Information authentication method and system

Abstract

The invention discloses an information authentication method and system. The method comprises the steps of outputting preset information in response to safety of a processing environment, and receiving voice information returned for the preset information; recognizing the voice information to obtain voice content in the voice information and voiceprint features corresponding to the voice information; the voice content is authenticated based on preset information to obtain a first authentication result, the voiceprint features are authenticated to obtain a second authentication result, the first authentication result is used for representing whether the voice content is consistent with the preset information, and the second authentication result is used for representing whether voiceprint consistency authentication is passed; and generating a target authentication result based on the first authentication result and the second authentication result. According to the invention, the technical problem of poor information security caused by easy failure of information authentication in the prior art is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of information security, in particular to an information authentication method and system. BACKGROUND

[0002] In the wave of digital transformation, online service fields from financial transactions, e-commerce to medical health, distance education, etc., almost cover all aspects of people's life. However, with the frequent occurrence of network impersonation technology, especially the emergence of deep fake technology, the traditional information authentication means still face great challenges.

[0003] The related art often uses active authentication methods such as SMS verification codes, but SMS verification codes are easy to lose or tamper with, which leads to the authentication mechanism being easy to crack, that is, the information authentication scheme in the related art still has the defect of poor information security.

[0004] In view of the above problems, no effective solution has been proposed so far. SUMMARY

[0005] The embodiments of the present application provide an information authentication method and system to at least solve the technical problem of poor information security caused by invalid information authentication in the related art.

[0006] According to an aspect of an embodiment of the present application, an information authentication method is provided, comprising: in response to a processing environment being secure, outputting preset information and receiving voice information returned in response to the preset information; identifying the voice information to obtain voice content in the voice information and a voiceprint feature corresponding to the voice information; authenticating the voice content based on the preset information to obtain a first authentication result, and authenticating the voiceprint feature to obtain a second authentication result, wherein the first authentication result is used to represent whether the voice content is consistent with the preset information, and the second authentication result is used to represent whether the voiceprint consistency authentication is passed; and generating a target authentication result based on the first authentication result and the second authentication result.

[0007] Optionally, identifying the voice information to obtain voice content in the voice information and a voiceprint feature corresponding to the voice information comprises: performing semantic recognition on the voice information to obtain the voice content; and performing voiceprint feature extraction on the voice information to obtain the voiceprint feature.

[0008] Optionally, authenticating the voice content based on the preset information to obtain the first authentication result comprises: performing format conversion on the preset information to obtain a preset string; performing format conversion on the voice content to obtain a voice string; and comparing the preset string and the voice string to obtain the first authentication result.

[0009] Optionally, the voiceprint feature is authenticated to obtain a second authentication result, including: obtaining identification information; querying a preset voiceprint feature corresponding to the identification information from the voiceprint database based on the identification information; comparing the voiceprint feature with the preset voiceprint feature to obtain the second authentication result.

[0010] Optionally, the method further includes: in response to the first authentication result being that the voice content is consistent with the preset information, repeatedly performing the steps of outputting the preset information and receiving the voice information returned for the preset information until the number of received voice information reaches a preset number; comparing the preset number of voice information for similarity to obtain a comparison result, wherein the comparison result is used to represent whether the similarity of the preset number of voice information is greater than a preset threshold; in response to the comparison result being that the similarity of the preset number of voice information is greater than the preset threshold, determining a preset voiceprint feature based on the preset number of voice information; and storing the mapping relationship between the preset voiceprint feature and the identification information in the voiceprint database.

[0011] Optionally, the method further includes: in response to the target authentication result being that the information authentication is passed, detecting an update time of the voiceprint database; in response to the update time being greater than a preset time period, adjusting the preset voiceprint feature based on the voice information to obtain a new preset voiceprint feature; and storing the mapping relationship between the new preset voiceprint feature and the identification information in the voiceprint database.

[0012] Optionally, the method further includes: in response to the target authentication result being that the information authentication is not passed, determining a risk level based on the identification information; authenticating the voice information using an authentication mode corresponding to the risk level to obtain a third authentication result, wherein the third authentication result is used to represent whether the voice information passes the authentication; and in response to the voice information passing the authentication, storing the voiceprint feature as the preset voiceprint feature in the voiceprint database.

[0013] Optionally, the method further includes one of: determining whether the identification information is included in a preset blacklist to obtain a detection result, wherein the detection result is used to represent whether the processing environment is safe; and performing abnormality detection based on the processing information to obtain a detection result.

[0014] According to another aspect of the embodiments of the present application, an information authentication system is also provided, comprising: an obtaining module, configured to output preset information in response to a processing environment being secure, and receive voice information returned in response to the preset information; an identifying module, configured to identify the voice information to obtain voice content in the voice information and a voiceprint feature corresponding to the voice information; an authenticating module, configured to authenticate the voice content based on the preset information to obtain a first authentication result, and authenticate the voiceprint feature to obtain a second authentication result, wherein the first authentication result is used to represent whether the voice content is consistent with the preset information, and the second authentication result is used to represent whether the voiceprint consistency authentication is passed; and a generating module, configured to generate a target authentication result based on the first authentication result and the second authentication result.

[0015] Optionally, the system further comprises an environment detecting module, configured to determine whether the identification information is included in the preset list library to obtain a detection result, wherein the detection result is used to represent whether the processing environment is secure, or perform abnormality detection based on the processing information to obtain the detection result.

[0016] According to another aspect of the embodiments of the present application, an electronic device is also provided, comprising: a memory, storing an executable program; and a processor, configured to run the program, wherein the program is executed to perform the method in each of the embodiments of the present application when the program is run.

