An AI-based digital identity consensus method and system

Abstract

The application belongs to the technical field of identity authentication, and provides an AI-based digital identity consensus method and system. The method comprises the following steps: obtaining user behavior characteristics associated with input digital identity information, calling corresponding historical verification information, inputting the user behavior characteristics and the historical verification information into a risk prediction model, and outputting a verification risk prediction value; determining the number of consensus nodes according to the verification risk prediction value, and screening a corresponding number of consensus nodes according to the number of consensus nodes; sending the digital identity information and the user behavior characteristics to each consensus node, receiving digital identity verification results fed back by each consensus node, and generating a verification pass result or a verification fail result of the digital identity information according to each digital identity verification result. The number of nodes participating in the consensus verification of the digital identity is determined through risk analysis, thereby realizing the targeted optimization and adjustment of the consensus strategy of the digital identity, and the best identity consensus effect is obtained.

Description

Technical Field

[0001] This invention relates to the field of identity verification technology, and more specifically, to an AI-based digital identity consensus method and system. Background Technology

[0002] Digital identity consensus refers to the shared understanding and agreement reached in a digital environment regarding the identification, verification, and recognition of the identity of an individual or entity. In the digital world, identity consensus ensures that users, systems, and services can interact with each other with mutual trust and security.

[0003] Current digital identity consensus methods increasingly focus on establishing decentralized and distributed identities, meaning they prioritize the security of the consensus protocol itself. However, these methods lack consideration for the behavioral characteristics of the digital identity owner (the user to be verified), preventing targeted optimization and adjustment of the consensus strategy and hindering the achievement of optimal identity consensus results. Summary of the Invention

[0004] To address this, the present invention provides an AI-based digital identity consensus method, system, electronic device, computer storage medium, and computer program product to solve the aforementioned technical problems.

[0005] This invention discloses an AI-based digital identity consensus method applied to a consensus system. The method includes the following steps: in response to receiving digital identity information input by a user to be verified, acquiring user behavior features associated with the digital identity information; wherein, the user behavior features include a first digital identity input feature and a first motion feature; retrieving historical verification information corresponding to the digital identity information, inputting the user behavior features and the historical verification information into a risk prediction model, and the risk prediction model outputting a verification risk prediction value; wherein, the historical verification information includes a second digital identity input feature and a second motion feature; determining the number of consensus nodes based on the verification risk prediction value, and filtering out a corresponding number of consensus nodes according to the number of consensus nodes; sending the digital identity information and the user behavior features to each of the consensus nodes, and receiving digital identity verification results fed back by each of the consensus nodes, and generating a verification pass result or verification fail result for the digital identity information based on each of the digital identity verification results.

[0006] Optionally, the digital identity information can be input in any of the following ways: First method: The user to be verified connects an external device to the consensus system, and the consensus system reads the digital identity information from the external device; Second method: The user to be verified aligns their physiological characteristics with the collection device of the consensus system, and the collection device extracts identity information from the physiological characteristics and retrieves the digital identity information based on the identity information; Third method: The user to be verified manually inputs the digital identity information into the input device of the consensus system.

[0007] Optionally, acquiring user behavior features associated with the digital identity information includes: determining a first acquisition duration based on the input method of the digital identity information; specifically: setting the first acquisition duration to a first duration when the input method is the first method; setting the first acquisition duration to a second duration when the input method is the second method; and setting the first acquisition duration to a third duration when the input method is the third method; wherein the durations of the first duration, the second duration, and the third duration are determined according to the usage ratio of the corresponding input method; and acquiring the first digital identity input features and the first motion features recorded by the user terminal device within the first acquisition duration before the digital identity information is input.

[0008] Optionally, the first digital identity input feature includes the number of inputs; then retrieving the historical verification information corresponding to the digital identity information includes: determining a second acquisition duration based on the number of inputs, wherein the second acquisition duration is directly proportional to the number of inputs; and retrieving the historical verification information corresponding to the digital identity information within the second acquisition duration prior to the digital identity information being input.

[0009] Optionally, determining the number of consensus nodes based on the predicted verification risk value includes: In the formula, The number of consensus nodes; The initial number of consensus nodes is an empirical value. The verified risk prediction value, The average of historical verification risk prediction values ​​corresponding to the digital identity information of the user to be verified; , These are weighting coefficients, and .

[0010] Optionally, each of the digital identity verification results includes a first verification pass probability; then, generating a verification pass result or verification fail result of the digital identity information based on each of the digital identity verification results includes: obtaining the verification count of the corresponding consensus node, and determining the corresponding weight based on the verification count; wherein the weight is positively correlated with the verification count; calculating a weighted average based on the first verification pass probability of each consensus node and the corresponding weight to obtain a second verification pass probability; if the second verification pass probability is higher than a probability threshold, then generating a verification pass result of the digital identity information; otherwise, generating a verification fail result of the digital identity information.

[0011] This invention also provides an AI-based digital identity consensus system, comprising a first processing module, a second processing module, a filtering module, and a verification processing module. The first processing module is configured to, in response to receiving digital identity information input by a user to be verified, acquire user behavior features associated with the digital identity information; wherein the user behavior features include a first digital identity input feature and a first motion feature. The second processing module is configured to retrieve historical verification information corresponding to the digital identity information, input the user behavior features and the historical verification information into a risk prediction model, and the risk prediction model outputs a verification risk prediction value; wherein the historical verification information includes a second digital identity input feature and a second motion feature. The filtering module is configured to determine the number of consensus nodes based on the verification risk prediction value, and filter out a corresponding number of consensus nodes according to the number of consensus nodes. The verification processing module is configured to send the digital identity information and the user behavior features to each of the consensus nodes, receive digital identity verification results from each of the consensus nodes, and generate a verification pass result or verification fail result for the digital identity information based on each digital identity verification result.

[0012] The present invention also provides 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 computer program, when executed by the processor, implements the method as described in any of the preceding claims.

[0013] The present invention also provides a computer storage medium storing a computer program that can be executed by a processor to implement the method as described in any of the preceding claims.

[0014] The present invention also provides a computer program product comprising a computer program that can be executed by a processor to implement the method as described in any of the preceding claims.

[0015] This invention determines the number of nodes participating in the consensus verification of digital identities by conducting risk analysis on the aforementioned users to be verified, thereby achieving targeted optimization and adjustment of the consensus strategy for digital identities and obtaining the best identity consensus effect. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating an AI-based digital identity consensus method disclosed in an embodiment of the present invention.

[0018] Figure 2 This is a schematic diagram of the structure of an AI-based digital identity consensus system disclosed in an embodiment of the present invention. Detailed Implementation

[0019] The following specific embodiments illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

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

[0021] like Figure 1As shown in the figure, an embodiment of the present invention discloses an AI-based digital identity consensus method applied to a consensus system. The method includes the following steps: in response to receiving digital identity information input by a user to be verified, acquiring user behavior features associated with the digital identity information; wherein, the user behavior features include a first digital identity input feature and a first motion feature; retrieving historical verification information corresponding to the digital identity information, inputting the user behavior features and the historical verification information into a risk prediction model, and the risk prediction model outputting a verification risk prediction value; wherein, the historical verification information includes a second digital identity input feature and a second motion feature; determining the number of consensus nodes based on the verification risk prediction value, and filtering out a corresponding number of consensus nodes according to the number of consensus nodes; sending the digital identity information and the user behavior features to each of the consensus nodes, and receiving digital identity verification results fed back by each of the consensus nodes, and generating a verification pass result or verification fail result for the digital identity information based on each of the digital identity verification results.

[0022] This invention determines the number of nodes participating in the consensus verification of digital identities by performing risk analysis on the aforementioned users to be verified, thereby achieving targeted optimization and adjustment of the consensus strategy for digital identities and obtaining the best identity consensus effect. Specifically, the user to be verified inputs their digital identity information into the consensus system through an input port. The consensus system further acquires user behavior features associated with the digital identity information, including digital identity input features and motion features, and retrieves historical verification information corresponding to the digital identity information, which also includes digital identity input features and motion features. Then, a risk prediction model is used to process the acquired user behavior features and historical verification information to predict the verification risk value corresponding to the current verification of the user to be verified. Based on the verification risk prediction value, the number of consensus nodes participating in the consensus verification of the aforementioned digital identity information is determined. Finally, the digital identity information and user behavior features are sent to each consensus node, which performs identity verification and feeds back the verification results to the consensus system. The consensus system then performs a comprehensive analysis of the digital identity verification results to obtain the final verification pass or fail result.

[0023] The digital identity information entered by the user to be verified can be identity information used for login, transactions, or remote authorization login, and this invention does not specifically limit it.

[0024] Optionally, the digital identity information can be input in any of the following ways: First method: The user to be verified connects the external device to the consensus system, and the consensus system reads the digital identity information from the external device.

[0025] The second method involves the user to be verified aligning their physiological characteristics with the consensus system's data collection device. The data collection device then extracts identity information from the physiological characteristics and retrieves the digital identity information based on the identity information.

[0026] The third method: The user to be verified manually enters the digital identity information into the input device of the consensus system.

[0027] In this embodiment, the user to be verified can input digital identity information into the consensus system through the three methods described above.

[0028] In the first method, digital identity information is pre-stored in a dedicated external device. The user to be verified connects the external device to the consensus system (i.e., plugs it into the port of the consensus system), and the consensus system can directly read the digital identity information from the external device.

[0029] In the second method, the user to be verified aligns their physiological characteristics (such as face, fingerprint, iris, palm print, etc.) with the corresponding collection device of the consensus system. The collection device can extract the corresponding identity information by recognizing the face, fingerprint, iris, palm print, etc. At the same time, the database of the consensus system also stores multiple sets of digital identity information of different users. The digital identity information can be retrieved from the database by comparing the identity information.

[0030] In the third approach, digital identity information is a set of numerical strings, which the user to be verified can manually enter on the input device of the consensus system.

[0031] It should be noted that each application can configure its own consensus system, which can be embedded in the user's terminal device. Thus, the consensus system can realize the input of the digital identity information of the user to be verified based on the terminal device's port, collection device, and input device.

[0032] Optionally, acquiring user behavior features associated with the digital identity information includes: determining a first acquisition duration based on the input method of the digital identity information; specifically: setting the first acquisition duration to a first duration when the input method is the first method; setting the first acquisition duration to a second duration when the input method is the second method; and setting the first acquisition duration to a third duration when the input method is the third method; wherein the durations of the first duration, the second duration, and the third duration are determined according to the usage ratio of the corresponding input method; and acquiring the first digital identity input features and the first motion features recorded by the user terminal device within the first acquisition duration before the digital identity information is input.

[0033] In this embodiment, after the user to be verified inputs digital identity information, it is necessary to acquire the user's behavioral characteristics prior to input for risk analysis. The user behavioral characteristics include a first digital identity input characteristic and a first motion characteristic. The first digital identity input characteristic refers to the characteristic information of the user to be verified during the process of inputting digital identity information, and the first motion characteristic refers to the motion characteristic information of the user's terminal device during the process of inputting digital identity information.

[0034] Meanwhile, the acquired user behavior characteristics should be within a reasonable range, neither too long nor too short. If too long, early user behavior characteristics unrelated to the input of digital identity information may be acquired, easily interfering with risk analysis; if too short, key risk-related behavioral characteristics during the digital identity information input process may be missed. To address this, this invention sets different first acquisition durations based on the input method of the aforementioned digital identity information, namely the first duration, second duration, and third duration mentioned above. Based on this first acquisition duration, personalized analysis of verification risks can be achieved, thereby enabling personalized determination of the number of consensus nodes, and ultimately achieving personalized consensus on the digital identity of a specific user.

[0035] The durations of the first, second, and third input methods are determined based on their respective usage ratios. Specifically, the number of times a user to be verified inputs digital identity information into the consensus system using the first, second, and third methods within the statistical period is counted. For example, if the number of times using the first method is 'a', the number of times using the second method is 'b', and the number of times using the third method is 'c', then the usage ratios of the three methods are a / (a+b+c), b / (a+b+c), and c / (a+b+c). Using the corresponding conversion formulas, the corresponding first duration is 5 seconds, the second duration is 10 seconds, and the third duration is 2 seconds.

[0036] It should be noted that this invention does not specifically limit the form of the conversion formula, but it must ensure that the initial acquisition time and usage ratio are inversely proportional. That is, the lower the usage ratio of a certain input method, the less frequently the user to be verified uses that input method. Due to lower input proficiency, the probability that the input of digital identity information takes longer is higher, and in this case, the acquisition of user behavior characteristics takes longer. Conversely, the higher the usage ratio of a certain input method, the more frequently the user to be verified uses that input method. Due to higher input proficiency, the probability that the input of digital identity information takes shorter is higher, and in this case, the acquisition of user behavior characteristics takes shorter time.

[0037] Optionally, the first digital identity input feature includes the number of inputs; then retrieving the historical verification information corresponding to the digital identity information includes: determining a second acquisition duration based on the number of inputs, wherein the second acquisition duration is directly proportional to the number of inputs; and retrieving the historical verification information corresponding to the digital identity information within the second acquisition duration prior to the digital identity information being input.

[0038] In this embodiment, the extracted first digital identity input feature includes the number of times the user to be verified inputs digital identity information. For example, if the user successfully inputs the information on the first try, the number of inputs is 1; if the user succeeds on the third try, the number of inputs is 3. The number of inputs here refers to the total number of times the user to be verified inputs digital identity information from the start of inputting the information until successfully inputting the digital identity information into the consensus system.

[0039] It should be noted that the above-mentioned number of inputs mainly refers to the number of times physiological features are input in the second method. Specifically, there is a certain failure rate when inputting facial features, fingerprints, iris scans, palm prints, etc., which means that accurate identity information cannot be extracted (e.g., incomplete identity information, mismatch between identity information and pre-stored identity information). In this case, the user to be verified needs to be prompted to re-enter the physiological features until accurate identity information is entered. Then, the digital identity information can be matched based on the identity information. The number of times physiological features are input is the number of inputs mentioned above.

[0040] For the first method, the default number of inputs can be set to 1. For the third method, each "backspace" or "delete" operation during the input process can be considered as one input count. For example, if the digital identity information is "ABCDE", and the user to be verified mistakenly enters "ABCE" for the first time, then deletes "E" through "backspace" or "delete" and re-enters "ABCD", this is counted as one input count. This process continues until "ABCDE" is entered.

[0041] Optionally, determining the number of consensus nodes based on the predicted verification risk value includes: In the formula, The number of consensus nodes; The initial number of consensus nodes is an empirical value. The verified risk prediction value, The average of historical verification risk prediction values ​​corresponding to the digital identity information of the user to be verified; , These are weighting coefficients, and ,For example The values ​​are 0.9, 0.95, 1, etc. The values ​​are 1.2, 1.5, 2, etc.

[0042] In this embodiment, user behavior characteristics include the first digital identity input characteristics (including the number of inputs) and the first motion characteristics of the user to be verified when inputting digital identity information. By comparing and analyzing the first digital identity input characteristics of the current input with multiple second digital identity input characteristics in historical verification information, the degree of deviation between the number of inputs of the current digital identity information and historical patterns can be determined, thereby deriving the corresponding verification risk prediction value. The greater the deviation, the higher the corresponding verification risk prediction value, and vice versa. For example, if historical data shows that the number of inputs of the digital identity information is less than 2, but the number of inputs this time is 4, it is considered abnormal, possibly because someone other than the user to be verified has stolen the digital identity information (e.g., stolen facial information, fingerprint information, etc.). Similarly, by comparing and analyzing the first motion characteristics of the current input with multiple second motion characteristics in historical verification information, the probability that the motion characteristics of the current input digital identity information are abnormal can be determined. For example, if historical data shows that the speed when the digital identity information was input was less than 5 km / h, but the speed when it was input this time was 20 km / h, it is considered abnormal. Of course, in addition to velocity information, the above-mentioned motion characteristics may also include acceleration information, positioning information, etc., and this invention does not make specific limitations on this.

[0043] After the risk prediction model yields the predicted value of the verification risk, substituting it into the above calculation formula will give the number of consensus nodes. In the above formula, the initial number of consensus nodes... This is an empirical value, for example, 3. Based on this, we then consider the impact of the predicted risk value on the initial number of consensus nodes. By making appropriate adjustments, the final number of consensus nodes is obtained. Increasing the number of consensus nodes appropriately improves the accuracy of consensus verification of digital identity information, preventing incorrect input of abnormal digital identity information from being erroneously verified, thereby effectively improving information security.

[0044] It should be noted that the risk prediction model in this invention is an AI-based model, primarily based on neural networks or machine learning models. After its establishment, it is trained and optimized using training data before being applied to the aforementioned technical solution of this invention for analyzing and validating risk predictions. Of course, the risk prediction model can also be implemented based on a more powerful general-purpose model, such as ChatGPT. A model specifically designed for validating risk predictions can be obtained by fine-tuning it using small sample data; further details will not be elaborated upon here.

[0045] Optionally, each of the digital identity verification results includes a first verification pass probability; then, generating a verification pass result or verification fail result of the digital identity information based on each of the digital identity verification results includes: obtaining the verification count of the corresponding consensus node, and determining the corresponding weight based on the verification count; wherein the weight is positively correlated with the verification count; calculating a weighted average based on the first verification pass probability of each consensus node and the corresponding weight to obtain a second verification pass probability; if the second verification pass probability is higher than a probability threshold, then generating a verification pass result of the digital identity information; otherwise, generating a verification fail result of the digital identity information.

[0046] In this embodiment, the consensus node can be a consensus system corresponding to other applications. For example, this consensus system is the consensus system of a shopping app, while the consensus nodes are the consensus systems of social apps, payment apps, etc. These consensus nodes also store the digital identity information of the user being verified, as well as the corresponding historical verification information. The consensus node can evaluate the reasonableness of the user's current verification behavior based on the stored digital identity information and the aforementioned historical verification information, and thus derive the corresponding first verification success probability. For example, if the consensus node analyzes and finds that the user usually inputs their digital identity information twice in a certain input method (including a certain number of failures, such as fingerprint input failures), but the number of inputs for this verification is five, then it determines that the reasonableness of this verification is insufficient, and correspondingly lowers the first verification success probability.

[0047] After receiving the first verification success probabilities from each consensus node, the consensus system needs to calculate a weighted average of these first verification success probabilities to obtain a more accurate second verification success probability. If the second verification success probability is higher than the probability threshold, the verification is deemed successful, and a verification success result for the digital identity information is generated accordingly; otherwise, the verification is deemed unsuccessful, and a verification failure result for the digital identity information is generated accordingly.

[0048] The weighting of the first verification pass probability for each consensus node is determined by the number of times the corresponding consensus node has participated in consensus verification. For example, if a consensus node participates in 3 consensus verifications within the statistical period, its corresponding weighting weight is d; if a consensus node participates in 5 consensus verifications within the statistical period, its corresponding weighting weight is e, where e > d. That is, the consensus node that participates in more consensus verifications has a higher weighting, thereby increasing the confidence of its first verification pass probability.

[0049] like Figure 2As shown, this invention also discloses an AI-based digital identity consensus system, comprising a first processing module, a second processing module, a filtering module, and a verification processing module. The first processing module is used to, in response to receiving digital identity information input by a user to be verified, acquire user behavior features associated with the digital identity information; wherein the user behavior features include a first digital identity input feature and a first motion feature. The second processing module is used to retrieve historical verification information corresponding to the digital identity information, input the user behavior features and the historical verification information into a risk prediction model, and the risk prediction model outputs a verification risk prediction value; wherein the historical verification information includes a second digital identity input feature and a second motion feature. The filtering module is used to determine the number of consensus nodes based on the verification risk prediction value, and filter out a corresponding number of consensus nodes according to the number of consensus nodes. The verification processing module is used to send the digital identity information and the user behavior features to each consensus node, receive digital identity verification results from each consensus node, and generate a verification pass result or verification fail result for the digital identity information based on each digital identity verification result.

[0050] 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 computer program, when executed by the processor, implements the method as described in any of the preceding claims.

[0051] The present invention also discloses a computer storage medium storing a computer program that can be executed by a processor to implement the method as described in any of the preceding claims.

[0052] The present invention also discloses a computer program product comprising a computer program that can be executed by a processor to implement the method as described in any of the preceding claims.

[0053] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0054] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0055] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connections shown or discussed may be indirect coupling or communication connections through some interfaces, apparatuses, or units, or they may be electrical, mechanical, or other forms of connection.

[0056] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of the present invention, depending on actual needs.

[0057] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0058] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0059] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. An AI-based digital identity consensus method, characterized in that: The method includes the following steps: In response to receiving digital identity information input by a user to be verified, acquiring user behavior features associated with the digital identity information; wherein, the user behavior features include a first digital identity input feature and a first motion feature, the first digital identity input feature referring to the feature information of the user to be verified during the process of inputting the digital identity information, and the first motion feature referring to the motion feature information of the user terminal device of the user to be verified during the process of inputting the digital identity information; retrieving historical verification information corresponding to the digital identity information, inputting the user behavior features and the historical verification information into a risk prediction model, and the risk prediction model outputting a verification risk prediction value; wherein, the historical verification information includes a second digital identity input feature and a second motion feature; determining the number of consensus nodes based on the verification risk prediction value, and filtering out a corresponding number of consensus nodes according to the number of consensus nodes; sending the digital identity information and the user behavior features to each of the consensus nodes, and receiving the digital identity verification results fed back by each of the consensus nodes, and generating a verification pass result or verification fail result for the digital identity information based on each of the digital identity verification results; The digital identity information can be input in any of the following ways: First method: The user to be verified connects an external device to the consensus system, and the consensus system reads the digital identity information from the external device; Second method: The user to be verified aligns their physiological characteristics with the consensus system's acquisition device, and the acquisition device extracts identity information from the physiological characteristics and retrieves the digital identity information based on the identity information; Third method: The user to be verified manually inputs the digital identity information into the consensus system's input device. Acquiring user behavior characteristics associated with the digital identity information includes: determining a first acquisition duration based on the input method of the digital identity information; specifically: setting the first acquisition duration to a first duration when the input method is the first method; setting the first acquisition duration to a second duration when the input method is the second method; and setting the first acquisition duration to a third duration when the input method is the third method; wherein the durations of the first duration, the second duration, and the third duration are determined according to the usage ratio of the corresponding input method; and acquiring the first digital identity input characteristics and the first motion characteristics recorded by the user terminal device within the first acquisition duration before the digital identity information is input. The first digital identity input feature includes the number of inputs; then retrieving the historical verification information corresponding to the digital identity information includes: determining a second acquisition duration based on the number of inputs, wherein the second acquisition duration is directly proportional to the number of inputs; retrieving the historical verification information corresponding to the digital identity information within the second acquisition duration prior to the digital identity information being input; Each of the digital identity verification results includes a first verification pass probability; then, generating a verification pass result or verification fail result for the digital identity information based on each of the digital identity verification results includes: obtaining the verification count of the corresponding consensus node, and determining the corresponding weight based on the verification count; wherein the weight is positively correlated with the verification count; calculating a weighted average based on the first verification pass probability and the corresponding weight of each consensus node to obtain a second verification pass probability; if the second verification pass probability is higher than a probability threshold, then generating a verification pass result for the digital identity information; otherwise, generating a verification fail result for the digital identity information.

2. An AI-based digital identity consensus system, wherein the system is based on the method of claim 1, characterized in that: The system includes a first processing module, a second processing module, a filtering module, and a verification processing module. The first processing module is used to, in response to receiving digital identity information input by a user to be verified, acquire user behavior features associated with the digital identity information; wherein the user behavior features include a first digital identity input feature and a first motion feature. The second processing module is used to retrieve historical verification information corresponding to the digital identity information, input the user behavior features and the historical verification information into a risk prediction model, and the risk prediction model outputs a verification risk prediction value; wherein the historical verification information includes a second digital identity input feature and a second motion feature. The filtering module is used to determine the number of consensus nodes based on the verification risk prediction value, and filter out a corresponding number of consensus nodes according to the number of consensus nodes. The verification processing module is used to send the digital identity information and the user behavior features to each of the consensus nodes, receive digital identity verification results from each of the consensus nodes, and generate a verification pass result or verification fail result for the digital identity information based on each digital identity verification result.

3. An electronic device, characterized in that: The electronic device includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the computer program, when executed by the processor, implements the method as claimed in claim 1.

4. A computer storage medium, characterized in that: The computer storage medium stores a computer program that can be executed by a processor to implement the method as described in claim 1.

5. A computer program product, characterized in that: The computer program product includes a computer program that can be executed by a processor to implement the method as described in claim 1.

Images