CN109657444B - Security verification method and device, storage medium and terminal - Google Patents
Security verification method and device, storage medium and terminal Download PDFInfo
- Publication number
- CN109657444B CN109657444B CN201811643560.3A CN201811643560A CN109657444B CN 109657444 B CN109657444 B CN 109657444B CN 201811643560 A CN201811643560 A CN 201811643560A CN 109657444 B CN109657444 B CN 109657444B
- Authority
- CN
- China
- Prior art keywords
- user
- answer
- voiceprint
- question
- standard
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/22—Interactive procedures; Man-machine interfaces
Abstract
A security verification method and device, a storage medium and a terminal are provided, wherein the security verification method comprises the following steps: receiving a question input by a user, and searching an answer according to the question; responding to the searched answer belonging to a preset safety category, and extracting the voiceprint features of the user; determining standard voiceprint features corresponding to the searched answers, and comparing the voiceprint features of the user with the searched standard voiceprint features; and displaying the searched answer to the user in response to the voiceprint features of the user being consistent with the standard voiceprint features. The technical scheme of the invention can improve the safety of answer check.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a security verification method and apparatus, a storage medium, and a terminal.
Background
In a question-and-answer scenario, such as in the field of intelligent customer service, it is common to answer user questions based on a knowledge base.
In the prior art, the knowledge base comprises a plurality of knowledge points, each of which comprises a standard question and an answer. Once the user's question matches the standard question in the knowledge base, the answer corresponding to the standard question is pushed to the user.
However, for answer data with privacy, how to ensure the safety of the answer is an urgent problem to be solved.
Disclosure of Invention
The invention solves the technical problem of how to improve the safety of answer checking.
In order to solve the above technical problem, an embodiment of the present invention provides a security verification method, where the security verification method includes: receiving a question input by a user, and searching an answer according to the question; responding to the searched answer belonging to a preset safety category, and extracting the voiceprint features of the user; determining standard voiceprint features corresponding to the searched answers, and comparing the voiceprint features of the user with the searched standard voiceprint features; and displaying the searched answer to the user in response to the voiceprint features of the user being consistent with the standard voiceprint features.
Optionally, the determining the corresponding standard voiceprint feature of the searched answer includes: determining at least one user identification corresponding to the searched answer; searching a preset voiceprint library according to the at least one user identifier to determine the voiceprint characteristics corresponding to the user identifiers; and taking the voiceprint features corresponding to the user identifications as the standard voiceprint features.
Optionally, the receiving the question input by the user comprises: determining at least one user identifier corresponding to each answer belonging to the preset safety category; collecting the voice of the user indicated by at least one user identification corresponding to each answer; and extracting the voiceprint features of the collected voice, and correlating the voiceprint features with the user identification and storing the voiceprint features in a preset voiceprint library.
Optionally, the extracting the voiceprint features of the user in response to the searched answer belonging to a preset security category includes: responding to the searched answer belonging to the preset safety category, and sending voice acquisition prompt information to prompt the user to input voice; and receiving the voice input by the user, and extracting the voiceprint features of the user according to the voice of the user.
Optionally, the determining the standard voiceprint feature corresponding to the searched answer includes: detecting the safety level of the preset safety category; and in response to that the security level reaches a preset level, determining that the voiceprint features of the user indicated by the plurality of user identifications corresponding to the preset level are the standard voiceprint features.
Optionally, the searching for answers according to the question includes: matching the question with knowledge points in a knowledge base; and determining the answer in the knowledge point matched with the question as the searched answer.
Optionally, the format of the question is selected from voice, picture, video and document; the answer is in a format selected from the group consisting of voice, picture, video, and document.
In order to solve the above technical problem, an embodiment of the present invention further discloses a security verification apparatus, including: the question receiving module is suitable for receiving a question input by a user and searching an answer according to the question; the voiceprint feature extraction module is suitable for responding to the fact that the searched answer belongs to the preset safety category, and extracting the voiceprint features of the user; the voiceprint comparison module is suitable for determining the standard voiceprint characteristics corresponding to the searched answers and comparing the voiceprint characteristics of the user with the searched standard voiceprint characteristics; and the answer display module is suitable for responding to the consistency of the voiceprint characteristics of the user and the standard voiceprint characteristics and displaying the searched answer to the user.
