CN117892277A - Login authentication method and device - Google Patents
Login authentication method and device Download PDFInfo
- Publication number
- CN117892277A CN117892277A CN202410103123.1A CN202410103123A CN117892277A CN 117892277 A CN117892277 A CN 117892277A CN 202410103123 A CN202410103123 A CN 202410103123A CN 117892277 A CN117892277 A CN 117892277A
- Authority
- CN
- China
- Prior art keywords
- authentication
- client
- login
- user
- answer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 61
- 230000003993 interaction Effects 0.000 claims abstract description 30
- 238000004590 computer program Methods 0.000 claims description 22
- 238000003860 storage Methods 0.000 claims description 12
- 238000010586 diagram Methods 0.000 description 22
- 238000000605 extraction Methods 0.000 description 19
- 238000012545 processing Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 9
- 238000012795 verification Methods 0.000 description 8
- 239000012634 fragment Substances 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000010276 construction Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 239000000463 material Substances 0.000 description 3
- 230000004927 fusion Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 210000000697 sensory organ Anatomy 0.000 description 2
- 241000282326 Felis catus Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a login authentication method and a login authentication device, which can be used in the financial field or other fields, and the method comprises the following steps: receiving a login authentication request, generating an authentication problem according to a pre-constructed knowledge graph, and sending the authentication problem to the client; receiving authentication answers fed back by the client through a virtual interaction mode corresponding to a user digital person, which is constructed in advance; the authentication answer is generated by the client according to the authentication problem; and generating an authentication result according to the knowledge graph and the authentication answer. The login authentication method and the login authentication device provided by the application realize that the dynamic problem is generated based on the knowledge of the user to perform login authentication under the condition that the user name and the password are not utilized, provide personalized service for the user, improve the safety and privacy of the user login, prevent the problem of forgetting the password and the like, and avoid the risk of being broken by violence when the user name and the password are used for login.
Description
Technical Field
The present application relates to the field of financial technologies, and in particular, to a login authentication method and device.
Background
At present, the on-line access system of the network service is rapidly developed, the diversity and complexity of the on-line access system are also rapidly increased, and higher requirements are provided for the convenience, safety and individuation of the authentication login of the service system. However, in actual service operation, the authentication login mode is mainly a traditional user name password login mode, and the authentication login mode is far away from the requirements of a new generation service system in terms of convenience, security and individuation. Therefore, innovative improvement is carried out on the login authentication mode, and meanwhile, the requirement of diversity is met, so that the login authentication method is an urgent problem to be solved.
Conventional user login authentication methods typically rely on a user name and password, which presents several risks and challenges: firstly, a user needs to memorize a plurality of different user names and passwords among a plurality of traditional user names and password login systems, which increases the burden of the user and increases the possibility of error occurrence, and if the same set of user name passwords is used, the user can easily lose account passwords after a single system account number is leaked, and other systems; secondly, when the user name and the password are used for login, risks such as theft, leakage or violent cracking of the password can exist, so that a user account is maliciously used or tampered, and meanwhile, the problems of weak passwords and weak passwords are frequent; thirdly, the user name and password are used for authentication login, personalized definition of the user cannot be reflected, and therefore user experience is poor.
Disclosure of Invention
Aiming at the problems in the prior art, the embodiment of the application provides a login authentication method and a login authentication device, which can at least partially solve the problems in the prior art.
In a first aspect, the present application provides a login authentication method, including:
receiving a login authentication request, generating an authentication problem according to a pre-constructed knowledge graph, and sending the authentication problem to the client;
receiving authentication answers fed back by the client through a virtual interaction mode corresponding to a user digital person, which is constructed in advance; the authentication answer is generated by the client according to the authentication problem;
and generating an authentication result according to the knowledge graph and the authentication answer.
Further, the step of pre-constructing the knowledge graph includes:
Sending a preset question to a client and receiving answer information fed back by the client according to the preset question;
and constructing a knowledge graph according to the preset questions and the answer information.
Further, the step of pre-constructing the user digital person includes:
receiving face data acquired by the client;
And constructing a user digital person according to the face data, and feeding back the user digital person to the client.
Further, generating an authentication problem according to a pre-constructed knowledge graph includes:
randomly selecting one or two adjacent edges from the knowledge graph;
And generating an authentication problem according to the edge.
Further, the generating an authentication result according to the knowledge graph and the authentication answer includes:
generating a correct result of the authentication questions corresponding to the authentication answers according to the knowledge graph;
Verifying the authentication answer by using the correct result;
If each authentication answer is consistent with the corresponding correct result, the authentication result is successful authentication;
if the authentication answer is inconsistent with the corresponding correct result, the authentication result is authentication failure.