[0017] According to another aspect of the embodiments of the present application, a computer readable storage medium is also provided, comprising a stored executable program, wherein the computer readable storage medium is controlled to perform the method in each of the embodiments of the present application when the executable program is run.

[0018] According to another aspect of the embodiments of the present application, a computer program product is also provided, comprising a computer program, which is executed by a processor to implement the method in each of the embodiments of the present application.

[0019] According to another aspect of the embodiments of the present application, a computer program product is also provided, comprising a non-volatile computer readable storage medium, which stores a computer program, wherein the computer program is executed by a processor to implement the method in each of the embodiments of the present application.

[0020] According to another aspect of the embodiments of the present application, a computer program is also provided, which is executed by a processor to implement the method in each of the embodiments of the present application.

[0021] In the embodiment of the present application, in response to the processing environment being safe, the preset information is output, and after receiving the voice information returned for the preset information, the voice information is recognized to obtain the voice content in the voice information and the voiceprint feature corresponding to the voice information, then the voice content is authenticated based on the preset information to obtain a first authentication result, and the voiceprint feature is authenticated to obtain a second authentication result, so as to generate a target authentication result based on the first authentication result and the second authentication result. The present application first ensures that the preset information is output only after the processing environment is safe, ensuring that the information authentication is performed in a safe and reliable environment, then the voice content and the voiceprint feature are obtained by recognizing the returned voice information, so as to authenticate the voice content and the voiceprint feature by using the preset information. The final target authentication result is obtained through the double authentication mechanism, improving the security of information authentication, achieving the purpose of protecting information security, thereby realizing the technical effect of improving the security of information authentication, and further solving the technical problem of poor information security caused by invalid information authentication in the related art. BRIEF DESCRIPTION OF DRAWINGS

[0022] The accompanying drawings, which are included to provide a further understanding of the present application and are incorporated in and constitute a part of this application, illustrate embodiments of the present application and serve to explain the present application. In the drawings:

[0023] Figure 1 is a flowchart of an information authentication method according to an embodiment of the present application;

[0024] Figure 2 is a schematic diagram of an information authentication system according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable persons skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by persons skilled in the art without creative labor should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and in the above-described drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not have to be limited to only those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to such a process, method, product or device.

[0027] In the technical solution of the present application, the collection, storage, use, processing, transmission, provision and disclosure of financial data or user data and other information comply with relevant laws and regulations and do not violate public order and good customs.

[0028] It should be noted that in the embodiments of the present application, some software, components, models and other existing solutions in the industry may be mentioned, which should be considered as exemplary, and the purpose is only to illustrate the feasibility of the implementation of the technical solution of the present application, but does not mean that the applicant has or will necessarily use the solution.

[0029] According to the embodiments of the present application, a method embodiment of an information authentication method is provided. It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0030] Figure 1 is a flowchart of an information authentication method according to an embodiment of the present application, as shown in Figure 1 The method comprises the following steps:

[0031] Step S102, in response to the processing environment security, outputting preset information and receiving voice information returned for the preset information.

[0032] The processing environment mentioned above can refer to the context environment when performing information authentication, including but not limited to the state, location, time, network connection quality, and other factors of the user device. The processing environment is directly related to the security and effectiveness of authentication, and the system evaluates these environmental factors comprehensively to ensure that the authentication is performed in a risk-free condition. For example, checking whether the user device is reset, judging whether the device is located in the normal service area, and verifying whether the current time conforms to the normal operation mode, etc., can all be part of the processing environment. The evaluation of the processing environment is a condition for information authentication, and the processing environment security can prevent authentication attempts in unsafe or abnormal conditions, effectively preventing external threats. By setting environmental security standards, most high-risk scenarios can be filtered out, creating a relatively reliable operating environment for subsequent authentication steps.

[0033] The preset information mentioned above is generated automatically by the system during the information authentication process and serves as the basis for identity verification. The preset information can be a randomly generated numerical sequence or alphanumeric combination used to test the user's response. For example, the preset information can be a dynamic voice digital code, i.e., a set of 4-6 random numbers, which requires the user to repeat it in order to simultaneously verify whether the voice content and voiceprint features match the expected. The role of the preset information is to provide a benchmark for the information authentication method to compare with the user's response. The randomness and one-time use characteristics of the preset information ensure the uniqueness of each authentication process. The use of preset information makes authentication not only dependent on fixed passwords or identifiers, but also combines real-time generated elements, enhancing overall security.

[0034] The voice information mentioned above refers to the audio signal transmitted by the user through the microphone or other audio input device when responding to the preset information output by the system. The voice information can include but is not limited to the user's voice reading, as well as the acoustic characteristics of the sound and noise, etc. Voice information is the basis for subsequent extraction of voice content and voiceprint features. Voice information is the true carrier of user identity, and voice information not only transmits the dynamic digital information repeated by the user, but also contains the unique voiceprint features of the individual. Through the analysis of voice information, the content of the user's speech and the verification of voice features can be completed simultaneously, achieving a higher level of security authentication. This avoids the limitations of traditional password verification and provides a more natural and difficult-to-replicate verification method.

[0035] In an alternative embodiment, on a mobile device such as a smartphone, through the integrated speech recognition software development kit and encrypted communication module, the user's voice information can be collected locally after confirming the safety of the device environment. The user reads out the preset information, and the voice is captured by the built-in microphone of the device, and the software development kit is used for preliminary processing and format conversion to ensure the quality and integrity of the voice signal. Subsequently, the voice information is encrypted and transmitted to the server through the device's network connection, and the subsequent voiceprint feature extraction and speech content recognition are performed.

