification on the first digital identity information and the associated access information to obtain a first access similarity index includes: screening a corresponding number of assisting nodes in the blockchain network according to the number of assisting nodes, wherein each of the assisting nodes is a node with the same business attributes registered and used by the access party; initiating a request for digital identity collaborative verification to each of the assisting nodes, and sending the first digital identity information and the associated access information to each of the assisting nodes; each of the assisting nodes determines a second span duration according to the number of assisting nodes, obtains second historical access information according to the second span duration, performs identity verification based on the first digital identity information, the associated access information and the second historical access information, and obtains a third verification pass value for the number of assisting nodes; calculating an average value of each of the third verification pass values, and determining a maximum value and a minimum value of each of the third verification pass values, and calculating the first access similarity index according to the average value, the maximum value, and the minimum value.

[0011] The present invention also discloses an artificial intelligence-based digital identity access management system, the system comprising a processor and a memory, the processor running a computer code stored in the memory to implement the following steps: receiving the first digital identity information of the access party input, and retrieving the associated access information and the first historical access information related to the access party according to the first digital identity information; using an artificial intelligence model to perform preliminary identity verification on the first digital identity information, the associated access information and the first historical access information to obtain a first verification pass value of the access party; determining the number of assisting nodes according to the first verification pass value, screening a corresponding number of assisting nodes in the blockchain network according to the number of assisting nodes, and having each of the assisting nodes perform identity verification on the first digital identity information and the associated access information respectively to obtain a first access similarity index; calculating a second verification pass value according to the first access similarity index and the first verification pass value, and determining whether to allow the access of the access party according to the second verification pass value.

[0012] The present invention also discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method described in any of the preceding items.

[0013] The present invention also discloses a computer storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement any of the above methods.

[0014] The present invention also discloses a computer program product. When the computer program product is run on a terminal, the terminal implements any of the above methods when executing the computer program product.

[0015] The beneficial effects of the present invention are as follows: the scheme of the present invention simultaneously authenticates the access party based on the digital identity information and associated access information of the access party, and also performs online auxiliary verification of the identity information based on the blockchain network, thereby improving the security of digital identity access management. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 It is a flow chart of a digital identity access management method based on artificial intelligence disclosed in an embodiment of the present invention.

[0018] Figure 2 It is a structural diagram of an artificial intelligence-based digital identity access management system disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The following is a description of the implementation of the present application by specific specific embodiments. People familiar with the technology can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0020] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0021] The existing digital identity access management is based on the local identity database to match and verify the identity information of the access party. If the match verification is passed, that is, there is a template identity information matching the identity information of the access party in the local identity database, the access party is allowed to access the corresponding system. The above existing digital identity access management method only matches and verifies the identity information of the access party, lacks synchronous analysis of other additional information, resulting in a large security defect in digital identity access management, which cannot meet actual needs.

[0022] Regarding the security defects of existing technologies, such as Figure 1 As shown, an embodiment of the present invention discloses an artificial intelligence-based digital identity access management method, the method comprising the following steps: receiving the first digital identity information of the access party input, and retrieving the associated access information and the first historical access information related to the access party according to the first digital identity information; using an artificial intelligence model to perform preliminary identity verification on the first digital identity information, the associated access information and the first historical access information to obtain a first verification pass value of the access party; determining the number of assisting nodes according to the first verification pass value, screening a corresponding number of assisting nodes in the blockchain network according to the number of assisting nodes, and having each of the assisting nodes perform identity verification on the first digital identity information and the associated access information respectively to obtain a first access similarity index; calculating a second verification pass value according to the first access similarity index and the first verification pass value, and determining whether to allow access to the access party according to the second verification pass value.

[0023] Compared with the existing method of access management based only on the identity information of the access party, the present invention also performs auxiliary verification based on the associated access information of the access party, and also performs online verification of identity information based on the blockchain network, thereby improving the security of digital identity access management. Specifically as follows: First, receive the first digital identity information input by the access party, the first digital identity information is, for example, an account password, an identity sequence code stored in a dedicated identity device, physiological identity information, etc.; retrieve the associated access information and the first historical access information of the access party according to the first digital identity information, both of which include one or more access information of the access terminal ID, access IP address, access time, and access geographic coordinates. Use an artificial intelligence model to perform preliminary identity verification on the first digital identity information, the associated access information, and the first historical access information to obtain the first verification pass value of the access party. The first verification pass value is used to represent the score value of the first digital identity information being verified as legal. The higher the score, the higher the legitimacy, and vice versa.

[0024] At the same time, the number of assisting nodes is determined based on the first verification pass value obtained above, and a corresponding number of assisting nodes are screened in the blockchain network based on the number of assisting nodes. These assisting nodes are used to perform online verification of the identity of the access party based on the first digital identity information and the associated access information, thereby obtaining a first access similarity index.

[0025] Finally, a second verification pass value is calculated based on the first access similarity index and the first verification pass value, and then it is determined based on the second verification pass value whether the first digital identity information of the access party has passed the verification. If the second verification pass value is higher than the threshold, it is decided to allow the access of the access party, otherwise it is decided not to allow the access of the access party.

[0026] Therefore, the solution of the present invention simultaneously authenticates the access party based on the digital identity information and associated access information of the access party, and also performs online auxiliary verification of the identity information based on the blockchain network, thereby improving the security of digital identity access management.

[0027] In some embodiments, retrieving first historical access information involving the access party based on the first digital identity information includes: determining type information of the first digital identity information; wherein the type information includes an account password, an identity sequence code stored in a dedicated identity device, and physiological identity information; determining a first span duration based on the type information, and retrieving first historical access information involving the access party based on the first span duration.

[0028] In an embodiment of the present invention, as described above, the access party can input the first digital identity information into the access management system in a variety of ways. The type information of the first digital identity information can be, for example, a conventional account password, physiological identity information, and the physiological identity information includes but is not limited to fingerprint information, face information, iris information, palm print information, etc.; the type information of the first digital identity information can also be an identity serial code stored in a dedicated identity device. The dedicated identity device is similar to the U shield commonly used in banking systems, which stores the identity serial code of the access party. After the dedicated identity device is plugged into the input terminal, the identity serial code stored inside it can be transmitted to the access management system.

[0029] At the same time, the security of different types of first digital identity information is different. Generally speaking, the security of account passwords, identity sequence codes stored in dedicated identity devices (easy to be stolen and cracked), and physiological identity information (especially multiple physiological identity information collaborative verification) increases in sequence. In this regard, the present invention is configured to determine an appropriate first span duration based on the type information determined above, and retrieve the first historical access information involving the access party based on the first span duration.

[0030] Therefore, the present invention changes the data volume and maximum time span of the acquired first historical access information by dynamically adjusting the first span duration. Obviously, the first historical access information with a larger first span duration will contain more access regularity characteristics of the access party, which is conducive to analyzing and obtaining a more accurate first verification pass value.

[0031] In some embodiments, determining the first span duration based on the type information includes: if the type information is an account password, setting the first span duration to a first value; if the type information is an identity sequence code stored in a dedicated identity device, setting the first span duration to a second value; if the physiological identity information is an account password, setting the first span duration to a third value; wherein the first value is greater than the second value, and the second value is greater than the third value.

[0032] In the embodiment of the present invention, when the security of the type information corresponding to the first digital identity information is lower, it is necessary to use the first historical access information with a larger first span time to assist in the security analysis of the first digital identity information, that is, to use more access regularity features (for example, medium-term and recent) of the access party contained in the first historical access information to analyze its historical access regularity, so as to obtain a more accurate first verification pass value. In contrast, when the security of the type information corresponding to the first digital identity information is higher, it is necessary to use the associated access information with a smaller first span time to assist in the security analysis of the first digital identity information, that is, to use fewer access regularity features (for example, only recent) of the access party contained in the first historical access information to analyze its historical access regularity, so as to maximize the analysis rate while ensuring that the confidence of the first verification pass value obtained by the analysis is sufficient.

[0033] Therefore, the present invention reasonably adjusts the first span time for obtaining the first historical access information according to the type information of the first digital identity information, thereby achieving a relative balance between the confidence of the first verification pass value and the analysis rate.

[0034] It is worth noting that the starting time of the first span duration is the time after receiving the first digital identity information of the access party, that is, the time when the first historical access information is started to be acquired; and the acquisition direction is the historical time direction.