Further, the method further comprises the following steps:
And when the user agrees to the voice recording, receiving voiceprint data collected by the client and performing auxiliary authentication according to the voiceprint data.
Further, the performing auxiliary authentication according to the voiceprint data includes:
extracting sound features from the voiceprint data;
and performing auxiliary authentication according to the sound characteristics.
In a second aspect, the present application provides an automatic check device for batch accounting processing, comprising:
an authentication problem sending unit, configured to receive a login authentication request, generate an authentication problem according to a pre-constructed knowledge graph, and send the authentication problem to the client;
the authentication answer receiving unit is used for receiving authentication answers fed back by the client through a virtual interaction mode corresponding to the user digital person constructed in advance; the authentication answer is generated by the client according to the authentication problem;
and the authentication result generation unit is used for generating an authentication result according to the knowledge graph and the authentication answer.
In a third aspect, the present application provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method according to any one of the embodiments above when executing the computer program.
In a fourth aspect, the present application provides a computer readable storage medium storing a computer program which, when executed by a processor, implements a method according to any of the embodiments described above.
In a fifth aspect, the application provides a computer program product comprising a computer program which, when executed by a processor, implements a method according to any of the embodiments described above.
According to the login authentication method and device, the login authentication request is received, the authentication problem is generated according to the pre-constructed knowledge graph, and the authentication problem is sent to the client; receiving authentication answers fed back by the client through a virtual interaction mode corresponding to a user digital person, which is constructed in advance; the authentication answer is generated by the client according to the authentication problem; according to the knowledge graph and the authentication answer, an authentication result is generated, so that under the condition that a user name and a password are not utilized, a dynamic problem is generated based on the knowledge of interest of the user to perform login authentication, personalized service is provided for the user, the safety and privacy of user login are improved, the problem of forgetting the password and the like is prevented, and meanwhile the risk of being broken by violence when the user name and the password are used for login can be avoided. And receiving authentication answers fed back by the client through a virtual interaction mode corresponding to the user digital person, and providing immersive login experience for the user. In addition, by receiving the voiceprint data collected by the client and performing auxiliary authentication according to the voiceprint data, the reliability of login authentication is ensured, and the login experience of a user is further improved.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a login authentication method according to an embodiment of the present application;
FIG. 2 is a flowchart of a login authentication method according to an embodiment of the present application;
FIG. 3 is a flowchart of a login authentication method according to an embodiment of the present application;
FIG. 4 is a flowchart of a login authentication method according to an embodiment of the present application;
FIG. 5 is a flowchart of a login authentication method according to an embodiment of the present application;
FIG. 6 is a flowchart of a login authentication method according to an embodiment of the present application;
FIG. 7 is a schematic diagram of a login authentication device according to an embodiment of the present application;
FIG. 8 is a schematic diagram of a login authentication device according to an embodiment of the present application;
FIG. 9 is a schematic diagram of a login authentication device according to an embodiment of the present application;
FIG. 10 is a schematic diagram of a login authentication device according to an embodiment of the present application;
FIG. 11 is a schematic diagram of a login authentication device according to an embodiment of the present application;
FIG. 12 is a schematic diagram of a login authentication device according to an embodiment of the present application;
FIG. 13 is a schematic diagram of a login authentication device according to an embodiment of the present application;
fig. 14 is a schematic physical structure of an electronic device according to an embodiment of the present application;
FIG. 15 is a schematic diagram of a user knowledge graph according to an embodiment of the present application;
Fig. 16 is a schematic diagram of virtual digital human interaction according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the embodiments of the present application will be described in further detail with reference to the accompanying drawings. The exemplary embodiments of the present application and their descriptions herein are for the purpose of explaining the present application, but are not to be construed as limiting the application. It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be arbitrarily combined with each other.
It should be noted that the login authentication method and device disclosed in the present application can be used in the financial technical field, and can also be used in any field other than the financial technical field, and the application field of the login authentication method and device disclosed in the present application is not limited.
Fig. 1 is a flow chart of a login authentication method according to an embodiment of the present application, and as shown in fig. 1, the login authentication method provided by the present application includes:
S101: receiving a login authentication request, generating an authentication problem according to a pre-constructed knowledge graph, and sending the authentication problem to the client;
S102: receiving authentication answers fed back by the client through a virtual interaction mode corresponding to a user digital person, which is constructed in advance; the authentication answer is generated by the client according to the authentication problem;
S103: and generating an authentication result according to the knowledge graph and the authentication answer.