[0036] In another alternative embodiment, on the web page side, real-time audio stream transmission can be realized using real-time communication technology, and after ensuring the safety of the network environment, the user is output with preset information. The user reads out the digital sequence through the microphone of the computer, and the real-time communication technology provides a low-delay and high-quality audio stream transmission channel, which can transmit the voice information to the authentication server without the need for local storage or processing.

[0037] Step S104, the voice information is recognized to obtain the voice content in the voice information and the voiceprint feature corresponding to the voice information.

[0038] The voice content mentioned above can be meaningful text information extracted from the voice information, which can include the numbers or alphanumeric combinations in the preset information repeated by the user. The voice content can be converted into text form through automatic speech recognition technology, which can be used for later matching authentication. Accurate recognition of voice content is the basis for verifying whether the user correctly understands and repeats the preset information. By converting voice information into text, it can be quickly and accurately determined whether the information provided by the user is consistent with the preset information, which is the key first step in the information authentication method, ensuring that the user's participation and response are correct at the cognitive level.

[0039] The voiceprint feature mentioned above can be a digital representation of the physiological and behavioral characteristics unique to an individual's voice extracted from the user's voice information. Voiceprint features can include, but are not limited to, frequency characteristics, intensity distribution, timbre, pitch, and pronunciation habits of the voice. The voiceprint feature can be a set of numerical features converted from the voice signal. Voiceprint features are biological identification markers of user identity, like fingerprints and irises, which are unique and stable. In the information authentication method, voiceprint features can be used to identify and verify the authenticity of the user's identity, even if the user cannot actively provide any information, it can also be determined whether it is the user's operation through silent voiceprint comparison, greatly enhancing the security of the authentication.

[0040] In an alternative embodiment, automatic speech recognition can be performed by a deep neural network, converting the received speech information into a spectrogram or mel-frequency cepstral coefficients, which are then input into a trained deep neural network model. This model is capable of converting the audio signal into textual information, i.e. the speech content. Meanwhile, the voiceprint recognition part uses a deep learning model to extract personal features from the speech, forming a voiceprint feature vector. This makes full use of the advantages of deep learning in speech recognition and biometric analysis, and can provide high-precision speech content recognition and voiceprint feature extraction.

[0041] In another alternative embodiment, speech recognition is performed by a hidden Markov model, which establishes a speech model containing state transitions and observation probabilities of each phoneme. After feature extraction (such as mel-frequency cepstrum) of the input speech information, the possible phoneme sequence is found, and then decoded into speech content. For voiceprint recognition, a Gaussian mixture model can be used, which first trains a general background model as a benchmark, and then learns a voiceprint feature for each user through maximum a posteriori probability adaptation.

[0042] Step S106, based on the preset information to authenticate the speech content, get the first authentication result, and authenticate the voiceprint feature, get the second authentication result.

[0043] Among them, the first authentication result is used to represent whether the speech content is consistent with the preset information, and the second authentication result is used to represent whether it passes the voiceprint consistency authentication.

[0044] The first authentication result described above can be the conclusion obtained after comparing the preset information and the speech content provided by the user. The first authentication result reflects whether the speech content fed back by the user matches the preset information generated by the system. The first authentication result is the result of judging whether the user correctly restates the preset information, which can quickly confirm whether the user's response is correct at the cognitive and information transmission level, which is the preliminary means of information verification, laying the foundation for subsequent more complex voiceprint consistency authentication.

[0045] The second authentication result described above is the result of the system judging whether the voiceprint feature in the user's speech information is consistent with the preset voiceprint feature stored in the voiceprint database through voiceprint comparison. The second authentication result is directly related to the user's biometric feature, i.e. the voiceprint. The second authentication result goes deep into the voice nature attribute that the user cannot easily change, and is used to confirm whether the operator is the corresponding user. This deep-level information verification enhances the reliability and security of authentication.

[0046] In an optional embodiment, during the voice content authentication, a deep learning model, such as a long short-term memory network model, is used to recognize and transcribe the preset information read by the user. First, the voice information is converted into time-frequency features, such as mel-frequency cepstral coefficients, and then input into the trained deep learning model. The model outputs the text information, which is compared with the preset information to obtain the first authentication result. In the voiceprint feature authentication, the deep learning model used extracts the voiceprint features in the voice, which are compared with the reference voiceprint stored in the voiceprint database to obtain the second authentication result based on the similarity score.

[0047] In another optional embodiment, the voice content authentication uses a hidden Markov model to decode the input voice signal and compare it with the preset information to obtain the authentication result of the voice content. The voiceprint feature authentication uses a Gaussian mixture model to convert the voice signal of the user into acoustic features, such as mel-frequency cepstrum, and then compares it with the user's personal Gaussian mixture model (voiceprint feature). At the same time, a general background model is used as a reference benchmark for voiceprint authentication scoring to obtain the second authentication result.

[0048] Step S108, based on the first authentication result and the second authentication result, generates the target authentication result.

[0049] The target authentication result described above is the final conclusion of the information authentication obtained by comprehensively judging the first authentication result and the second authentication result. The target authentication result determines whether the user can pass the current security authentication process. The target authentication result can comprehensively consider the consistency of the voice content and the matching of the voiceprint features, realizing a double authentication security mechanism. This result can be used to determine whether to grant the user's rights, which is an important content to protect software services and network security.

