An authentication method, device, electronic device, and storage medium

Abstract

An embodiment of the present application provides an identity authentication method, device, electronic device, and storage medium, which relate to the field of network security technology. The method includes: obtaining the first historical viewing data of a user; generating a first verification question for the first historical viewing data; and using the first verification question to authenticate the user. By applying the technical solution provided by the embodiment of the present application, human-machine verification and self-verification can be achieved, improving network security.

Description

Technical Field

[0001] This application relates to the field of network security technology, and in particular, to an identity authentication method, apparatus, electronic device, and storage medium. Background Art

[0002] Cybercriminals use automated tools such as cat pools and multi-opening tools to launch large-scale attacks on users in the network. With the wide application of network technology, cybercriminals are becoming more and more common. Therefore, identity authentication has become an important part of network security protection. Currently, identity authentication is mainly human-machine authentication. Specifically, by means of human-machine authentication methods such as sliding, character selection, and graphics and texts, it is distinguished whether the account user is a human or a machine.

[0003] The above identity authentication method can distinguish humans and machines, but it cannot authenticate the account user himself / herself, and it cannot distinguish whether the account user is the user himself / herself. Moreover, for the above identity authentication method, it can be countered by machine learning technology, and the network security is low. Summary of the Invention

[0004] The purpose of the embodiments of this application is to provide an identity authentication method, apparatus, electronic device, and storage medium to achieve human-machine authentication and self-authentication, and improve network security. The specific technical solutions are as follows:

[0005] In the first aspect implemented in this application, an identity authentication method is provided. The method includes:

[0006] Obtain the first historical viewing data of the user;

[0007] Generate a first verification question for the first historical viewing data;

[0008] Use the first verification question to authenticate the user.

[0009] In the second aspect implemented in this application, an identity authentication apparatus is provided. The apparatus includes:

[0010] An obtaining unit, configured to obtain the first historical viewing data of the user;

[0011] A first generating unit, configured to generate a first verification question for the first historical viewing data;

[0012] A verification unit, configured to use the first verification question to authenticate the user.

[0013] In the third aspect implemented in this application, an electronic device is provided, including a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete mutual communication through the communication bus;

[0014] A memory for storing computer programs;

[0015] A processor, which when executing the program stored in the memory, implements the steps of any of the described authentication methods.

[0016] In a fourth aspect of the implementation of this application, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of any of the described authentication methods are implemented.

[0017] In yet another aspect of the implementation of this application, a computer program is further provided. When it runs on a computer, it causes the computer to execute the steps of any of the described authentication methods.

[0018] In the technical solution provided by the embodiments of this application, verification questions are generated based on the user's historical viewing data, and then the user is authenticated using these verification questions. Because the user's viewing behavior is formed based on preferences. Different users have different preferences, so different users have different viewing behaviors. The verification questions generated using historical viewing data have a high degree of uniqueness and a high degree of user customization. Therefore, using the verification questions generated based on historical viewing data can achieve human-machine verification and self-verification, and it is difficult to be countered by means such as machine learning, improving network security. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or in the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art.

[0020] Figure 1a-1c A schematic diagram of an authentication method in the related art;

[0021] Figure 2 The first flowchart of the authentication method provided by the embodiments of this application;

[0022] Figure 3 A schematic diagram of a verification question provided by the embodiments of this application;

[0023] Figure 4 The second flowchart of the authentication method provided by the embodiments of this application;

[0024] Figure 5 A schematic diagram of a knowledge graph provided by the embodiments of this application;

[0025] Figure 6 The third flowchart of the authentication method provided by the embodiments of this application;

[0026] Figure 7The fourth process schematic diagram of the identity authentication method provided by the embodiments of the present application;

[0027] Figure 8 A partial process schematic diagram of the identity authentication method provided by the embodiments of the present application;

[0028] Figure 9 The fifth process schematic diagram of the identity authentication method provided by the embodiments of the present application;

[0029] Figure 10 The sixth process schematic diagram of the identity authentication method provided by the embodiments of the present application;

[0030] Figure 11 The seventh process schematic diagram of the identity authentication method provided by the embodiments of the present application;

[0031] Figure 12 A structural schematic diagram of the identity authentication device provided by the embodiments of the present application;

[0032] Figure 13 A structural schematic diagram of the electronic device provided by the embodiments of the present application. Detailed implementation manners

[0033] Next, the technical solutions in the embodiments of the present application will be described with reference to the accompanying drawings in the embodiments of the present application.

[0034] For ease of understanding, the terms that appear in the embodiments of the present application will be explained below.

[0035] Human-machine verification: It refers to verifying whether the account user is a human or a machine. The essence of human-machine verification is to propose problems that humans can solve but machines can hardly solve to distinguish humans from machines.

[0036] Identity verification: It indicates verifying whether the account user is the user himself / herself. The essence of identity verification is the problems that the user himself / herself can solve but others can hardly solve.

[0037] Currently, identity authentication is mainly through human-machine verification methods such as swiping, character selection, and graphics and texts to distinguish whether the account user is a human or a machine.

[0038] For example, through the Figure 1a shown swiping human-machine verification method for identity authentication. Specifically: If the slider slides along the set route, it is determined that the account user is a human; if the slider does not slide along the set route, it is determined that the account user is a machine.