As can be seen from the flow shown in fig. 1, in the login authentication method provided by the application, an authentication problem is generated by receiving a login authentication request according to a pre-constructed knowledge graph and is sent to the client; receiving authentication answers fed back by the client through a virtual interaction mode corresponding to a user digital person, which is constructed in advance; the authentication answer is generated by the client according to the authentication problem; according to the knowledge graph and the authentication answer, an authentication result is generated, so that under the condition that a user name and a password are not utilized, a dynamic problem is generated based on the knowledge of interest of the user to perform login authentication, personalized service is provided for the user, the safety and privacy of user login are improved, the problem of forgetting the password and the like is prevented, and meanwhile the risk of being broken by violence when the user name and the password are used for login can be avoided.
It should be noted that, in the technical scheme of the application, the acquisition, storage, use, processing and the like of the data all conform to the relevant regulations of national laws and regulations. The user information in the embodiment of the application is obtained through legal compliance approaches, and the user information is obtained, stored, used, processed and the like through the approval of the client.
The application scene of the application comprises a client, a server and a database, wherein the client collects face data of a user when the user registers and logs in to construct personalized interactive digital people and realize face auxiliary authentication; collecting voice data of a user to identify input contents through voice to text and realize voiceprint identification auxiliary authentication; and constructing digital human page dialogue interaction, and realizing the functions of dynamic display of pictures and text reading. The server performs feature extraction, virtual digital person construction, knowledge graph construction, authentication question generation, authentication answer verification and auxiliary verification on the face data and the sound data of the user. The database comprises a graph database and a relational database and is used for storing a knowledge graph constructed by a user, voiceprint data and face characteristic data. The face data and the voiceprint data are subjected to differential privacy treatment before being stored, and the data are stored after being disturbed.
Each step is explained in detail below.
S101: receiving a login authentication request, generating an authentication problem according to a pre-constructed knowledge graph, and sending the authentication problem to the client;
Specifically, when a user registers, the user performs real-name authentication by using a mobile phone number at a client, receives a verification code fed back by a server, and if the verification passes, registration information can be input, basic authentication information of the user, such as name, identity card number, age, gender and the like, can be introduced from an operator side through the real-name authentication of the mobile phone number, and each person is ensured to have an independent and unique login authentication environment. The client requests the user to model the image by the digital person according to the mobile phone number to the server and inquires whether the user is registered and whether a knowledge graph is constructed when the user is registered. If the user does not register, the user information is not acquired, and the user registration process is skipped. If the user has completed registration, the user returns to the client after acquiring the digital person modeling image and then enters a login authentication interaction page.
The server receives the login authentication request, finds a knowledge graph constructed by the user during registration according to the authenticated mobile phone number, generates an authentication problem according to the knowledge graph, and sends the authentication problem to the client.
Fig. 2 is a flowchart of a login authentication method according to an embodiment of the present application, as shown in fig. 2, before S101, further includes:
s201: sending a preset question to a client and receiving answer information fed back by the client according to the preset question;
Specifically, the server sends the preset questions to the client and receives the content of answer information fed back by the client according to the preset questions to perform knowledge extraction so as to construct a knowledge graph.
For example, before the server presents the preset questions to the user for knowledge graph construction, the client displays a plurality of question domain keywords to the user, the user selects one to three interesting domains (such as sports, movies, music, etc.) to feed back to the system digital person, the server constructs a plurality of corresponding preset questions (such as what is you looking at the favorite movie.
S202: and constructing a knowledge graph according to the preset questions and the answer information.
Specifically, the content of the answer information replied by the preset questions and the user belongs to unstructured data, and information extraction processing is required to be performed on the data. The information extraction includes entity extraction, relationship extraction and attribute extraction. For example, the server may use a chinese natural language entity extraction tool for entity extraction, may use a language recognition capable relationship extraction tool to implement relationship extraction, and may employ a cluster-based entity-attribute extraction method for attribute extraction. A large amount of triplet data is formed through knowledge extraction, and the triplet data is specifically expressed in the form of a triplet of entity-relation-entity and entity-attribute value, and is taken as a basic unit of knowledge expression. And then, carrying out knowledge fusion on the triplet data, using a framework based on entity attribute similarity by a server, finishing entity alignment and knowledge fusion by defining similarity measurement and combination, and finally storing the knowledge triplet data into a graph database by the server.