[0050] In an optional embodiment, the voice content (first authentication result) and voiceprint feature (second authentication result) can be integrated using a decision tree fusion strategy. A decision tree model is pre-trained, and the input of the model includes the numerical scores of the two authentication results. The nodes inside the model are split according to predefined thresholds and logical rules, for example, when the similarity score of the voice content is higher than a certain threshold and the matching degree of the voiceprint feature also meets the standard, the decision tree will follow the positive path and finally output the target authentication result of authentication success at the leaf node. Otherwise, the negative path is followed to output the result of authentication failure.

[0051] In another alternative embodiment, a comprehensive evaluation can be made by using a probability model, taking the first authentication result and the second authentication result as independent events, combining the prior probability and the conditional probability, and calculating the posterior probability. For example, assuming that the prior accuracy rate of voice content recognition is 95%, and the prior accuracy rate of voiceprint feature matching is 90%. According to the evidence in the current authentication process, such as the score and the matching degree, these prior probabilities are updated, and finally the probability score of the target authentication result is obtained by calculating the product of the two independent events and the normalization factor. If the comprehensive probability score exceeds the set threshold, the authentication is considered to be passed.

[0052] In the embodiment of the application, in response to the processing environment being safe, the preset information is output, and after receiving the voice information returned for the preset information, the voice information is recognized to obtain voice content in the voice information and a voiceprint feature corresponding to the voice information, then the voice content is authenticated based on the preset information to obtain a first authentication result, and the voiceprint feature is authenticated to obtain a second authentication result, thereby generating a target authentication result based on the first authentication result and the second authentication result. The application first ensures that the preset information is output only after the processing environment is safe, ensuring that information authentication is performed in a safe and reliable environment, and then voice content and a voiceprint feature are obtained by recognizing returned voice information, so that the voice content is authenticated using the preset information, and the voiceprint feature is authenticated, and the final target authentication result is obtained through a double authentication mechanism, improving the security of information authentication and achieving the purpose of protecting information security, thereby realizing the technical effect of improving the security of information authentication, and further solving the technical problem of poor information security caused by invalid information authentication in related technologies.

[0053] Optionally, the voice information is recognized to obtain voice content in the voice information and a voiceprint feature corresponding to the voice information, including: performing semantic recognition on the voice information to obtain the voice content; and performing voiceprint feature extraction on the voice information to obtain the voiceprint feature.

[0054] In an alternative embodiment, the process of double processing of the voice information provided by the user. Through semantic recognition technology, voice signals can be converted into text form, ensuring that the specific information conveyed by the user can be understood. The voiceprint feature extraction step focuses on analyzing the biological features of the voice, i.e. the voiceprint, for subsequent identity verification. This processing method ensures accurate communication of information and biological feature verification of personal identity, providing a comprehensive authentication basis for the system. In this way, semantic recognition ensures the authenticity and integrity of voice information content, while voiceprint feature extraction provides a data basis for non-password authentication of personal identity, and the combination of the two can effectively prevent password guessing and information leakage, enhancing information security and user experience.

[0055] Optionally, the voice content is authenticated based on the preset information to obtain a first authentication result, including: converting the preset information into a preset string; converting the voice content into a voice string; and comparing the preset string and the voice string to obtain the first authentication result.

[0056] The voice string is a result of converting the voice content into a text format by the system. The voice string can be a string composed of numbers or letters, facilitating subsequent text comparison and processing. The voice string is an abstract representation of the voice content, reducing the complexity of the voice itself and converting it into a data format that can be directly processed. By comparing it with the preset string form of the preset information, the accuracy of the user's repetition can be quickly and accurately verified.

[0057] In an optional embodiment, the preset information is first converted into a preset string form, and then the voice content input by the user is also converted into a corresponding voice string. The comparison result of the two strings will directly determine the first result of information authentication, i.e., the first authentication result. By comparing the preset string and the voice string, the accuracy of the voice content is verified. Through format conversion and comparison, it is ensured that the information conveyed by the user is consistent with the expectation, and this step is the basis of the entire authentication process, ensuring the effectiveness of subsequent voiceprint feature extraction and authentication. And prevent information input errors, thereby improving security and accuracy.

[0058] Optionally, the voiceprint feature is authenticated to obtain a second authentication result, including: obtaining identification information; based on the identification information, querying the preset voiceprint feature corresponding to the identification information from the voiceprint database; and comparing the voiceprint feature with the preset voiceprint feature to obtain the second authentication result.

[0059] The identification information is a data element used to uniquely identify the user's identity. The identification information is a key bridge connecting the user and the personal profile in the system. In the voiceprint recognition system, the identification information ensures that each voiceprint feature query and comparison can accurately locate the correct user record, thereby achieving efficient and accurate identity verification. The type of identification information can include but is not limited to user identification, which can be a unique number generated or assigned by the system; an electronic mailbox for account login and information confirmation; a username; a biological feature identification, which can be a unique identification generated by combining biological features such as fingerprints and facial features. The identification information ensures that each authentication is performed on the correct user, avoiding identity confusion. In a large voiceprint database, the identification information is used as an index to quickly and accurately locate the voiceprint record of a specific user, improving the speed and efficiency of authentication. And through effective identification information management, the privacy and security of user data can be protected, preventing unauthorized access or data leakage.

[0060] The voiceprint database is a database storing the mapping relationship between the user identification information and the corresponding voiceprint features. The voiceprint database is used for querying and storing the voiceprint features in the information verification process, and for updating and maintaining the voiceprint features. The voiceprint database stores the voiceprint feature archives of the users, so that the system can quickly retrieve the user information, compare the voiceprint features, and complete the consistency authentication of the voiceprint when the user performs the identity verification. In addition, it also supports periodic updating of the voiceprint features, ensuring the timeliness and accuracy of the voiceprint data and maintaining the effectiveness of the authentication mechanism.

[0061] In an optional embodiment, the comparison authentication focusing on the voiceprint features is performed. First, the user identification information is obtained, which can be actively provided in the registration process or obtained through cross-platform calling. Then, the preset voiceprint features matching the identification information in the voiceprint database are queried. By comparing the real-time obtained voiceprint features with the preset voiceprint features, the system can obtain the second authentication result, i.e., the biometric authentication result of the user identity. The comparison authentication of the voiceprint features ensures the biometric consistency of the identity verification, so that even if the information is leaked, this layer of authentication can prevent unauthorized access. In addition, by utilizing the uniqueness of the voiceprint of each person, an identity verification method that is difficult to imitate is provided, enhancing the security and reliability of the system.

[0062] Optionally, the above method further includes: in response to the first authentication result being that the voice content is consistent with the preset information, repeatedly performing the steps of outputting the preset information and receiving the voice information returned for the preset information until the number of received voice information reaches a preset number; comparing the similarity of the preset number of voice information to obtain a comparison result, wherein the comparison result is used to represent whether the similarity of the preset number of voice information is greater than a preset threshold; in response to the comparison result being that the similarity of the preset number of voice information is greater than the preset threshold, determining the preset voiceprint features based on the preset number of voice information; and storing the mapping relationship between the preset voiceprint features and the identification information in the voiceprint database.

[0063] The comparison result refers to the result of comparing the similarity of the voiceprint features in the collected voice information to determine whether they come from the same person after sufficient voice information is collected. The comparison result is a key verification step in the voiceprint model establishment process. By collecting the voice information of the user multiple times and comparing the voiceprint features, it can be ensured that the creation of the preset voiceprint features of the user is based on the real voiceprint data of the user, rather than accidentally similar samples. This process effectively avoids security vulnerabilities caused by single misidentification, and is an indispensable part of the creation and updating of voiceprint features.

[0064] In an optional embodiment, after the first authentication result is passed, the preset information is repeatedly output and the returned voice information is received until a preset number of voice samples are collected. Then, similarity comparison is performed on the preset number of voice information, and if the similarity exceeds a preset threshold, it is considered that the voiceprint feature is successfully established or updated, so as to map the voiceprint feature and the user identification information and store them in the voiceprint database. Dynamic establishment and update of the voiceprint feature can adapt to natural changes of the user's voice, such as changes in health status, etc., ensuring the long-term accuracy and effectiveness of the voiceprint database.

[0065] Optionally, the above method further comprises: in response to the target authentication result being pass information authentication, detecting the update time of the voiceprint database; in response to the update time being greater than a preset time period, adjusting the preset voiceprint feature based on the voice information to obtain a new preset voiceprint feature; and storing the mapping relationship between the new preset voiceprint feature and the identification information in the voiceprint database.

[0066] In an optional embodiment, since the voice feature may change as the user's health status changes, the preset voiceprint feature can be updated periodically. When the target authentication result is passed, the update time of the voiceprint database can be checked. If the update time exceeds the preset time period, the preset voiceprint feature is adjusted using the latest voice information to generate a new preset voiceprint feature, which is updated to the voiceprint database to maintain the timeliness and accuracy of the voiceprint feature. By periodically updating the voiceprint feature, long-term changes in the user's voice can be adapted to, ensuring the continuous effectiveness and accuracy of the preset voiceprint feature. This mechanism enhances the adaptability and security of the system, reduces the misrecognition rate caused by the aging of the voiceprint feature, and maintains the security and reliability of user authentication.

[0067] Optionally, the above method further comprises: in response to the target authentication result being unpass information authentication, determining a risk level based on the identification information; authenticating the voice information using an authentication method corresponding to the risk level to obtain a third authentication result, wherein the third authentication result is used to represent whether the voice information passes the authentication; and in response to the voice information passing the authentication, storing the voiceprint feature as the preset voiceprint feature in the voiceprint database.

[0068] The third authentication result described above can be the final verification state obtained by additional authentication based on the risk level of the user identification information after the target authentication result is unpassed, i.e., the user's first voice content or voiceprint feature authentication fails. This result integrates more stringent or alternative authentication methods to verify the authenticity of the user's identity. The authentication method on which the third authentication result is based can be fingerprint or face recognition, or require the user to input a reserved password or answer a security question, or confirm whether the user uses a pre-registered device to attempt.

[0069] In an optional embodiment, when the target authentication result fails, the risk level of the user can be determined based on the user identification information, and an additional authentication method can be adopted based on the risk level to obtain a third authentication result. This process enhances the response capability of the system when facing potential security threats, ensuring that appropriate measures are taken even in complex or high-risk scenarios, providing additional information protection. The risk level assessment and the introduction of additional authentication mechanisms provide a dynamic security protection layer for the system, which can adjust the authentication strategy according to different security conditions. Not only does it improve security, but it also provides users with multi-level authentication opportunities, ensuring that user access is not improperly denied even in the case of initial authentication failure.

[0070] Optionally, the above method further includes one of the following: determining whether the identification information is included in a preset whitelist, obtaining a detection result, wherein the detection result is used to represent whether the processing environment is safe; performing anomaly detection based on the processing information, obtaining a detection result.

