WO2019228135A1

WO2019228135A1 - Method and device for adjusting matching threshold, storage medium and electronic device

Info

Publication number: WO2019228135A1
Application number: PCT/CN2019/085534
Authority: WO
Inventors: 李冠; 达剑; 董治; 高亮; 李海泉; 刘嘉飞; 文昭彦; 熊万江; 周伍润; 朱忠磊
Original assignee: Oppo广东移动通信有限公司
Priority date: 2018-05-30
Filing date: 2019-05-05
Publication date: 2019-12-05
Also published as: CN108766443A

Abstract

A method for adjusting a matching threshold, comprising: acquiring vocal print feature information of a current user (101); matching the vocal print feature information of the current user with preset vocal print feature information to obtain a corresponding target matching rate (102); if the target matching rate and a preset matching threshold satisfy a present condition, performing authentication on the current user (103); and adjusting a numerical value of the preset matching threshold after authentication is passed.

Description

Method, device, storage medium and electronic equipment for adjusting matching threshold

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on May 30, 2018, with an application number of 201810542931.2, and the application name is "Adjustment method, device, storage medium, and electronic device for matching threshold". Citations are incorporated in this application.

Technical field

The present application belongs to the technical field of terminals, and in particular, to a method, an apparatus, a storage medium, and an electronic device for adjusting a matching threshold.

Background technique

With the development of technology, the interaction modes between human and machine have become more and more abundant. In related technology, a user can control a terminal by using a voice, that is, after receiving a voice message sent by the user, the terminal can analyze the voice information to obtain a control instruction. Before executing the control instruction, the terminal needs to extract voiceprint features from the voice information, and perform voiceprint recognition for the user according to the extracted voiceprint features. Only after the voiceprint recognition is passed, the terminal will execute the control instruction corresponding to the voice information.

Summary of the Invention

The embodiments of the present application provide a method, a device, a storage medium, and an electronic device for adjusting a matching threshold, which can improve the flexibility of voiceprint recognition.

An embodiment of the present application provides a method for adjusting a matching threshold, including:

Obtain the voiceprint feature information of the current user;

Matching the voiceprint feature information of the current user with preset voiceprint feature information to obtain a corresponding target matching degree;

If a preset condition is satisfied between the target matching degree and a preset matching threshold, performing identity verification on the current user;

After the identity verification is passed, the value of the preset matching threshold is adjusted.

An embodiment of the present application provides a device for adjusting a matching threshold, including:

An acquisition module, configured to acquire voiceprint feature information of the current user;

A matching module, configured to match the voiceprint feature information of the current user with preset voiceprint feature information to obtain a corresponding target matching degree;

A verification module, configured to perform identity verification on the current user if a preset condition is satisfied between the target matching degree and a preset matching threshold;

An adjustment module is configured to adjust the value of the preset matching threshold after the identity verification is passed.

An embodiment of the present application provides a storage medium having a computer program stored thereon. When the computer program is executed on a computer, the computer is caused to execute a process in a method for adjusting a matching threshold provided by an embodiment of the present application.

An embodiment of the present application further provides an electronic device including a memory and a processor, where the processor executes a process in a method for adjusting a matching threshold provided by an embodiment of the present application by calling a computer program stored in the memory.

BRIEF DESCRIPTION OF THE DRAWINGS

The following detailed description of specific embodiments of the present application will make the technical solution of the present application and its beneficial effects obvious with reference to the accompanying drawings.

FIG. 1 is a schematic flowchart of a method for adjusting a matching threshold according to an embodiment of the present application.

FIG. 2 is another schematic flowchart of a method for adjusting a matching threshold according to an embodiment of the present application.

3 to 5 are schematic diagrams of a method for adjusting a matching threshold according to an embodiment of the present application.

FIG. 6 is a schematic structural diagram of a matching threshold adjustment device according to an embodiment of the present application.

FIG. 7 is another schematic structural diagram of a matching threshold adjustment device according to an embodiment of the present application.

FIG. 8 is a schematic structural diagram of a mobile terminal according to an embodiment of the present application.

FIG. 9 is another schematic structural diagram of a mobile terminal according to an embodiment of the present application.

Detailed ways

Please refer to the figure, wherein the same component symbols represent the same components. The principle of the present application is illustrated by implementing in an appropriate computing environment. The following description is based on the exemplified specific embodiments of the present application, which should not be construed as limiting other specific embodiments that are not detailed herein.

Obtain the voiceprint feature information of the current user;

In an implementation manner, if the target matching degree and a preset matching threshold satisfy a preset condition, performing identity verification on the current user may include: if the target matching degree is less than the preset matching threshold Obtaining the difference between the preset matching threshold and the target matching degree; if it is detected that the difference is less than or equal to the preset difference, determining between the target matching degree and the preset matching threshold The preset conditions are met, and the current user is authenticated.