For example, the knowledge graph is constructed in a top-down manner, the user number is taken as a central entity, and authentication information (such as name, mobile phone number, gender, age and identity card number) of the user is taken as an attribute to construct a mode layer of the graph.
Fig. 4 is a flowchart of a login authentication method according to an embodiment of the present application, as shown in fig. 4, S101 includes:
s401: randomly selecting one or two adjacent edges from the knowledge graph;
Specifically, the server generates authentication questions according to pre-constructed and stored knowledge patterns, for example, three to five questions can be generated from the knowledge patterns corresponding to each user, and each authentication question can be generated according to one or two adjacent sides selected randomly from the knowledge patterns, namely, the authentication question is generated for a certain node in the knowledge patterns.
S402: and generating an authentication problem according to the edge.
Specifically, the server generates an authentication problem according to the entity and entity between two nodes of the selected edge in the knowledge graph and the entity and attribute value by using the natural language model, for example, if the knowledge graph constructed by a certain user is shown in fig. 15, if the edge numbers of the knowledge graph randomly selected by the server are 1 and 3, the generated authentication problem is "who the favorite movie is being led by? The node with the content of A is the correct result of the authentication problem; if the edge number is chosen to be 2, then a verification question can be constructed as "what is you the pet in which is? The node whose content is "cat" is the correct result of the authentication problem.
S102: receiving authentication answers fed back by the client through a virtual interaction mode corresponding to a user digital person, which is constructed in advance; the authentication answer is generated by the client according to the authentication problem;
Specifically, the client provides a login authentication interaction page for a user, the digital person and the digital person image of the user are displayed through the login authentication interaction page, the digital person image, the open speaking and reading problem text is driven to present authentication problems for the user, and the client adds mouth-shaped actions and hand gestures to the virtual digital person to strengthen interaction. As shown in fig. 16, the content of the authentication question is presented in the form of a dialogue bubble on the login authentication interaction page, and the user can select to answer the authentication question by voice or text input, and the content of the answer to the answer is presented in the form of a dialogue bubble on the login authentication interaction page. The client performs virtual interaction through the stylized virtual digital human images, excessive rendering performance is not required to be consumed, and smoothness of user interaction experience is improved. After the user confirms the user digital person image through the client, the system digital person and the user digital person propose preset questions and answer information in a dialogue mode, and each user is helped to construct a unique knowledge graph. The dialogue content is presented in a way of virtual digital person opening reading on one hand, and is synchronously displayed on the client in the form of dialogue bubbles containing words on the other hand.
The user answers the authentication questions in two ways, a text input answer and a speech input answer. If the voice input answer is selected, the voice input answer is also converted into a text interactive dialog box for display through voice recognition. For example, the offline speech recognition SDK invokes a speech recognition function, uses the pre-downloaded offline speech recognition packet to convert the collected voice signal into a digital signal, and matches the digital signal with the speech packet data after noise removal processing to form a recognition word for text recognition. And then, the identified result is presented in a dialogue bubble form to form a virtual interaction form of the system digital person and the user digital person. The character recognition result is encrypted, then the unique identification consistent with the voice fragment is marked (the authentication question, the authentication answer voice, the authentication answer text and the authentication question correct answer use consistent ID numbers), and the encrypted character data is sent to the server.
Fig. 3 is a flowchart of a login authentication method according to an embodiment of the present application, as shown in fig. 3, before S102, further includes:
s301: receiving face data acquired by the client;
Specifically, the client applies for the front camera authority of the equipment, acquires face data of the user, prompts the user to input a positive face non-shielding photo through a prompting function of a character view-finding frame, inputs the face to fit the character view-finding frame, automatically shoots after the ambient light is sufficient, detects that the face cannot be shielded (wearing a mask, wearing a hat and the like) at the same time, and informs the user that the input is successful through sound or vibration feedback (playing sound in an unmuted state of the equipment, and triggering vibration feedback of a mobile phone in a muted state). The client encrypts the data of the front face non-shielding face picture and sends the encrypted data to the server, and the server receives the face data acquired by the client.
S302: and constructing a user digital person according to the face data, and feeding back the user digital person to the client.