The embodiment of the invention also discloses a storage medium, wherein a computer instruction is stored on the storage medium, and the steps of the safety verification method are executed when the computer instruction runs.
The embodiment of the invention also discloses a terminal which comprises a memory and a processor, wherein the memory is stored with a computer instruction capable of running on the processor, and the processor executes the steps of the security verification method when running the computer instruction.
Compared with the prior art, the technical scheme of the embodiment of the invention has the following beneficial effects:
the technical scheme of the invention receives the questions input by the user and searches answers according to the questions; responding to the searched answer belonging to a preset safety category, and extracting the voiceprint features of the user; determining standard voiceprint features corresponding to the searched answers, and comparing the voiceprint features of the user with the searched standard voiceprint features; and displaying the searched answer to the user in response to the voiceprint features of the user being consistent with the standard voiceprint features. According to the technical scheme, after an answer is searched for a question of a user, under the condition that the type of the answer belongs to a preset safety type, voiceprint characteristics of the user are compared with standard voiceprint characteristics corresponding to the answer, and the answer is displayed to the user under the condition that the voiceprint characteristics and the standard voiceprint characteristics are consistent; the safety of answer checking can be ensured through a voiceprint verification mode.
Further, at least one user identification corresponding to the searched answer is determined; searching a preset voiceprint library according to the at least one user identifier to determine the voiceprint characteristics corresponding to the user identifiers; and taking the voiceprint features corresponding to the user identifications as the standard voiceprint features. In the technical scheme of the invention, the answers in the knowledge base have a corresponding relation with the user identification, and the user identification and the voiceprint characteristics are stored in the preset voiceprint library; therefore, by establishing the association between the answer and the user identification, the data volume needing to be associated can be reduced, the efficiency of searching the voiceprint in the voiceprint library is improved, and the storage resource can be saved.
Drawings
FIG. 1 is a flow chart of a security verification method according to an embodiment of the present invention;
FIG. 2 is a flowchart of one embodiment of step S103 shown in FIG. 1;
fig. 3 is a schematic structural diagram of a security verification apparatus according to an embodiment of the present invention.
Detailed Description
As described in the background art, how to ensure the safety of the answer is an urgent problem to be solved for the answer data with privacy.
The inventor of the present application finds that in the technical field of biometric identification, voiceprint identification is a technology of voice parameters according to physiological and behavioral characteristics of a speaker reflected by a voice waveform. The voiceprint features extracted from the voice can uniquely represent the identity of the speaker, are effective, stable and reliable, and can be used as the basis for identity verification.
According to the technical scheme, after an answer is searched for a question of a user, under the condition that the type of the answer belongs to a preset safety type, voiceprint characteristics of the user are compared with standard voiceprint characteristics corresponding to the answer, and the answer is displayed to the user under the condition that the voiceprint characteristics and the standard voiceprint characteristics are consistent; the safety of answer checking can be ensured through a voiceprint verification mode.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
Fig. 1 is a flowchart of a security verification method according to an embodiment of the present invention.
The security authentication method shown in fig. 1 may include the steps of:
step S101: receiving a question input by a user, and searching an answer according to the question;
step S102: responding to the searched answer belonging to a preset safety category, and extracting the voiceprint features of the user;
step S103: determining standard voiceprint features corresponding to the searched answers, and comparing the voiceprint features of the user with the searched standard voiceprint features;
step S104: and displaying the searched answer to the user in response to the voiceprint features of the user being consistent with the standard voiceprint features.
It should be noted that the sequence numbers of the steps in this embodiment do not represent a limitation on the execution sequence of the steps.
In the implementation of step S101, the question input by the user may be specifically a word input by the user, or may be a text obtained by converting the voice of the user.