[0039] For another example, through the Figure 1bPerform identity verification using the character selection human-machine verification method shown below. Specifically: The verification question includes character A, and the alternative answers include the verification answer (i.e., character A) and the interference answer (i.e., character B). If the selected character is the verification answer (i.e., character A), it is determined that the account user is human; if the selected character is the interference answer (i.e., character B), it is determined that the account user is a machine.

[0040] Also, for example, through the Figure 1c graphic human-machine verification method shown below, perform identity verification. Specifically: The verification question includes picture 1 of object a, and the alternative answers include the verification answer (i.e., picture 2 of object a) and the interference answer (i.e., picture 3 of object b). If the selected picture is the verification answer (i.e., picture 2), it is determined that the account user is human; if the selected picture is the interference answer (i.e., picture 3), it is determined that the account user is a machine.

[0041] The above identity verification methods can distinguish between humans and machines, but cannot verify the account user themselves and cannot distinguish whether the account user is the user himself. Moreover, for the above identity verification methods, they can be countered through machine learning techniques, that is, by using machine learning algorithms to learn the verification questions to simulate humans for identity verification, thereby countering the above identity verification methods, causing the electronic device to misidentify a machine as the account user as a human. This results in low network security.

[0042] To achieve human-machine verification and self-verification and improve network security. An embodiment of the present application provides an identity verification method, as shown in Figure 2 below, and the method includes the following steps.

[0043] Step S21, obtain the user's first historical viewing data;

[0044] Step S22, generate a first verification question for the first historical viewing data;

[0045] Step S23, use the first verification question to perform identity verification on the user.

[0046] In the technical solution provided by the embodiment of the present application, verification questions are generated based on the user's historical viewing data, and then the user is verified using these verification questions. Because the user's viewing behavior is formed based on preferences. Different users have different preferences, so different users have different viewing behaviors. The verification questions generated using historical viewing data have a high degree of uniqueness and a high degree of user customization. Therefore, using the verification questions generated based on historical viewing data can achieve human-machine verification and self-verification, and it is difficult to be countered by means such as machine learning, improving network security.

[0047] For ease of understanding, the following description is made with an electronic device as the execution subject, which is not restrictive. The electronic device can be a mobile phone, a tablet computer, a laptop computer, a personal computer, a server, etc.

[0048] Regarding the above step S21, the user refers to the account user. The viewing data is the relevant data of the content watched by the user (for example, the watched content can include but is not limited to videos), such as the script outline of the content watched by the user, the original content of the content watched by the user, the original long video to which the short video watched by the user belongs, etc.

[0049] The first historical viewing data can be one or more viewing data that the user has watched within a preset duration ending at the moment of identity verification. The viewing data can be the data generated or recorded during the user's viewing of movies, TV dramas, short videos, etc.

[0050] When the user needs to be authenticated, the electronic device obtains the user's first historical viewing data.

[0051] In the embodiments of the present application, when the user logs in to the electronic device, the electronic device can periodically execute steps S21 - S23 to authenticate the user.

[0052] In the embodiments of the present application, the electronic device can also execute steps S21 - S23 to authenticate the user when a preset request is obtained. The preset request can be a login request, a payment request, a query request, a sending request, an access request, a search request, an edit request, etc. In other words, the present application has no special restrictions on the triggering process of this authentication process, and has strong universality.

[0053] Taking the login request as an example for illustration. After the electronic device receives the user's login request, it can obtain the user's account information from the login request, and then authenticate the user's account; in the case where the account authentication is successfully passed, steps S21 - S23 are executed to authenticate the user.

[0054] Regarding the above step S22, the verification question can be a multiple-choice question, a true or false question, or other types of questions, which are not limited herein. The verification question can be multimodal. For example, the verification question includes text, pictures, tables, etc. The text can be the name of a character or an actor in a movie or TV drama, and the picture can be a still of a character in a movie or TV drama. Through the multimodal verification question, the difficulty of machine learning verification questions is increased, and the difficulty of cracking the verification question is increased.

[0055] After obtaining the first historical viewing data, the electronic device can analyze the first historical viewing data according to the semantic rules of natural language to generate a verification question for the first historical viewing data, that is, the first verification question.

[0056] For example, the first historical viewing data is the video data of "Reunion: The Sound of Thunder in the Depths of the Sea". For this first historical viewing data, the electronic device generates verification questions for "Reunion: The Sound of Thunder in the Depths of the Sea" as follows Figure 3 shown

[0057] For the same historical viewing data, the electronic device can generate multiple different verification questions. In the embodiments of the present application, the electronic device can generate only one verification question as the first verification question, or can generate multiple verification questions, and randomly select one verification question from the multiple verification questions for the first historical viewing data as the first verification question. There is no limitation on this

[0058] In the embodiments of the present application, for the same historical viewing data, multiple verification questions can be generated. That is, at different times, the verification questions generated based on the same historical viewing data can be different. This increases the diversity of verification questions, further increases the difficulty of learning the verification questions for each viewing data through machine learning and other methods, and improves the difficulty of technical confrontation against the identity verification method through machine learning and other methods, thus improving network security

[0059] For the above step S23, after obtaining the first verification question, the electronic device can output the first verification question. The user inputs the answer to this first verification question. Furthermore, the electronic device completes the identity verification of the user based on the answer input by the user. For example, if the answer input by the user is the correct answer, it is determined that the user is a human and is the user himself / herself; if the answer input by the user is the wrong answer, it is determined that the user is a machine and / or not the user himself / herself

[0060] In the embodiments of the present application, to improve the accuracy of identity verification, the electronic device can obtain a preset number of first historical viewing data, and use these preset number of first historical viewing data to generate corresponding preset number of first verification questions. The electronic device uses the preset number of first verification questions to conduct identity verification on the user. In this case, if the answers input by the user to these preset number of first verification questions are all correct answers, the electronic device determines that the user is a human and is the user himself / herself; otherwise, the electronic device determines that the user is a machine and / or not the user himself / herself

[0061] The preset number can be set according to actual needs. For example, the preset number can be 1, 2, 3, etc

[0062] In the embodiments of the present application, the viewing behavior of a user is a "viewing fingerprint" formed based on preferences. Since there are natural differences in the viewing habits and interested content of each user, the "viewing fingerprint" has a very high uniqueness. Therefore, the uniqueness of the verification questions generated using the "viewing fingerprint" (i.e., the data used to represent the personal viewing preferences of a user determined based on historical viewing data) is also very high, and the degree of user customization is very high. It is very difficult to learn a "viewing fingerprint" with a very high uniqueness through machine learning and other means. Therefore, it is very difficult to technically counter the identity verification method through machine learning and other means, improving network security.

[0063] In addition, the verification questions are generated based on the historical viewing data of the user. Therefore, the verification questions can be answered by a human who has watched the video (i.e., the user himself), while it is difficult for a human who has not watched the video to answer. Using these verification questions, human-machine verification and self-verification can be achieved, further improving network security.

[0064] Furthermore, the identity verification method based on historical viewing data utilizes video understanding technology. Video understanding belongs to the problem of strong artificial intelligence, while the current artificial intelligence technology still remains at the stage of intelligence based on statistical calculations, which is somewhat insufficient for the problem of strong artificial intelligence to which the identity verification method provided in the embodiments of the present application belongs, further increasing the difficulty of countering the identity verification method provided in the embodiments of the present application through machine learning and other means, and further improving network security.

[0065] In the embodiments of the present application, historical viewing data is used to verify the identity of a user. This better fits the business nature of a video company, being novel and interesting. In addition, this identity verification method can also be used as a way to promote, publicize, and display new dramas or advertisements to complete traffic diversion and increase the revenue of the video company.

[0066] Based on Figure 2 the identity verification method shown, the embodiments of the present application also provide an identity verification method, as Figure 4 shown. In this method, step S22 can be refined into step S221.

[0067] Step S221: Generate a first verification question according to at least one object corresponding to the first historical viewing data or at least one association relationship between objects.

[0068] In the technical solution provided by the embodiments of the present application, key information in the first historical viewing data, such as an object or an association relationship between objects, is used to generate a first verification question. In the embodiments of the present application, the information referred to when an electronic device generates a verification question is simplified, the complexity of generating a verification question is simplified, and the generation efficiency of the verification question is improved.

[0069] For the above-mentioned step S221, the objects may include, but are not limited to, the names of viewing data, the role names of characters, the actor names of characters, animal names, object names, event names, building names, and locations, etc. There are corresponding association relationships between different objects.

[0070] For example, the characters included in the viewing data "Journey to the West" are: Sun Wukong, Tang Seng, and Patriarch Bodhi. Sun Wukong, Tang Seng, and Patriarch Bodhi are the role names of the characters. The actor of Sun Wukong is XX, and XX is the actor name of Sun Wukong. Both Sun Wukong and Patriarch Bodhi have the supernatural powers of somersault cloud and seventy-two transformations. Based on the above, the objects in "Journey to the West" can be obtained: Journey to the West, Sun Wukong, Tang Seng, Patriarch Bodhi, XX, somersault cloud, and seventy-two transformations.

[0071] The association relationships between Journey to the West and Sun Wukong, Journey to the West and Tang Seng, and Journey to the West and Patriarch Bodhi are: role relationships, that is, the latter are the roles in the former; the association relationships between Sun Wukong and Tang Seng, and Sun Wukong and Patriarch Bodhi are: master-disciple relationships, that is, the latter are the masters of the former; the association relationship between Sun Wukong and XX is: acting relationship, that is, the latter is the actor of the former; the association relationships between Sun Wukong and somersault cloud, Sun Wukong and seventy-two transformations, Patriarch Bodhi and somersault cloud, and Patriarch Bodhi and seventy-two transformations are: supernatural power relationships, that is, the latter are the supernatural powers that the former can do. Specifically, see Figure 5 .

[0072] The objects associated with the first historical viewing data can be one or more, and the association relationships associated with the first historical viewing data are one or more. These one or more association relationships exist between different objects associated with the first historical viewing data.

[0073] The electronic device generates the first verification question according to at least one object corresponding to the first historical viewing data or at least one association relationship between objects.