[0035] In some embodiments, the use of an artificial intelligence model to perform preliminary identity verification on the first digital identity information, the associated access information and the first historical access information to obtain a first verification pass value of the access party includes: matching and verifying the first digital identity information with a number of second digital identity information preset in a database, and if there is at least one matching second digital identity information in the matching verification result, calculating a third verification pass value according to a negative correlation relationship based on the number of second digital identity information; inputting the associated access information and the first historical access information of the access party into the artificial intelligence model, and the artificial intelligence model outputting a second access similarity index between the associated access information and the first historical access information; and calculating the first verification pass value of the access party based on the second access similarity index and the third verification pass value.

[0036] In the embodiment of the present invention, the determination of the first verification pass value is divided into the following two parts: the first part: the first digital identity information is matched and verified with a number of second digital identity information preset in the database in a conventional manner. If there is at least one matching second digital identity information in the matching verification result, the third verification pass value is calculated according to the number of second digital identity information according to the negative correlation relationship. Among them, the more the number of second digital identity information obtained by matching verification, the less significant the first digital identity information of the access party is, and at this time, the third verification pass value needs to be set to a lower value; the fewer the number of second digital identity information obtained by matching verification, the more significant the first digital identity information of the access party is, and at this time, the third verification pass value is set to a higher value. In addition, if the number of second digital identity information obtained by matching verification is zero, it means that there is no matching second digital identity information in the database, and at this time, it can be directly concluded that the verification of the first digital identity information has failed.

[0037] Part 2: Use an artificial intelligence model to conduct an in-depth analysis of the associated access information and the first historical access information of the access party, that is, to analyze the similarity between the associated access information and the first historical access information, that is, the second access similarity index. Then use the second access similarity index multiplied by the third verification pass value to calculate the first verification pass value of the access party. Obviously, the larger the second access similarity index, the higher the similarity between the analyzed associated access information and the first historical access information, and correspondingly, the larger the first verification pass value.

[0038] Among them, the artificial intelligence model is a model built based on neural networks or Transformer.

[0039] In some embodiments, the determining the number of assisting nodes according to the first verification pass value includes: calculating the number of assisting nodes by the following formula: ; In the above formula, is the number of assisting nodes, is the minimum number of assisting nodes; is the first verified passed value, is an average value of all the first verification pass values ​​for digital identity access management of the access party; is the first span duration, is an average value of all the first span durations for performing digital identity access management on the access party.

[0040] In the embodiment of the present invention, the number of assisting nodes of the present invention is based on the minimum number of assisting nodes, while taking into account the first verification pass value and the first span duration obtained above. It can be seen from the above formula that the number of assisting nodes is negatively correlated with the first verification pass value and the first span duration (where , It can be regarded as a constant value within the update cycle), that is, the higher the first verification pass value, the higher the credibility of the identity authentication result obtained by the local analysis of the access management system (mainly reflected by the second access similarity index); the longer the first span time is, the higher the credibility of the first verification pass value obtained by referring to more first historical access information. Correspondingly, fewer assisting nodes are required to perform collaborative verification of digital identities; otherwise, more assisting nodes are required to perform collaborative verification of digital identities.

[0041] In some embodiments, the method of screening a corresponding number of assisting nodes in the blockchain network according to the number of assisting nodes, and having each of the assisting nodes perform identity verification on the first digital identity information and the associated access information to obtain a first access similarity index includes: screening a corresponding number of assisting nodes in the blockchain network according to the number of assisting nodes, wherein each of the assisting nodes is a node with the same business attributes registered and used by the access party; initiating a request for digital identity collaborative verification to each of the assisting nodes, and sending the first digital identity information and the associated access information to each of the assisting nodes; each of the assisting nodes determines a second span duration according to the number of assisting nodes, obtains second historical access information according to the second span duration, performs identity verification based on the first digital identity information, the associated access information and the second historical access information, and obtains a third verification pass value for the number of assisting nodes; calculating an average value of each of the third verification pass values, and determining a maximum value and a minimum value of each of the third verification pass values, and calculating the first access similarity index according to the average value, the maximum value, and the minimum value.

[0042] In the embodiment of the present invention, the present invention also sets up an online collaborative verification method, that is, the node registered and used by the access party performs collaborative verification on the first digital identity information of the access party, and then calculates the first access similarity index based on the third verification pass value obtained by each collaborative node. Among them, the node currently performing digital identity verification by the access party is the local node, and other registered and used nodes can be nodes with the same business attributes as the local node. For example, the local node is shopping APP-1, and other registered and used nodes can be shopping APP-2, shopping APP-3, etc.

[0043] After receiving the request for collaborative digital identity verification, each assisting node obtains the second historical access information based on the second span duration, similar to the above, and verifies the first digital identity information of the accessing party based on the first digital identity information, the associated access information and the second historical access information, thereby obtaining the third verification pass value of each assisting node. Finally, the first access similarity index is calculated based on the average, maximum and minimum values ​​of each third verification pass value, the first access similarity index = (average value * adjustment coefficient) / (maximum value - minimum value), wherein the adjustment coefficient can be a dynamic value, which is used to limit the first access similarity index to a preset interval, and the preset interval is, for example, [0.8, 1.2].

[0044] Among them, the second span time for each assisting node to obtain the second historical access information is determined according to the number of assisting nodes, and there is a positive correlation between the two. The reason for this setting is that when the number of assisting nodes determined by the local node is greater, it indicates that the confidence of the preliminary identity verification result determined by the local node is insufficient, and more collaborative nodes are needed for collaborative verification. Therefore, the present invention sets each collaborative node to perform collaborative verification with richer second historical access information to improve the accuracy of collaborative verification; conversely, less second historical access information is used for collaborative verification to reduce the computing power of collaborative verification and improve the rate of collaborative verification.

[0045] It is worth noting that the first access similarity index of the present invention represents the distribution of the third verification pass values ​​of each collaborative node. When the average value is larger, it means that each assisting node generally recognizes that the legitimacy of the first digital identity information is higher. At this time, a larger first access similarity index is used to appropriately increase the aforementioned first verification pass value; conversely, when the average value is smaller, it means that each assisting node generally recognizes that the legitimacy of the first digital identity information is lower. At this time, a smaller first access similarity index is used to appropriately lower the aforementioned first verification pass value, or no adjustment is made (that is, the first access similarity index is 1).

[0046] like Figure 2As shown, an embodiment of the present invention also discloses an artificial intelligence-based digital identity access management system, the system comprising a processor and a memory, the processor running a computer code stored in the memory to implement the following steps: receiving a first digital identity information of an input access party, retrieving associated access information and first historical access information related to the access party according to the first digital identity information; performing preliminary identity verification on the first digital identity information, the associated access information and the first historical access information using an artificial intelligence model to obtain a first verification pass value of the access party; determining the number of assisting nodes according to the first verification pass value, screening a corresponding number of assisting nodes in a blockchain network according to the number of assisting nodes, and having each of the assisting nodes perform identity verification on the first digital identity information and the associated access information respectively to obtain a first access similarity index; calculating a second verification pass value according to the first access similarity index and the first verification pass value, and determining whether to allow access to the access party according to the second verification pass value.

[0047] An embodiment of the present invention further discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, characterized in that: the processor executes the computer program to implement the method described in the above embodiment.

[0048] An embodiment of the present invention further discloses a computer storage medium, wherein the computer storage medium stores a computer program, and is characterized in that: the computer program is executed by a processor to implement the method described in the above embodiment.

[0049] The embodiment of the present invention further discloses a computer program product. When the computer program product is run on a terminal, the terminal implements the method described in the above embodiment.

[0050] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0051] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0052] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0053] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.

Claims

1. A digital identity access management method based on artificial intelligence, characterized in that , the method comprises the following steps: Receive the first digital identity information of the access party input, and retrieve the associated access information and the first historical access information related to the access party according to the first digital identity information, wherein the associated access information and the first historical access information both include one or more of an access terminal ID, an access IP address, an access time, and an access geographic coordinate; Use an artificial intelligence model to perform preliminary identity verification on the first digital identity information, the associated access information, and the first historical access information to obtain a first verification pass value of the access party; Determine the number of assisting nodes according to the first verification pass value, screen and obtain a corresponding number of assisting nodes in the blockchain network according to the number of assisting nodes, and have each of the assisting nodes perform identity verification on the first digital identity information and the associated access information to obtain a first access similarity index; Calculating a second verification pass value according to the first access similarity index and the first verification pass value, and deciding whether to allow access of the access party according to the second verification pass value; Retrieving first historical access information related to the access party according to the first digital identity information includes: Determine the type information of the first digital identity information; wherein the type information includes an account password, an identity sequence code stored in a dedicated identity device, and physiological identity information; Determine a first span duration according to the type information, and retrieve first historical access information related to the access party based on the first span duration; different type information corresponds to different security, and the first span duration is negatively correlated with the security; Determining a first span duration according to the type information includes: If the type information is an account password, the first span duration is set to a first value; if the type information is an identity sequence code stored in a dedicated identity device, the first span duration is set to a second value; if the physiological identity information is an account password, the first span duration is set to a third value; Wherein, the first value is greater than the second value, and the second value is greater than the third value; Using an artificial intelligence model to perform preliminary identity verification on the first digital identity information, the associated access information, and the first historical access information to obtain a first verification pass value of the access party, including: Matching and verifying the first digital identity information with a plurality of second digital identity information preset in a database, and if there is at least one matching second digital identity information in the matching and verification result, calculating a third verification pass value according to the number of the second digital identity information in a negative correlation relationship; Inputting the associated access information of the access party and the first historical access information into the artificial intelligence model, and the artificial intelligence model outputting a second access similarity index between the associated access information and the first historical access information; The first verification pass value of the access party is calculated according to the second access similarity index and the third verification pass value.

2. According to claim 1, a method for digital identity access management based on artificial intelligence is characterized in that: Determining the number of assisting nodes according to the first verification pass value includes: The number of assisting nodes is calculated by the following formula: , in the above formula, is the number of assisting nodes, is the minimum number of assisting nodes; is the first verified passed value, is an average value of all the first verification pass values ​​for digital identity access management of the access party; is the first span duration, is an average value of all the first span durations for performing digital identity access management on the access party.

3. According to claim 2, a method for digital identity access management based on artificial intelligence is characterized in that: A corresponding number of assisting nodes are screened in the blockchain network according to the number of assisting nodes, and each of the assisting nodes performs identity verification on the first digital identity information and the associated access information to obtain a first access similarity index, including: A corresponding number of assisting nodes are screened in the blockchain network according to the number of assisting nodes, wherein each of the assisting nodes is a node with the same service attribute that has been registered and used by the access party; Initiate a request for collaborative digital identity verification to each of the assisting nodes, and send the first digital identity information and the associated access information to each of the assisting nodes; Each of the assisting nodes determines a second span duration according to the number of assisting nodes, obtains second historical access information according to the second span duration, performs identity verification based on the first digital identity information, the associated access information, and the second historical access information, and obtains a third verification pass value for the number of assisting nodes; An average value of each of the third verification pass values ​​is calculated, and a maximum value and a minimum value of each of the third verification pass values ​​are determined, and the first access similarity index is calculated based on the average value, the maximum value, and the minimum value.

4. A digital identity access management system based on artificial intelligence, the system is based on the method according to any one of claims 1 to 3, the system includes a processor and a memory, and is characterized in that: The processor runs the computer code stored in the memory to implement the following steps: Receiving input first digital identity information of an access party, and retrieving associated access information and first historical access information related to the access party according to the first digital identity information; Use an artificial intelligence model to perform preliminary identity verification on the first digital identity information, the associated access information, and the first historical access information to obtain a first verification pass value of the access party; Determine the number of assisting nodes according to the first verification pass value, screen and obtain a corresponding number of assisting nodes in the blockchain network according to the number of assisting nodes, and have each of the assisting nodes perform identity verification on the first digital identity information and the associated access information to obtain a first access similarity index; A second verification pass value is calculated based on the first access similarity index for the first verification pass value, and a decision is made based on the second verification pass value as to whether to allow access to the accessing party.

5. An electronic device comprising: At least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method according to any one of claims 1 to 3.

6. A computer storage medium storing a computer program, characterized in that: The computer program is executed by a processor to implement the method according to any one of claims 1 to 3.

7. A computer program product comprising a computer program stored on a non-transitory computer readable medium, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 3 is implemented.

Images