In one embodiment, adjusting the value of the preset matching threshold may include: acquiring multiple voices of the current user, and extracting target voiceprint feature information from each voice; The pattern feature information is matched with the preset voiceprint feature information one by one to obtain a plurality of standby matching degrees; an average value of the plurality of standby matching degrees is calculated; and the value of the preset matching threshold is changed from the current The target value is adjusted to the average value.

In an implementation manner, after the value of the preset matching threshold is adjusted from the current target value to the average value, the method may further include: setting a valid period; and when the valid period ends, setting the preset period The value of the matching threshold is restored from the average value to the target value.

In an implementation manner, before acquiring the multi-segment voice of the current user, the method further includes: calculating a percentage difference between the preset matching threshold and the target matching degree; and converting the percentage difference into one hundred Is the fraction of the denominator; the number of the numerator of the fraction is determined as the target value.

Then, acquiring the multi-segment voices of the current user may include: acquiring multiple multi-segment voices whose number is the target value.

In an implementation manner, before acquiring the multi-segment voice of the current user, the method may further include: setting a preset value;

Then, acquiring the multi-segment voices of the current user may include: acquiring the multi-segment voices whose quantity is the preset value.

In an implementation manner, performing identity verification on the current user may include: performing identity verification on the current user through fingerprint recognition, face recognition, or iris recognition.

It can be understood that the execution subject of the embodiment of the present application may be a terminal device such as a smart phone or a tablet computer.

Please refer to FIG. 1. FIG. 1 is a schematic flowchart of a matching threshold adjustment method according to an embodiment of the present application. The process may include:

In 101, voiceprint feature information of the current user is acquired.

With the development of technology, the interaction modes between human and machine have become more and more abundant. In related technology, a user can control a terminal by using a voice, that is, after receiving a voice message sent by the user, the terminal can analyze the voice information to obtain a control instruction. Before executing the control instruction, the terminal needs to extract voiceprint features from the voice information, and perform voiceprint recognition for the user according to the extracted voiceprint features. Only after the voiceprint recognition is passed, the terminal will execute the control instruction corresponding to the voice message. However, in the related art, the terminal has poor flexibility when performing voiceprint recognition on the user.

In 101 of this application, for example, when a user uses a voice assistant provided by the terminal to operate the terminal, that is, when voiceprint recognition is required, the terminal may obtain voiceprint feature information of the current user. For example, the terminal may first obtain a voice uttered by the current user, and then extract voiceprint feature information from the voice.

In 102, the voiceprint feature information of the current user is matched with the preset voiceprint feature information to obtain a corresponding target matching degree.

For example, after acquiring the voiceprint feature information of the current user, the terminal may match the voiceprint feature information of the current user with the preset voiceprint feature information to obtain a corresponding target matching degree. In one embodiment, the preset voiceprint feature information may be voiceprint feature information of the terminal owner and / or voiceprint feature information of a user (such as the owner ’s family, etc.) permitted by the terminal owner.

After obtaining the target matching degree between the voiceprint feature information of the current user and the preset voiceprint feature information, the terminal may detect whether the target matching degree and the preset matching threshold value meet a preset condition. The preset matching threshold value is a value used to determine whether the voiceprint recognition is passed (that is, the preset matching threshold value is a value used to determine whether the voiceprint feature information of the current user and the preset voiceprint feature information are successfully matched), that is, During voiceprint recognition, if the degree of matching between the user's voiceprint feature information and the preset voiceprint feature information reaches a preset matching threshold, the terminal may determine that the voiceprint recognition passes.

If it is detected that the preset condition is not satisfied between the target matching degree and the preset matching threshold, the terminal may perform other operations.

If it is detected that the preset condition is satisfied between the target matching degree and the preset matching threshold, then step 103 is performed.

In 103, if a preset condition is satisfied between the target matching degree and a preset matching threshold, the current user is authenticated.

In step S104, after the identity verification is passed, the value of the preset matching threshold is adjusted.

For example, 103 and 104 can include:

The terminal detects that a preset condition is satisfied between the target matching degree and a preset matching threshold. In this case, the terminal can authenticate the current user to verify whether the current user is the terminal owner or other legal user.

After the identity verification of the current user is passed, that is, after the terminal determines that the current user is the terminal owner or another legal user, the terminal can preset a value of the matching threshold value for adjustment. After that, the terminal can perform voiceprint recognition according to the preset matching threshold adjusted by the value.

It can be understood that, in the embodiment of the present application, when the terminal detects that the matching degree between the voiceprint feature information and the preset voiceprint feature information of the current user satisfies a preset condition and presets a matching threshold, The current user is authenticated. After the identity verification is passed, the terminal can adjust the value of the preset matching threshold, so that the terminal can subsequently perform voiceprint recognition according to the preset matching threshold adjusted by the value. Since the preset matching threshold for judging whether the voiceprint recognition passes can be adjusted in this embodiment, this embodiment can improve the flexibility of the terminal when performing voiceprint recognition.

Please refer to FIG. 2. FIG. 2 is another schematic flowchart of a matching threshold adjustment method according to an embodiment of the present application. The process may include:

In 201, the terminal acquires voiceprint feature information of the current user.

For example, when a user uses a voice assistant provided by the terminal to operate the terminal, that is, when voiceprint recognition is required, the terminal may obtain voiceprint characteristic information of the current user.

In 202, the terminal matches the voiceprint feature information of the current user with the preset voiceprint feature information to obtain a corresponding target matching degree.

After obtaining the target matching degree between the voiceprint feature information of the current user and the preset voiceprint feature information, the terminal may compare the target matching degree with a preset matching threshold. The preset matching threshold is a value used to determine whether voiceprint recognition is passed. That is, when the voiceprint recognition is performed, if the degree of matching between the user's voiceprint feature information and the preset voiceprint feature information reaches a preset matching threshold, Then the terminal may determine that the voiceprint recognition is passed.

If it is detected that the target matching degree reaches the preset matching threshold, for example, the matching degree of the voiceprint feature information of the current user and the preset voiceprint feature information is 95%, and the preset matching threshold is 90%, that is, the target matching degree exceeds If the preset matching threshold is set, the current user can be regarded as a legitimate user. In this case, the terminal can execute the control instruction corresponding to the voice issued by the current user.

If it is detected that the target matching degree is less than the preset matching threshold, then the process may proceed to 203.

In 203, if the target matching degree is less than a preset matching threshold, the terminal obtains a difference between the preset matching threshold and the target matching degree.

In 204, if it is detected that the difference is less than or equal to a preset difference, the terminal determines that a preset condition is satisfied between the target matching degree and the preset matching threshold, and performs identity verification on the current user.

For example, 203 and 204 can include:

The terminal detects that the target matching degree between the voiceprint feature information of the current user and the preset voiceprint feature information is 86%, which is less than a preset matching threshold of 90%. In this case, the terminal may obtain a difference between the preset matching threshold and the target matching degree. For example, the terminal obtains that the difference between the preset matching threshold and the target matching degree is 4% (90% -86%).

After that, the terminal can detect whether the difference is less than or equal to a preset difference.

If the difference is detected to be greater than a preset difference, the terminal may perform other operations.

If the difference is detected to be less than or equal to a preset difference, for example, the preset difference is 5%, and the matching degree of the voiceprint feature information of the current user with the preset voiceprint feature information is 86% and the preset matching threshold is 90% The difference is 4%, then the terminal can determine that the target matching degree between the voiceprint feature information and the preset voiceprint feature information of the current user and the preset matching threshold satisfy a preset condition. In this case, it can be considered that the voiceprint feature information of the current user is close to the preset voiceprint feature information. At this point, the terminal can be triggered to authenticate the current user.

In one embodiment, the terminal may perform identity authentication on the current user by using other methods than voiceprint recognition, such as fingerprint recognition, face recognition, or iris recognition.

If the authentication of the current user fails, the current user may be considered as an illegal user, and the terminal may not execute the voice instruction sent by the current user at this time.

If the authentication of the current user passes, then 205 can be entered.

In 205, after the identity verification is passed, the terminal obtains multiple pieces of speech of the current user, and extracts target voiceprint feature information from each piece of speech.

In 206, the terminal matches all the target voiceprint feature information with the preset voiceprint feature information one by one, and obtains multiple standby matching degrees.

In 207, the terminal calculates an average value of the plurality of standby matching degrees.

In 208, the terminal adjusts the value of the preset matching threshold value from the current target value to the average value.

For example, 205, 206, 207, and 208 can include:

After the identity verification of the current user is passed, the terminal can obtain multiple pieces of voice of the current user and extract voiceprint feature information from each voice, that is, target voiceprint feature information.

Then, the terminal can match all target voiceprint feature information with the preset voiceprint feature information one by one, that is, the terminal can match each target voiceprint feature information with the preset voiceprint feature information, thereby obtaining multiple matching degrees. , That is, multiple in-use matches.

After obtaining multiple standby matching degrees, the terminal may calculate an average of the standby matching degrees. Then, the terminal may adjust the value of the preset matching threshold from the current target value to the average value.

For example, the terminal may acquire 5 segments of voice of the current user, and extract target voiceprint feature information from each segment of voice. Then, the terminal can match each target voiceprint feature information with preset voiceprint feature information, thereby obtaining 5 standby matching degrees. For example, the five standby matches are 88%, 87%, 85%, 85%, 87%, respectively. After that, the terminal can calculate an average of the five standby matching degrees, for example, the average is 86.4%. After calculating the average value, the terminal may adjust the value of the preset matching threshold from the current 90% to 86.4%.

In 209, the terminal sets a validity period, and when the validity period ends, the preset matching threshold value is restored from the average value to the target value.

For example, after adjusting the preset matching threshold from the current 90% to 86.4%, the terminal may set a validity period. When the end of the validity period is detected, the terminal may restore the value of the preset matching threshold from 86.4% to 90%.

For example, after adjusting the preset matching threshold from the current 90% to 86.4%, the terminal may set the validity period for the value adjustment to 5 days, that is, the terminal needs to restore the preset matching threshold value from 86.4% after 5 days 90%.

In an implementation manner, before the process for the terminal to obtain the multi-segment voice of the current user in 205, the process may further include the following process:

The terminal calculates a percentage difference between a preset matching threshold and a target matching degree;

The terminal converts the percentage difference into a fraction with a hundred as a denominator;

The terminal determines the number of the numerator of the score as the target value.

Then, the process of obtaining the multi-segment voice of the current user by the terminal in 205 may include: The terminal obtains the multi-segment voice whose quantity is the target value.

For example, after the identity verification is passed, the terminal may first calculate a percentage difference between a preset matching threshold and a target matching degree. For example, if the preset matching threshold is 90% and the target matching degree is 86%, then the percentage difference between the preset matching threshold and the target matching degree is 4%.

After that, the terminal may convert the percentage difference between the preset matching threshold and the target matching degree into a score with a hundred as the denominator, and determine the number of the numerator of the score as the target value. For example, after a percentage difference of 4% is converted to a fraction with a hundred as the denominator, the numerator of the fraction is 4. Then, the target value can be determined to be 4.

After that, when the terminal needs to obtain the multi-segment voice of the current user, the terminal can obtain the multi-segment voice whose number is the target value. For example, if the target value is 4, then the terminal can obtain 4 segments of voice of the current user.

It can be understood that, in this embodiment, the terminal may determine specifically how many pieces of speech to acquire according to the difference between the preset matching threshold and the target matching degree. In the case where the difference between the preset matching threshold and the target matching degree is small, that is, the change of the voiceprint characteristics of the current user is small, the terminal can obtain fewer segments of speech. However, when the difference between the preset matching threshold and the target matching degree is large, that is, when the voiceprint feature of the current user changes greatly, the terminal can obtain more voices, so that the terminal can more accurately The voiceprint changes to adjust the value of the preset matching threshold, and also increases the flexibility of adjusting the preset matching threshold.

In some implementations, when it is necessary to obtain multiple voices of the current user and adjust the value of the preset matching threshold according to the multiple voices, the terminal may also determine the specific needs to acquire several voices by:

For example, the terminal may set a preset value in advance, and when the terminal needs to obtain multiple segments of speech, the terminal obtains multiple segments of speech with the preset value. For example, if the preset value is 5, then the terminal can obtain the 5 voices of the current user, and extract the target voiceprint feature information of the current user from each of the 5 voices, and set each target voiceprint feature information. Match with the preset voiceprint feature information to get 5 standby matching degrees. Then, the terminal may calculate an average value of the five standby matching degrees, and adjust the preset matching threshold value from the current value to the average value.

In one embodiment, the terminal may randomly generate 5 segments of speech, and ask the user to pronounce these 5 segments of speech, and then extract target voiceprint feature information of the current user from each of the 5 segments of speech spoken by the user, Each target voiceprint feature information is matched with preset voiceprint feature information to obtain 5 standby matching degrees. Then, the terminal may calculate an average value of the five standby matching degrees, and adjust the preset matching threshold value from the current value to the average value. In one embodiment, the terminal may also obtain the required 5 segments of user voice when performing voice interaction with the user, and execute subsequent related processes.

Alternatively, the terminal may first analyze the voice issued by the current user. If the control instruction corresponding to the voice includes two or more alternative operations, the terminal may also determine the specific needs to obtain several segments of voice according to the number of alternative operations. For example, if the user's voice is "Open Music Application", then if the terminal detects that the terminal contains 3 music applications, such as A application, B application, and C application, then the terminal can determine that it needs to obtain 3 segments of voice. Then, the terminal can sequentially generate 3 pieces of voice information for asking the user whether to open an application. When receiving the answer voice of the current user, the terminal may extract the voiceprint feature information of the current user from it.

Please refer to FIG. 3 to FIG. 5, which are schematic diagrams of a method for adjusting a matching threshold provided by an embodiment of the present application.

In daily life, the user's voiceprint characteristics are not static. In some cases, there are some changes in the user's voiceprint characteristics. For example, when the user's throat is inflamed, the user's voice will become hoarse, or when the user is eating and talking, the user's voice will also change slightly.

For example, in this embodiment, the current user's voice is hoarse due to throat inflammation, which causes the voiceprint characteristics of the current user to change. In this case, for example, the current user needs to use the terminal's voice assistant function at this time. For example, the current user sends the following voice "Xiaoou, please open the music application" to the terminal, as shown in Figure 3.

After receiving the voice "Xiaoou, please open the music application", the terminal can extract the voiceprint feature information of the current user from the voice, and then match the voiceprint feature information of the current user with the preset voiceprint feature information. And get the corresponding target match. The preset voiceprint feature information is the voiceprint feature information of the owner of the terminal. For example, due to the hoarse voice of the current user, the target matching degree between the voiceprint feature information of the current user and the preset voiceprint feature information is only 86%, and the preset matching threshold is not reached 90%, that is, the voiceprint recognition of the current user Fail.

After that, the terminal may calculate a difference between the target matching degree and a preset matching threshold. For example, the difference between the target matching degree and the preset matching threshold is 4% (90% -86%).

After obtaining the difference between the target matching degree and the preset matching threshold, the terminal can detect whether the difference is less than or equal to the preset difference. For example, the preset difference is 5%. Therefore, in this embodiment, the terminal can detect that the difference between the target matching degree and the preset matching threshold 4% is less than the preset difference 5%. In this case, the terminal may determine that the target matching degree and the preset matching threshold satisfy a preset condition, that is, the terminal may consider that the voiceprint feature information of the current user and the preset voiceprint feature information are close to match. The terminal can then authenticate the current user. For example, the terminal may authenticate the current user in one or more of fingerprint recognition, face recognition, and iris recognition to verify whether the current user is the terminal owner.

For example, in this embodiment, the identity verification of the current user passes, that is, the terminal can confirm that the current user is the terminal owner. In this case, the terminal can obtain multiple voices of the current user and extract target voiceprint feature information from each voice. For example, after receiving the voice “Xiaoou, please open the music application” from the user, the terminal parses the voice and detects that the terminal contains two music applications, namely, the A application and the B application. At this point, the terminal can issue the following voice to the user: "The current terminal contains A music application and B music application, may I ask which application you need to open now", as shown in Figure 4.

For example, after hearing the voice from the terminal, the current user answers the following voice "Open A application", as shown in FIG. 5. After receiving the user's response and determining that the current user is the owner, the terminal can open the A application.

After that, the user can continue to use the voice assistant to control the terminal to complete corresponding operations as needed. In this process, the terminal can continue to obtain the multi-segment voice of the current user. Then, the terminal may select a plurality of pieces of speech with a preset number from the terminal. For example, if the preset value is 5, then the terminal can obtain 5 segments of voice of the current user and extract target voiceprint feature information of the current user from each segment of the voice. Then, the terminal may match the target voiceprint feature information with the preset voiceprint feature information, thereby obtaining a corresponding matching degree. That is, the terminal may obtain multiple matching degrees and determine the multiple matching degrees as the standby matching degrees. After that, the terminal may calculate an average value of the plurality of standby matching degrees, and adjust the value of the preset matching threshold value from the current target value to the average value.

For example, when the current user uses a voice assistant to control the terminal to play music, the terminal obtains 5 segments of voice and extracts 5 target voiceprint feature information from the terminal. The matching degree between the five target voiceprint feature information and the preset voiceprint feature information is 88%, 87%, 85%, 85%, 87% in order. After that, the terminal can calculate the average of the five matching degrees, for example, the average is 86.4%. After calculating the average value, the terminal may adjust the value of the preset matching threshold from the current 90% to 86.4%.

The terminal can then set a validity period. For example, if the terminal is set to be valid for 5 days, then in the next 5 days, the terminal can perform voiceprint quilts on the current user according to a matching threshold of 86.4%, and after 5 days, the terminal can set a preset matching threshold The value was restored from 86.4% to 90%.

It can be understood that, in general, in the case that the user's throat sound changes due to throat inflammation caused by the inflammation of the throat, the user's throat inflammation will heal after a period of time, so the terminal can set a validity period, which can correspond to The time it takes for the user's throat to heal. When the validity period expires, the terminal may restore the value of the preset matching threshold.

Please refer to FIG. 6, which is a schematic structural diagram of a matching threshold adjustment device according to an embodiment of the present application. The matching threshold adjustment device 300 may include: an obtaining module 301, a matching module 302, a verification module 303, and an adjustment module 304.

The obtaining module 301 is configured to obtain voiceprint feature information of a current user.

The matching module 302 is configured to match the voiceprint feature information of the current user with preset voiceprint feature information to obtain a corresponding target matching degree.

The verification module 303 is configured to perform identity verification on the current user if a preset condition is satisfied between the target matching degree and a preset matching threshold.

The adjustment module 304 is configured to adjust the value of the preset matching threshold after the identity verification is passed.

In one embodiment, the verification module 303 may be configured to:

If the target matching degree is less than the preset matching threshold, obtaining a difference between the preset matching threshold and the target matching degree;

If it is detected that the difference is less than or equal to a preset difference, it is determined that a preset condition is satisfied between the target matching degree and the preset matching threshold, and the current user is authenticated.

In an implementation manner, the adjustment module 304 may be configured to:

Acquiring a plurality of voices of the current user, and extracting target voiceprint feature information from each voice;

Matching all the target voiceprint feature information with the preset voiceprint feature information one by one, and obtaining multiple standby matching degrees;

Calculating an average value of the plurality of standby matching degrees;

Adjusting the value of the preset matching threshold from the current target value to the average value.

In one embodiment, the adjustment module is further configured to:

Set a preset value;

Acquire multiple pieces of speech with the preset value.

In an implementation manner, the verification module 303 may be configured to:

Performing identity verification on the current user through fingerprint recognition, face recognition or iris recognition.

Please refer to FIG. 7 together. FIG. 7 is another schematic structural diagram of a matching threshold adjustment device according to an embodiment of the present application. In an embodiment, the matching threshold adjustment device 300 may further include a restoration module 305 and a determination module 306.

The restoration module 305 is configured to set a validity period, and when the validity period ends, restore the value of the preset matching threshold value from the average value to the target value.

A determining module 306, configured to: calculate a percentage difference between the preset matching threshold and the target matching degree; convert the percentage difference into a fraction with a hundred denominator; determine the number of the numerator of the fraction Is the target value.

Then, the adjustment module 304 may be configured to: obtain a plurality of pieces of speech whose quantity is the target value.

An embodiment of the present application provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed on a computer, the computer is caused to execute the method in the method for adjusting a matching threshold provided in this embodiment. step.

An embodiment of the present application further provides an electronic device including a memory and a processor, where the processor executes steps in the method for adjusting a matching threshold provided by the embodiment by calling a computer program stored in the memory.

For example, the above electronic device may be a mobile terminal such as a tablet computer or a smart phone. Please refer to FIG. 8, which is a schematic structural diagram of a mobile terminal according to an embodiment of the present application.

The mobile terminal 400 may include components such as a microphone 401, a memory 402, and a processor 403. Those skilled in the art can understand that the structure of the mobile terminal shown in FIG. 8 does not constitute a limitation on the mobile terminal, and may include more or fewer components than those shown in the figure, or some components may be combined, or different components may be arranged.

The microphone 401 may be used to pick up a voice and the like emitted by a user.

The memory 402 may be used to store application programs and data. The application program stored in the memory 402 contains executable code. Applications can be composed of various functional modules. The processor 403 executes various functional applications and data processing by running application programs stored in the memory 402.

The processor 403 is the control center of the mobile terminal. It uses various interfaces and lines to connect various parts of the entire mobile terminal, and executes the mobile terminal by running or executing application programs stored in the memory 402, and calling data stored in the memory 402. Various functions and processing data to monitor the mobile terminal as a whole.

In this embodiment, the processor 403 in the mobile terminal loads the executable code corresponding to the process of one or more applications into the memory 402 according to the following instructions, and the processor 403 runs and stores the memory in the memory. 402 application to achieve the steps:

Obtain the voiceprint feature information of the current user;

Referring to FIG. 9, the mobile terminal 500 may include a microphone 501, a memory 502, a processor 503, an input unit 504, an output unit 505, a speaker 506, and other components.

The microphone 501 may be used to pick up a voice and the like emitted by a user.

The memory 502 may be used to store application programs and data. The application program stored in the memory 502 contains executable code. Applications can be composed of various functional modules. The processor 503 executes various functional applications and data processing by running an application program stored in the memory 502.

The processor 503 is the control center of the mobile terminal. It uses various interfaces and lines to connect various parts of the entire mobile terminal, and executes the mobile terminal by running or executing application programs stored in the memory 502, and calling data stored in the memory 502. Various functions and processing data to monitor the mobile terminal as a whole.

The input unit 504 can be used to receive inputted numbers, character information, or user characteristic information (such as fingerprints), and generate keyboard, mouse, joystick, optical, or trackball signal inputs related to user settings and function control.

The output unit 505 may be used to display information input by the user or information provided to the user and various graphical user interfaces of the mobile terminal. These graphical user interfaces may be composed of graphics, text, icons, videos, and any combination thereof. The output unit may include a display panel.

In this embodiment, the processor 503 in the mobile terminal loads the executable code corresponding to the process of one or more applications into the memory 502 according to the following instructions, and the processor 503 runs the stored code in the memory 502 application to achieve the steps:

Obtain the voiceprint feature information of the current user;

In one embodiment, when the processor 503 executes the step of authenticating the current user if a preset condition is satisfied between the target matching degree and a preset matching threshold, the processor 503 may perform: if the target If the degree of matching is less than the preset matching threshold, a difference between the preset matching threshold and the target matching degree is obtained; if it is detected that the difference is less than or equal to the preset difference, determining the target matching degree And a preset condition is met between the preset matching threshold and the current user is authenticated.

In an implementation manner, when the processor 503 executes the step of adjusting the value of the preset matching threshold, the processor 503 may perform: obtaining multiple voices of the current user, and extracting a target voiceprint from each voice Feature information; matching all of the target voiceprint feature information with the preset voiceprint feature information one by one, and obtaining multiple standby matching degrees; calculating an average of the multiple standby matching degrees; The value of the preset matching threshold is adjusted from the current target value to the average value.

In an implementation manner, after the step of adjusting the value of the preset matching threshold value from the current target value to the average value, the processor 503 may further perform: setting a validity period; when the validity period ends, Restoring the value of the preset matching threshold from the average value to the target value. The processor 503 executes

In an embodiment, before the step of obtaining the multi-segment voice of the current user, the processor 503 may further perform: calculating a percentage difference between the preset matching threshold and the target matching degree; and dividing the percentage difference Converting the value to a fraction with a hundred as the denominator; determining the number of the numerator of the fraction as the target value;

Then, when the processor 503 executes the step of acquiring the multi-segment voice of the current user, it may execute: acquiring the multi-segment voice whose quantity is the target value.

In an implementation manner, before acquiring the multi-segment voice of the current user, the processor 503 may further perform: setting a preset value.

Then, when the processor 503 executes acquiring the multi-segment voice of the current user, it may execute: acquiring the multi-segment voice whose quantity is the preset value.

In an embodiment, when the processor 503 performs identity verification on the current user, the processor 503 may execute: identity verification on the current user through fingerprint recognition, face recognition, or iris recognition.

In the above embodiments, the description of each embodiment has its own emphasis. For the parts that are not described in detail in an embodiment, please refer to the detailed description of the adjustment method for the matching threshold above, which will not be repeated here.

The apparatus for adjusting the matching threshold provided in the embodiment of the present application and the method for adjusting the matching threshold in the foregoing embodiment belong to the same concept. The apparatus for adjusting the matching threshold may be run in the embodiment of the method for adjusting the matching threshold. For the specific implementation process of any method provided, see the embodiment of the method for adjusting the matching threshold in detail, and details are not described herein again.

It should be noted that, for the method for adjusting the matching threshold described in the embodiments of the present application, those skilled in the art can understand that all or part of the process for implementing the method for adjusting the matching threshold described in the embodiments of the present application can be implemented by a computer program. Controlling related hardware to complete, the computer program may be stored in a computer-readable storage medium, such as stored in the memory, and executed by at least one processor, and may include adjustment of the matching threshold during the execution process The flow of an embodiment of the method. The storage medium may be a magnetic disk, an optical disk, a read only memory (ROM, Read Only Memory), a random access memory (RAM, Random Access Memory), and the like.

For the device for adjusting the matching threshold according to the embodiment of the present application, its functional modules may be integrated into one processing chip, or each module may exist separately physically, or two or more modules may be integrated into one module. . The above integrated modules can be implemented in the form of hardware or software functional modules. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium, such as a read-only memory, a magnetic disk, or an optical disk. .

The method, device, storage medium and electronic device for adjusting the matching threshold provided in the embodiments of the present application have been described in detail above. The specific examples are used in this document to explain the principle and implementation of the present application. The description is only used to help understand the method of the application and its core ideas; at the same time, for those skilled in the art, according to the ideas of the application, there will be changes in the specific implementation and application scope. In summary, The contents of this description should not be construed as limiting the present application.

Claims

A method for adjusting a matching threshold, including:

Obtain the voiceprint feature information of the current user;

Matching the voiceprint feature information of the current user with preset voiceprint feature information to obtain a corresponding target matching degree;

If a preset condition is satisfied between the target matching degree and a preset matching threshold, performing identity verification on the current user;

After the identity verification is passed, the value of the preset matching threshold is adjusted.
The method for adjusting a matching threshold according to claim 1, wherein, if the preset condition is satisfied between the target matching degree and the preset matching threshold, authenticating the current user comprises:

If the target matching degree is less than the preset matching threshold, obtaining a difference between the preset matching threshold and the target matching degree;

If it is detected that the difference is less than or equal to a preset difference, it is determined that a preset condition is satisfied between the target matching degree and the preset matching threshold, and the current user is authenticated.
The method for adjusting a matching threshold according to claim 1, wherein adjusting the value of the preset matching threshold comprises:

Acquiring a plurality of voices of the current user, and extracting target voiceprint feature information from each voice;

Matching all the target voiceprint feature information with the preset voiceprint feature information one by one, and obtaining multiple standby matching degrees;

Calculating an average value of the plurality of standby matching degrees;

Adjusting the value of the preset matching threshold from the current target value to the average value.
The method for adjusting a matching threshold according to claim 3, wherein after adjusting a value of the preset matching threshold from a current target value to the average value, further comprising:

Set a validity period;

When the validity period ends, the value of the preset matching threshold is restored from the average value to the target value.
The method for adjusting a matching threshold according to claim 3, wherein before acquiring the multi-segment voice of the current user, further comprising:

Calculating a percentage difference between the preset matching threshold and the target matching degree;

Converting the percentage difference into a fraction with a hundred denominator;

Determining the number of the numerator of the score as the target value;

Acquiring the multi-segment speech of the current user includes: acquiring a multi-segment speech whose number is the target value.
The method for adjusting the matching threshold according to claim 3, wherein before acquiring the multi-segment voice of the current user, further comprising: setting a preset value;

Acquiring the multi-segment speech of the current user includes: acquiring a plurality of multi-segment speeches with the preset value.
The method for adjusting a matching threshold according to claim 1, wherein the authenticating the current user comprises:

Performing identity verification on the current user through fingerprint recognition, face recognition or iris recognition.
A device for adjusting a matching threshold, including:

An acquisition module, configured to acquire voiceprint feature information of the current user;

A matching module, configured to match the voiceprint feature information of the current user with preset voiceprint feature information to obtain a corresponding target matching degree;

A verification module, configured to perform identity verification on the current user if a preset condition is satisfied between the target matching degree and a preset matching threshold;

An adjustment module is configured to adjust the value of the preset matching threshold after the identity verification is passed.
The apparatus for adjusting a matching threshold according to claim 8, wherein the verification module is configured to:

If the target matching degree is less than the preset matching threshold, obtaining a difference between the preset matching threshold and the target matching degree;

If it is detected that the difference is less than or equal to a preset difference, it is determined that a preset condition is satisfied between the target matching degree and the preset matching threshold, and the current user is authenticated.
The apparatus for adjusting a matching threshold according to claim 9, wherein the adjustment module is configured to:

Acquiring a plurality of voices of the current user, and extracting target voiceprint feature information from each voice;

Matching all the target voiceprint feature information with the preset voiceprint feature information one by one, and obtaining multiple standby matching degrees;

Calculating an average value of the plurality of standby matching degrees;

Adjusting the value of the preset matching threshold from the current target value to the average value.
The apparatus for adjusting a matching threshold according to claim 10, wherein the apparatus further comprises a recovery module, configured to:

Set a validity period;

When the validity period ends, the value of the preset matching threshold is restored from the average value to the target value.
The device for adjusting a matching threshold according to claim 10, wherein the device further comprises a determining module, configured to: calculate a percentage difference between the preset matching threshold and the target matching degree; and set the percentage difference Convert to a fraction with one hundred as the denominator; determine the number of the numerator of the fraction as the target value;

The adjustment module is configured to obtain a plurality of pieces of speech whose quantity is the target value.
A storage medium having stored thereon a computer program, wherein when the computer program is executed on a computer, the computer is caused to perform the method according to any one of claims 1 to 7.
An electronic device includes a memory and a processor, wherein the processor is configured to execute a computer program by calling a computer program stored in the memory:

Obtain the voiceprint feature information of the current user;

Matching the voiceprint feature information of the current user with preset voiceprint feature information to obtain a corresponding target matching degree;

If a preset condition is satisfied between the target matching degree and a preset matching threshold, performing identity verification on the current user;

After the identity verification is passed, the value of the preset matching threshold is adjusted.
The electronic device according to claim 14, wherein the processor is configured to perform:

If the target matching degree is less than the preset matching threshold, obtaining a difference between the preset matching threshold and the target matching degree;

If it is detected that the difference is less than or equal to a preset difference, it is determined that a preset condition is satisfied between the target matching degree and the preset matching threshold, and the current user is authenticated.
The electronic device according to claim 14, wherein the processor is configured to perform:

Acquiring a plurality of voices of the current user, and extracting target voiceprint feature information from each voice;

Matching all the target voiceprint feature information with the preset voiceprint feature information one by one, and obtaining multiple standby matching degrees;

Calculating an average value of the plurality of standby matching degrees;

Adjusting the value of the preset matching threshold from the current target value to the average value.
The electronic device of claim 16, wherein the processor is configured to perform:

Set a validity period;

When the validity period ends, the value of the preset matching threshold is restored from the average value to the target value.
The electronic device of claim 16, wherein the processor is configured to perform:

Calculating a percentage difference between the preset matching threshold and the target matching degree;

Converting the percentage difference into a fraction with a hundred denominator;

Determining the number of the numerator of the score as the target value;

Acquire multiple pieces of speech with the target value.
The electronic device of claim 16, wherein the processor is configured to perform:

Set a preset value;

Acquire multiple pieces of speech with the preset value.
The electronic device according to claim 14, wherein the processor is configured to perform:

Performing identity verification on the current user through fingerprint recognition, face recognition or iris recognition.