[0074] Based on Figure 4 the identity verification method shown, the embodiment of the present application also provides an identity verification method, as Figure 6 shown, in this method, step S221 can be refined into step S2211 and step S2212.

[0075] Step S2211, determine the target answer information from at least one object corresponding to the first historical viewing data or at least one association relationship between objects, and the target answer information is an object or an association relationship.

[0076] In the embodiment of the present application, the electronic device can randomly select one or more objects from at least one object corresponding to the first historical viewing data or at least one association relationship between objects as the target answer information.

[0077] The electronic device may also randomly select one or more association relationships from at least one object corresponding to the first historical viewing data or at least one association relationship between objects as target answer information.

[0078] The specific number of objects or association relationships obtained may be set according to actual requirements. For example, if the first verification question is a multiple-choice question, the target answer information is multiple objects or multiple association relationships; if the second verification question is a multiple-choice question, the target answer information is one object or one association relationship.

[0079] In the embodiments of the present application, in order to meet the requirements of multiple-choice questions, the first historical viewing data may correspond to a first object group and / or a second object group; the first object group includes a first object and a second object, and there is at least one first association relationship between the first object and the second object; the second object group includes: a third object and a second association relationship, and at least one fourth object having a second association relationship with the third object.

[0080] Step S2212: Generate a first verification question for the target answer information according to semantic rules.

[0081] After obtaining the target answer information, the electronic device generates a first verification question according to semantic rules, and the correct answer to the first verification question is the target answer information.

[0082] In the technical solution provided by the embodiments of the present application, the electronic device generates a first verification question according to semantic rules, which can make the generated first verification question conform to the laws of natural language, facilitate the user to understand the first verification question, and thus accurately verify the user's identity.

[0083] In an embodiment of the present application, the electronic device may pre-store a verification question stem lacking a subject. After obtaining the target answer information, the electronic device uses the target answer information as the subject and combines it with the pre-stored verification question stem lacking a subject to obtain the first verification question.

[0084] In the embodiments of the present application, the electronic device only needs to fill the target answer information into the verification question stem to obtain the first verification question, without the need for semantic rule analysis, which improves the generation efficiency of the first verification question and the efficiency of identity verification.

[0085] Based on Figure 4 the identity verification method shown, the embodiments of the present application also provide an identity verification method, as Figure 7 shown, in this method, step S221 may be refined into step S2213 and step S2214.

[0086] Step S2213: Obtain at least one object corresponding to the first historical viewing data or at least one association relationship between objects from the preset knowledge graph.

[0087] In the embodiments of the present application, the preset knowledge graph can be a knowledge graph crawled by the electronic device from the network, or a knowledge graph generated by the electronic device based on the user's historical viewing data, and this is not limited. The preset knowledge graph includes multiple objects corresponding to multiple viewing data, and the edges connecting these multiple objects represent the association relationships between the objects.

[0088] In an alternative embodiment, the electronic device can extract triple information: (object 1, object 2, association relationship) based on the script outline or original content of the viewing data, using relevant technologies in the field of natural language or purely manual methods, etc. Using the objects as nodes in the knowledge graph and the association relationship as the edge connecting the nodes in the knowledge graph, construct the knowledge graph based on the extracted triple information.

[0089] After obtaining the first historical viewing data, the electronic device obtains at least one object corresponding to the first historical viewing data from the preset knowledge graph; or, the electronic device obtains at least one association relationship between the objects corresponding to the first historical viewing data from the preset knowledge graph.

[0090] Step S2214: Generate a first verification question according to the at least one object or at least one association relationship between objects obtained.

[0091] If at least one object corresponding to the first historical viewing data is obtained from the preset knowledge graph, generate a first verification question according to the at least one object obtained; if at least one association relationship between the objects corresponding to the first historical viewing data is obtained from the preset knowledge graph, generate a first verification question according to the at least one association relationship between the objects obtained.

[0092] In the embodiments of the present application, when generating the first verification question, the electronic device directly obtains the object or association relationship from the preset knowledge graph without analyzing the first historical viewing data. Therefore, the time consumed for analyzing the viewing data is saved, and the efficiency of identity verification is improved.

[0093] Based on Figure 4 The identity verification method shown, in addition to the foregoing method, there may also be a situation where at least one object corresponding to the first historical viewing data and at least one association relationship between objects do not exist in the preset knowledge graph. For this situation, the embodiments of the present application also provide an identity verification method, as Figure 8 shown, this method may further include Step S81, Step S82 and Step S83.

[0094] Step S81: If at least one object corresponding to the first historical viewing data and at least one association relationship between the objects are not included in the preset knowledge graph, then at least one object that conforms to the preset object attributes and at least one association relationship between the objects are extracted from the first historical viewing data.

[0095] In the embodiments of the present application, if at least one object corresponding to the first historical viewing data and at least one association relationship between the objects are not included in the preset knowledge graph, then in order to generate verification questions, the electronic device analyzes the first historical viewing data, and extracts at least one object that conforms to the preset object attributes and at least one association relationship between the objects from the first historical viewing data.

[0096] Step S82: Generate a first verification question according to the at least one object or at least one association relationship between the objects extracted.

[0097] For the generation of the first verification question, reference can be made to the above relevant description, and details will not be elaborated here.

[0098] After generating the first verification question, the electronic device can use the first verification question to authenticate the user. For specific details, reference can be made to the relevant description in the above Step S23.

[0099] In the embodiments of the present application, Steps S81 - S82 and Step S2213 are two parallel execution schemes, and there is no sequential execution order.

[0100] Step S83: Update the at least one object and at least one association relationship between the objects extracted to the preset knowledge graph.

[0101] In order to facilitate the subsequent rapid generation of verification questions for the first historical viewing data, the electronic device updates the at least one object and at least one association relationship between the objects extracted to the preset knowledge graph.

[0102] In the embodiments of the present application, Step S83 is a further supplement to the identity verification method. Step S83 can be executed before Step S23, after Step S23, or simultaneously with Step S23, and no limitation is imposed thereon.

[0103] In an embodiment of the present application, when at least one object corresponding to the first historical viewing data and at least one association relationship between the objects are not included in the preset knowledge graph, at least one object that conforms to the preset object attributes and at least one association relationship between the objects are extracted from the first historical viewing data, and the preset knowledge graph is updated. Subsequently, the electronic device can directly generate a verification question based on at least one object corresponding to the first historical viewing data and at least one association relationship between the objects in the preset knowledge graph. That is, the subsequent electronic device does not need to analyze the first historical viewing data to generate a verification question for the first historical viewing data, which improves the generation efficiency of the subsequent verification question, and thus improves the identity verification problem.

[0104] In practical applications, an account can be logged in on multiple terminals. If an account is logged in on multiple terminals, the user's first historical viewing data may include multiple historical viewing sub-data from multiple terminals. In this case, based on Figure 2 the identity verification method shown, an embodiment of the present application further provides an identity verification method, as Figure 9 shown, in this method, step S22 can be refined into step S222 and step S223.

[0105] Step S222, according to the terminal information corresponding to each historical viewing sub-data, determine the target historical viewing sub-data of the current terminal from the multiple historical viewing sub-data.

[0106] Different historical viewing sub-data come from different terminals. The terminal information may include but is not limited to the terminal identifier, IP (Internet Protocol) address, MAC (Media Access Control) address, etc.

[0107] After obtaining the first historical viewing data, the electronic device obtains the terminal information of the terminal corresponding to each historical viewing sub-data, and determines the historical viewing sub-data from the current terminal (i.e., the electronic device) from the multiple historical viewing sub-data, that is, the target historical viewing sub-data.

[0108] Step S223, generate a first verification question for the current terminal according to the target historical viewing sub-data.

[0109] After determining the target historical viewing sub-data, the electronic device generates a first verification question for the current terminal according to at least one object or at least one association relationship between the objects corresponding to the target historical viewing sub-data. For the specific generation method, reference can be made to the above related description, which will not be elaborated here.

[0110] Based on Figure 2The authentication method shown, embodiments of the present application also provide an authentication method. As Figure 10 shown, the method may further include steps S24 - S26.

[0111] Step S24, detect whether there is a second verification problem for the second historical viewing data of the user in the historical record within a preset duration. If so, execute step S25; if not, execute step S21, and after generating the first verification problem for the first historical viewing data, execute step S23 and step S26.

[0112] In embodiments of the present application, the preset duration can be set according to actual needs. For example, the preset duration can be 1 hour, 12 hours, or 24 hours, etc. The historical record records the verification problems for the historical viewing data of the user. That is, within the past time, the verification problems generated when the electronic device authenticates the user are recorded in the historical record.

[0113] If the user needs to be authenticated currently, the electronic device detects whether there is a second verification problem for the second historical viewing data of the user in the historical record within a preset duration. The second historical viewing data can be any historical viewing data that the user has watched, and the second verification problem is the verification problem generated for the second historical viewing data when the user was authenticated in the past. The number of the second historical viewing data can be one or more. Correspondingly, the second verification problem can be one or more.

[0114] If there is a second verification problem for the second historical viewing data of the user, the electronic device executes step S25; if there is no second verification problem for the second historical viewing data of the user, the electronic device executes step S26.

[0115] Step S25, authenticate the user using the second verification problem.

[0116] For the manner of authenticating the user using the second verification problem, reference can be made to the manner of authenticating the user using the first verification problem as described above. It will not be elaborated here again.

[0117] Step S26, record the first verification problem.

[0118] In the case where there is no second verification problem in the historical record, the electronic device records the first verification problem for the first historical viewing data. When the user is authenticated again later, the recorded first verification problem can be understood as the second verification problem, and the electronic device can directly obtain the first verification problem to authenticate the user. In this case, the electronic device needs to skip the process of generating verification problems and directly authenticate the user, improving the efficiency of authentication.

[0119] In one embodiment of the present application, in order to save storage space and improve the timeliness of verification problems, when the recording duration of the first verification problem exceeds a preset duration, the electronic device can clear the first verification problem.

[0120] Taking the verification problem as a multiple-choice question as an example, the identity verification method provided by the embodiments of the present application will be described in detail below.

[0121] Step 1, the electronic device obtains first historical viewing data;

[0122] Step 2, the electronic device determines the verification answer and the question subject from the objects corresponding to the first historical viewing data and the association relationships between the objects, and determines the interfering answers.

[0123] Among them, the verification answer is the correct answer to the verification problem, and the interfering answer is the wrong answer to the verification problem. The question subject is the object or association relationship used to generate the verification problem.

[0124] In the embodiments of the present application, the question subject is an object having a direct and / or indirect association relationship with the verification answer. For example, as Figure 5 shown, when the verification answer is XX, the question subject can be Sun Wukong having a direct association relationship with XX, or Tang Seng having an indirect association relationship with XX.

[0125] Step 3, the electronic device combines the question subject according to semantic rules to generate a first verification problem for the verification answer.

[0126] Still taking Figure 5 as an example for illustration. The verification answer is XX, and the question subjects are Patriarch Bodhi and Tang Seng. According to semantic rules, based on the association relationships between Patriarch Bodhi and Tang Seng and XX respectively, combining Patriarch Bodhi and Tang Seng, the electronic device generates the verification problem: Who is the actor of the disciples of Patriarch Bodhi and Tang Seng?

[0127] In the embodiments of the present application, the electronic device can also expand the question subject to increase the difficulty of the verification questions, so that people who have watched the first historical viewing data can answer them, while people who have not watched the first historical viewing data are difficult to answer, further improving network security.

[0128] Still taking Figure 5 as an example for illustration. The verification answer is the master-disciple relationship between Sun Wukong and Tang Seng, and the question subjects are Sun Wukong and Tang Seng. Expanding Sun Wukong, Patriarch Bodhi and the 72 Transformations are obtained. Then, according to semantic rules, based on the association relationship between Sun Wukong and Tang Seng, and the association relationships between Patriarch Bodhi and the 72 Transformations and Sun Wukong respectively, combining Tang Seng, Patriarch Bodhi and the 72 Transformations, the electronic device generates the verification problem: What is the relationship between Tang Seng and the disciple of Patriarch Bodhi who can perform the 72 Transformations?

[0129] Step 4, the electronic device inputs the first verification question, the verification answer, and the interfering answer.

[0130] If the user selects the verification answer based on the first verification question, the electronic device can determine that the user has passed the identity verification, that is, the user is a human and is the user himself; otherwise, the user has not passed the identity verification, that is, the user is a machine and / or not the user himself.

[0131] In the embodiment of the present application, the electronic device can specifically generate the first verification question in the following two ways.

[0132] The first way is to use an object as the verification answer:

[0133] Step a1, select an object from at least one object corresponding to the first historical viewing data as the verification answer.

[0134] Step a2, determine the question subject from the objects that have an associated relationship with the verification answer.

[0135] In the knowledge graph, the objects that have an associated relationship with the verification answer are manifested as: the objects adjacent to the verification answer.

[0136] Step a3, combine the question subject according to the semantic rules to generate the first verification question for the verification answer.

[0137] Step a4, randomly select an object of the same type as the verification answer as the interfering answer.

[0138] In the embodiment of the present application, the type of the object can be set according to actual needs. For example, the type of the object can be the role of the viewed character, the actor of the character, an animal, an object, an event, a building, and a location, etc.

[0139] Still taking Figure 5 as an example for illustration. The electronic device randomly selects the object "Sun Wukong" as the verification answer, and selects two objects adjacent to "Sun Wukong", namely "Patriarch Bodhi" and "72 Transformations". The associated relationships between these two objects and the verification answer are "master-disciple" and "divine power" respectively. Then, according to the semantic rules, the electronic device can generate the verification question: "Who is the disciple of Patriarch Bodhi and has the divine power of 72 Transformations?". The electronic device randomly selects other objects of the same type as the verification answer as the interfering answer.

[0140] The verification answer "Sun Wukong" and the interfering answer of the corresponding verification question can be either text or stills associated with the character, and this is not limited.

[0141] Many verification questions can be randomly generated in this way.

[0142] The second method is to use the association relationship as the verification answer:

[0143] Step b1: Select an association relationship from at least one association relationship among the objects corresponding to the first historical viewing data as the verification answer.

[0144] Step b2: Use the objects connected by the verification answer as the question subject.

[0145] Step b3: Combine the question subject according to semantic rules to generate the first verification question for the verification answer.

[0146] Step b4: Randomly select other association relationships as the distracting answers.

[0147] Still taking Figure 5 as an example for illustration. The electronic device randomly selects the "master-disciple" association relationship between the two objects "Tang Seng" and "Sun Wukong" as the verification answer, and uses the two objects "Tang Seng" and "Sun Wukong" as the question subject.

[0148] The electronic device can directly combine the question subject according to semantic rules to generate the verification question "What is the relationship between Tang Seng and Sun Wukong?".

[0149] The electronic device can also expand the question subject "Tang Seng" and "Sun Wukong". For example, expand "Sun Wukong" to the two objects adjacent to "Sun Wukong", namely "Puti Laozu" and "Seventy-two Transformations". The electronic device can directly combine the question subject (including the expanded question subject) according to semantic rules to generate the verification question "What is the relationship between Tang Seng and the disciple of Puti Laozu who can perform seventy-two transformations?". The electronic device selects other types of association relationships as the distracting answers.

[0150] Many verification questions can be randomly generated in this way.

[0151] In the embodiments of the present application, as long as the question subject can be described by other objects or association relationships, verification questions can be generated. Here, the uniqueness of the verification answer can be used to generate multiple-choice verification questions or single-choice verification questions.

[0152] For example, taking an object as the verification answer. The verification answer to the verification question "Who is the disciple of Puti Laozu who has the supernatural power of seventy-two transformations?" may not be only "Sun Wukong". It is very likely that Puti Laozu has other disciples who can also perform seventy-two transformations and happen to appear in the distracting answers. In this case, there is a problem if the verification answer is only "Sun Wukong". Taking the association relationship as the verification answer. There may be more than one association relationship between two objects. Therefore, there may be more than one association relationship that conforms to the answer to the verification question described by the two objects.

[0153] Therefore, after generating the verification question, if the verification question is required to be a single-choice question, the interfering answers should avoid selecting the objects or associated relationships that simultaneously satisfy the verification question. Conversely, if the verification question is required to be a multiple-choice question, the objects or associated relationships that meet the conditions are selected and placed in the answer of the verification question.

[0154] Based on the above various embodiments, an embodiment of the present application provides an identity verification method, as Figure 11 shown, including a composition stage and a verification stage.

[0155] Composition stage:

[0156] Step S111, construct a knowledge graph of the viewing data based on the viewing data.

[0157] Step S112, store the knowledge graph.

[0158] Verification stage:

[0159] Step S113, extract the first historical viewing data from the user's historical viewing data,

[0160] Step S114, generate a first verification question for the first historical viewing data based on the knowledge graph.

[0161] Step S115, use the first verification question to authenticate the user.

[0162] The descriptions of the above steps S111 - S115 are relatively simple. For specific details, please refer to the relevant descriptions in the above Figure 2-10 part.

[0163] Corresponding to the above identity verification method, an embodiment of the present application also provides an identity verification device, as Figure 12 shown. The device includes:

[0164] An acquisition unit 121, configured to acquire the first historical viewing data of the user;

[0165] A first generation unit 122, configured to generate a first verification question for the first historical viewing data;

[0166] A verification unit 123, configured to authenticate the user using the first verification question.

[0167] Optionally, the first generation unit 122 may specifically be used for:

[0168] Generate a first verification question according to at least one object corresponding to the first historical viewing data or at least one associated relationship between objects.

[0169] Optionally, the first generation unit 122 may specifically be used for:

[0170] Determine target answer information from at least one object corresponding to the first historical viewing data or at least one association relationship between objects, where the target answer information is an object or an association relationship;

[0171] Generate a first verification question for the target answer information according to semantic rules.

[0172] Optionally, the first historical viewing data corresponds to a first object group and / or a second object group;

[0173] The first object group includes a first object and a second object, and there is at least one first association relationship between the first object and the second object;

[0174] The second object group includes: a third object and a second association relationship, and at least one fourth object having a second association relationship with the third object.

[0175] Optionally, the first generation unit 122 may specifically be used for:

[0176] Obtain at least one object corresponding to the first historical viewing data or at least one association relationship between objects from a preset knowledge graph;

[0177] Generate a first verification question according to the obtained at least one object or at least one association relationship between objects.

[0178] Optionally, the above identity verification device may further include:

[0179] A second generation unit, configured to, if the preset knowledge graph does not include at least one object corresponding to the first historical viewing data and at least one association relationship between objects, extract at least one object that conforms to a preset object attribute and at least one association relationship between objects from the first historical viewing data; generate a first verification question according to the extracted at least one object or at least one association relationship between objects;

[0180] An update unit, configured to update the extracted at least one object and at least one association relationship between objects to the preset knowledge graph.

[0181] Optionally, the first historical viewing data includes multiple historical viewing sub-data from multiple terminals;

[0182] The first generation unit 122 may specifically be used for:

[0183] Determine the target historical viewing sub-data of the current terminal from the multiple historical viewing sub-data according to the terminal information corresponding to each historical viewing sub-data;

[0184] Generate a first verification question for the current terminal according to the target historical viewing sub-data.

[0185] Optionally, the above authentication device may further include:

[0186] A detection unit, configured to detect whether there is a second verification question for the second historical viewing data of the user in the historical record within a preset duration;

[0187] A verification unit, further configured to, if the detection result of the detection unit is yes, use the second verification question to authenticate the user;

[0188] A recording unit, configured to, if the detection result of the detection unit is no, perform the step of obtaining the first historical viewing data of the user, and record the first verification question after generating the first verification question for the first historical viewing data.

[0189] Optionally, the above authentication device may further include:

[0190] A clearing unit, configured to clear the first verification question when the recording duration of the first verification question exceeds the preset duration after recording the first verification question.

[0191] In the technical solution provided by the embodiments of the present application, verification questions are generated according to the historical viewing data of the user, and then the user is authenticated using the verification questions. Because the viewing behavior of the user is formed based on preferences. The preferences of different users are different. Therefore, the viewing behaviors of different users are different. The verification questions generated using the historical viewing data have a very high uniqueness and a very high degree of user customization. Therefore, using the verification questions generated based on the historical viewing data can achieve human-machine verification and self-verification, and it is difficult to be countered by means such as machine learning, improving network security.

[0192] Corresponding to the above authentication method, an embodiment of the present application further provides an electronic device, as Figure 13 shown, including a processor 131, a communication interface 132, a memory 133, and a communication bus 134. Among them, the processor 131, the communication interface 132, and the memory 133 complete mutual communication through the communication bus 134.

[0193] The memory 133 is used to store a computer program;

[0194] The processor 131 is configured to implement the steps of the authentication method described in any of the above method embodiments when executing the program stored in the memory 103.

[0195] The communication bus can be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience in representation, only a thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0196] The communication interface is used for communication between the above-mentioned electronic device and other devices.

[0197] The memory can include a Random Access Memory (RAM), and can also include a non-volatile memory, such as at least one disk memory. Optionally, the memory can also be at least one storage device located far from the aforementioned processor.

[0198] The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0199] Corresponding to the above authentication method, in another embodiment provided by this application, a computer-readable storage medium is also provided. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the authentication method steps described in any of the above method embodiments are implemented.

[0200] Corresponding to the above authentication method, in another embodiment provided by this application, a computer program is also provided. When it runs on a computer, the computer is made to execute the authentication method steps described in any of the above method embodiments.

[0201] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)).

[0202] It should be noted that in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including", or any other variation thereof is intended to cover non-exclusive inclusion, so that a process, method, article, or device including a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article, or device including the element.

[0203] Each embodiment in this specification is described in a related manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of the device, electronic device, storage medium, and computer program, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiments.

[0204] The above are only the preferred embodiments of the present application and are not intended to limit the protection scope of the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application are all included in the protection scope of the present application.

Claims

1. An authentication method, characterized in that, The method includes: Obtaining the first historical viewing data of the user; Generating a first verification question according to at least one object corresponding to the first historical viewing data or at least one association relationship between objects; wherein, the at least one object or at least one association relationship between objects is information in the first historical viewing data and is preset; the first verification question has target answer information as the verification answer, and the target answer information is an object or an association relationship; the generation method of the first verification question includes: selecting an object or an association relationship from at least one object corresponding to the first historical viewing data or at least one association relationship between objects as the verification answer; determining the question subject from the objects having an association relationship with the verification answer, or using the objects connected by the verification answer as the question subject; combining the question subject according to semantic rules to generate a first verification question for the verification answer; Authenticating the identity of the user by using the first verification question.

2. The method according to claim 1, wherein The first historical viewing data corresponds to a first object group and / or a second object group; The first object group includes a first object and a second object, and there is at least one first association relationship between the first object and the second object; The second object group includes: a third object and a second association relationship, and at least one fourth object having the second association relationship with the third object.

3. The method according to claim 1, characterized in that The step of generating the first verification question according to at least one object corresponding to the first historical viewing data or at least one association relationship between objects includes: Obtaining at least one object corresponding to the first historical viewing data or at least one association relationship between objects from a preset knowledge graph; Generating the first verification question according to the at least one object or at least one association relationship obtained.

4. The method according to claim 3, wherein The method further includes: If the preset knowledge graph does not include at least one object corresponding to the first historical viewing data and at least one association relationship between objects, extracting at least one object conforming to the preset object attributes from the first historical viewing data, and at least one association relationship between objects; Generating the first verification question according to the at least one object or at least one association relationship extracted; Updating the at least one object and at least one association relationship extracted to the preset knowledge graph.

5. The method according to claim 1, wherein The first historical viewing data includes multiple historical viewing sub-data from multiple terminals; The step of generating a first verification question for the first historical viewing data includes: Determining the target historical viewing sub-data of the current terminal from the multiple historical viewing sub-data according to the terminal information corresponding to each historical viewing sub-data; Generating a first verification question for the current terminal according to the target historical viewing sub-data.

6. The method according to claim 1, wherein The method further includes: Detecting whether there is a second verification question for the second historical viewing data of the user in the historical records within a preset duration; If so, authenticating the identity of the user by using the second verification question; Otherwise, execute the step of obtaining the first historical viewing data of the user, and after generating the first verification question for the first historical viewing data, record the first verification question.

7. The method according to claim 6, wherein After recording the first verification question, the method further includes: When the recording duration of the first verification question exceeds the preset duration, clear the first verification question.

8. An authentication device, characterized in that, The apparatus includes: An obtaining unit, configured to obtain the first historical viewing data of the user; A first generating unit, configured to generate a first verification question according to at least one object corresponding to the first historical viewing data or at least one association relationship between objects; wherein, the at least one object or at least one association relationship between objects is information in the first historical viewing data and is preset; the first verification question has target answer information as a verification answer, and the target answer information is an object or an association relationship; the generating manner of the first verification question includes: selecting an object or an association relationship from at least one object corresponding to the first historical viewing data or at least one association relationship between objects as the verification answer; determining a question subject from the objects having an association relationship with the verification answer, or using the objects connected by the verification answer as the question subject; and combining the question subject according to semantic rules to generate the first verification question for the verification answer; A verification unit, configured to authenticate the user by using the first verification question.

9. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete mutual communication through the communication bus; The memory is used for storing a computer program; The processor is configured to implement the method steps described in any one of claims 1-7 when executing the program stored on the memory.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the method steps described in any one of claims 1-7 are implemented.

Images