Specifically, the server sets sampling points for the front face photo shot by the user, and extracts the shape parameter, the detail parameter, the light shadow parameter and the additional parameter of the face of the user. The shape parameters include a face outline and a face size; the detail parameters comprise the size, the position and the shape of the five sense organs; the shadow parameters comprise five sense organs depth which are marked by the shadow degree reflected by the light on the face; additional parameters include the user's hairstyle and whether the person being identified wears glasses and earrings. After the encrypted face photo is decrypted by the server, the face modeling is carried out by shooting the uploaded face photo of the user by the client, and the encrypted face photo is realized through a trusted third-party digital content production line cloud platform. The face modeling comprises feature recognition, geometric deformation and material matching, a stylized user virtual digital person is finally constructed, the stylized user virtual digital person is returned to the client, the user is allowed to conduct fine adjustment according to personal preference, and the client displays the user virtual digital person.
S103: and generating an authentication result according to the knowledge graph and the authentication answer.
Specifically, an authentication question is presented to the user through a virtual interaction mode of the system digital person and the user digital person, and the user waits for replying an authentication answer. And matching the authentication answer replied by the user with the correct answer, finishing authentication login if the matching is passed, failing to authenticate login if the matching is failed, and failing to pass the login request of the user.
Fig. 5 is a flowchart of a login authentication method according to an embodiment of the present application, as shown in fig. 5, S103 includes:
s501: generating a correct result of the authentication questions corresponding to the authentication answers according to the knowledge graph;
Specifically, after generating the authentication question, the server generates a correct result of the authentication question according to the knowledge graph, and the correct result is used for verifying whether an authentication answer replied by the user according to the authentication question is correct.
S502: verifying the authentication answer by using the correct result;
Specifically, the content of the authentication answer of the user is transmitted back to the server through text form encryption, and the server performs word segmentation and information extraction on the answer content and compares the answer content with a correct answer. And the server performs verification and comparison on the text content of the authentication answer replied by the user and the correct result of the authentication question corresponding to the authentication answer generated according to the knowledge graph, and verifies whether the authentication answer is correct or not.
S503: if each authentication answer is consistent with the corresponding correct result, the authentication result is successful authentication;
Specifically, in the authentication process of all authentication questions, each time a user answers an authentication question, the server verifies whether an authentication answer is consistent with a correct result, if all authentication questions pass, namely, each authentication answer is consistent with a corresponding correct result, a login authentication flow is completed, user authentication is successful, and the server passes a login request of the user.
S504: if the authentication answer is inconsistent with the corresponding correct result, the authentication result is authentication failure.
Specifically, in the authentication process of all authentication questions, if the authentication answer is inconsistent with the corresponding correct result, that is, the user answers incorrectly, the next authentication question is not presented, and the user authentication fails. If authentication fails, the server needs to perform auxiliary authentication on the user.
In an embodiment, the login authentication method further includes:
And when the user agrees to the voice recording, receiving voiceprint data collected by the client and performing auxiliary authentication according to the voiceprint data.
Specifically, when a user selects a preset question set by a virtual digital person of a voice answering system, the client applies for the microphone authority of the device to collect sound, records a sound fragment when the user replies answer information, and marks a unique identifier for the sound fragment for replying each preset question. The client encrypts the sound fragment data and sends the sound fragment data to the server, and the server receives the voiceprint data collected by the client and performs subsequent auxiliary authentication by utilizing the voiceprint data. On one hand, the collected answer information is subjected to local voice character recognition and converted into characters for constructing a user knowledge graph, and on the other hand, the collected answer information is processed aiming at sound fragments, sound characteristics are extracted, voiceprint information is obtained, and the collected answer information is used for assisting in verification of voiceprint recognition. The face data and voiceprint data of the user belong to user privacy data, and the user privacy data and the voiceprint data are stored in a cloud relational database after being subjected to differential privacy processing and data disturbance.
Fig. 6 is a flowchart of a login authentication method according to an embodiment of the present application, as shown in fig. 6, for performing auxiliary authentication according to the voiceprint data, including:
S601: extracting sound features from the voiceprint data;
Specifically, the server includes the following operations for voiceprint data: 1. pretreatment: the method comprises the steps of endpoint detection, noise elimination, pre-emphasis and the like, invalid information and interference are removed, and valid voice information is reserved; 2. framing and windowing: dividing the continuous speech signal into short-time speech frames, and multiplying each frame by a window function to reduce boundary effects; 3. feature extraction: feature extraction is performed on each frame, and parameters capable of reflecting physiological and behavioral features of a speaker, such as fundamental frequency, energy, mel-frequency cepstrum coefficient (MFCC), linear Prediction Coefficient (LPC), and the like, are extracted from a speech signal.
S602: and performing auxiliary authentication according to the sound characteristics.