[0071] In an optional embodiment, the detection result can be obtained by checking the preset whitelist to determine whether the user identification information is associated with known risks. The detection result is the basis for determining whether the user's behavior is abnormal, and determines the level of subsequent authentication process. Environmental safety detection provides a comprehensive security perspective for the information authentication process, which can actively identify and respond to potential threats such as device tampering, login location anomalies, etc. If an environmental anomaly is detected, a higher level of authentication process can be triggered, such as secondary biometric verification, sending a verification code to a reserved email, etc., to ensure that the correct user is performing the operation. This enhances security and provides a more secure and reliable use environment for users.

[0072] In another optional embodiment, abnormal behavior is monitored based on the user's processing information. By analyzing the user's processing information, such as login time, login location, device information, etc., abnormal activities that deviate from normal behavior patterns can be identified. This can detect potential security threats before the user performs authentication or operations, thereby improving the overall security and response speed of the information authentication process. This provides a security check for the entire authentication process, ensuring that it can maintain its security and stability in a highly dynamic and complex environment, while protecting users from potential security threats.

[0073] According to an embodiment of the present application, a system embodiment of an information authentication system is provided. It should be noted that the device can be used to execute the above-mentioned information authentication method, and the specific implementation scheme and application scenario in this embodiment are the same as those in the above-mentioned embodiments, which will not be repeated here.

[0074] Figure 2 is a schematic diagram of an information authentication system according to an embodiment of the present application,Figure 2 As shown, the device comprises the following:

[0075] The acquisition module 20 is configured to output preset information and receive voice information returned in response to the security of the processing environment.

[0076] The recognition module 22 is configured to recognize the voice information to obtain voice content in the voice information and a voiceprint feature corresponding to the voice information.

[0077] The authentication module 24 is configured to authenticate the voice content based on the preset information to obtain a first authentication result, and authenticate the voiceprint feature to obtain a second authentication result, wherein the first authentication result is used to represent whether the voice content is consistent with the preset information, and the second authentication result is used to represent whether the voiceprint consistency authentication is passed.

[0078] The generation module 26 is configured to generate a target authentication result based on the first authentication result and the second authentication result.

[0079] The embodiment provides an information authentication system, which outputs preset information and receives voice information returned by a user in response to the security state of a processing environment through an acquisition module, and realizes non-active and silent authentication of the identity of the user. A recognition module performs content recognition and voiceprint feature extraction on the received voice information to obtain voice content and a voiceprint feature, respectively, and then an authentication module matches the voice content based on preset information to obtain a first authentication result, and simultaneously performs consistency authentication on the voiceprint feature to obtain a second authentication result. Finally, a generation module generates a target authentication result based on the two authentication results, which is used to determine whether the information authentication is passed. This not only improves the concealment and security of the recognition, but also enhances the user experience and avoids the shortcomings that the traditional authentication methods are easy to be cracked or bypassed.

[0080] Optionally, the system further comprises an environment detection module configured to determine whether the identification information is included in a preset list library to obtain a detection result, wherein the detection result is used to represent whether the processing environment is safe, or perform abnormal detection based on the processing information to obtain a detection result.

[0081] The information authentication system integration environment detection module is used to determine whether the identification information is included in the preset list library, and a detection result is obtained, wherein the detection result is used to represent whether the processing environment is safe; or, based on the processing information, an abnormality detection is performed, and a detection result is obtained. This can improve the security of the information processing environment by checking whether the identification information of the user equipment exists in the preset list library or analyzing the processing information such as the running state of the equipment and the user behavior mode to identify potential abnormalities and risks. The running mechanism of the environment detection module can effectively prevent information processing in an unsafe or abnormal environment, and provides a more reliable basis for subsequent voiceprint recognition and dynamic verification. Through the environment detection module, it is ensured that information authentication is performed only in a safe environment, thereby protecting the privacy and account security of the user.

[0082] Optionally, the identification module is further configured to perform semantic recognition on the voice information to obtain voice content; and perform voiceprint feature extraction on the voice information to obtain a voiceprint feature.

[0083] Optionally, the authentication module is further configured to perform format conversion on the preset information to obtain a preset string; perform format conversion on the voice content to obtain a voice string; and compare the preset string and the voice string to obtain a first authentication result.

[0084] Optionally, the authentication module is further configured to obtain the identification information; query, based on the identification information, a preset voiceprint feature corresponding to the identification information from a voiceprint database; and compare the voiceprint feature and the preset voiceprint feature to obtain a second authentication result.

[0085] Optionally, the system further includes a voiceprint database module configured to, in response to the first authentication result being that the voice content is consistent with the preset information, repeatedly perform the steps of outputting the preset information and receiving voice information returned for the preset information until the number of received voice information reaches a preset number; performing similarity comparison on the preset number of voice information to obtain a comparison result, wherein the comparison result is used to represent whether the similarity of the preset number of voice information is greater than a preset threshold; in response to the comparison result being that the similarity of the preset number of voice information is greater than the preset threshold, determining a preset voiceprint feature based on the preset number of voice information; and storing a mapping relationship between the preset voiceprint feature and the identification information in the voiceprint database.

[0086] Optionally, the system further includes an update module configured to, in response to the target authentication result being that the information authentication is passed, detect an update time of the voiceprint database; in response to the update time being greater than a preset time period, adjust the preset voiceprint feature based on the voice information to obtain a new preset voiceprint feature; and store a mapping relationship between the new preset voiceprint feature and the identification information in the voiceprint database.

[0087] Optionally, the updating module is further configured to: determine a risk level based on the identification information in response to the target authentication result being the non-pass information authentication result; perform authentication on the voice information by using an authentication manner corresponding to the risk level to obtain a third authentication result, wherein the third authentication result is used to represent whether the voice information passes the authentication; and store the voiceprint feature as a preset voiceprint feature in the voiceprint database in response to the voice information passing the authentication.

[0088] The technical solution proposed in the present application is described below in combination with an optional embodiment. The present application proposes a non-active identity recognition method.

[0089] The method adopts a silent voiceprint retention mode. In the first registration and login link, a dynamic voice digital code verification is added, and the user reads the generated dynamic digital code to confirm. After the digital verification, the voiceprint retention is performed silently, and a voiceprint model is established for the user. In the subsequent high-risk information processing link, a dynamic voice digital code verification is added. At this time, in addition to the digital verification, voiceprint authentication is also performed to verify whether it is the user's operation.

[0090] In the silent voiceprint retention link, to prevent others from being retained due to non-personal operation, a dynamic voice digital code verification is added in the first registration and real-name authentication link. When the traditional risk control means does not detect the risk, multiple voiceprints are retained, and the similarity between the two is compared after 4-6 voiceprints are retained. If they are all judged to be the same person, the voiceprint is retained and bound to the user.

[0091] If it is judged to be a different person in the voiceprint retention and authentication link based on the digital voice dynamic code, it is added as one of the risk factors for risk control verification. The security verification can be performed to improve the security of information processing. If the final verification is passed, the voiceprint is updated as the user's voiceprint.

[0092] In this way, the authentication method is performed in a natural way such as reading, without the need for active reservation environment. Compared with the traditional voiceprint authentication and face authentication, which need to be registered in advance, the authentication method disturbs the user. In addition, in the entire reading link, the voiceprint authentication recognition is not displayed, and it is difficult to find the non-personal verification mechanism, which can reduce the targeted attack. As a non-personal authentication method, the voiceprint authentication, which is a feature only owned by the user himself, can well ensure its reliability. The verification methods such as the short message verification code held by the user may be leaked, so the voiceprint biological feature authentication method is more reliable and safer. At present, the face has been regarded as an unsafe authentication means due to the maturity of image generation technology. Moreover, the dynamic reading interactive method does not require the user to record the password or check the short message, and uses a very natural interactive means, which is good for user experience.

[0093] Specifically, the method can include the following steps when applied.

[0094] In the voiceprint retention step, when the user performs the first account registration and user identity recognition, the comprehensive risk discrimination module discriminates whether the current environment is safe. The discrimination content mainly includes: whether the current device environment is normal, whether the Internet protocol address, media access control address, etc. hit the preset database, and gives a comprehensive discrimination result. If there is a risk in the registration step, the security verification module is called for verification according to the discrimination risk level. If it passes, the dynamic voice verification module is called to generate and display a dynamic voice digital code, guiding the user to read the generated 4-6 digit number, and performing reading matching. If the dynamic voice verification passes, the voiceprint recognition module is called to retain the voiceprint features. In the subsequent real-name authentication step and login step, the dynamic voice verification module and the voiceprint recognition module can be called as needed to verify the dynamic verification code and retain the voiceprint until the voiceprint retention voice is sufficient for model creation, generally 4-6. After the number of voiceprints that meet the voiceprint model creation is met, the voiceprint model is retained, and the corresponding user is bound.

[0095] In the voiceprint verification step, when performing online services, the comprehensive risk discrimination module comprehensively discriminates the device environment, processing environment, and operation behavior. If it is identified that there is an abnormal risk, the security verification module is used for security verification according to the risk disposal rules. For dynamic voice verification, after verifying whether the reading is accurate, it is also necessary to verify whether the voiceprint is consistent with the reserved one. If the reading is incorrect, the user can be guided to retry within a limited number of times (generally 3 times), and if the voiceprint verification is successful, it is considered to pass.

[0096] In the voiceprint update step, because the silent voiceprint retention method is adopted, no active voiceprint retention portal is developed for users, so in order to ensure the sustainable update of the voiceprint, a voiceprint update mechanism needs to be introduced, which is as follows: the voiceprint recognition module sets an update frequency for each voiceprint model, such as 3 months. If the next voiceprint recognition of the user is successful, it is determined whether the model update time of the user exceeds the specified update frequency. If it exceeds, the voiceprint of this time is combined with the latest retained voiceprint information to generate the voiceprint model of the user and update the retention. For the interaction of dynamic digital voice verification failure, a feedback mechanism is established. After the failure, other security verifications are triggered, and if the final authentication is successful, it is considered to be the user's operation behavior, and the voiceprint feature of this time is retained to update the voiceprint of the user.

[0097] The technical scheme provided in the present application is described below in combination with an optional embodiment, and the present application also provides a non-active identity recognition system. The system comprises: a comprehensive risk judgment module, configured to identify the credibility of a current processing environment and whether it is in a safe environment; a dynamic voice verification module, configured to generate a dynamic number for human-computer verification and to perform semantic conversion on the voice of a user and match whether it is the corresponding generated dynamic number; a voiceprint recognition module, configured to analyze the voice, generate voiceprint features, and have voiceprint retention, comparison and updating capabilities, and also have voiceprint splicing, recording and other security detection capabilities; a security verification module, configured to, for an information processing process determined to be risky, give a risk control strategy according to the risk level, such as providing a security verification means or performing rejection; and a voiceprint library module, configured to encrypt and store the retained voiceprint features and bind them with a user identifier.

[0098] Embodiments of the present application also provide an electronic device, comprising: a memory storing an executable program; and a processor configured to run the program, wherein the program, when running, performs the method in each of the embodiments of the present application.

[0099] Embodiments of the present application also provide a computer-readable storage medium, comprising a stored executable program, wherein the executable program, when running, controls a device where the computer-readable storage medium is located to perform the method in each of the embodiments of the present application.

[0100] Embodiments of the present application also provide a computer program product, comprising a computer program, which, when executed by a processor, implements the method in each of the embodiments of the present application.

[0101] Embodiments of the present application also provide a computer program product, comprising a non-volatile computer-readable storage medium, which is configured to store a computer program, and the computer program, when executed by a processor, implements the method in each of the embodiments of the present application.

[0102] Embodiments of the present application also provide a computer program, which, when executed by a processor, implements the method in each of the embodiments of the present application.

[0103] In the above embodiments of the present application, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0104] In several embodiments provided in the present application, it should be understood that the disclosed technology can be implemented by other means. Among them, the above-mentioned device embodiments are only schematic, for example, the division of the units can be a logical function division, and actual implementation can have another division mode, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be through some interface, indirect coupling or communication connection between units or modules, which can be electrical or other forms.

[0105] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or they can be distributed to multiple units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0106] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically, or two or more units can be integrated into one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0107] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0108] The above is only the preferred embodiment of the present application, and it should be pointed out that for ordinary skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements should be considered as the protection scope of the present application.

Claims

1. An information authentication method, characterized in that, include: In response to environmental safety, it outputs preset information and receives voice information returned in response to the preset information; The speech information is identified to obtain the speech content in the speech information and the corresponding voiceprint features; The voice content is authenticated based on the preset information to obtain a first authentication result, and the voiceprint features are authenticated to obtain a second authentication result. The first authentication result is used to characterize whether the voice content is consistent with the preset information, and the second authentication result is used to characterize whether the voiceprint consistency authentication is passed. Based on the first authentication result and the second authentication result, a target authentication result is generated.

2. The method according to claim 1, characterized in that, The speech information is recognized to obtain the speech content and the corresponding voiceprint features, including: The speech information is semantically recognized to obtain the speech content; The voiceprint features are extracted from the voice information to obtain the voiceprint features.

3. The method according to claim 1, characterized in that, The voice content is authenticated based on the preset information to obtain a first authentication result, including: The preset information is formatted to obtain a preset string; The audio content is format-converted to obtain an audio string; The preset string and the voice string are compared to obtain the first authentication result.

4. The method according to claim 1, characterized in that, The voiceprint features are authenticated to obtain a second authentication result, including: Obtain identification information; Based on the identification information, query the preset voiceprint feature corresponding to the identification information from the voiceprint database; The voiceprint feature is compared with the preset voiceprint feature to obtain the second authentication result.

5. The method according to claim 4, characterized in that, The method further includes: In response to the first authentication result being that the voice content is consistent with the preset information, the steps of outputting the preset information and receiving voice information returned in response to the preset information are repeated until the number of received voice information reaches a preset number. The preset number of voice information is compared for similarity to obtain a comparison result, wherein the comparison result is used to characterize whether the similarity of the preset number of voice information is greater than a preset threshold. In response to the comparison result that the similarity of the preset number of voice information is greater than a preset threshold, the preset voiceprint feature is determined based on the preset number of voice information; The mapping relationship between the preset voiceprint features and the identification information is stored in the voiceprint database.

6. The method according to claim 4, characterized in that, The method further includes: In response to the target authentication result being successful, the update time of the voiceprint database is detected; In response to the update time being greater than a preset time period, the preset voiceprint features are adjusted based on the voice information to obtain new preset voiceprint features; The mapping relationship between the new preset voiceprint features and the identification information is stored in the voiceprint database.

7. The method according to claim 4, characterized in that, The method further includes: In response to the target authentication result being a failed information authentication, the risk level is determined based on the identification information; The voice information is authenticated using the authentication method corresponding to the risk level to obtain a third authentication result, wherein the third authentication result is used to characterize whether the voice information has passed authentication; In response to the voice information being authenticated, the voiceprint features are stored as preset voiceprint features in the voiceprint database.

8. The method according to any one of claims 1-7, characterized in that, The method also includes one of the following: Determine whether the identification information is included in the preset list database to obtain a detection result, wherein the detection result is used to characterize whether the processing environment is secure; Anomaly detection is performed based on the processed information to obtain the detection results.

9. An information authentication system, characterized in that, include: The acquisition module is used to respond to environmental safety by outputting preset information and receiving voice information returned in response to the preset information; The recognition module is used to recognize the voice information to obtain the voice content in the voice information and the voiceprint features corresponding to the voice information; An authentication module is used to authenticate the voice content based on the preset information to obtain a first authentication result, and to authenticate the voiceprint features to obtain a second authentication result. The first authentication result is used to characterize whether the voice content is consistent with the preset information, and the second authentication result is used to characterize whether the voiceprint consistency authentication is passed. The generation module is used to generate a target authentication result based on the first authentication result and the second authentication result.

10. The system according to claim 9, characterized in that, The system also includes: An environment detection module is used to determine whether the preset list database contains identification information and obtain a detection result, wherein the detection result is used to characterize whether the processing environment is safe; or, based on the processing information, anomaly detection is performed to obtain the detection result.

11. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, performs the method according to any one of claims 1 to 8.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the storage medium is located to perform the method according to any one of claims 1 to 8.

13. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 8.

Images