In a non-limiting embodiment, step S101 may specifically include the following steps: acquiring the voice of a user; and converting the voice of the user into characters to obtain the question.
In a non-limiting embodiment, when searching for an answer according to the question, the question may be matched with standard questions in a knowledge base, and the answer corresponding to the standard questions matched with the question is the searched answer. Specifically, if there is no standard question matching the question, matching the question with an extended question, and taking an answer corresponding to the extended question matching the question as the searched answer.
In the implementation of step S102, each answer in the knowledge base has a category. For example, answer 1 belongs to preset security class 1, answer 2 belongs to preset security class 2, answer 3 belongs to non-preset security class, and so on. If the searched answer belongs to the preset safety category, the answer is displayed in a safety verification mode, and therefore safety of the answer is guaranteed. In this case, the voiceprint feature of the user can be extracted.
In one non-limiting example, if the format of the question entered by the user is speech, the user's voiceprint features can be extracted directly from the speech.
In another non-limiting example, if the format of the question entered by the user is non-speech, such as text, pictures, etc., the user may be prompted to capture speech and extract voiceprint features of the user using the captured speech.
In a specific implementation, step S102 may include the following steps: responding to the searched answer belonging to the preset safety category, and sending voice acquisition prompt information to prompt the user to input voice; and receiving the voice input by the user, and extracting the voiceprint features of the user according to the voice of the user. The voiceprint feature of the user can be an audio feature parameter, and the user can be uniquely characterized.
Specifically, if the format of the question input by the user is non-voice and the searched answer belongs to a preset security category, the voice collection prompt message may be sent to the terminal used by the user. And receiving the voice fed back by the terminal of the user, and extracting the voiceprint characteristics of the user according to the fed-back voice.
More specifically, for the collected voice, the collected voice may be further subjected to a preprocessing operation. The preprocessing operation may specifically be one or more of the following operations, which performs Haar wavelet transform on the acquired voice to compress the data volume; noise in speech is filtered.
It should be noted that, a specific algorithm and a specific process for extracting the voiceprint feature may refer to the prior art, and are not described in detail herein.
In the specific implementation of step S103 and step S104, the corresponding standard voiceprint feature of the searched answer is determined, and the voiceprint feature of the user is compared with the standard voiceprint feature. And displaying the searched answer to the user in response to the consistency of the voiceprint features and the standard voiceprint features.
Specifically, comparing the voiceprint feature of the user with the standard voiceprint feature may refer to calculating a similarity between the voiceprint feature and the standard voiceprint feature.
It can be understood by those skilled in the art that the process of calculating the similarity between two voiceprints can refer to the prior art, and the embodiment of the present invention is not limited thereto.
In a non-limiting embodiment of the present invention, the number of the standard voiceprint features corresponding to the searched answer may be one, and the agreement between the voiceprint features and the standard voiceprint features means that the similarity between the voiceprint features and the standard voiceprint features reaches a preset threshold. For example, similarity is a normalized coefficient, and similarity in the range (0-0.30) indicates that the voiceprint feature is micro-correlated with the standard voiceprint feature; similarity in the range (0.30-0.50) indicates that the voiceprint feature correlates with the standard voiceprint feature indication; similarity in the range (0.50-0.80) indicates that the voiceprint features are significantly correlated with the standard voiceprint features; similarity in the range (0.80-1) indicates that the voiceprint feature is highly correlated with the standard voiceprint feature; the preset threshold may be set to 0.8, i.e. the case where the voiceprint feature is highly correlated with the standard voiceprint feature indicates that the voiceprint feature is consistent with the standard voiceprint feature.
In a non-limiting embodiment of the present invention, the number of the standard voiceprint features corresponding to the searched answer may be multiple, in which case, the voiceprint features of multiple users need to be collected and compared with the multiple standard voiceprint features respectively. The consistency of the voiceprint features and the standard voiceprint features means that the voiceprint features of a plurality of users all have the standard voiceprint features with the similarity reaching a preset threshold.
It is understood that if the searched answer belongs to a non-preset security category, the answer may be directly presented to the user.
