Music playing method, music playing device and terminal equipment

Abstract

The present disclosure provides a music playing method, a music playing device and a terminal device, and relates to the technical field of multimedia. The method comprises the following steps: receiving a first voice instruction for requesting to wake up the terminal device; receiving a second voice instruction for requesting to play music; determining whether there is a reference voiceprint feature matching a first voiceprint feature of the first voice instruction in a voiceprint library to obtain a first determination result; determining whether there is a reference voiceprint feature matching a second voiceprint feature of the second voice instruction in the voiceprint library to obtain a second determination result; in the case that the first determination result and the second determination result are both no, determining whether the first voiceprint feature and the second voiceprint feature match to obtain a third determination result; in the case that the third determination result is yes, playing a song, and saving at least one of the first voiceprint feature and the second voiceprint feature as a reference voiceprint feature in the voiceprint library corresponding to a user identifier.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of multimedia technology, in particular to a music playing method, a music playing device and a terminal device. BACKGROUND

[0002] In the related art, a user identity can be recognized based on a voice instruction issued by a user, and some personalized music can be pushed to the user based on the recognized user identity.

[0003] However, this requires the user to spend time and effort to perform voiceprint input in advance to save his own voiceprint features in a voiceprint library, which is not good for user experience. SUMMARY

[0004] To solve the above problems, the embodiments of the present disclosure propose the following solutions.

[0005] According to an aspect of an embodiment of the present disclosure, a music playing method is provided, including: receiving a first voice instruction requesting to wake up a terminal device; receiving a second voice instruction requesting to play music; determining whether there is a reference voiceprint feature matching a first voiceprint feature of the first voice instruction in a voiceprint library to obtain a first determination result; determining whether there is a reference voiceprint feature matching a second voiceprint feature of the second voice instruction in the voiceprint library to obtain a second determination result; in a case where the first determination result and the second determination result are both no, determining whether the first voiceprint feature and the second voiceprint feature match to obtain a third determination result; in a case where the third determination result is yes, playing a song, and saving at least one of the first voiceprint feature and the second voiceprint feature as a reference voiceprint feature corresponding to a user identity in the voiceprint library.

[0006] In some embodiments, the second voice instruction does not include a limitation on a song; the method further includes: in a case where the first determination result and the second determination result are both yes, determining whether a first user identity of the reference voiceprint feature matching the first voiceprint feature and a second user identity of the reference voiceprint feature matching the second voiceprint feature are the same to obtain a fourth determination result; in a case where the fourth determination result is yes, querying a first playing record corresponding to the first user identity; determining a first song based on the first playing record, and playing the first song.

[0007] In some embodiments, the first playing record includes playing information of each song in a first group of played songs, and the playing information includes at least one of a song name and a music style of the song; determining the first song based on the first playing record includes: determining the first song from at least one of a first group of songs and a second group of songs, wherein the first group of songs is determined based on the music style, and the second group of songs is determined based on the song name.

[0008] In some embodiments, the first group of songs is determined according to the following manner: determining a first proportion of each music style in the first playback record; determining one or more music styles whose first proportion is greater than a first threshold; and determining songs conforming to the one or more music styles as the first group of songs.

[0009] In some embodiments, the second group of songs is determined according to the following manner: determining a second proportion of each song in the first playback record; determining one or more songs whose second proportion is greater than a second threshold; querying a second playback record corresponding to a third user identifier different from the first user identifier, the second playback record including the playback information of each song in a second group of played songs, the second group of played songs including the one or more songs; determining a third proportion of each song in the second playback record; and determining songs whose third proportion is greater than a third threshold as the second group of songs.

[0010] In some embodiments, determining songs from the first group of songs and the second group of songs includes: determining a third group of songs belonging to the first group of songs and the second group of songs; and determining the first song from the third group of songs.

[0011] In some embodiments, the playback information of each song further includes a fourth proportion of a playback duration of the song at the end of playback to a total duration; and determining songs based on the first playback record further includes: determining a fourth group of songs whose average value of the fourth proportion in the first playback record is less than a fourth threshold, the first group of songs and the second group of songs not including the fourth group of songs.

[0012] In some embodiments, the method further includes: in the case that the third determination result is no, not saving the first voiceprint feature and the second voiceprint feature, and playing the song.

[0013] In some embodiments, the method further includes: in the case that the fourth determination result is no, entering a sleep mode.

[0014] According to another aspect of the embodiments of the present disclosure, a music playing apparatus is provided, comprising: a receiving module configured to receive a first voice instruction requesting to wake up a terminal device; receive a second voice instruction requesting to play music; a judging module configured to judge whether there is a reference voice feature in a voice feature library matching a first voice feature of the first voice instruction to obtain a first judgment result; judge whether there is a reference voice feature in the voice feature library matching a second voice feature of the second voice instruction to obtain a second judgment result; in a case where the first judgment result and the second judgment result are both no, judge whether the first voice feature and the second voice feature match to obtain a third judgment result; and a playing module configured to play a song in a case where the third judgment result is yes, and save at least one of the first voice feature and the second voice feature as a reference voice feature in the voice feature library corresponding to a user identifier.

[0015] According to still another aspect of the embodiments of the present disclosure, a music playing apparatus is provided, comprising: a memory; and a processor coupled to the memory, the processor being configured to execute the method according to any one of the above embodiments based on instructions stored in the memory.

[0016] According to yet another aspect of the embodiments of the present disclosure, a terminal device is provided, comprising the music playing apparatus according to any one of the above embodiments.

[0017] According to still another aspect of the embodiments of the present disclosure, a computer readable storage medium is provided, comprising computer executable instructions, which, when executed by one or more processors, cause the one or more processors to perform the method according to any one of the above embodiments.

[0018] In the embodiments of the present disclosure, in a case where neither the first voice feature nor the second voice feature can match a reference voice feature in the voice feature library, at least one of the first voice feature and the second voice feature that match each other is saved as a reference voice feature in the voice feature library. In this way, the personalized music can be pushed without additional voice entry, thereby improving user experience. On the other hand, the voice feature is not simply saved after receiving the first voice instruction, but is saved in a case where the third judgment result is yes, so that the storage space of the voice feature library can be effectively utilized. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0020] Figure 1 This is a flowchart of a music playback method according to some embodiments of the present disclosure;

[0021] Figure 2 This is a flowchart of a music playback method according to other embodiments of this disclosure;

[0022] Figure 3 This is a schematic diagram of the structure of a music playback device according to some embodiments of the present disclosure;

[0023] Figure 4 This is a schematic diagram of the structure of a music playback device according to other embodiments of the present disclosure. Detailed Implementation

[0024] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0025] Unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of this disclosure.

[0026] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0027] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0028] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0029] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0030] Figure 1 This is a flowchart of a music playback method according to some embodiments of the present disclosure.

[0031] like Figure 1 As shown, the music playback method includes steps 102 to 112.

[0032] At step 102, a first voice instruction requesting to wake up the terminal device is received.

[0033] It should be understood that the terminal device is capable of receiving voice and playing music. For example, the terminal device can be a smart speaker or a mobile phone, etc.

[0034] In some embodiments, the first voice instruction can include a wake-up word preset by a manufacturer of the terminal device or customized by a user. For example, first, the terminal device is in a sleep mode. After receiving the first voice instruction, the terminal device enters a wake-up mode from the sleep mode, so that step 104 can be performed.

[0035] At step 104, a second voice instruction requesting to play music is received.

[0036] In some embodiments, the second voice instruction can include a limitation on a song. For example, the second voice instruction can include a specific song name or a specific music style, such as pop music, rock music, instrumental music, etc.

[0037] In yet some embodiments, the second voice instruction does not include a limitation on a song. For example, the second voice instruction is “please play music”.

[0038] At step 106, it is determined whether there is a reference voice feature matching the first voice feature of the first voice instruction in a voice feature library, to obtain a first determination result.

[0039] At step 108, it is determined whether there is a reference voice feature matching the second voice feature of the second voice instruction in the voice feature library, to obtain a second determination result.

[0040] Here, a suitable voiceprint recognition algorithm can be used for determination. For example, determination can be made by comparing the distribution of formants of the two voice features.

[0041] In some embodiments, the voice feature library can include a plurality of reference voice features. Each reference voice feature has a corresponding user identifier.

[0042] For example, voice A uttered by a user can be collected in a voice entry stage. A voice feature of the user can be extracted based on voice A, and the voice feature is saved in the voice feature library as a reference voice feature corresponding to the user identifier of the user. When a subsequent voice B (e.g., the first voice instruction or the second voice instruction) uttered by the user is received, the voice feature of voice B can be matched with the reference voice feature in the voice feature library, so that it can be determined that the utterer of voice B and voice A is the same.

[0043] It should be understood that step 106 can be performed after step 104 or before step 104. It should also be understood that step 104 and step 106 can be performed simultaneously.

[0044] At step 110, in the case that the first judgment result and the second judgment result are both no, it is judged whether the first voiceprint feature and the second voiceprint feature match, to obtain a third judgment result.

[0045] In other words, in the case that there is no reference voiceprint feature matching the first voiceprint feature and there is also no reference voiceprint feature matching the second voiceprint feature in the voiceprint library, it is further judged whether the utterers of the first voice instruction and the second voice instruction are the same.

[0046] At step 112, in the case that the third judgment result is yes, the song is played, and at least one of the first voiceprint feature and the second voiceprint feature is saved as a reference voiceprint feature in the voiceprint library corresponding to the user identification.

[0047] In other words, in the case that the utterers of the first voice instruction and the second voice instruction are the same, the song is played, and at least one of the first voiceprint feature and the second voiceprint feature is saved as a reference voiceprint feature in the voiceprint library corresponding to the user identification.

[0048] For example, both the first voiceprint feature and the second voiceprint feature can be saved as reference voiceprint features in the voiceprint library. The first voiceprint feature and the second voiceprint feature correspond to the same user identification. It can be understood that the user identification is different from the user identification of any reference voiceprint feature included in the voiceprint library of steps 106 to 108. In this way, the accuracy of voiceprint recognition can be improved.

[0049] In some embodiments, in the case that the third judgment result is no, the first voiceprint feature and the second voiceprint feature are not saved, and the song is played. In this way, the effective utilization rate of the storage space of the voiceprint library can be improved.

[0050] In the above embodiments, on the one hand, in the case that neither the first voiceprint feature nor the second voiceprint feature can match the reference voiceprint features of the voiceprint library, at least one of the first voiceprint feature and the second voiceprint feature that match each other is saved as a reference voiceprint feature in the voiceprint library. In this way, personalized music pushing can be realized without additional voiceprint registration, thereby improving user experience. On the other hand, the voiceprint feature is not simply saved after receiving the first voice instruction, but is saved in the case that the third judgment result is yes, so that the storage space of the voiceprint library can be effectively utilized.

[0051] Figure 2 is a flowchart of a music playing method according to another embodiment of the present disclosure.

[0052] As shown in Figure 2 The music playing method further includes steps 202 to 206.

[0053] Here, the second voice instruction in step 104 does not include a limitation on the song.

[0054] In step 202, in a case where the first judgment result and the second judgment result are both yes, it is judged whether the first user identity of the reference voiceprint feature matched with the first voiceprint feature and the second user identity of the reference voiceprint feature matched with the second voiceprint feature are the same, to obtain a fourth judgment result.

[0055] In other words, in a case where the reference voiceprint feature matched with the first voiceprint feature and the reference voiceprint feature matched with the second voiceprint feature both exist in the voiceprint library, it is further judged whether the utterer of the first voice instruction and the second voice instruction is the same.

[0056] In step 204, in a case where the fourth judgment result is yes, the first playback record corresponding to the first user identity is queried.

[0057] In other words, when the utterer of the first voice instruction and the second voice instruction is the same, the first playback record corresponding to the first user identity (or the second user identity) is queried.

[0058] In some embodiments, the first playback record includes the playback information of each song in the first set of played songs. The playback information of each song can include at least one of the song name and the music style of the song.

[0059] For example, the voiceprint library includes the reference voiceprint feature of a certain user. Whenever the user utters the first voice instruction and the second voice instruction successively, the song is played for the user, and the playback information of the song is saved to the first playback record corresponding to the identity of the user.

[0060] In some embodiments, in a case where the fourth judgment result is no, the sleep mode is entered. Since the user identity will affect the content of the personalized push, entering the sleep mode in a case where the first user identity and the second user identity are different can ensure the accuracy of the song of the personalized push, so as to improve the user experience.

[0061] It should be understood that the first playback record of the user can reflect the preference of the user for music.

[0062] In step 206, the first song is determined based on the first playback record, and the first song is played.

[0063] In the following, how to determine the first song based on the first playback record will be described in combination with some embodiments.

[0064] In the above embodiments, in the case that the user identifier of the reference voiceprint feature to which the first voiceprint feature and the second voiceprint feature match is the same, the first song determined based on the first play record corresponding to the user identifier is played. In this way, personalized music pushing can be implemented while improving the accuracy of user identity recognition, thereby improving user experience.

[0065] How to determine the first song based on the first play record will be described below in some embodiments.

[0066] In some embodiments, the first song is determined from at least one of the first group of songs and the second group of songs. The first group of songs is determined based on music styles. The second group of songs is determined based on song names.

[0067] Some implementations of determining the first group of songs and the second group of songs will be given below.

[0068] In some implementations, first, a first proportion of each music style in the first play record is determined. Then, one or more music styles whose first proportions are greater than a first threshold value are determined. Finally, songs conforming to the one or more music styles are determined as the first group of songs.

[0069] In some implementations, first, a second proportion of each song in the first play record is determined. Then, one or more songs whose second proportions are greater than a second threshold value are determined. Next, a second play record corresponding to a third user identifier different from the first user identifier is queried. Similarly, the second play record includes play information of each song in a second group of played songs. Here, the second group of played songs includes the one or more songs whose second proportions are greater than the second threshold value. Then, a third proportion of each song in the second play record is determined. Finally, a song whose third proportion is greater than a third threshold value is determined as the second group of songs.

[0070] For example, the first group of songs can be taken as a song library to be played, and the first song in the first group of songs conforming to one or more music styles commonly listened to by the user can be played. In this way, the number of songs in the song library to be played can be ensured while user experience is improved.

[0071] For another example, the second group of songs can be taken as a song library to be played, and the first song in the second group of songs commonly listened to by similar users can be played. In this way, the number of songs in the song library to be played can be ensured while user experience is improved.

[0072] For another example, a third group of songs belonging to the first group of songs and the second group of songs can be determined from the first group of songs and the second group of songs. Then, the third group of songs can be taken as a song library to be played, and the first song determined from the third group of songs can be played. In this way, the number of songs in the song library to be played can be ensured while user experience is further improved.

[0073] In some embodiments, the playback information for each song also includes a fourth proportion of the song's playback duration as a percentage of the total playback duration at the end of playback. In this case, a fourth group of songs can be identified where the average of the fourth proportions for each song in the first playback record is less than a fourth threshold. The first and second groups of songs mentioned above do not include the fourth group of songs.

[0074] Since the fourth ratio can reflect the user's level of liking for the songs, by removing the fourth group of songs whose average fourth ratio is less than the fourth threshold from the first and second groups of songs, the user experience can be further improved while ensuring the number of songs in the library to be played.

[0075] Figure 3 This is a schematic diagram of the structure of a music playback device according to some embodiments of the present disclosure.

[0076] like Figure 3 As shown, the music playback device includes a receiving module 301, a judging module 302, and a playback module 303.

[0077] The receiving module 301 is configured to receive a first voice command requesting to wake up the terminal device; and to receive a second voice command requesting to play music.

[0078] The judgment module 302 is configured to determine whether there is a reference voiceprint feature in the voiceprint library that matches the first voiceprint feature of the first voice command, so as to obtain a first judgment result; determine whether there is a reference voiceprint feature in the voiceprint library that matches the second voiceprint feature of the second voice command, so as to obtain a second judgment result; and if both the first judgment result and the second judgment result are negative, determine whether the first voiceprint feature and the second voiceprint feature match, so as to obtain a third judgment result.

[0079] The playback module 303 is configured to play a song if the third judgment result is yes, and save at least one of the first voiceprint feature and the second voiceprint feature as a reference voiceprint feature corresponding to the user identifier in the voiceprint library.

[0080] In some embodiments, the music playback device further includes a query module (not shown).

[0081] The judgment module 302 is further configured to, when both the first judgment result and the second judgment result are yes, determine whether the first user identifier of the reference voiceprint feature that matches the first voiceprint feature and the second user identifier of the reference voiceprint feature that matches the second voiceprint feature are the same, so as to obtain a fourth judgment result.

[0082] The query module is configured to query the first playback record corresponding to the first user identifier if the fourth judgment result is yes.

[0083] The playing module 303 is further configured to determine the first song based on the first playing record, and play the first song.

[0084] Figure 4 is a structural schematic diagram of a music playing device according to another embodiment of the present disclosure.

[0085] As shown in Figure 4 The music playing device 400 includes a memory 401 and a processor 402 coupled to the memory 401, and the processor 402 is configured to execute the music playing method according to any one of the preceding embodiments based on instructions stored in the memory 401.

[0086] The memory 401 may, for example, include a system memory, a fixed nonvolatile storage medium, etc. The system memory may, for example, store an operating system, an application program, a Boot Loader, and other programs.

[0087] The music playing device 400 may further include an input / output interface 403, a network interface 404, a storage interface 405, etc. These interfaces 403, 404, 405, and the memory 401 and the processor 402 may be connected through a bus 406, for example. The input / output interface 403 provides a connection interface for display, mouse, keyboard, touch screen, and other input / output devices. The network interface 404 provides a connection interface for various networking devices. The storage interface 405 provides a connection interface for external storage devices such as SD card and U disk.

[0088] The present disclosure further provides a terminal device including the music playing device according to any one of the preceding embodiments.

[0089] The present disclosure further provides a computer readable storage medium having computer executable instructions stored thereon, which, when executed by one or more processors, implement the method according to any one of the preceding embodiments.

[0090] So far, the embodiments of the present disclosure have been described in detail. In order to avoid obscuring the concept of the present disclosure, some details known in the art are not described. Those skilled in the art can fully understand how to implement the technical solutions disclosed herein according to the above description.

[0091] Each of the embodiments in the specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the music playing device and terminal device embodiments, since they basically correspond to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiment.

[0092] In addition, in the description of the present disclosure, the terms "first", "second", and the like are used only for descriptive purposes, and cannot be understood as indicating or implying relative importance and sequence.

[0093] Those skilled in the art will understand that the embodiments of the present disclosure can be provided as methods, systems, or computer program products. Therefore, the present disclosure can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present disclosure can take the form of a computer program product implemented on one or more computer-usable non-transitory storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0094] The present disclosure is described with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present disclosure. It should be understood that the functions specified in one or more flows in the flowcharts and / or one or more blocks in the block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce an apparatus that implements the functions specified in the flowchart flow or flows and / or the block diagram block or blocks. Figure 1 The functions specified in one or more flows in the flowcharts and / or one or more blocks in the block diagrams can be implemented by computer program instructions. Figure 1 The functions specified in one or more flows in the flowcharts and / or one or more blocks in the block diagrams can be implemented by computer program instructions.

[0095] These computer program instructions can also be stored in a computer-readable memory that can direct the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction apparatus, which implements the functions specified in the flowchart flow or flows and / or the block diagram block or blocks. Figure 1 The functions specified in one or more flows in the flowcharts and / or one or more blocks in the block diagrams can be implemented by computer program instructions. Figure 1 The functions specified in one or more flows in the flowcharts and / or one or more blocks in the block diagrams can be implemented by computer program instructions.

[0096] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable data processing apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable data processing apparatus provide steps for implementing the functions specified in the flowchart flow or flows and / or the block diagram block or blocks. Figure 1 The functions specified in one or more flows in the flowcharts and / or one or more blocks in the block diagrams can be implemented by computer program instructions. Figure 1 The functions specified in one or more flows in the flowcharts and / or one or more blocks in the block diagrams can be implemented by computer program instructions.

[0097] Although some specific embodiments of the present disclosure have been described in detail by way of example with reference to the drawings, it is to be understood that the above examples are intended to be illustrative only and are not intended to limit the scope of the present disclosure. It is to be understood that modifications or equivalent arrangements of the above embodiments can be made by those skilled in the art without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A method for playing music, comprising: Receive the first voice command requesting to wake up the terminal device; Receive a second voice command requesting the playback of music; Determine whether there is a reference voiceprint feature in the voiceprint database that matches the first voiceprint feature of the first voice command, so as to obtain a first determination result; Determine whether there is a reference voiceprint feature in the voiceprint database that matches the second voiceprint feature of the second voice command, so as to obtain a second determination result; If both the first and second judgment results are negative, determine whether the first voiceprint feature and the second voiceprint feature match to obtain a third judgment result; If the third judgment result is yes, the song is played, and at least one of the first voiceprint feature and the second voiceprint feature is stored in the voiceprint database as a reference voiceprint feature corresponding to the user identifier.

2. The method according to claim 1, wherein, The second voice command does not include restrictions on songs; The method further includes: If both the first and second judgment results are yes, determine whether the first user identifier of the reference voiceprint feature that matches the first voiceprint feature and the second user identifier of the reference voiceprint feature that matches the second voiceprint feature are the same, so as to obtain the fourth judgment result. If the fourth judgment result is yes, query the first playback record corresponding to the first user identifier; The first song is determined based on the first playback record, and the first song is played.

3. The method according to claim 2, wherein, The first playback record includes playback information for each song in the first group of played songs, and the playback information includes at least one of the song name and music style of the song; Based on the first playback record, the first song is determined to include: The first song is determined from at least one of a first group of songs and a second group of songs, wherein the first group of songs is determined based on musical style and the second group of songs is determined based on song title.

4. The method according to claim 3, wherein, The first group of songs was determined as follows: Determine the first proportion of each music style in the first playback record; Identify one or more music styles where the first proportion is greater than a first threshold; Songs that conform to one or more of the aforementioned musical styles are identified as the first group of songs.

5. The method according to claim 3, wherein, The second group of songs was determined as follows: Determine the second proportion of each song in the first playback record; Identify one or more songs whose second proportion is greater than the second threshold; Query the second playback record corresponding to a third user identifier that is different from the first user identifier. The second playback record includes the playback information of each song in the second group of played songs. The second group of played songs includes one or more songs. Determine the third proportion of each song in the second playback record; Songs with a third proportion greater than the third threshold are identified as the second group of songs.

6. The method according to claim 3, wherein, The songs identified from the first and second groups of songs include: Identify the third group of songs that belong to the first group of songs and the second group of songs; The first song is determined from the third group of songs.

7. The method according to any one of claims 3-6, wherein, The playback information for each song also includes the fourth percentage of the total playback time when the song ends; Based on the first playback record, the song also includes: A fourth group of songs is identified, whose average fourth proportion in the first playback record is less than a fourth threshold. The first group of songs and the second group of songs do not include the fourth group of songs.

8. The method according to claim 1, further comprising: If the third judgment result is negative, the first voiceprint feature and the second voiceprint feature are not saved, and the song is played.

9. The method according to claim 2, further comprising: If the fourth judgment result is negative, enter sleep mode.

10. A music playback device, comprising: The receiving module is configured to receive the first voice command requesting the wake-up of the terminal device; Receive a second voice command requesting the playback of music; The judgment module is configured to determine whether there is a reference voiceprint feature in the voiceprint library that matches the first voiceprint feature of the first voice command, so as to obtain a first judgment result. Determine whether there is a reference voiceprint feature in the voiceprint database that matches the second voiceprint feature of the second voice command, so as to obtain a second determination result; if both the first determination result and the second determination result are negative, determine whether the first voiceprint feature and the second voiceprint feature match, so as to obtain a third determination result. The playback module is configured to play a song if the third judgment result is yes, and to store at least one of the first voiceprint feature and the second voiceprint feature as a reference voiceprint feature corresponding to the user identifier in the voiceprint library.

11. A music playback device, comprising: Memory; and A processor coupled to the memory, the processor being configured to perform the method of any one of claims 1-9 based on instructions stored in the memory.

12. A terminal device, comprising: The music playback device according to claim 10 or 11.

13. A computer-readable storage medium comprising computer-executable instructions, which, when executed by one or more processors, cause the one or more processors to perform the method of any one of claims 1-9.

Images