A memory behavior confrontation interaction identity verification method and device based on a meta universe

Abstract

This invention discloses a memory-based behavioral adversarial interactive identity verification method and apparatus based on a metaverse. The method involves: acquiring first behavioral information from user feedback based on received interactive information during the interaction process; determining a difficulty weight index for each interactive message received by the user in historical interactions and its historical average response time; constructing a memory tree for each user based on the difficulty weight index; building an adversarial model; obtaining second behavioral information through the adversarial model's feedback of interactive information; performing conditional loop-based adversarial verification based on the first and second behavioral information to obtain a verification result; determining the order of interactive information by combining the memory tree and the previous verification result during the adversarial verification process; obtaining a comprehensive verification score based on all verification results and the difficulty weight index; and determining the user's identity verification result based on the comprehensive verification score, thus making the identity verification result more accurate and objective.

Description

Technical Field

[0001] This invention relates to the field of identity verification, and more specifically to a memory behavior-based adversarial interactive identity verification method and apparatus based on the metaverse. Background Technology

[0002] The metaverse is a digital living space constructed by humans using digital technology, possessing a new social system. Humans can enter a computer-simulated virtual three-dimensional "reality" through devices and terminals. Everything in the real world is digitally replicated, and people can use digital avatars to do anything in the virtual world that happens in real life. Actions in the virtual world can also affect the real world. However, verifying whether the digital identity in the virtual world is a forged or genuine identity increases the difficulty of identity verification during the interaction between the virtual and real worlds.

[0003] Traditional identity authentication typically involves setting questions during initial registration. Users, eager to complete registration quickly, are prone to providing arbitrary answers. Question templates are also limited, and users easily forget their answers. Furthermore, verification relies on randomness and lacks control over difficulty. In addition, in a more virtualized metaverse, the forgery potential of existing biometric identification methods such as facial recognition, fingerprint scanning, and iris scanning is increasing.

[0004] The patent with announcement number CN108958573B, entitled "Identity Authentication Method and Device Based on Virtual Reality Scenes," uses user-selected 3D interactive options as user-input authentication information. This method relies on a VR terminal and is limited to displacement data during 3D interaction, making it unsuitable for fixed scenarios. The patent with publication number CN106022030A, entitled "Identity Authentication System and Method Based on User Habitual Behavioral Characteristics," requires the collection and analysis of raw user behavior data samples from different dimensions using various sensors and applications built into the mobile terminal. All behavioral habits also depend on these hardware devices, presenting significant limitations. Summary of the Invention

[0005] In view of the aforementioned technical problems, the purpose of the embodiments of this application is to propose a method and apparatus for memory behavior adversarial interactive authentication based on the metaverse, so as to solve the technical problems mentioned in the background section above.

[0006] In a first aspect, the present invention provides a memory behavior-based adversarial interactive authentication method based on the metaverse, comprising the following steps:

[0007] S1, Obtain the first behavioral information fed back by the user based on the received interactive information during the interaction process;

[0008] S2, determine the difficulty weight index of each interaction information received by the user in the historical interaction process and its historical average response time, and build a memory tree for each user based on the difficulty weight index;

[0009] S3, construct an adversarial model, obtain the second behavioral information by feeding back the interactive information through the adversarial model. The first and second behavioral information include the feedback results and response times of the user and the adversarial model to the interactive information, respectively. Perform adversarial verification based on conditional loops based on the first and second behavioral information to obtain the verification result. During the adversarial verification process, combine the memory tree and the previous verification result to determine the order of the interactive information.

[0010] S4 calculates the overall verification score based on all verification results and the difficulty weight index, and determines the user's identity verification result based on the overall verification score.

[0011] Preferably, step S2 specifically includes:

[0012] The difficulty weight index of each interactive message is determined based on the type of interactive information, feedback method, and historical average response time during the historical interaction process.

[0013] Based on the chronological order of interactive information received by the user during historical interactions and their corresponding difficulty weights, a binary tree-based memory tree is constructed according to the following requirements:

[0014] ω1<ω0<ω2;

[0015] The memory tree includes a parent node and its first child node to the left and its second child node to the right; ω1 is the difficulty weight index of the first child node, ω0 is the difficulty weight index of the parent node, and ω2 is the difficulty weight index of the second child node.

[0016] The interactive information and its corresponding first-line information are stored in the corresponding nodes of the binary tree.

[0017] Preferably, step S3 involves constructing an adversarial model, specifically including:

[0018] A database is constructed by acquiring historical behavioral information of all users' responses to each interactive message, and statistical analysis is performed based on the database to obtain the adversarial module.

[0019] Preferably, in step S3, an adversarial verification based on a conditional loop is performed according to the first and second line information to obtain the verification result, specifically including:

[0020] S31, match the feedback results in the first line information and the second line information with the correct results respectively to obtain the first matching result and the second matching result;

[0021] S32, determine the passability result of the interaction information based on the first matching result and the second matching result. If the passability result is passable, use the interaction information stored in the second child node of the user's memory tree as the interaction information for the next verification. If the passability result is failable, use the interaction information stored in the first child node of the user's memory tree as the interaction information for the next verification.

[0022] S33. Repeat steps S31-32 until the set number of loops is reached, then exit the loop and record all verification results. The number of loops is determined according to the level of the memory tree.

[0023] Preferably, the passability result determination in step S32 specifically includes:

[0024] If the first matching result is a successful match and the second matching result is a successful match, or if the first matching result is a successful match and the second matching result is a failed match, then the pass result is pass;

[0025] If the first matching result is a failed match and the second matching result is a successful match, or if the first matching result is a failed match and the second matching result is a successful match, then the pass / fail result is failed.

[0026] Preferably, step S4 specifically includes:

[0027] The historical average response time, historical average positive feedback response time, and pass rate of each interactive message are statistically analyzed. The historical average positive feedback response time is the average response time when the feedback result is successfully matched with the correct result in the historical behavioral information. The pass rate is the percentage of feedback results that are successfully matched with the correct result among all feedback results.

[0028] S41, the difficulty coefficient weight is calculated based on the historical average response time, pass rate, and set timeout time:

[0029]

[0030] in, The difficulty coefficient is represented by the weight, x0 is the initial weight, and a, b, and c are all constants. The historical average response time S represents the timeout period, and S represents the pass rate.

[0031] S42, the adversarial weights are calculated based on the historical average response time and the historical positive feedback average response time:

[0032]

[0033] in, To counteract the weighting, e is the natural logarithm, and T s The historical average response time for positive feedback;

[0034] S43, the overall verification score is determined based on the difficulty coefficient weight, adversarial weight, first matching result, and second matching result:

[0035]

[0036] Among them, Score A This represents the user's overall verification score in this round of the cycle, where a0 is the score corresponding to the first matching result of the user's interaction information at the beginning of the cycle. i and b i , i and n are the scores corresponding to the first and second matching results in each verification process in the loop, respectively, i is the loop index, and n is the loop number.

[0037] S44. Compare the overall verification score with a preset threshold. If the overall verification score is greater than the preset threshold, the identity verification result is successful; if the overall verification score is less than the preset threshold, the identity verification result is unsuccessful.

[0038] Preferably, in step S1, the first line of information is transmitted using symmetric encryption.

[0039] Secondly, the present invention provides a memory behavior adversarial interactive identity verification device based on the metaverse, comprising:

[0040] The data acquisition module is configured to acquire the first behavioral information fed back by the user based on the received interactive information during the interaction process;

[0041] The memory tree construction module is configured to determine the difficulty weight index of each interaction information received by the user in the historical interaction process and its historical average response time, and to construct a memory tree for each user based on the difficulty weight index.

[0042] The adversarial verification module is configured to build an adversarial model, obtain second behavioral information by feeding back interactive information through the adversarial model, and the first and second behavioral information include the feedback results and response times of the user and the adversarial model to the interactive information, respectively. Based on the first and second behavioral information, adversarial verification based on conditional loop is performed to obtain the verification result. During the adversarial verification process, the order of interactive information is determined by combining the memory tree and the previous verification result.

[0043] The comprehensive analysis module is configured to calculate a comprehensive verification score based on all verification results and a difficulty weight index, and then determine the user's identity verification result based on the comprehensive verification score.

[0044] Thirdly, the present invention provides an electronic device including one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any implementation of the first aspect.

[0045] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method as described in any of the implementations of the first aspect.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] (1) By constructing a memory tree based on user history behavior, this invention not only meets the needs of the verification process, but also leverages the efficient retrieval performance of the tree storage structure. Furthermore, it can characterize the identity projected into the metaverse in a more scientific way during the interaction process, making subsequent identity verification more accurate.

[0048] (2) This invention not only effectively combines the memory tree with the adversarial verification process, but also introduces an adversarial model to assist in judging the pass rate in the verification process. It can comprehensively and objectively evaluate the interactive information accurately, making the verification process more reasonable and more in line with the real situation of memory behavior.

[0049] (3) The present invention can perform statistical analysis on the verification results obtained by adversarial verification, and calculate the comprehensive verification score by combining the difficulty weight coefficient and number of interactive information, so as to obtain the identity verification result more reasonably and accurately. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 This is an exemplary device architecture diagram in which an embodiment of this application can be applied;

[0052] Figure 2 This is a flowchart illustrating the memory behavior adversarial interactive authentication method based on metaverse, as an embodiment of this application.

[0053] Figure 3 A schematic diagram of a memory tree for an embodiment of the metaverse-based memory behavior adversarial interactive authentication method of this application;

[0054] Figure 4This is a schematic diagram of the adversarial verification process of the metaverse-based memory behavior adversarial interaction authentication method according to an embodiment of this application;

[0055] Figure 5 This is a schematic diagram of a metaverse-based memory behavior adversarial interactive authentication device according to an embodiment of this application;

[0056] Figure 6 This is a schematic diagram of the structure of a computer device suitable for implementing the electronic device of the present application. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0058] Figure 1 An exemplary device architecture 100 is shown, to which the metaverse-based memory behavior adversarial interactive authentication method or the metaverse-based memory behavior adversarial interactive authentication device of the present application embodiments can be applied.

[0059] like Figure 1 As shown, the device architecture 100 may include terminal devices 101, 102, and 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, and 103 and the server 105. The network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0060] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various applications, such as data processing applications and file processing applications, can be installed on terminal devices 101, 102, and 103.

[0061] Terminal devices 101, 102, and 103 can be either hardware or software. When terminal devices 101, 102, and 103 are hardware, they can be various electronic devices, including but not limited to smartphones, tablets, laptops, and desktop computers. When terminal devices 101, 102, and 103 are software, they can be installed in the electronic devices listed above. They can be implemented as multiple software programs or software modules (e.g., software programs or software modules used to provide distributed services) or as a single software program or software module. No specific limitations are imposed here.

[0062] Server 105 can be a server that provides various services, such as a background data processing server that processes files or data uploaded by terminal devices 101, 102, and 103. The background data processing server can process the acquired files or data and generate processing results.

[0063] It should be noted that the memory behavior adversarial interactive authentication method based on metaverse provided in this application embodiment can be executed by server 105 or by terminal devices 101, 102, and 103. Correspondingly, the memory behavior adversarial interactive authentication device based on metaverse can be set in server 105 or in terminal devices 101, 102, and 103.

[0064] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Any number of terminal devices, networks, and servers can be included depending on implementation needs. If the data being processed does not need to be retrieved remotely, the above architecture may not include a network, requiring only servers or terminal devices.

[0065] Figure 2 The present application illustrates an embodiment of a memory behavior-based adversarial interactive authentication method, comprising the following steps:

[0066] S1, obtain the first behavioral information of the user based on the received interactive information during the interaction process.

[0067] In a specific embodiment,

[0068] Specifically, interactive information can be designed as question-and-answer questions based on the actual scenario. The first behavioral information includes the user's feedback and response time to the interactive information, which can be proposed in conjunction with the operation of the metaverse platform, forming an interactive process with the user. The user's reaction to the interactive information during this process constitutes the first behavioral information. For example, in an NTF scenario, users can be asked to answer simple questions after logging in periodically under the pretext of "security risks," or interactive questions can be designed based on the product when browsing products of interest. For example, in an immersive metaverse platform (including games, tourism, exhibitions, etc.), game users may spend too much time in the virtual world; under the pretext of relaxation, they can be asked to interact and relax every two hours. Tourism and exhibitions can involve evaluation questions and interactions. When collecting users' first behavioral information, two-factor authentication will be enabled for user terminal information transmission to ensure data security. In one embodiment, symmetric encryption can be used to transmit the first behavioral information.

[0069] The interactive message should meet as many of the following five requirements as possible:

[0070] 1) Open-ended questions;

[0071] 2) It can reflect memory behavior;

[0072] 3) It must be unique, able to portray and highlight a person's characteristics;

[0073] 4) Highly interactive and easy to answer;

[0074] 5) Try to avoid involving privacy to prevent arousing defensiveness.

[0075] The Q&A system needs to be dynamically updated and supplemented in stages. Furthermore, the format and content of the Q&A questions should be adjusted based on historical statistical analysis results collected after operation, with the adjustment goal being to better meet the above five requirements. The types of Q&A questions include preference questions, evaluative questions, and descriptive questions. Feedback methods for the first behavioral information include text input, selection input, or limited input. When a user answers a Q&A question, the time taken to respond to that question is calculated, the response time is obtained, and the answer result is recorded. Therefore, the first behavioral information of user feedback during the interaction process can be collected.

[0076] S2, determine the difficulty weight index of each interaction message received by the user in the historical interaction process and its historical average response time, and build a memory tree for each user based on the difficulty weight index.

[0077] In a specific embodiment, step S2 specifically includes:

[0078] The difficulty weight index of each interactive message is determined based on the type of interactive information, feedback method, and historical average response time during the historical interaction process.

[0079] Based on the chronological order of interactive information received by the user during historical interactions and their corresponding difficulty weights, a binary tree-based memory tree is constructed according to the following requirements:

[0080] ω1<ω0<ω2;

[0081] The memory tree includes a parent node and its first child node to the left and its second child node to the right; ω1 is the difficulty weight index of the first child node, ω0 is the difficulty weight index of the parent node, and ω2 is the difficulty weight index of the second child node.

[0082] Each interaction and its corresponding first action are stored in the corresponding node of the binary tree.

[0083] Specifically, based on the principles of memory characteristics: the shorter the time a user takes to answer a question, the simpler the question, and vice versa. Combining the characteristics of the interactive information itself, an initial weight x0 is defined. During the interaction, the response time is combined with the type of question and the feedback method of the first line of information to calculate the user's difficulty weight index for that question. To better avoid network latency interference, a user terminal (client) time-counting strategy is adopted.

[0084] refer to Figure 3 The memory tree is designed as a binary tree of user history behavior, helping users organize historical behavioral events according to their difficulty. Based on the conclusions and difficulty weights of user-reported questions and answers, the ordered user binary tree is continuously built or updated. Each user ID corresponds to a tree, where the difficulty weight of the second child node is greater than that of its parent node, and the difficulty weight of the first child node is less than that of its parent node. This tree structure allows the system to determine whether to choose an interaction with a higher or lower difficulty weight during adversarial verification.

[0085] S3. Construct an adversarial model. The second behavioral information is obtained by the feedback of the interactive information through the adversarial model. The first and second behavioral information include the feedback results and response times of the user and the adversarial model to the interactive information, respectively. Based on the first and second behavioral information, perform adversarial verification based on conditional loop to obtain the verification result. During the adversarial verification process, the order of the interactive information is determined by combining the memory tree and the previous verification result.

[0086] In a specific embodiment, step S3, which involves constructing an adversarial model, specifically includes:

[0087] A database is constructed by acquiring historical behavioral information of all users' responses to each interactive message, and statistical analysis is performed based on the database to obtain the adversarial module.

[0088] In a specific embodiment, step S3 involves performing an adversarial verification based on a conditional loop according to the first and second line information to obtain the verification result, specifically including:

[0089] S31, match the feedback results in the first line information and the second line information with the correct results respectively to obtain the first matching result and the second matching result;

[0090] S32, determine the passability result of the interaction information based on the first matching result and the second matching result. If the passability result is passable, use the interaction information stored in the second child node of the user's memory tree as the interaction information for the next verification. If the passability result is failable, use the interaction information stored in the first child node of the user's memory tree as the interaction information for the next verification.

[0091] S33. Repeat steps S31-32 until the set number of loops is reached, then exit the loop and record all verification results. The number of loops is determined according to the level of the memory tree.

[0092] In a specific embodiment, the passability result determination in step S32 specifically includes:

[0093] If the first matching result is a successful match and the second matching result is a successful match, or if the first matching result is a successful match and the second matching result is a failed match, then the pass result is pass;

[0094] If the first matching result is a failed match and the second matching result is a successful match, or if the first matching result is a failed match and the second matching result is a successful match, then the pass / fail result is failed.

[0095] Specifically, the adversarial model uses big data analysis of the first behavioral information reported by other users regarding similar issues to obtain second behavioral information, which serves as an aid to avoid interactive information that does not reflect memory characteristics. In other embodiments, machine learning techniques can also be used to train the adversarial model, for example, training the BERT model. By combining the second behavioral information reported by the adversarial model with the first behavioral information reported by the user, the pass / fail result is finally determined and classified. If the user's first behavioral information response to the interactive information is a_answer, the adversarial model statistically analyzes the feedback results of all other first behavioral information to obtain the second behavioral information response b_answer. If both a_answer and b_answer are matched, it indicates that a_answer may not be based on actual memory to some extent. If both a_answer and b_answer are not matched, it indicates that the interactive information may be somewhat complex or inapplicable, and it cannot be completely determined that the user's first behavioral information represents the behavior of the original identity. Therefore, by combining the second behavioral information obtained by the adversarial model with the user's first behavioral information, the user's identity can be verified more accurately.

[0096] For details, please refer to Figure 4The adversarial verification process employs a conditional loop. During implementation, the user is guided to recall memories by being presented with the first verification question, corresponding to a parent node in the memory tree. After the user answers the first verification question, the loop begins. Within the loop, the user is guided to answer questions based on their previous interactions and the associated binary memory tree information and verification rules. Specifically, the pass / fail result is determined by comparing the user's feedback to each verification question with the adversarial model's feedback. If the pass / fail result is successful, the interaction information of the second child node below that parent node in the memory tree becomes the next verification question; if the pass / fail result is unsuccessful, the interaction information of the first child node below that parent node becomes the next verification question. The pass / fail result for the next verification question is then assessed. The number of loop iterations within the loop can be designed based on the hierarchy of the memory tree. The loop exit mechanism is set to a number of iterations less than or equal to the hierarchy of the memory tree, and then exits the loop according to the exit mechanism. After exiting, a statistical analysis is performed based on the overall pass / fail results.

[0097] Specifically, when judging the first or second matching result, fuzzy matching can be used simply, or machine learning or a fusion of machine learning models can be used for judgment.

[0098] S4 calculates the overall verification score based on all verification results and the difficulty weight index, and determines the user's identity verification result based on the overall verification score.

[0099] In a specific embodiment, step S4 specifically includes:

[0100] The historical average response time, historical average positive feedback response time, and pass rate of each interactive message are statistically analyzed. The historical average positive feedback response time is the average response time when the feedback result is successfully matched with the correct result in the historical behavioral information. The pass rate is the percentage of feedback results that are successfully matched with the correct result among all feedback results.

[0101] S41, the difficulty coefficient weight is calculated based on the historical average response time, pass rate, and set timeout time:

[0102]

[0103] in, The difficulty coefficient is represented by the weight, x0 is the initial weight, and a, b, and c are all constants. The historical average response time S represents the timeout period, and S represents the pass rate.

[0104] S42, the adversarial weights are calculated based on the historical average response time and the historical positive feedback average response time:

[0105]

[0106] in, To counteract the weighting, e is the natural logarithm, and T s The historical average response time for positive feedback;

[0107] S43, the overall verification score is determined based on the difficulty coefficient weight, adversarial weight, first matching result, and second matching result:

[0108]

[0109] Among them, Score A This represents the user's overall verification score in this round of the cycle, where a0 is the score corresponding to the first matching result of the user's interaction information at the beginning of the cycle. i and b i , i and n are the scores corresponding to the first and second matching results in each verification process in the loop, respectively, i is the loop index, and n is the loop number.

[0110] S44. Compare the overall verification score with a preset threshold. If the overall verification score is greater than the preset threshold, the identity verification result is successful; if the overall verification score is less than the preset threshold, the identity verification result is unsuccessful.

[0111] Specifically, in the process of designing interactive messages, initial weights are set, and the historical average response time of each interactive message is periodically calculated. and the initial timeout period Regularly calculate the pass rate for each interactive message and use the formula above to calculate the difficulty coefficient weight. Where a, b, and c are all constants, specifically initialized to 0.5, 0.3, and 0.2, respectively.

[0112] The system calculates a comprehensive verification score for each user during the interaction process by combining the number of interactive messages they respond to, the difficulty level of those messages, and the second behavioral information from the adversarial model. This comprehensive score is then compared to a preset threshold to determine if the user's identity verification has been successful. If the comprehensive verification score is greater than the threshold, the user's identity verification is successful; if the score is less than the threshold, the user's identity verification has failed.

[0113] The scenarios to which the embodiments of this application are applicable include, but are not limited to, immersive metaverse platforms (games, tourism, exhibitions, etc.) or trading platforms for NFT digital collectibles.

[0114] Further reference Figure 5As an implementation of the methods shown in the above figures, this application provides an embodiment of a memory behavior adversarial interactive authentication device based on the metaverse. This device embodiment is similar to... Figure 2 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0115] This application provides a memory behavior adversarial interactive authentication device based on the metaverse, including:

[0116] Data acquisition module 1 is configured to acquire the first behavioral information fed back by the user based on the received interactive information during the interaction process;

[0117] Memory tree construction module 2 is configured to determine the difficulty weight index of each interaction information received by the user in the historical interaction process and its historical average response time, and to construct a memory tree for each user based on the difficulty weight index.

[0118] The adversarial verification module 3 is configured to build an adversarial model, obtain second behavioral information by feeding back interactive information through the adversarial model, and the first and second behavioral information include the feedback results and response times of the user and the adversarial model to the interactive information, respectively. Based on the first and second behavioral information, adversarial verification based on conditional loop is performed to obtain the verification result. During the adversarial verification process, the order of interactive information is determined by combining the memory tree and the previous verification result.

[0119] The comprehensive analysis module 4 is configured to calculate a comprehensive verification score based on all verification results and the difficulty weight index, and determine the user's identity verification result based on the comprehensive verification score.

[0120] The following is for reference. Figure 6 It illustrates an electronic device suitable for implementing embodiments of this application (e.g., Figure 1 The diagram shows the structure of a computer device 600 (a server or terminal device). Figure 6 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0121] like Figure 6As shown, the computer device 600 includes a central processing unit (CPU) 601 and a graphics processing unit (GPU) 602, which can perform various appropriate actions and processes according to programs stored in read-only memory (ROM) 603 or programs loaded from storage section 609 into random access memory (RAM) 604. The RAM 604 also stores various programs and data required for the operation of the device 600. The CPU 601, GPU 602, ROM 603, and RAM 604 are interconnected via a bus 605. An input / output (I / O) interface 606 is also connected to the bus 605.

[0122] The following components are connected to I / O interface 606: an input section 607 including a keyboard, mouse, etc.; an output section 608 including an LCD, speakers, etc.; a storage section 609 including a hard disk, etc.; and a communication section 610 including a network interface card, such as a LAN card or modem. The communication section 610 performs communication processing via a network such as the Internet. A drive 611 may also be connected to I / O interface 606 as needed. A removable medium 612, such as a hard disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 611 as needed so that computer programs read from it can be installed into storage section 609 as needed.

[0123] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 610, and / or installed from removable medium 612. When the computer program is executed by central processing unit (CPU) 601 and graphics processing unit (GPU) 602, the functions defined in the methods of this application are performed.

[0124] It should be noted that the computer-readable medium described in this application can be a computer-readable signal medium, a computer-readable medium, or any combination thereof. A computer-readable medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor device, or any combination thereof. More specific examples of a computer-readable medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution device, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than a computer-readable medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution device, apparatus, or apparatus. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0125] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Python, and C++. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0126] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using dedicated hardware-based means to perform the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0127] The modules described in the embodiments of this application can be implemented in software or hardware. These modules can also be located within a processor.

[0128] In another aspect, this application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: acquire first behavioral information fed back by the user based on received interactive information during the interaction process; determine a difficulty weight index for each interactive information received by the user in historical interactions and its historical average response time; construct a memory tree for each user based on the difficulty weight index; construct an adversarial model, and obtain second behavioral information by feeding back the interactive information through the adversarial model, wherein the first and second behavioral information respectively include the user's and the adversarial model's feedback results and response times on the interactive information; perform conditional loop-based adversarial verification based on the first and second behavioral information to obtain verification results; determine the order of interactive information by combining the memory tree and the previous verification results during the adversarial verification process; calculate a comprehensive verification score based on all verification results and the difficulty weight index; and determine the user's identity verification result based on the comprehensive verification score.

[0129] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A memory-behavior adversarial interactive authentication method based on the metaverse, characterized in that, Includes the following steps: S1, Obtain the first behavioral information fed back by the user based on the received interactive information during the interaction process. The interactive information is a question and answer question. The first behavioral information includes the user's feedback result and response time to the interactive information. S2, determine the difficulty weight index of each interaction message received by the user during historical interactions and its historical average response time, and construct a memory tree for each user based on the difficulty weight index, specifically including: The difficulty weight index of each interactive message is determined based on the type of interactive information, feedback method, and historical average response time during the historical interaction process. Based on the chronological order of the interaction information received by the user during historical interactions and their corresponding difficulty weight indices, the memory tree based on a binary tree is constructed according to the following requirements: ω1<ω0<ω2; The memory tree includes a parent node and its first child node to the left and a second child node to the right below it; ω1 is the difficulty weight index of the first child node, ω0 is the difficulty weight index of the parent node, and ω2 is the difficulty weight index of the second child node. The interaction information and its corresponding first behavior information are stored on the corresponding node in the binary tree; S3, constructing an adversarial model, specifically includes: A database is constructed by acquiring historical behavioral information of all users' responses to each interactive message, and statistical analysis is performed based on the database to obtain the adversarial model; The adversarial model provides feedback on the interaction information to obtain second behavioral information. The first and second behavioral information respectively include the user's and the adversarial model's feedback results and response times to the interaction information. Based on the first and second behavioral information, a conditional loop-based adversarial verification is performed to obtain a verification result, specifically including: S31, the feedback results in the first behavior information and the second behavior information are matched with the correct results respectively to obtain the first matching result and the second matching result; S32, determine the passability result of the interaction information based on the first matching result and the second matching result. If the passability result is passable, use the interaction information stored in the second child node in the user's memory tree as the interaction information for the next verification. If the passability result is failable, use the interaction information stored in the first child node in the user's memory tree as the interaction information for the next verification. S33, Repeat steps S31-32 until the set number of loops is reached, then exit the loop and record all verification results. The number of loops is determined according to the hierarchy of the memory tree. During the adversarial verification process, the order of the interactive information is determined by combining the memory tree and the previous verification result. S4, calculate the overall verification score based on all verification results, and determine the user's identity verification result based on the overall verification score, specifically including: The historical average response time, historical average positive feedback response time, and pass rate of each interactive message are statistically analyzed. The historical average positive feedback response time is the average response time in which the feedback result successfully matches the correct result in the historical behavioral information. The pass rate is the percentage of feedback results that successfully match the correct result among all feedback results. S41, the difficulty coefficient weight is calculated based on the historical average response time, pass rate, and set timeout time: = +b ( )+c S; in, As the difficulty coefficient weight, The initial weights are a, b, and c, which are all constants. The historical average response time is... The timeout period is S, and the pass rate is S. S42, the adversarial weight is calculated based on the historical average response time and the historical positive feedback average response time: = ； in, Let e ​​be the adversarial weight, and let e be the natural logarithm. The historical average response time; S43, determine the comprehensive verification score based on the difficulty coefficient weight, the adversarial weight, the first matching result, and the second matching result: ； in, The overall verification score for the user in this round of the cycle. The score corresponds to the first matching result of the user's interaction information at the beginning of the loop. and Let i and n be the scores corresponding to the first and second matching results in each verification process in the loop, respectively, where i is the loop index and n is the loop number. S44. The overall verification score is compared with a preset threshold. If the overall verification score is greater than the preset threshold, the identity verification result is successful; if the overall verification score is less than the preset threshold, the identity verification result is unsuccessful.

2. The memory behavior adversarial interactive authentication method based on metaverse as described in claim 1, characterized in that, The passability result determination in step S32 specifically includes: If the first matching result is a successful match and the second matching result is a successful match, or if the first matching result is a successful match and the second matching result is a failed match, then the pass result is pass; If the first matching result is a failed match and the second matching result is a successful match, or if the first matching result is a failed match and the second matching result is a failed match, then the pass / fail result is a failure.

3. The memory behavior adversarial interactive authentication method based on metaverse as described in claim 1, characterized in that, In step S1, the first behavioral information is transmitted using symmetric encryption information.

4. A memory behavior adversarial interactive identity verification device based on the metaverse, characterized in that, The memory behavior adversarial interactive authentication method based on any one of claims 1-3 includes: The data acquisition module is configured to acquire the first behavioral information fed back by the user based on the received interactive information during the interaction process; The memory tree construction module is configured to determine the difficulty weight index of each interaction information received by the user in the historical interaction process and its historical average response time, and to construct a memory tree for each user based on the difficulty weight index. The adversarial verification module is configured to construct an adversarial model, and obtain second behavioral information by feeding back the interaction information through the adversarial model. The first behavioral information and the second behavioral information respectively include the feedback results and response times of the user and the adversarial model to the interaction information. Based on the first behavioral information and the second behavioral information, adversarial verification based on conditional loop is performed to obtain a verification result. During the adversarial verification process, the order of the interaction information is determined by combining the memory tree and the previous verification result. The comprehensive analysis module is configured to calculate a comprehensive verification score based on all verification results and a difficulty weight index, and to determine the user's identity verification result based on the comprehensive verification score.

5. An electronic device, comprising: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-3.

Images