In one non-limiting embodiment of the present invention, the question is in a format selected from the group consisting of voice, picture, video, and document; the answer is in a format selected from the group consisting of voice, picture, video, and document.
In this embodiment, the format of the question input by the user may be one or more of voice, picture, video, and document, so that convenience in user input can be realized. For the problems in the original format, the problems can be uniformly converted into the text format, and then the answers are searched by using the problems with the text format.
The format of the answer displayed to the user can be one or more of voice, pictures, videos and documents, so that the diversity and richness of the feedback to the user are realized. Accordingly, the format of the answers in the knowledge points stored in the knowledge base may also be selected from the group consisting of voice, picture, video, and document.
In one embodiment of the present invention, the answers in the knowledge base correspond to standard voiceprint features, that is, each answer in the knowledge base corresponds to at least one standard voiceprint feature. Specifically, the knowledge base may store the answer and the identifier of the standard voiceprint feature corresponding to the answer. The preset voiceprint library can store the identification of the standard voiceprint features and the voiceprint features indicated by the standard voiceprint features. For example, for answer 1 in the knowledge base, the corresponding standard voiceprint feature is identified as a; for answer 2, its corresponding standard voiceprint feature is identified as b.
Step S103 shown in fig. 1 may include the following steps: determining the identifier of the standard voiceprint feature corresponding to the searched answer; and searching a preset voiceprint library according to the identifier of the standard voiceprint feature to determine the standard voiceprint feature, wherein the identifier of the plurality of standard voiceprint features and the pointed standard voiceprint feature thereof are stored in the preset voiceprint library.
In a non-limiting embodiment of the present invention, the answer corresponds to the user identifier. The preset voiceprint library stores the user identification and the corresponding voiceprint characteristics. And presetting a voiceprint characteristic corresponding to each user identifier in the voiceprint library.
Specifically, the knowledge base may store the answer and the corresponding user identifier.
Referring to fig. 2, step S103 shown in fig. 1 may include the following steps:
step S201: determining at least one user identification corresponding to the searched answer;
step S202: searching a preset voiceprint library according to the at least one user identifier to determine the voiceprint characteristics corresponding to the user identifiers;
step S203: and taking the voiceprint features corresponding to the user identifications as the standard voiceprint features.
In particular, the user identification may be a character or a string of characters to indicate the user. The correspondence between the answer and the at least one user identifier corresponding thereto may be preset. For example, for answer 1 in the knowledge base, the corresponding user identifier is user a; for answer 2, its corresponding user identification is user B.
Therefore, when the standard voiceprint features corresponding to the searched answers are determined, the user identifications corresponding to the searched answers can be determined firstly. And matching the user identification with each user identification in a preset voiceprint library, and determining the matched voiceprint characteristics in the preset voiceprint library as standard voiceprint characteristics.
In the embodiment of the invention, the answers in the knowledge base have a corresponding relation with the user identification, the user identification and the voiceprint characteristics are stored in the preset voiceprint base, and a plurality of answers possibly correspond to the same user identification; therefore, by establishing the association between the answer and the user identification, the data volume needing to be associated can be reduced, the efficiency of searching the voiceprint in the voiceprint library is improved, and the storage resource can be saved.
In a non-limiting embodiment of the present invention, step S101 shown in fig. 1 may be preceded by the following steps: determining at least one user identifier corresponding to each answer belonging to the preset safety category; collecting the voice of the user indicated by at least one user identification corresponding to each answer; and extracting the voiceprint features of the collected voice, and correlating the voiceprint features with the user identification and storing the voiceprint features in a preset voiceprint library.
The present embodiment may construct a preset voiceprint library. Specifically, as described above, the answers belonging to the preset security category correspond to the standard voiceprint features, and when the knowledge base is constructed, at least one user identifier corresponding to each answer belonging to the preset security category may be determined first. And determining the user indicated by the at least one user identification and collecting the voice of the user. The voiceprint features of the voices of the respective users are extracted as standard voiceprint features.
And the standard voiceprint features in the preset voiceprint library have an association relation with the user identification. For example, the user identifier a corresponds to the standard voiceprint feature a, and the user identifier B corresponds to the standard voiceprint feature B.
In a specific implementation, the process of collecting the voice of the user may be to obtain voice data of each user by crawling from other devices or a local database. Or sending prompt information to the user terminal used by each user and receiving the voice fed back by the user terminal.
More specifically, for the collected voice, the collected voice may be further subjected to a preprocessing operation. The preprocessing operation may specifically be one or more of the following operations, which performs Haar wavelet transform on the acquired voice to compress the data volume; noise in speech is filtered.
In a preferred embodiment of the present invention, step S103 shown in fig. 1 may include the following steps: detecting the safety level of the preset safety category; and in response to that the security level reaches a preset level, determining that the voiceprint features of the user indicated by the plurality of user identifications corresponding to the preset level are the standard voiceprint features.
In this embodiment, the preset security category may include a plurality of security levels, and the higher the security level is, the higher the security of the answer belonging to the security level is. And when the security level reaches a preset level, the answers belonging to the preset level correspond to a plurality of standard voiceprint features.
In specific implementation, when the security level reaches a preset level, a plurality of user identifiers may be determined, and a plurality of standard voiceprint features may be determined according to the plurality of user identifiers. The plurality of standard voiceprint features correspond to the searched answer.
Further, when comparing the voiceprint features of the users with the standard voiceprint features, the voiceprint features of a plurality of users need to be collected according to the number of the standard voiceprint features and are compared respectively, so that the verification safety is improved.
In a preferred embodiment of the present invention, step S101 shown in fig. 1 may include the following steps: matching the question with knowledge points in a knowledge base; and determining the answer in the knowledge point matched with the question as the searched answer.
In this embodiment, the knowledge points in the knowledge base may be preset, and specifically, the corresponding knowledge points may be configured according to an actual application scenario. By matching the question with questions (e.g., standard questions and/or extended questions) in the knowledge point, answers to the questions may be determined.
Further, as described above, the knowledge base may further include an identifier of a standard voiceprint feature corresponding to the answer, or an identifier of the user corresponding to the answer, which is not limited in this embodiment of the present invention.
For more details of the knowledge base, reference may be made to the prior art, and the embodiments of the present invention are not limited thereto.
Referring to fig. 3, the embodiment of the invention further discloses a security verification device 30. The security authentication device 30 includes: the system comprises a question receiving module 301, a voiceprint feature extraction module 302, a voiceprint comparison module 303 and an answer presentation module 304.
The question receiving module 301 is adapted to receive a question input by a user and search for an answer according to the question; the voiceprint feature extraction module 302 is adapted to extract voiceprint features of the user in response to the searched answer belonging to a preset security category; the voiceprint comparison module 303 is adapted to determine a standard voiceprint feature corresponding to the searched answer, and compare the voiceprint feature of the user with the searched standard voiceprint feature; the answer presentation module 304 is adapted to present the searched answer to the user in response to the user's voiceprint features being consistent with the standard voiceprint features.
After the answer is searched for the question of the user, comparing the voiceprint features of the user with the standard voiceprint features corresponding to the answer under the condition that the type of the answer belongs to the preset safety type, and displaying the answer to the user under the condition that the voiceprint features of the user are consistent with the standard voiceprint features corresponding to the answer; the safety of answer checking can be ensured through a voiceprint verification mode.
Further, the voiceprint comparison module 303 shown in fig. 3 may include: the user identification determining unit is suitable for determining at least one user identification corresponding to the searched answer; the voiceprint searching unit is suitable for searching a preset voiceprint library according to the at least one user identifier so as to determine the voiceprint characteristics corresponding to the user identifiers; and the first standard voiceprint characteristic determining unit is suitable for taking the voiceprint characteristics corresponding to the user identifications as the standard voiceprint characteristics.
In the embodiment of the invention, the answer in the knowledge base has a corresponding relation with the user identification, and the user identification and the voiceprint characteristics are stored in the preset voiceprint base; therefore, by establishing the association between the answer and the user identification, the data volume needing to be associated can be reduced, the efficiency of searching the voiceprint in the voiceprint library is improved, and the storage resource can be saved.
In a non-limiting embodiment of the present invention, the voiceprint comparison module 303 shown in fig. 3 may also include: the safety level detection unit is suitable for detecting the safety level of the preset safety category; and the second standard voiceprint determination unit is suitable for responding to the situation that the security level reaches a preset level, and determining the voiceprint characteristics of the user indicated by the plurality of user identifications corresponding to the preset level as the standard voiceprint characteristics.
In this embodiment, the preset security category may include a plurality of security levels, and the higher the security level is, the higher the security of the answer belonging to the security level is. And when the security level reaches a preset level, the answers belonging to the preset level correspond to a plurality of standard voiceprint features.
In specific implementation, when the security level reaches a preset level, a plurality of user identifiers may be determined, and a plurality of standard voiceprint features may be determined according to the plurality of user identifiers. The plurality of standard voiceprint features correspond to the searched answer.
Further, when comparing the voiceprint features of the users with the standard voiceprint features, the voiceprint features of a plurality of users need to be collected according to the number of the standard voiceprint features and are compared respectively, so that the verification safety is improved.
In one non-limiting embodiment of the present invention, the security verification device 30 shown in FIG. 3 may further include: the user identification generation module is suitable for determining at least one user identification corresponding to each answer belonging to the preset safety category; the voice acquisition module is suitable for acquiring the voice of the user indicated by at least one user identification corresponding to each answer; and the association storage module is suitable for extracting the voiceprint characteristics of the collected voice, associating the voiceprint characteristics with the user identification and storing the voiceprint characteristics in a preset voiceprint library.
The present embodiment may construct a preset voiceprint library. Specifically, as described above, the answers belonging to the preset security category correspond to the standard voiceprint features, and when the knowledge base is constructed, at least one user identifier corresponding to each answer belonging to the preset security category may be determined first. And determining the user indicated by the at least one user identification and collecting the voice of the user. The voiceprint features of the voices of the respective users are extracted as standard voiceprint features.
In a specific implementation, the process of collecting the voice of the user may be to obtain voice data of each user by crawling from other devices or a local database. Or sending prompt information to the user terminal used by each user and receiving the voice fed back by the user terminal.
In one non-limiting embodiment of the present invention, as shown in fig. 3, the voiceprint feature extraction module 302 can include: the voice acquisition unit is suitable for responding to the searched answer belonging to the preset safety category and sending voice acquisition prompt information to prompt the user to input voice; and the voiceprint extraction unit is suitable for receiving the voice input by the user and extracting the voiceprint characteristics of the user according to the voice of the user.
For more details of the operation principle and the operation mode of the security authentication apparatus 30, reference may be made to the description in fig. 1 to 2, and details are not repeated here.
The embodiment of the invention also discloses a storage medium, wherein computer instructions are stored on the storage medium, and when the computer instructions are operated, the steps of the method shown in the figure 1 or the figure 2 can be executed. The storage medium may include ROM, RAM, magnetic or optical disks, etc. The storage medium may further include a non-volatile memory (non-volatile) or a non-transitory memory (non-transient), and the like.
The embodiment of the invention also discloses a terminal which can comprise a memory and a processor, wherein the memory is stored with computer instructions capable of running on the processor. The processor, when executing the computer instructions, may perform the steps of the method shown in fig. 1 or fig. 2. The terminal includes, but is not limited to, a mobile phone, a computer, a tablet computer and other terminal devices.
Although the present invention is disclosed above, the present invention is not limited thereto. Various changes and modifications may be effected therein by one skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (9)
1. A security authentication method, comprising:
receiving a question input by a user, searching an answer according to the question, if the question is matched with a standard question in a knowledge base, taking the answer in the standard question as the search answer, and if the standard question matched with the question does not exist, taking the answer corresponding to an extended question matched with the question as the search answer; responding to the searched answer belonging to a preset safety category, and extracting the voiceprint features of the user; if the searched answer belongs to the non-preset safety category, directly displaying the answer to the user;
determining standard voiceprint features corresponding to the searched answers, and comparing the voiceprint features of the user with the searched standard voiceprint features;
responding to the voiceprint feature of the user and the standard voiceprint feature to be consistent, and displaying the searched answer to the user;
the extracting the voiceprint features of the user in response to the searched answer belonging to a preset security category comprises:
responding to the searched answer belonging to the preset safety category, and sending voice acquisition prompt information to prompt the user to input voice;
and receiving the voice input by the user, and extracting the voiceprint features of the user according to the voice of the user.
2. The security verification method of claim 1, wherein the determining the corresponding standard voiceprint features of the searched answers comprises:
determining at least one user identification corresponding to the searched answer;
searching a preset voiceprint library according to the at least one user identifier to determine the voiceprint characteristics corresponding to the user identifiers;
and taking the voiceprint features corresponding to the user identifications as the standard voiceprint features.
3. The security authentication method of claim 1, wherein said receiving a question of user input is preceded by:
determining at least one user identifier corresponding to each answer belonging to the preset safety category;
collecting the voice of the user indicated by at least one user identification corresponding to each answer;
and extracting the voiceprint features of the collected voice, and associating the collected voiceprint features of the voice with the user identification and storing the same in a preset voiceprint library.
4. The security verification method of claim 1, wherein the determining the standard voiceprint feature corresponding to the searched answer comprises:
detecting the safety level of the preset safety category;
and in response to that the security level reaches a preset level, determining that the voiceprint features of the user indicated by the plurality of user identifications corresponding to the preset level are the standard voiceprint features.
5. The security authentication method of claim 1, wherein the searching for answers from the question comprises:
matching the question with knowledge points in a knowledge base;
and determining the answer in the knowledge point matched with the question as the searched answer.
6. The security authentication method according to any one of claims 1 to 5, wherein the format of the question is selected from the group consisting of voice, picture, video, and document; the answer is in a format selected from the group consisting of voice, picture, video, and document.
7. A security authentication apparatus, comprising:
the question receiving module is suitable for receiving a question input by a user and searching an answer according to the question, if the question is matched with a standard question in a knowledge base, the answer in the standard question is used as the search answer, and if the standard question which is matched with the question does not exist, the answer corresponding to an extended question which is matched with the question is used as the search answer;
the voiceprint feature extraction module is suitable for responding to the fact that the searched answer belongs to the preset safety category, and extracting the voiceprint features of the user;
the voiceprint comparison module is suitable for determining the standard voiceprint characteristics corresponding to the searched answers and comparing the voiceprint characteristics of the user with the searched standard voiceprint characteristics;
the answer display module is suitable for responding to the consistency of the voiceprint characteristics of the user and the standard voiceprint characteristics and displaying the searched answer to the user; if the searched answer belongs to the non-preset safety category, directly displaying the answer to the user;
the voiceprint feature extraction module comprises: the voice acquisition unit is suitable for responding to the searched answer belonging to the preset safety category and sending voice acquisition prompt information to prompt the user to input voice; and the voiceprint extraction unit is suitable for receiving the voice input by the user and extracting the voiceprint characteristics of the user according to the voice of the user.
8. A storage medium having stored thereon computer instructions, wherein said computer instructions when executed perform the steps of the security authentication method of any one of claims 1 to 6.
9. A terminal comprising a memory and a processor, the memory having stored thereon computer instructions executable on the processor, wherein the processor, when executing the computer instructions, performs the steps of the security authentication method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811643560.3A CN109657444B (en) | 2018-12-29 | 2018-12-29 | Security verification method and device, storage medium and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811643560.3A CN109657444B (en) | 2018-12-29 | 2018-12-29 | Security verification method and device, storage medium and terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109657444A CN109657444A (en) | 2019-04-19 |
| CN109657444B true CN109657444B (en) | 2021-06-25 |
Family
ID=66116952
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811643560.3A Active CN109657444B (en) | 2018-12-29 | 2018-12-29 | Security verification method and device, storage medium and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109657444B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106471502A (en) * | 2016-06-29 | 2017-03-01 | 深圳狗尾草智能科技有限公司 | Intension recognizing method based on water conservancy diversion and system |
| CN107729491A (en) * | 2017-10-18 | 2018-02-23 | 广东小天才科技有限公司 | Improve the method, apparatus and equipment of the accuracy rate of topic answer search |
| CN108010519A (en) * | 2017-11-10 | 2018-05-08 | 上海爱优威软件开发有限公司 | A kind of information search method and system |
| CN108776693A (en) * | 2018-06-06 | 2018-11-09 | 广东小天才科技有限公司 | It is a kind of that topic method and private tutor's equipment are searched based on the voice for customizing corpus |
| CN108830059A (en) * | 2018-05-23 | 2018-11-16 | 出门问问信息科技有限公司 | Control method, device and the electronic equipment of media interviews |
-
2018
- 2018-12-29 CN CN201811643560.3A patent/CN109657444B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106471502A (en) * | 2016-06-29 | 2017-03-01 | 深圳狗尾草智能科技有限公司 | Intension recognizing method based on water conservancy diversion and system |
| CN107729491A (en) * | 2017-10-18 | 2018-02-23 | 广东小天才科技有限公司 | Improve the method, apparatus and equipment of the accuracy rate of topic answer search |
| CN108010519A (en) * | 2017-11-10 | 2018-05-08 | 上海爱优威软件开发有限公司 | A kind of information search method and system |
| CN108830059A (en) * | 2018-05-23 | 2018-11-16 | 出门问问信息科技有限公司 | Control method, device and the electronic equipment of media interviews |
| CN108776693A (en) * | 2018-06-06 | 2018-11-09 | 广东小天才科技有限公司 | It is a kind of that topic method and private tutor's equipment are searched based on the voice for customizing corpus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109657444A (en) | 2019-04-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10824874B2 (en) | Method and apparatus for processing video | |
| US20200151310A1 (en) | Method and apparatus for identity authentication | |
| US10593334B2 (en) | Method and apparatus for generating voiceprint information comprised of reference pieces each used for authentication | |
| US10777207B2 (en) | Method and apparatus for verifying information | |
| US9979721B2 (en) | Method, server, client and system for verifying verification codes | |
| WO2019196303A1 (en) | User identity authentication method, server and storage medium | |
| CN109194689B (en) | Abnormal behavior recognition method, device, server and storage medium | |
| CN108388672B (en) | Video searching method and device and computer readable storage medium | |
| KR20150041592A (en) | Method for updating contact information in callee electronic device, and the electronic device | |
| US20160351185A1 (en) | Voice recognition device and method | |
| CN111312286A (en) | Age identification method, age identification device, age identification equipment and computer readable storage medium | |
| CN111128179A (en) | Intelligent supervision method and system based on voice recognition technology | |
| KR20080046490A (en) | Method for identifying face using montage and apparatus thereof | |
| CN109657444B (en) | Security verification method and device, storage medium and terminal | |
| CN110955796B (en) | Case feature information extraction method and device based on stroke information | |
| CN105843890B (en) | Knowledge base-based big data and common data oriented data acquisition method and system | |
| CN112581967A (en) | Voiceprint retrieval method, front-end back-end server and back-end server | |
| CN109388695B (en) | User intention recognition method, apparatus and computer-readable storage medium | |
| CN103093213A (en) | Video file classification method and terminal | |
| CN112015773A (en) | Knowledge base retrieval method and device, electronic equipment and storage medium | |
| CN113190660A (en) | Questionnaire survey method and device | |
| CN111078082A (en) | Point reading method based on image recognition and electronic equipment | |
| CN110580243A (en) | file comparison method and device, electronic equipment and storage medium | |
| CN115794889B (en) | Personal relationship processing method and device, electronic equipment and computer readable storage medium | |
| CN111666403B (en) | Conference summary processing method and device and conference summary processing equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |