Voiceprint recognition method and device, electronic equipment and storage medium

Abstract

The application provides a voiceprint recognition method, device, electronic equipment and storage medium, the method comprises: online audio splicing step: real-time splicing the received online audio, and storing in the audio storage; voiceprint recognition step: taking the set sleep time as the interval, polling the audio storage, to carry out voiceprint recognition to the online audio stored in the audio storage, and send the voiceprint recognition result to the message queue; voiceprint recognition result taking step: in the set maximum taking number, the voiceprint recognition result is consumed from the message queue in the mode of asynchronous calling. The application optimizes voiceprint recognition, to avoid the situation that there is no effective audio or the effective audio is too short to support the voiceprint recognition result, and avoid the situation that the upstream cannot support long-time waiting for result return, and the conflict situation that the identity verification in the communication process requires returning the result in a short time.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer application, and in particular to a voiceprint recognition method and device, electronic equipment and storage medium. BACKGROUND

[0002] Voiceprint recognition is a kind of biometric technology, also known as speaker recognition, which is a technology for identifying the identity of a speaker through voice. There are two types of voiceprint recognition technology, text-dependent and text-independent. Text-dependent requires the speaker to pronounce according to the specified content, which can achieve good recognition effect, but requires user cooperation; text-independent does not limit the pronunciation content of the speaker, and the model is relatively difficult to establish, but the user experience satisfaction is high and the application range is wide.

[0003] Text-dependent real-time voiceprint recognition technology is commonly used in voice wake-up technology with voiceprint authentication function, a fixed wake-up word is set, and each target speaker has a registered voice. Only when the target speaker's speech content is consistent with the wake-up word, the device wakes up successfully. Text-independent real-time voiceprint recognition technology can be found in identity verification tasks with high real-time requirements. Since users are less likely to accept multiple question inquiries related to verification, and generally need to provide order numbers and other information that need to be specifically consulted, the experience is very poor and seriously affects the work efficiency of front-line customer service, so the verification is carried out by text-independent real-time voiceprint recognition technology, and the verification result is required to be returned within a short time.

[0004] Regardless of text-dependent or text-independent, to achieve good application effect, there is a certain limitation on the effective audio length. The text-dependent effective audio can be relatively short, but generally more than 2 seconds; the text-independent effective time length needs to be longer than the text-dependent, generally more than 8 seconds. However, in many scenarios, the effective audio supporting voiceprint recognition is too short.

[0005] Therefore, how to optimize voiceprint recognition to avoid the conflict situation that there is no effective audio or the effective audio is too short to support the voiceprint recognition result, and the upstream cannot support long-time waiting for result return, while the identity verification in the process of call requires the result to be returned within a short time, is a technical problem to be solved by those skilled in the art. SUMMARY

[0006] The present application is to overcome the defects of the prior art, and provides a voiceprint recognition method, device, electronic equipment and storage medium, thereby optimizing voiceprint recognition to avoid the conflict situation that there is no effective audio or the effective audio is too short to support the voiceprint recognition result, and the upstream cannot support long-time waiting for result return, while the identity verification in the process of call requires the result to be returned within a short time.

[0007] According to an aspect of the present application, a voiceprint recognition method is provided, comprising:

[0008] Online audio splicing step: real-time splicing the received online audio and storing it in an audio storage;

[0009] Voiceprint recognition step: polling the audio storage at a set sleep time interval to perform voiceprint recognition on the online audio stored in the audio storage and send the voiceprint recognition result to a message queue;

[0010] Voiceprint recognition result taking step: using asynchronous calling to consume the voiceprint recognition result from the message queue for a set maximum number of times.

[0011] In some embodiments of the present application, the online audio splicing step comprises:

[0012] Real-time receiving of online audio and audio identification of the online audio;

[0013] Querying whether there is audio associated with the audio identification in the audio storage;

[0014] If there is, splicing the real-time received online audio and the audio stored in the audio storage;

[0015] Storing the spliced online audio in the audio storage,

[0016] Wherein, the length of the spliced audio stored in the audio storage is less than a maximum storage length.

[0017] In some embodiments of the present application, further comprising:

[0018] In response to real-time receiving of the end of a call associated with the audio identification, deleting the audio associated with the audio identification from the audio storage.

[0019] In some embodiments of the present application, the real-time receiving of online audio and the audio identification of the online audio further comprises:

[0020] Performing voice activity detection on the real-time received online audio.

[0021] In some embodiments of the present application, the voiceprint recognition step comprises:

[0022] Polling the audio storage at a set sleep time interval until in this access:

[0023] There is audio associated with the audio identification in the audio storage and the length of the audio is greater than or equal to a minimum effective length, performing voiceprint recognition on the online audio stored in the audio storage and sending the voiceprint recognition result to a message queue; or

[0024] The polling times are greater than the maximum polling times.

[0025] In some embodiments of the present application, the voiceprint recognition result taking step comprises:

[0026] The message queue is consumed at intervals of the set taking time until in this consumption:

[0027] The voiceprint recognition result is obtained; or

[0028] The taking times are greater than the maximum taking times.

[0029] In some embodiments of the present application, further comprising:

[0030] A user tag is obtained according to the voiceprint recognition result;

[0031] The voiceprint recognition result and the user tag are pushed to an agent.

[0032] According to another aspect of the present application, a voiceprint recognition device is also provided, comprising:

[0033] An online audio splicing module is configured to splice the received online audio in real time and store the online audio in an audio storage;

[0034] A voiceprint recognition module is configured to poll the audio storage at intervals of a set sleep time, to perform voiceprint recognition on the online audio stored in the audio storage, and send a voiceprint recognition result to a message queue;

[0035] A voiceprint recognition result taking module is configured to take the voiceprint recognition result from the message queue in a manner of asynchronous calling, with a set maximum taking number.

[0036] According to another aspect of the present application, an electronic device is also provided, comprising: a processor; a storage medium having a computer program stored thereon, the computer program being executed by the processor to perform the steps of the voiceprint recognition method as described above.

[0037] According to another aspect of the present application, a storage medium is also provided, having a computer program stored thereon, the computer program being executed by a processor to perform the steps of the voiceprint recognition method as described above.

[0038] Compared with the prior art, the present application has the following advantages:

[0039] A high timeliness voiceprint recognition system is provided, which can return the voiceprint recognition result to the agent as soon as possible under the calling condition of no valid audio or too short valid audio. Thus, the problems of no valid audio and too short valid audio under calling, long waiting time for result return by upstream, and limitation of actual application on returning the result to the agent within a short time can be avoided. BRIEF DESCRIPTION OF DRAWINGS

[0040] The above and other features and advantages of the present application will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings in which:

[0041] Figure 1 A flow chart of a voiceprint recognition method according to an embodiment of the present application is shown.

[0042] Figure 2 A flow chart of an online audio splicing step according to an embodiment of the present application is shown.

[0043] Figure 3 A flow chart of a voiceprint recognition step according to an embodiment of the present application is shown.

[0044] Figure 4 A flow chart of a voiceprint recognition result taking step according to an embodiment of the present application is shown.

[0045] Figure 5 A module diagram of a voiceprint recognition device according to an embodiment of the present application is shown.

[0046] Figure 6 A schematic diagram of a computer readable storage medium in an exemplary embodiment of the present disclosure is schematically shown.

[0047] Figure 7 A schematic diagram of an electronic device in an exemplary embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0048] Example implementations will now be described more fully with reference to the accompanying drawings. Example implementations may, however, be implemented in many different forms and should not be construed as limited to the examples set forth herein; rather, these implementations are provided so that this disclosure will be thorough and complete, and will fully convey the scope of example implementations to those skilled in the art. The described features, structures, or characteristics can be combined in one or more implementations.

[0049] Further, the accompanying drawings are included to provide a further understanding of the present disclosure and are incorporated in and constitute a part of this specification. The drawings are not necessarily to scale, the same reference numerals in different drawings representing the same or similar elements so as to facilitate understanding of the present disclosure. In the drawings:

[0050] Referring first to Figure 1 , Figure 1 A schematic diagram of a voiceprint recognition method according to an embodiment of the present application is shown. The voiceprint recognition method comprises the following steps:

[0051] Step S110: Online audio splicing step: real-time splicing of received online audio and storage in an audio storage.

[0052] Specifically, the audio storage is, for example, Redis (an open source in-memory storage data structure server, which can be used as a database, cache and message queue agent), which is not limited by the present application.

[0053] Specifically, the online audio splicing step can splice the online audio in real time to meet the shortest valid audio length, thereby solving the problem of no valid audio and too short valid audio when calling. The audio stream segment thrown by the upstream is received in real time, the audio segment is spliced with the previous part after VAD (Voice Activity Detection), and uploaded to the audio storage for storage. The maximum storage length is limited, only the latest audio is retained, and the storage space is reduced while the voiceprint recognition result is returned.

[0054] Step S120: Voiceprint recognition step: polling the audio storage at intervals of a set sleep time to perform voiceprint recognition on the online audio stored in the audio storage, and sending the voiceprint recognition result to a message queue.

[0055] Step S130: Voiceprint recognition result taking step: using an asynchronous calling mode to consume the voiceprint recognition result from the message queue for a set maximum number of times.

[0056] Specifically, the sleep time can be set as needed. The sleep time can also be calculated based on the average time, the shortest time, the median time, etc. obtained by statistical calculation of the time of splicing the online audio to the shortest valid length in the historical audio processing data. The sleep time can be updated with the historical data of a set period to improve the voiceprint recognition efficiency and reduce the waiting time.

[0057] Therefore, in the voiceprint recognition method of the embodiment, the voiceprint recognition is optimized, and the system architecture returns the voiceprint recognition result to the agent as soon as possible under the calling condition of no valid audio or too short valid audio. Therefore, the calling condition of no valid audio or too short valid audio can be avoided, the upstream cannot support long-time waiting for the result to be returned, and the actual application limits the result to be returned to the agent within a short time.

[0058] Reference will now be made to the following Figure 2 , Figure 2 A flowchart of the online audio splicing step according to an embodiment of the present application is shown. Figure 2 The following steps are shown:

[0059] Real-time online audio and audio identification of the online audio are received, and the online audio is subjected to voice activity detection. The purpose of voice activity detection is to identify and eliminate long periods of silence from a sound signal stream, so as to save channel resources without reducing service quality, which is an important part of IP telephone application. Silence suppression can save valuable bandwidth resources and can be beneficial to reduce the end-to-end delay perceived by the user.

[0060] Then, step S201 is performed: determining, according to the audio identification, whether the audio identification has associated audio data in the audio storage 210.

[0061] The audio identification may, for example, be identification information assigned to the audio, or may also be a call identification to distinguish the audio. In some embodiments, there may be agent transfer or other transfer services in the same call, so that the audio identification may also include a call identification and a stage identification, so as to distinguish the online audio in different stages of the same call.

[0062] If step S201 determines yes, step S202 is performed: splicing the audio data associated with the audio identification in the audio storage 210 with the real-time received online audio. After step S202, step S203 is performed.

[0063] Specifically, the real-time received online audio can be directly spliced after the stored audio data. The present application is not limited thereto, and other splicing methods are also within the protection scope of the present application.

[0064] If step S201 determines no, step S203 is performed.

[0065] Step S203: determining whether the length of the spliced audio is greater than the maximum storage length.

[0066] If step S203 determines no, the spliced audio associated with the audio identification is stored in the audio storage 210.

[0067] If the step S203 judges yes, the audio data of the maximum storage length is kept from the spliced audio (for example, the audio data of the latest time is kept), and the kept audio is associated with the audio identifier and stored in the audio storage 210.

[0068] Further, in the embodiment, in response to the real-time receiving of the call end of the audio identifier association, the audio associated with the audio identifier is deleted from the audio storage, so as to reduce the storage occupation space.

[0069] Therefore, the real-time splicing and real-time deletion of the online audio can be realized through the above steps.

[0070] Figure 3 A flow chart of the voiceprint recognition step according to the embodiment of the application is shown. Specifically, the voiceprint recognition service can be called asynchronously, and this part is processed by using a polling mechanism. After the audio satisfying the minimum effective time length is obtained, the processing is performed to return the voiceprint recognition result, and the voiceprint recognition result is pushed to the message queue and waits for the upstream consumption. First, the maximum sleep number is set, and the subsequent steps are shown as follows:

[0071] In some embodiments of the application, the voiceprint recognition step includes:

[0072] When the real-time online audio is received, the step S205 is performed: waiting for the sleep time, and the polling number is initialized to 1.

[0073] The step S206 is performed: the audio associated with the audio identifier of the real-time online audio is extracted from the audio storage 210, and it is judged whether the audio exists and satisfies the minimum effective time length.

[0074] If the step S206 judges no, the step S207 is performed: it is judged whether the current polling number is greater than the maximum polling number.

[0075] If the step S207 judges yes, the step is ended.

[0076] If the step S207 judges no, the step S208 is performed: waiting for the sleep time, and the polling number is increased by 1. Then, the step S206 is continuously performed.

[0077] If the step S206 judges yes, the step S209 is performed: the voiceprint recognition is performed on the obtained audio, and the voiceprint recognition result is sent to the message queue.

[0078] Specifically, the voiceprint recognition can be performed by sequentially extracting the voiceprint features in the audio, comparing with the voiceprints in the library, and thus obtaining the voiceprint recognition result.

[0079] Specifically, the sleep time in step S208 is less than the sleep time in step S205. For example, the sleep time in step S205 is an integer multiple of the sleep time in step S205. Further, the sleep time in step S208 can be set as needed, or can be obtained by statistical calculation according to the variance of the time of online audio splicing to the shortest valid length in the historical audio processing data, so as to improve the voiceprint recognition efficiency. The sleep time in step S208 can be updated with historical data in a set period, so as to improve the voiceprint recognition efficiency and reduce the waiting time.

[0080] Referring to the following Figure 4 , Figure 4 A flowchart of a voiceprint recognition result taking step according to an embodiment of the present application is shown. Figure 4 The following steps are shown:

[0081] After the voiceprint recognition service call succeeds, step S211 is performed: waiting for a set taking time, and initializing the taking number to 1.

[0082] Then step S212 is performed: judging whether there is a recognition result in the message queue 220.

[0083] If step S212 is judged as no, step S213 is performed: judging whether the current taking number is greater than the maximum taking number.

[0084] If step S213 is judged as no, step S214 is performed: waiting for the taking time, and increasing the taking number by 1.

[0085] If step S212 is judged as yes, step S216 is performed: pushing the voiceprint recognition result to the agent.

[0086] If step S213 is judged as yes, step S215 is performed: returning no voiceprint recognition result, and continuing to perform step S216 to push the no voiceprint recognition result to the agent.

[0087] Further, in some embodiments, when the voiceprint recognition result is pushed to the agent, the following steps can also be included: obtaining a user label according to the voiceprint recognition result; and pushing the voiceprint recognition result and the user label to the agent. The user label can include, for example, user gender, user preference, user intention prediction, and the like, so that the agent can provide targeted services according to the user label.

[0088] The above merely describes some implementations of the present application, and the present application is not limited thereto.

[0089] The present application also provides a voiceprint recognition device, Figure 5A schematic diagram of a voiceprint recognition device according to an embodiment of the present application is shown. The voiceprint recognition device 400 comprises an online audio splicing module 410, a voiceprint recognition module 420, and a voiceprint recognition result taking module 430.

[0090] The online audio splicing module 410 is configured to splice the received online audio in real time and store it in an audio storage.

[0091] The voiceprint recognition module 420 is configured to poll the audio storage at intervals of a set sleep time, perform voiceprint recognition on the online audio stored in the audio storage, and send the voiceprint recognition result to a message queue.

[0092] The voiceprint recognition result taking module 430 is configured to take the voiceprint recognition result from the message queue in an asynchronous call manner, with a set maximum number of taking times.

[0093] In the voiceprint recognition device provided by the present application, a high-timeliness voiceprint recognition system is provided, which can return the voiceprint recognition result to the agent as soon as possible in the case of no valid audio or too short valid audio. Thus, the problems of no valid audio or too short valid audio in the calling, long waiting time for the result return by the upstream, and the limitation of the actual application on the result return to the agent within a short time can be avoided.

[0094] Figure 5 The voiceprint recognition device provided by the present application is only schematically shown, and the splitting, merging, and adding of the modules are within the protection scope of the present application without departing from the concept of the present application. The voiceprint recognition device provided by the present application can be realized by software, hardware, firmware, plug-ins, and any combination thereof, and the present application is not limited in this way.

[0095] In the exemplary embodiments of the present disclosure, a computer readable storage medium having a computer program stored thereon is also provided, and the program can implement the steps of the voiceprint recognition method described in any one of the above embodiments when executed by a processor. In some possible implementation manners, various aspects of the present application can also be implemented in the form of a program product, which includes program code for causing a terminal device to perform the steps described in the voiceprint recognition method part of the present specification according to various exemplary embodiments of the present application when the program product is run on the terminal device.

[0096] Reference Figure 6As shown, a program product 400 for implementing the above-described method according to an embodiment of the present application is described, which can take the form of a portable compact disc read-only memory (CD-ROM) and includes a program code, and can be run on an end device, such as a personal computer. However, the program product of the present application is not limited thereto, and in the present document, the readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus or device.

[0097] The program product can take any combination of one or more readable media. The readable media can be a readable signal medium or a readable storage medium. The readable storage medium, for example, can be, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any suitable combination of the above. More specific examples (a non-exhaustive list) of the readable storage medium include an electrical connection having one or more wires, a portable disc, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0098] The computer readable storage medium can include a data signal transported, propagated or transmitted, in baseband or as part of a carrier, having readable program code embodied therein. The data signal can take any number of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination thereof. The computer readable storage medium can be any readable medium that can be read by an instruction execution system, apparatus or device, such as but not limited to one or more memories or one or more storage devices including without limitation semiconductor memory devices, floppy disks, hard disk drives, or any other storage medium. The readable program code embodied on the computer readable storage medium can be transmitted by any programmed medium including, but not limited to, wireless, wired, optical fiber cable, RF, or any suitable combination thereof.

[0099] The program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++, or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the tenant computing device, partly on the tenant device, as a stand-alone software package, partly on the tenant computing device and partly on a remote computing device or entirely on the remote computing device or server. In the latter scenario, the remote computing device can be connected to the tenant computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computing device, such as through the Internet using an Internet Service Provider.

[0100] In an example embodiment of the present disclosure, an electronic device is also provided, which can include a processor, and a memory for storing executable instructions of the processor. Wherein the processor is configured to perform the steps of the voiceprint recognition method in any one of the above embodiments via executing the executable instructions.

[0101] Those skilled in the art can understand that various aspects of the present application can be implemented as a system, a method or a program product. Therefore, various aspects of the present application can be embodied in a form of entirely hardware, entirely software (including firmware, microcode, etc.), or a combination of hardware and software, which can be collectively referred to as "circuitry", "module" or "system".

[0102] The electronic device 600 according to this embodiment of the present application will be described below with reference to Figure 7 Figure 7 The display electronic device 600 is merely an example and should not impose any limitation on the function and use range of the embodiments of the present application.

[0103] As shown in Figure 7 The electronic device 600 is in the form of a general computing device. The components of the electronic device 600 can include, but are not limited to, at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different system components (including the storage unit 620 and the processing unit 610), a display unit 640, etc.

[0104] Wherein the storage unit stores program codes, which can be executed by the processing unit 610, so that the processing unit 610 performs the steps according to various example embodiments of the present application described in the voiceprint recognition method part of the present specification. For example, the processing unit 610 can perform the steps as shown in Figure 1

[0105] The storage unit 620 can include a readable medium in the form of a volatile storage unit, such as a random access memory (RAM) 6201 and / or a cache memory unit 6202, and can further include a read-only memory (ROM) 6203.

[0106] The storage unit 620 can also include program / utilities 6204 with a set of (at least one) program modules 6205, such as an operating system, one or more application programs, other program modules, and program data, each of which or some combination of which can include implementation of a network environment.

[0107] ​​​​​​​​​​​​​​​​​​​​​Bus 630 can be one or more of several types of bus structure including a memory bus or memory controller, a peripheral bus, a graphics bus, a processor or local bus using any of a variety of bus architectures.

[0108] Electronic device 600 can also communicate with one or more external devices 700 such as a keyboard or pointing device, a Bluetooth device, etc.; other devices that enable a user to interact with electronic device 600; and / or any devices (e.g., a router, a modem, a printer, etc.) that enable electronic device 600 to communicate with one or more other computing devices. Such communication can occur via Input / Output (I / O) interface 650. Still yet, electronic device 600 can communicate with one or more networks, such as one or more local area networks (LANs), one or more wide area networks (WANs), and / or the Internet, through network adapter 660. Network adapter 660 can communicate with the other components of electronic device 600 via bus 630. It should be understood that although not shown, other hardware and / or software components could be used in conjunction with electronic device 600. These include, but are not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archival storage systems, etc.

[0109] Those skilled in the art will readily understand that the example embodiments described herein can be implemented by software and / or by software in combination with the necessary hardware. Thus, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash disk, a mobile hard disk, etc.) or a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, or a network device, etc.) to perform the voiceprint recognition method according to the embodiments of the present disclosure.

[0110] Compared with the prior art, the advantages of the present application are that:

[0111] The present application provides a high timeliness voiceprint recognition system, which can return the voiceprint recognition result to the agent as soon as possible under the calling condition of no valid audio or too short valid audio. Thus, the problems of no valid audio and too short valid audio during calling, long waiting time for result return by the upstream, and limitation of the actual application on the result return to the agent within a short time can be avoided.

[0112] Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the features disclosed herein. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

Claims

1. A voiceprint recognition method, characterized in that, include: Online audio splicing steps include: Receive online audio in real time, with audio identifiers associated with a specific call session; The online audio is subjected to voice activity detection to filter out silent portions; The online audio that has been detected by voice activity is spliced ​​in real time with the audio that has been stored in the audio storage and has the same audio identifier, so as to update the audio in the audio storage. Voiceprint recognition steps include: The audio storage is polled at a set sleep time interval until one of the following preset termination conditions is met: a) there is an audio file associated with the audio identifier and with a length greater than or equal to the minimum effective length in the audio storage, or b) the number of polls is greater than the maximum number of polls. Specifically, if and only if the preset termination condition a) is met, voiceprint recognition is performed on the online audio stored in the audio storage that has the audio identifier, and the voiceprint recognition result is sent to the message queue. The steps for obtaining voiceprint recognition results include: The voiceprint recognition results are consumed from the message queue using an asynchronous call method. The voiceprint recognition result retrieval steps specifically include: Consume the message queue at set retrieval intervals until one of the following conditions is met in a single consumption operation: c) Obtain the voiceprint recognition result; or d) The number of consumption operations exceeds the maximum number of takeout operations; It also includes an audio cleanup step: In response to the termination of the call session associated with the audio identifier, the audio associated with the audio identifier is deleted from the audio storage.

2. The voiceprint recognition method as described in claim 1, characterized in that, Also includes: The user tag is obtained based on the voiceprint recognition result; The voiceprint recognition results and the user tags are pushed to the agent.

3. A voiceprint recognition device for implementing the voiceprint recognition method as described in any one of claims 1 to 2, characterized in that, include: Online audio splicing module: used to splice received online audio in real time and store it in the audio storage device; Voiceprint recognition module: used to poll the audio storage at a set sleep time interval to perform voiceprint recognition on the online audio stored in the audio storage, and send the voiceprint recognition result to the message queue; Voiceprint recognition result retrieval module: Used to consume voiceprint recognition results from the message queue using an asynchronous call method, with a set maximum number of retrievals.

4. An electronic device, characterized in that, The electronic device includes: processor; A storage medium having a computer program stored thereon, the computer program being executed by the processor to perform the voiceprint recognition method as described in any one of claims 1 to 2.

5. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, performs the voiceprint recognition method as described in any one of claims 1 to 2.

Images