Specifically, if the user selects text to input an answer in the answer question stage, and voice information cannot be acquired, the auxiliary authentication is only face recognition authentication. If the voice input answer is selected, the auxiliary authentication is provided with face recognition authentication and voiceprint contrast authentication. Face recognition is carried out by taking a front unobstructed photo of a face through a camera and extracting face features of the face photo collected in a registration stage, and voiceprint comparison is carried out by collecting sound through a microphone to carry out feature extraction processing and comparing sound features stored in a cloud database. And if all the authentications pass, finishing login, otherwise, not passing the login request of the user. And login authentication is not allowed to be initiated again for a period of time (e.g., one hour).
The server can adopt a machine learning or deep learning method to carry out voiceprint comparison authentication, such as Gaussian Mixture Model (GMM), i-vector or Deep Neural Network (DNN), and the like, generate a voiceprint model by utilizing sound characteristics, and carry out similarity calculation or classification judgment with a pre-trained target voiceprint model so as to carry out auxiliary authentication on a user.
The application provides a login authentication method, which comprises the steps of receiving a login authentication request, generating an authentication problem according to a pre-constructed knowledge graph and sending the authentication problem to a client; receiving authentication answers fed back by the client through a virtual interaction mode corresponding to a user digital person, which is constructed in advance; the authentication answer is generated by the client according to the authentication problem; according to the knowledge graph and the authentication answer, an authentication result is generated, so that under the condition that a user name and a password are not utilized, a dynamic problem is generated based on the knowledge of interest of the user to perform login authentication, personalized service is provided for the user, the safety and privacy of user login are improved, the problem of forgetting the password and the like is prevented, and meanwhile the risk of being broken by violence when the user name and the password are used for login can be avoided. And receiving authentication answers fed back by the client through a virtual interaction mode corresponding to the user digital person, and providing immersive login experience for the user. In addition, by receiving the voiceprint data collected by the client and performing auxiliary authentication according to the voiceprint data, the reliability of login authentication is ensured, and the login experience of a user is further improved.
Based on the same inventive concept, the embodiment of the present application also provides a login authentication device, which can be used to implement the method described in the above embodiment, as described in the following embodiment. Since the principle of solving the problem of the login authentication device is similar to that of the login authentication method, the implementation of the login authentication device can be referred to the implementation of the determination method based on the software performance reference, and the repetition is omitted. As used below, the term "unit" or "module" may be a combination of software and/or hardware that implements the intended function. While the system described in the following embodiments is preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
Fig. 7 is a schematic structural diagram of a login authentication device according to an embodiment of the present application, as shown in fig. 7, the device includes:
An authentication problem sending unit 701, configured to receive a login authentication request, generate an authentication problem according to a pre-constructed knowledge graph, and send the authentication problem to the client;
An authentication answer receiving unit 702, configured to receive an authentication answer fed back by the client through a virtual interaction mode corresponding to a user digital person, where the authentication answer is constructed in advance; the authentication answer is generated by the client according to the authentication problem;
An authentication result generating unit 703, configured to generate an authentication result according to the knowledge graph and the authentication answer.
Fig. 8 is a schematic diagram of a login authentication structure according to an embodiment of the present application, and further, as shown in fig. 8, the login authentication device according to the present application further includes:
An answer information receiving unit 801, configured to send a preset question to a client and receive answer information fed back by the client according to the preset question;
the knowledge graph construction unit 802 is configured to construct a knowledge graph according to the preset questions and the answer information.
Fig. 9 is a schematic diagram of a login authentication structure according to an embodiment of the present application, and further, as shown in fig. 9, the login authentication device according to the present application further includes:
a face data receiving unit 901, configured to receive face data collected by the client;
and a user digital person constructing unit 902, configured to construct a user digital person according to the face data, and feed back the user digital person to the client.
Fig. 10 is a schematic diagram of a login authentication structure according to an embodiment of the present application, and further, as shown in fig. 10, the login authentication device according to the present application further includes:
A random selection module 1001, which randomly selects one or two adjacent edges from the knowledge graph;
An authentication problem generating module 1002, configured to generate an authentication problem according to the edge.
Fig. 11 is a schematic diagram of a login authentication structure according to an embodiment of the present application, and further, as shown in fig. 11, the login authentication device according to the present application further includes:
a correct result generating module 1101, configured to generate a correct result of the authentication question corresponding to the authentication answer according to the knowledge graph;
an authentication answer verification module 1102, configured to verify the authentication answer by using the correct result;
the first authentication result generation module 1103 is configured to, if each authentication answer is consistent with the corresponding correct result, determine that the authentication result is successful;
the second authentication result generation module 1104 is configured to, if there is an authentication answer inconsistent with the corresponding correct result, determine that the authentication result is an authentication failure.
Fig. 12 is a schematic diagram of a login authentication structure according to an embodiment of the present application, and further, as shown in fig. 12, the login authentication device according to the present application further includes:
And the auxiliary authentication unit 1201 is used for receiving voiceprint data collected by the client and performing auxiliary authentication according to the voiceprint data when the user agrees to voice recording.
Fig. 13 is a schematic diagram of a login authentication structure according to an embodiment of the present application, and further, as shown in fig. 13, the login authentication device according to the present application further includes:
A sound feature extraction module 1301, configured to extract sound features from the voiceprint data;
the auxiliary authentication module 1302 is configured to perform auxiliary authentication according to the sound feature.
The application provides a login authentication method and a login authentication device, which are characterized in that an authentication problem is generated according to a pre-constructed knowledge graph and sent to a client by receiving a login authentication request; receiving authentication answers fed back by the client through a virtual interaction mode corresponding to a user digital person, which is constructed in advance; the authentication answer is generated by the client according to the authentication problem; and generating an authentication result according to the knowledge graph and the authentication answer, so that login authentication is performed based on the knowledge of interest of the user under the condition that the user name and the password are not utilized, personalized service is provided for the user, the problem of forgetting the password and the like is prevented, and meanwhile, the risk of being broken by violence when the user name and the password are used for login can be avoided. And receiving authentication answers fed back by the client through a virtual interaction mode corresponding to the user digital person, and providing immersive login experience for the user. In addition, by receiving the voiceprint data collected by the client and performing auxiliary authentication according to the voiceprint data, the reliability of login authentication is ensured, and the login experience of a user is further improved.
Fig. 14 is a schematic physical structure of an electronic device according to an embodiment of the present application, as shown in fig. 14, the electronic device may include: a processor 1401, a communication interface Communications Interface, a memory 1403 and a communication bus 1404, wherein the processor 1401, the communication interface 1402 and the memory 1403 communicate with each other via the communication bus 1404. The processor 1401 may call logic instructions in the memory 1403 to perform the following method: receiving a login authentication request, generating an authentication problem according to a pre-constructed knowledge graph, and sending the authentication problem to the client; receiving authentication answers fed back by the client through a virtual interaction mode corresponding to a user digital person, which is constructed in advance; the authentication answer is generated by the client according to the authentication problem; and generating an authentication result according to the knowledge graph and the authentication answer.
Further, the logic instructions in the memory 1403 described above may be implemented in the form of software functional units and may be stored in a computer readable storage medium when sold or used as a stand alone product. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a read-only memory (ROM), a random access memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The present embodiment discloses a computer program product comprising a computer program stored on a computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the methods provided by the above-described method embodiments, for example comprising: receiving a login authentication request, generating an authentication problem according to a pre-constructed knowledge graph, and sending the authentication problem to the client; receiving authentication answers fed back by the client through a virtual interaction mode corresponding to a user digital person, which is constructed in advance; the authentication answer is generated by the client according to the authentication problem; and generating an authentication result according to the knowledge graph and the authentication answer.
The present embodiment provides a computer-readable storage medium storing a computer program that causes the computer to execute the methods provided by the above-described method embodiments, for example, including: receiving a login authentication request, generating an authentication problem according to a pre-constructed knowledge graph, and sending the authentication problem to the client; receiving authentication answers fed back by the client through a virtual interaction mode corresponding to a user digital person, which is constructed in advance; the authentication answer is generated by the client according to the authentication problem; and generating an authentication result according to the knowledge graph and the authentication answer.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In the description of the present specification, reference to the terms "one embodiment," "one particular embodiment," "some embodiments," "for example," "an example," "a particular example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the application, and is not meant to limit the scope of the application, but to limit the application to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the application are intended to be included within the scope of the application.
Claims (11)
1. A login authentication method, comprising:
Receiving a login authentication request, generating an authentication problem according to a pre-constructed knowledge graph, and sending the authentication problem to a client;
receiving authentication answers fed back by the client through a virtual interaction mode corresponding to a user digital person, which is constructed in advance; the authentication answer is generated by the client according to the authentication problem;
and generating an authentication result according to the knowledge graph and the authentication answer.
2. The login authentication method according to claim 1, wherein the step of constructing a knowledge-graph in advance includes:
Sending a preset question to a client and receiving answer information fed back by the client according to the preset question;
and constructing a knowledge graph according to the preset questions and the answer information.
3. The login authentication method according to claim 1, wherein the step of pre-constructing the user digital person comprises:
receiving face data acquired by the client;
And constructing a user digital person according to the face data, and feeding back the user digital person to the client.
4. The login authentication method according to claim 1, wherein generating an authentication problem from a pre-constructed knowledge-graph comprises:
randomly selecting one or two adjacent edges from the knowledge graph;
And generating an authentication problem according to the edge.
5. The login authentication method according to claim 1, wherein the generating an authentication result from the knowledge-graph and the authentication answer comprises:
generating a correct result of the authentication questions corresponding to the authentication answers according to the knowledge graph;
Verifying the authentication answer by using the correct result;
If each authentication answer is consistent with the corresponding correct result, the authentication result is successful authentication;
if the authentication answer is inconsistent with the corresponding correct result, the authentication result is authentication failure.
6. The login authentication method according to claim 1, further comprising:
And when the user agrees to the voice recording, receiving voiceprint data collected by the client and performing auxiliary authentication according to the voiceprint data.
7. The login authentication method according to claim 6, wherein the performing the auxiliary authentication according to the voiceprint data includes:
extracting sound features from the voiceprint data;
and performing auxiliary authentication according to the sound characteristics.
8. A login authentication device, comprising:
The authentication problem sending unit is used for receiving a login authentication request, generating an authentication problem according to a pre-constructed knowledge graph and sending the authentication problem to the client;
the authentication answer receiving unit is used for receiving authentication answers fed back by the client through a virtual interaction mode corresponding to the user digital person constructed in advance; the authentication answer is generated by the client according to the authentication problem;
and the authentication result generation unit is used for generating an authentication result according to the knowledge graph and the authentication answer.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of claims 1 to 7 when executing the computer program.
10. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program which, when executed by a processor, implements the method of any one of claims 1 to 7.
11. A computer program product, characterized in that the computer program product comprises a computer program which, when executed by a processor, implements the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410103123.1A CN117892277A (en) | 2024-01-24 | 2024-01-24 | Login authentication method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410103123.1A CN117892277A (en) | 2024-01-24 | 2024-01-24 | Login authentication method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117892277A true CN117892277A (en) | 2024-04-16 |
Family
ID=90641129
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410103123.1A Pending CN117892277A (en) | 2024-01-24 | 2024-01-24 | Login authentication method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117892277A (en) |
-
2024
- 2024-01-24 CN CN202410103123.1A patent/CN117892277A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10158633B2 (en) | Using the ability to speak as a human interactive proof | |
| KR101757990B1 (en) | Method and device for voiceprint indentification | |
| KR101908711B1 (en) | Artificial intelligence based voiceprint login method and device | |
| US20200097643A1 (en) | rtCaptcha: A Real-Time Captcha Based Liveness Detection System | |
| CN111033501B (en) | Secure authorization for access to private data in virtual reality | |
| US9979721B2 (en) | Method, server, client and system for verifying verification codes | |
| CN110169014A (en) | Device, method and computer program product for certification | |
| WO2016015687A1 (en) | Voiceprint verification method and device | |
| JP2016511475A (en) | Method and system for distinguishing humans from machines | |
| WO2020051971A1 (en) | Identity recognition method, apparatus, electronic device, and computer-readable storage medium | |
| US10936705B2 (en) | Authentication method, electronic device, and computer-readable program medium | |
| Zhang et al. | Volere: Leakage resilient user authentication based on personal voice challenges | |
| KR102079303B1 (en) | Voice recognition otp authentication method using machine learning and system thereof | |
| CN108447489B (en) | Continuous voiceprint authentication method and system with feedback | |
| CN117892277A (en) | Login authentication method and device | |
| CN108416592A (en) | A kind of high speed voice recognition methods | |
| CN108550368A (en) | A kind of processing method of voice data | |
| CN107454044A (en) | A kind of e-book reading protection of usage right method and system | |
| CN106407783A (en) | An online verification method and system | |
| Firc | Applicability of Deepfakes in the Field of Cyber Security | |
| CN114979088B (en) | Psychological consultation method and system based on intelligent auxiliary system | |
| US20240086508A1 (en) | System and method for facilitating multi-factor face authentication of user | |
| Turner | Security and privacy in speaker recognition systems | |
| US20230359719A1 (en) | A computer implemented method | |
| KR102640359B1 (en) | Control method of system for non-face-to-face identification using keyword repetition frequency and voice characteristics |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |