Music playing control method and device, program product and electronic equipment

Abstract

The invention provides a music playing control method and device, a program product and electronic equipment, and relates to the technical field of computers. The method comprises the following steps: playing first music; in response to a music recommendation operation for the first music, determining second music; the second music is music recommended for the current user according to the first music; and playing the second music. According to the method and the device, the music recommendation function is realized, the experience of the user for listening to the music is enriched, the time spent by the user for actively searching the interested music is shortened, the related user operation, page browsing, music audition and the like are reduced, and the resource consumption of the server or the terminal is reduced.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of computer technology, and more specifically, the embodiments of the present disclosure relate to a music playback control method, a music playback control device, a computer program product and an electronic device. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the disclosure that are recited in the claims, and no description herein is admitted to be prior art by inclusion in this section.

[0003] In music apps (Applications), users can usually only listen to the music they select or playlists. Therefore, users often need to actively search for music they are interested in, and in this process they may perform a lot of operations, browse related pages, and listen to related music. Summary of the invention

[0004] The user experience is relatively monotonous as only the selected music or playlist can be listened to. In addition, the process of users actively searching for music of interest may take a lot of time. Since users perform a lot of operations, browse pages, and listen to music during this process, it consumes a lot of resources on the server or terminal.

[0005] In view of the above problems, embodiments of the present disclosure provide a music playback control method, a music playback control device, a computer program product, and an electronic device.

[0006] According to a first aspect of the present disclosure, a music playback control method is provided, including: playing first music; determining second music in response to a music recommendation operation for the first music; the second music is music recommended for a current user based on the first music; and playing the second music.

[0007] Optionally, the method further includes: providing a first control in the playback interface of the first music; and the music recommendation operation for the first music includes: a first preset operation for the first control.

[0008] Optionally, providing a first control in the playback interface of the first music includes: providing a first control in the playback interface of the first music when the first music meets a preset condition.

[0009] Optionally, the first music meets a preset condition, including: the first music is music having a preset association relationship with the current user.

[0010] Optionally, providing the first control in the playback interface of the first music also includes: when the first music does not meet a preset condition, in response to a second preset operation for the first music, providing the first control in the playback interface of the first music; the second preset operation is used to establish a preset association relationship between the first music and the current user.

[0011] Optionally, the method also includes: displaying a first identifier in the playback interface of the first music; the first identifier has a first state and a second state, the first identifier being in the first state indicates that the first music meets a preset condition, and the first identifier being in the second state indicates that the first music does not meet the preset condition.

[0012] Optionally, playing the second music includes: interrupting the playing of the first music and switching to playing the second music; or playing the second music after finishing playing the first music.

[0013] Optionally, the method also includes: providing a first control and a second control in the playback interface of the first music; the music recommendation operation for the first music includes: a first preset operation for the first control, or a third preset operation for the second control.

[0014] Optionally, the playing of the second music includes: in response to a first preset operation for the first control and when the second music is determined to be played, interrupting the playing of the first music and switching to playing the second music; in response to a third preset operation for the second control and when the second music is determined to be played, playing the second music after the playing of the first music is finished.

[0015] Optionally, the music recommendation operation for the first music includes one or more of the following operations: a preset gesture operation; a fourth preset operation for an external device associated with the terminal playing the first music; an operation of controlling the terminal playing the first music to make a preset motion trajectory.

[0016] Optionally, the responding to the music recommendation operation for the first music and determining the second music includes: when the first music satisfies a preset condition, responding to the music recommendation operation for the first music and determining the second music; when the first music does not satisfy the preset condition, responding to the music recommendation operation for the first music, setting the first music to satisfy the preset condition and determining the second music.

[0017] Optionally, the playing of the second music includes: generating a recommended playlist including at least one second music, and playing the second music according to the recommended playlist.

[0018] Optionally, the method also includes: responding to an editing operation on the recommended playlist, adjusting the recommended playlist according to the editing operation; the editing operation includes at least one of the following operations: deleting music from the recommended playlist; adjusting the order of music in the recommended playlist; and adjusting the playback mode of the recommended playlist.

[0019] Optionally, after the second music is finished playing, the method further includes at least one of the following steps: presenting a prompt message or a prompt special effect for indicating the end of the second music playing; switching to playing an initial playlist; the initial playlist is a playlist before determining the second music.

[0020] Optionally, the response to the music recommendation operation for the first music to determine the second music includes: responding to the music recommendation operation for the first music to send a music recommendation request to a server; receiving feedback information from the server, and determining the second music based on the feedback information.

[0021] Optionally, the determining the second music in response to the music recommendation operation for the first music includes: responding to the music recommendation operation for the first music, determining the second music based on user information of the current user and first music information of one or more reference music with which the current user most recently interacted.

[0022] Optionally, determining the second music based on user information of a current user and first music information of one or more reference music with which the current user has recently interacted includes: determining recommendation values ​​of one or more candidate music based on the user information and the first music information; and determining the second music from the candidate music based on the recommendation values.

[0023] Optionally, determining the recommendation value of one or more candidate music based on the user information and the first music information includes: extracting a first feature based on the user information; extracting a second feature based on the first music information and the second music information of the candidate music; fusing the first feature and the second feature to obtain a third feature; and outputting the recommendation value of the candidate music based on the third feature.

[0024] Optionally, extracting the first feature based on the user information includes: combining the user information and the first prompt information to obtain second prompt information; processing the second prompt information using a language model and extracting intermediate features from the language model; and obtaining the first feature based on the intermediate features.

[0025] Optionally, the second prompt information is processed using a language model and intermediate features are extracted from the language model, including: segmenting the second prompt information and encoding it to obtain a word unit encoding sequence; concatenating the word unit encoding sequence with additional word unit encoding and inputting the concatenated word unit encoding into the language model, and obtaining intermediate features output by the language model.

[0026] Optionally, the extracting the second feature based on the first music information and the second music information of the candidate music includes: extracting the first music feature based on the first music information; the first music feature includes music features of each reference music; extracting the second music feature based on the candidate music; determining the similarity between the first music feature and the second music feature; and performing weighted fusion of the music features of each reference music based on the similarity to obtain the second feature.

[0027] Optionally, determining the similarity between the first music feature and the second music feature includes: determining an interaction feature between the first music feature and the second music feature; fusing the first music feature, the second music feature, and the interaction feature and inputting them into a similarity model for processing, and obtaining the similarity based on the processing result.

[0028] Optionally, weighted fusion of music features of each reference music according to the similarity to obtain the second feature includes: determining weights of each reference music according to the similarity, and adding an additional weight to the weight of the first music therein; the first music is the reference music with the most recent interaction time; and weighted fusion of music features of each reference music according to the weights of each reference music to obtain the second feature.

[0029] Optionally, the fusing the first feature and the second feature to obtain a third feature includes: fusing the first feature and the second feature and inputting the fusing features into a feature alignment model for processing to obtain the third feature.

[0030] Optionally, outputting the recommendation value of the candidate music based on the third feature includes: combining the third feature with the second music feature of the candidate music and inputting the combined features into a recommendation prediction model for processing to obtain the recommendation value of the candidate music.

[0031] According to a second aspect of the present disclosure, a music playback control device is provided, including: a first playback module, configured to play a first music; a music determination module, configured to determine a second music in response to a music recommendation operation for the first music; the second music is music recommended for a current user based on the first music; and a second playback module, configured to play the second music.

[0032] According to a third aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method of the first aspect and possible implementation methods thereof are implemented.

[0033] According to a fourth aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the method of the above-mentioned first aspect and its possible implementation methods by executing the executable instructions.

[0034] The present disclosure achieves the following beneficial technical effects:

[0035] A music recommendation function is provided to support users to make music recommendations. The program recommends and plays a second piece of music for users based on the first piece of music currently being played. This broadens the scope of music listening in addition to the music or playlist selected by the user and enriches the user experience. It reduces the time users spend actively searching for music of interest, reduces related user operations, and reduces the number of page browsing, music audition, etc., and reduces the resource consumption of the server or terminal. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A schematic diagram showing an operating environment system architecture in this exemplary embodiment.

[0037] Figure 2 A flowchart of a music playback control method in this exemplary embodiment is shown.

[0038] Figure 3A A schematic diagram showing a playback interface in this exemplary embodiment.

[0039] Figure 3B A schematic diagram showing another playback interface in this exemplary embodiment.

[0040] Figure 3C A schematic diagram showing yet another playback interface in this exemplary embodiment.

[0041] Figure 4 A flowchart for determining a recommended value in this exemplary embodiment is shown.

[0042] Figure 5 A schematic diagram of extracting a first feature in this exemplary embodiment is shown.

[0043] Figure 6 A flow chart for obtaining the second feature in this exemplary embodiment is shown.

[0044] Figure 7 A schematic diagram showing a method of determining similarity in this exemplary embodiment is shown.

[0045] Figure 8 A schematic diagram showing a feature alignment in this exemplary embodiment.

[0046] Fig. 9 A schematic diagram showing a method of determining a recommendation value of candidate music in this exemplary embodiment.

[0047] Fig.10 A schematic structural diagram of a music playing control device in this exemplary embodiment is shown.

[0048] Fig.11 A schematic structural diagram of an electronic device in this exemplary embodiment is shown.

[0049] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts. DETAILED DESCRIPTION

[0050] The following is a detailed description of the principles and spirit of the present disclosure with reference to several representative embodiments of the present disclosure. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present disclosure, and are not intended to limit the scope of the present disclosure in any way. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0051] The embodiments of the present disclosure may be implemented as a system, device, apparatus, method or computer program product. Therefore, the present disclosure may be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software. SUMMARY OF THE INVENTION

[0053] In the related art, users can usually only listen to the corresponding music according to the selected music or playlist, which makes the user experience relatively simple. Users often need to actively search for music they are interested in, which may take a lot of time, and in this process they may perform a lot of operations, browse related pages, and listen to related music, which brings high resource consumption to the server or terminal.

[0054] In view of the above problems, the present disclosure provides a music playback control method, a music playback control device, a computer program product and an electronic device. A music recommendation function is provided to support users to perform music recommendation operations. The program recommends and plays a second music for the user based on the first music currently being played, thereby broadening the scope of listening to music in addition to the music or playlist selected by the user and enriching the user experience. The time spent by users actively searching for music of interest is reduced, and related user operations, as well as browsing pages, auditioning music, etc., are reduced, thereby reducing the resource consumption of the server or terminal.

[0055] After introducing the basic principles of the present disclosure, various non-limiting embodiments of the present disclosure are described in detail below.

[0056] Application Scenario Overview

[0057] It should be noted that the following application scenarios are only shown to facilitate understanding of the spirit and principle of the present disclosure, and the embodiments of the present disclosure are not limited in this respect. On the contrary, the embodiments of the present disclosure can be applied to any applicable scenario.

[0058] The exemplary embodiments of the present disclosure may be used to implement a music recommendation function in scenarios such as music apps, music websites, and music stores, determine second music based on first music, and control the music playback process.

[0059] Figure 1 The system architecture of the operating environment of the embodiment of the present disclosure is shown. The system architecture may include a terminal 110 and a server 120. The terminal 110 may be a mobile phone, a personal computer, a tablet computer, a smart wearable device, etc., and has an audio function. It can run audio-related programs, such as a music app, a music website, a music store, etc., to play the first music or the second music. The terminal 110 has an interactive function, such as being provided with interactive components such as a touch screen, a voice interaction module, a gesture interaction module, or operating devices such as a mouse and a keyboard, so that the user can perform interactive operations such as music recommendation operations. The server 120 is a background for providing music-related services, and may be a server, or a cluster formed by multiple servers. The terminal 110 and the server 120 may be connected via a wired or wireless communication link to achieve information interaction.

[0060] The music playback control method in the embodiments of the present disclosure may be executed by the terminal 110 or the server 120 alone, or may be executed by the terminal 110 and the server 120 together. For example, the terminal 110 may play the first music, respond to the music recommendation operation for the first music, determine the second music, and play the second music. The server 120 may determine the second music based on the user information of the current user and the first music information of one or more reference music that the current user has recently interacted with.

[0061] Exemplary Methods

[0062] An exemplary embodiment of the present disclosure provides a music playback control method. Figure 2 As shown, the music playing control method includes the following steps S210 to S230:

[0063] Step S210, playing the first music.

[0064] The first music is the currently playing music, which may be the music selected by the user to play. When the first music is played, the playing interface of the first music may be displayed, such as Figure 3A The playback interface of the first music (ie, song AA) is shown.

[0065] In one embodiment, the user can select an initial playlist to play, and the first music can be the music in the initial playlist.

[0066] Step S220, in response to the music recommendation operation for the first music, determining the second music; the second music is the music recommended for the current user based on the first music.

[0067] The music recommendation operation is used to recommend similar music to the first music request. It can be an operation performed in the playback interface of the first music, or an operation performed when the currently playing music is the first music. In one embodiment, if the playback is paused during the playback of the first music, such as when the user clicks Figure 3A The pause control “||” in the figure can be considered that the pause state still belongs to the situation where the currently playing music is the first music, and the user can perform music recommendation operations in the pause state.

[0068] The present disclosure does not specifically limit the operation mode of the music recommendation operation. For example, the music recommendation operation can be an operation performed through a specific control, or an operation of shaking the terminal, a gesture operation, a voice operation, etc.

[0069] In one embodiment, the music playback control method may further include the following steps: providing a first control in the playback interface of the first music. Accordingly, the music recommendation operation for the first music may include: a first preset operation for the first control. The first preset operation may be any form of operation such as clicking, long pressing, dragging, etc. Figure 3A As shown, a first control 301 is provided in the playing interface of the first music, and the operation of the user clicking the first control 301 is the first preset operation. It is very convenient to implement the music recommendation operation in this way.

[0070] In one implementation, a first control may be provided in a playback interface of any music, and a user may implement a music recommendation operation for the current music through the first control.

[0071] In one implementation, the first control may be provided only in the playback interface of some music. Exemplarily, the above-mentioned provision of the first control in the playback interface of the first music may include the following steps:

[0072] When the first music meets a preset condition, a first control is provided in the playback interface of the first music.

[0073] The preset condition is used to limit the range of music that can be recommended, and can be set according to experience or specific circumstances. Exemplarily, the first music meeting the preset condition may include: the first music is in a music recommendation library set by the platform.

[0074] In one embodiment, the preset condition may be a condition for the interactivity between the user and the music. Exemplarily, the first music meeting the preset condition may include: the first music is music that has a preset association relationship with the current user. That is, the first music is relatively special music for the current user. The preset association relationship may include, but is not limited to, one or more of the following relationships: the first music is music collected by the current user; the current user has listened to the first music a preset number of times; the current user has listened to the first music for a preset time; the current user has commented on the first music; the first music is in the current user's specific music collection.

[0075] When the first music meets the preset condition, the first control is provided in the playback interface of the first music. In addition, when the first music does not meet the preset condition, the first control may not be provided.

[0076] In one implementation, providing the first control in the playback interface of the first music may further include the following steps:

[0077] When the first music does not meet the preset condition, in response to a second preset operation for the first music, a first control is provided in the playback interface of the first music; the second preset operation is used to establish a preset association relationship between the first music and the current user.

[0078] Among them, if the first music does not meet the preset conditions, the first control is not provided in the playback interface of the first music. If the user performs the second preset operation in this case, and establishes a preset association relationship between the first music and the current user, that is, the first music meets the preset conditions, then the first control can be provided. That is, before the second preset operation is performed, there is no first control in the playback interface of the first music, and after the second preset operation is performed, the first control appears in the playback interface of the first music. Then, the music recommendation operation can be implemented through the first control. This makes it convenient for users to use the music recommendation function in different situations.

[0079] In one embodiment, the music playback control method may further include the following steps:

[0080] A first identifier is displayed in a playback interface of a first music; the first identifier has a first state and a second state, the first identifier being in the first state indicates that the first music meets a preset condition, and the first identifier being in the second state indicates that the first music does not meet the preset condition.

[0081] Figure 3A The first mark 302 is displayed in the playing interface shown, and the first mark 302 is displayed in the first state, indicating that the first music currently meets the preset conditions, such as indicating that the first music is the music that the current user likes. Figure 3B Another schematic diagram of a playback interface of a first music is shown, wherein the first identifier 302 is in the second state, indicating that the first music does not currently meet the preset condition, such as indicating that the first music is not the music that the current user likes. In this way, the user can clearly see whether the first music meets the preset condition through the state of the first identifier.

[0082] In one implementation, the second preset operation may be a trigger operation for the first identifier. Figure 3B As shown, since the first music does not currently meet the preset condition, the first control 301 is not displayed in the playback interface. In this case, if the user clicks the first mark 302, the click operation is the second preset operation, which triggers the first music to be added to the music currently liked by the user, so that the first music meets the preset condition. Figure 3A The playing interface shown includes a first control 301. The user can further perform music recommendation operations through the first control 301.

[0083] In one embodiment, a second control may be provided in the playback interface of the first music. The music recommendation operation for the first music may include: a third preset operation for the second control. The second control may be another control different from the first control. The third preset operation may be any form of operation such as clicking, long pressing, dragging, etc. Figure 3A or Figure 3B As shown, in the first music playback interface, click the "..." (indicates more operations and information) in the lower right corner to trigger the display Figure 3C The playing interface of the first music includes an operation sub-interface, which can be regarded as a part of the playing interface of the first music. The second control 303 is displayed in the operation sub-interface, and the user can click the second control 303 to implement the music recommendation operation.

[0084] In one embodiment, in order to save the playback interface of the first music (which may refer to Figure 3A or Figure 3B The interface space of the main interface of the playback interface shown in the figure may not provide the first control, but provide the second control in the operation sub-interface.

[0085] When the user performs a music recommendation operation, the program can determine the second music. The second music can be determined by the terminal or by the server.

[0086] In one implementation, the above-mentioned determination of the second music in response to the music recommendation operation for the first music may include the following steps:

[0087] In response to the music recommendation operation for the first music, a music recommendation request is sent to the server;

[0088] Receive feedback information from the server, and determine the second music according to the feedback information.

[0089] The music recommendation request may include information about the first music, and may also include user information of the current user, etc. After receiving the music recommendation request, the server may determine a second music similar to the first music based on the information about the first music (and may also be combined with the user information of the current user), and feed back the information about the second music (such as the name and identifier of the second music) to the terminal. The terminal determines the second music based on the feedback information from the server.

[0090] Step S230, play the second music.

[0091] In one implementation, the playing of the first music may be interrupted and switched to the playing of the second music, that is, the playing of the first music may be immediately switched to the playing of the second music when the second music is determined; or the second music may be played after the playing of the first music is finished.

[0092] In one embodiment, a first control and a second control may be provided in the playback interface of the first music. Accordingly, the music recommendation operation for the first music may include: a first preset operation for the first control, or a third preset operation for the second control. For example, the user can click Figure 3A The first control 301 shown in the figure can be used to perform music recommendation operations, or you can click Figure 3C The second control 303 shown is used to perform music recommendation operations.

[0093] In one implementation, playing the second music may include the following steps:

[0094] In response to the first preset operation on the first control, when the second music is determined, interrupting the playing of the first music and switching to playing the second music;

[0095] In response to the third preset operation for the second control, when the second music is determined, the second music is played after the first music is finished playing.

[0096] That is to say, if the user performs a music recommendation operation through the first control, after determining the second music, the user can immediately switch from playing the first music to playing the second music. If the user performs a music recommendation operation through the second control, after determining the second music, the user can wait until the first music is finished before playing the second music. In this way, the user can use two controls to achieve two music recommendation playback methods, and can choose which method to use according to their own needs, which is very flexible and convenient.

[0097] In one implementation, the music recommendation operation for the first music may include one or more of the following operations:

[0098] Preset gesture operation, or preset gesture operation when the first music meets the preset conditions. The preset gesture operation can be determined by the program, such as double-clicking the touch screen or multi-finger touch and pinch gesture operation. The user can implement the music recommendation operation through the preset gesture operation. Or allow the user to implement the music recommendation operation through the preset gesture operation when the first music meets the preset conditions. If the first music does not meet the preset conditions, the preset gesture operation does not generate the music recommendation operation (such as no response after the operation), or the program issues a prompt through voice or other means to prompt that the first music needs to be set to meet the preset conditions before the music recommendation function can be used. Or the user sets the first music to meet the preset conditions and implements the music recommendation operation through the preset gesture operation.

[0099] A fourth preset operation for an external device associated with the terminal playing the first music, or a fourth preset operation for an external device when the first music meets a preset condition. The external devices associated with the terminal include, but are not limited to, headphones, smart watches, smart wearable glasses, etc. The fourth preset operation can be any type of operation for the external device, such as a single or multiple pinching operation of the headphones, a double-click or long press operation of the touch screen of a smart watch, etc. The user can implement the music recommendation operation through the fourth preset operation of the external device, so that there is no need to directly operate the terminal, and the music recommendation operation can even be performed when the terminal is not around. Or the user is allowed to implement the music recommendation operation through the fourth preset operation when the first music meets the preset condition. If the first music does not meet the preset condition, the fourth preset operation does not generate a music recommendation operation (such as no response after the operation), or the program issues a prompt through voice or other means to prompt that the first music needs to be set to meet the preset condition before the music recommendation function can be used. Or the user implements the setting of the first music to meet the preset condition and implements the music recommendation operation through the fourth preset operation.

[0100] The terminal playing the first music is controlled to make a preset motion trajectory, or the terminal is controlled to make a preset motion trajectory when the first music meets the preset conditions. The motion trajectory of the terminal can be detected by an inertial sensor (such as a gyroscope, an accelerometer, etc.) built into the terminal. The preset motion trajectory can be determined based on experience or specific circumstances, such as a trajectory formed by a user holding the terminal to make a specific action (such as shaking it), which is not a natural trajectory under normal use. Detecting that the terminal makes a preset motion trajectory indicates that the user has taken a specific action, and in this case, a music recommendation operation is implemented. Or the user is allowed to make a preset motion trajectory by controlling the terminal when the first music meets the preset conditions to implement the music recommendation operation. If the first music does not meet the preset conditions, the terminal makes a preset motion trajectory without generating a music recommendation operation (such as no response after the user shakes the terminal), or the program issues a prompt by voice or the like to prompt that the first music needs to be set to meet the preset conditions before the music recommendation function can be used. Or the user controls the terminal to make a preset motion trajectory, which can realize setting the first music to meet the preset conditions and implement the music recommendation operation.

[0101] The above music recommendation operation can be performed outside the playback interface of the first music. In this way, the user can perform the music recommendation operation without displaying the playback interface (such as the terminal playing the first music and the screen is locked or turned off), which further improves the user's operational convenience.

[0102] In one implementation, the above-mentioned determination of the second music in response to the music recommendation operation for the first music may include the following steps:

[0103] In the case where the first music meets the preset condition, in response to the music recommendation operation for the first music, determining the second music;

[0104] In the case that the first music does not meet the preset condition, in response to the music recommendation operation for the first music, the first music is set to meet the preset condition, and the second music is determined.

[0105] For example, if the first music is the music that the current user likes, when the user performs a music recommendation operation, the instruction for determining the second music is executed. If the first music is not the music that the current user likes, when the user performs a music recommendation operation, the first music can be added to the music that the current user likes, and the instruction for determining the second music is executed. In this way, when the first music does not meet the preset conditions, the music recommendation operation can be used to achieve two operation results: setting the first music to meet the preset conditions, and recommending the second music. This further improves the user's operational convenience.

[0106] In one implementation, when the first music does not meet the preset condition, the first preset gesture operation is responded to to trigger setting the first music to meet the preset condition, and then the second preset gesture operation is responded to to determine the second music. The operation modes of the first preset gesture operation and the second preset gesture operation may be the same or different. For example, when the first music does not meet the preset condition, the user double-clicks the touch screen for the first time to trigger setting the first music to meet the preset condition, and double-clicks the touch screen for the second time to trigger activation of the music recommendation function and determine the second music.

[0107] In one implementation, playing the second music may include the following steps:

[0108] A recommended playlist including at least one second music is generated, and the second music is played according to the recommended playlist.

[0109] The program may determine one or more second music. In one embodiment, in response to a user performing a music recommendation operation (such as a user clicking a first control), a second music is determined. If the user performs multiple music recommendation operations, multiple second music are determined accordingly.

[0110] All the second music can be formed into a new recommended playlist, which only includes the second music and does not include the music originally played by the current user (such as the first music). The second music can also be added to the initial playlist to form a recommended playlist, such as inserting the second music after the first music in the initial playlist, and the recommended playlist includes the music originally played by the current user and the second music.

[0111] When a recommended playlist is generated, the second music can be played in the order of playback in the recommended playlist. In one embodiment, in response to the user performing multiple music recommendation operations, the second music corresponding to each music recommendation operation is determined, and the second music is added to the recommended playlist in the order of the user's operation. If the user clicks the first control three times in the playback interface of the first music, the program determines the second music B1, B2, and B3 in sequence, B1 corresponds to the first operation, B2 corresponds to the second operation, and B3 corresponds to the third operation, and inserts them into the initial playlist in this order and places them after the first music to form a recommended playlist. According to the recommended playlist, after playing the first music, play B1, then play B2, and finally play B3.

[0112] In one embodiment, the music playback control method may further include the following steps:

[0113] In response to an edit operation on the recommended playlist, the recommended playlist is adjusted according to the edit operation. That is, the user is allowed to edit and adjust the recommended playlist. The edit operation includes at least one of the following operations: deleting music from the recommended playlist; adjusting the order of music in the recommended playlist, such as dragging the tracks in the recommended playlist to adjust the order; adjusting the play mode of the recommended playlist, such as switching between sequential play, single loop, random play and other play modes. The program makes corresponding adjustments to the recommended playlist according to the user's edit operation to meet the user's music listening needs.

[0114] In one implementation, after the second music is played, the music playing control method may further include at least one of the following steps:

[0115] Present a prompt message or prompt special effect for prompting the end of the second music playback. The prompt message can be presented in any form such as text or voice, and the prompt special effect can be a specific visual animation special effect, etc. Exemplarily, when the playback interface of the second music is displayed, the user is prompted to end the playback of the second music by displaying text information, prompt special effects, etc. When the playback interface of the second music is not displayed (such as when the terminal screen is off), the prompt message is presented by voice to prompt the user to end the playback of the second music.

[0116] Switch to playing the initial playlist; the initial playlist is the playlist before the second music is determined. For example, after the second music is finished playing, switch back to playing the first music, or play the tracks after the first music in the initial playlist, etc., so that the user can continue to listen to the music from the original progress.

[0117] The above describes the interactive process of recommending the second music. The following further describes how to determine the appropriate second music.

[0118] In one implementation, the above-mentioned determination of the second music in response to the music recommendation operation for the first music may include the following steps:

[0119] In response to a music recommendation operation for the first music, the second music is determined based on the user information of the current user and the first music information of one or more reference music that the current user has recently interacted with.

[0120] Among them, user information includes but is not limited to: basic user information, such as age, gender, etc.; user's current music interaction behavior information, such as the lyrics of the song the user is browsing; user's recent music interaction behavior information, such as comment information on the songs the user has recently interacted with. The one or more reference music that the current user has recently interacted with refers to the music that the current user has interacted with in the recent period of time. Interaction behaviors include but are not limited to one or more behaviors of listening, commenting, collecting, liking, and sharing. The reference music includes the first music, and the first music is the music with the most recent interaction time. Exemplarily, K (K is a positive integer set based on experience or specific circumstances) music (i.e., reference music) that the user has recently listened to can be obtained, and relevant information of these music can be obtained and recorded as the first music information.

[0121] The program can determine the second music based on the user information and the first music information to ensure that the second music is similar to the reference music including the first music and conforms to the music preference of the current user.

[0122] In one embodiment, the determining of the second music according to the user information of the current user and the first music information of one or more reference music with which the current user has recently interacted may include the following steps:

[0123] Determining recommendation values ​​of one or more candidate music according to the user information and the first music information;

[0124] The second music is determined from the candidate music according to the recommendation value.

[0125] Among them, candidate music is the recommended music that is initially recalled. The present disclosure does not limit the specific method of determining candidate music. Exemplarily, music in the same set as the first music can be used as candidate music. The music in the same set can have the same or similar features such as style, which is equivalent to the result of music clustering. The candidate music thus determined is relatively similar to the first music. In one embodiment, different music can be divided into sets according to features such as style and language in the offline stage, so as to facilitate the rapid recall of candidate music in the music recommendation process. Similar candidate music can also be recalled based on the first music in the offline stage.

[0126] When candidate music is determined, the matching degree of different candidate music and the similarity degree with the first music can be evaluated to obtain the recommendation value. One or more candidate music with the highest recommendation value among the candidate music can be recommended to the current user as the second music.

[0127] In one embodiment, reference Figure 4 As shown, the above-mentioned determination of the recommendation value of one or more candidate music according to the user information and the first music information may include the following steps S410 to S440:

[0128] Step S410: extracting a first feature based on user information.

[0129] The user information may be information based on natural language, and the first feature is information learned by the computer from the information, which may be abstract information, such as a vector, a matrix, etc. For example, the user information may be encoded by embedding, etc. to obtain the first feature. In one embodiment, the first feature may be a user's real-time content preference feature.

[0130] In one implementation, the extracting of the first feature according to the user information may include the following steps:

[0131] Combining the user information and the first prompt information to obtain second prompt information;

[0132] Processing the second prompt information using a language model and extracting intermediate features from the language model;

[0133] The first feature is obtained according to the intermediate feature.

[0134] The language model may be a generative artificial intelligence model, such as an LLM (large language model). A pre-trained language model may be used, or the language model may be trained in a scenario of extracting user information features, such as by fine-tuning. The present disclosure does not limit the training method of the language model.

[0135] The first prompt information may be a prompt information template, which combines the user information and the first prompt information to facilitate the language model to identify key information in the user information. Figure 5 As shown, the user information is filled in according to the items in the first prompt information to obtain the second prompt information.

[0136] The second prompt information may be input into the language model, or the second prompt information may be further processed and then input into the language model. The language model performs a series of feature engineering on the second prompt information, and may extract intermediate features from any one or more intermediate layers of the language model.

[0137] In one implementation, the above-mentioned processing of the second prompt information by using a language model and extracting intermediate features from the feature layer of the language model may include the following steps:

[0138] Segment and encode the second prompt information into words to obtain a word unit encoding sequence;

[0139] The word unit encoding sequence and the additional word unit encoding are concatenated and input into the language model, and the intermediate features output by the language model are obtained.

[0140] Among them, any word segmentation tool can be used to segment the second prompt information, and each word can be encoded, such as obtaining a word vector for each word to form a word unit encoding sequence. The additional word unit encoding can be a preset word encoding or a random word encoding, which is spliced ​​with the word unit encoding sequence, so that the additional word unit encoding occupies at least one position therein, leaving space for the reasoning of the language model, such as being used to store information inferred by the language model based on the word unit encoding sequence. The spliced ​​encoding sequence is input into the language model, and after processing, intermediate features are extracted from the language model, such as the intermediate features output by the last feature layer of the language model (which can be the layer before the output layer) can be obtained.

[0141] Furthermore, the intermediate feature can be used as the first feature, or the intermediate feature can be further processed, such as performing an average pooling operation on the intermediate feature to perform feature compression to obtain the final first feature.

[0142] Figure 5 The schematic diagram of extracting the first feature based on the user information is shown. The user information and the first prompt information are combined to obtain the second prompt information, which can reflect the user context information. The word segmentation and encoding are performed by the word segmenter to obtain the word element encoding sequence [t1, t2, …, t n ], where t i The encoding vector of the i-th character in the second prompt information is n, and n represents the length of the word unit encoding sequence. A randomly initialized word vector can be used as an additional word unit encoding, denoted as T, and it is concatenated with the word unit encoding sequence. The concatenated sequence length is n+1 and is input into the language model. The language model processes the concatenated sequence to obtain a series of intermediate data. The last layer of word vectors in the intermediate data of the language model can be extracted through a specially set feature extraction layer. As an intermediate feature. Finally, the intermediate feature can be compressed by average pooling or other methods to obtain the first feature E that reflects the user's real-time content preference. c , specifically expressed as follows:

[0143]

[0144] Step S420, extracting a second feature based on the first music information and the second music information of the candidate music.

[0145] The first music information includes information about the reference music (including the first music) that the user has recently listened to, such as the name, style, lyrics, duration, etc. of the reference music. The second music information is information about the candidate music, such as the name, style, lyrics, duration, etc. of the candidate music. In one embodiment, for ease of processing, the dimensions of the first music information and the second music information can be set to be the same, such as the first music information includes the name and style, and the second music information also includes the name and style.

[0146] The second feature is a feature extracted based on the combination of the first music information and the second music information, and may include features related to the matching (or similarity) of the first music information and the second music information, and may also include features of the first music information and the second music information, etc. Exemplarily, the first music information and the second music information may be fused to extract the second feature. In one embodiment, the second feature may be a user's real-time music style preference feature.

[0147] In one embodiment, reference Figure 6 As shown, the above-mentioned extraction of the second feature based on the first music information and the second music information of the candidate music may include the following steps S610 to S640:

[0148] Step S610, extracting a first music feature according to the first music information; the first music feature includes music features of each reference music.

[0149] Step S620: extracting a second music feature based on the candidate music.

[0150] For the first music information and the second music information, features of the same category can be extracted, including but not limited to style features, lyrics features, comment features, etc., to obtain the first music feature and the second music feature respectively. Taking the style feature as an example, k reference music that the user has interacted with can be obtained within a specified recent time window to construct a user real-time interaction sequence. Assuming that the current user u belongs to the user set The item collection is The user interaction sequence is in Then, each reference music is mapped to the corresponding style feature through the pre-established style mapping table. Assuming that the style feature set is E, the user's real-time style interaction sequence is: in This sequence is the first music feature. The candidate music can be mapped to the corresponding music style feature through the music style mapping table, which is recorded as Et , which is the second musical feature.

[0151] Step S630: determine the similarity between the first music feature and the second music feature.

[0152] The first music feature includes the music feature of each reference music, and the similarity between the first music feature and the second music feature can be calculated to obtain the similarity between the second music feature and the music feature of each reference music, which is substantially equivalent to the similarity between the candidate music and each reference music. Exemplarily, the music feature of each reference music and the second music feature are both vectors, and the similarity between the vectors (such as cosine similarity) can be calculated to obtain the similarity between the first music feature and the second music feature.

[0153] In one implementation, the above-mentioned determination of the similarity between the first music feature and the second music feature may include the following steps:

[0154] determining an interaction feature between the first music feature and the second music feature;

[0155] The first music feature, the second music feature, and the interactive feature are fused and input into a similarity model for processing, and the similarity is obtained according to the processing result.

[0156] The interactive feature is a feature that combines information from both the first music feature and the second music feature, and can reflect the relationship between the first music feature and the second music feature. For example, the Hadamard product of the first music feature and the second music feature can be calculated as the interactive feature, and the specific calculation formula is as follows:

[0157]

[0158] refer to Figure 7 As shown, the first music feature, the second music feature, and the interactive feature are fused. For example, the three can be spliced ​​through a feature splicing layer and then input into a similarity model for processing. The similarity model can be any type of machine learning model such as DNN (Deep Neural Network). Exemplarily, the similarity model can include DNN, a linear layer, and a sigmoid activation function. The processing result output by the similarity model can be used as the similarity, or the similarity can be obtained after further processing. For example, the result output by the DNN is processed through a linear layer and a sigmoid activation function to output the similarity, and the calculation formula is as follows:

[0159]

[0160] Where σ() is the Sigmoid activation function; W∈R d×1Represents the linear transformation parameters of the linear layer, which is used to map the processing results of the DNN output to one dimension; DNN() represents the processing process of DNN; concat() represents concatenation.

[0161] Step S640, weighted fusion is performed on the music features of each reference music according to the similarity to obtain a second feature.

[0162] Similarity can characterize the similarity between the candidate music and each reference music. In the feature extraction process, reference music with a high degree of similarity to the candidate music can be given priority consideration, which is equivalent to implementing an attention mechanism to focus attention on reference music with a high degree of similarity to the candidate music. Specifically, the weight corresponding to the music features of each reference music can be determined according to the similarity. The higher the similarity, the greater the corresponding weight. Then, the music features of each reference music are weighted and fused to obtain the second feature.

[0163] In one embodiment, the weighted fusion of the music features of each reference music according to the similarity to obtain the second feature may include the following steps:

[0164] Determine the weight of each reference music according to the similarity, and add an additional weight to the weight of the first music among them; the first music is the reference music with the most recent interaction time;

[0165] The music features of each reference music are weighted and fused according to the weight of each reference music to obtain the second feature.

[0166] For example, s(E t ,E s )=[s1,s2,…,s k ], where s i represents the similarity between the music feature of the i-th reference music and the second music feature. The weight of the reference music can be calculated based on the similarity, as follows:

[0167]

[0168] Among them, α i In addition, for the first music, i.e., the kth reference music among the k reference music, an additional weight β is added, which can be set according to experience or specific circumstances, and the weight of the first music is α i +β.

[0169] According to the weight of each reference music, the music features of the corresponding reference music are weighted and fused to obtain the second feature E p , refer to the following formula:

[0170]

[0171] Step S430, fusing the first feature and the second feature to obtain a third feature.

[0172] For example, the first feature and the second feature may be concatenated to obtain the third feature, or the first feature and the second feature may be weightedly fused to obtain the third feature.

[0173] In one embodiment, the above-mentioned fusion of the first feature and the second feature to obtain the third feature may include the following steps:

[0174] The first feature and the second feature are fused and input into the feature alignment model for processing to obtain the third feature.

[0175] The first feature comes from user information, and the second feature comes from music information. They are features of different modalities. The features of the two modalities can be aligned through the feature alignment model to improve the synergy and consistency of different information. Figure 8 As shown, the first feature E c and the second feature E p Splicing, concat the spliced ​​features (E c ,E p ) is then input into the feature alignment model, which can concat(E c ,E p ) c 、E p At least one of them is mapped to a unified feature space, such as E c 、E p The spliced ​​first feature and the second feature are respectively mapped to the aligned first feature E c ' and the aligned second feature E p ', that is, the third feature is obtained

[0176] In one implementation, the third feature may be a user preference feature, reflecting the user's real-time preference information for music.

[0177] In one embodiment, the feature alignment model can be trained by contrastive learning. A first sample feature and a second sample feature can be obtained, the first sample feature is a feature extracted from the sample user information, and the second sample feature is a feature extracted from the music information. The first sample feature and the second sample feature are used to construct a sample pair. If the first sample feature and the second sample feature in the sample pair have correspondence (such as both are features extracted from the user information of the same user and the music information of the interacted music), it is a positive sample pair. If the first sample feature and the second sample feature in the sample pair do not have correspondence, it is a negative sample pair. The sample pair is input into the feature alignment model to be trained, and the similarity (such as cosine similarity) of the aligned first sample feature and the second sample feature is calculated. InfoNCE (Information Noise Contrastive Estimation) loss is used as the contrast loss function, so that the two features of the positive sample pair after alignment by the feature alignment model have a higher similarity, while the two features of the negative sample pair after alignment by the feature alignment model have a lower similarity. The loss function of contrastive learning is as follows:

[0178]

[0179] in, It represents the aligned first sample feature corresponding to the first sample feature in the positive sample pair and the aligned second sample feature corresponding to the second sample feature. It represents the first sample feature after alignment corresponding to the first sample feature and the second sample feature after alignment corresponding to the second sample feature in any sample pair. B is the number of negative samples, and τ is the temperature coefficient, which is a hyperparameter and can be set based on experience or specific circumstances. The parameters of the feature alignment model can be updated through the above loss function.

[0180] Step S440: output the recommendation value of the candidate music according to the third feature.

[0181] For example, the third feature can be processed through a linear model layer to output a recommendation value for the candidate music.

[0182] In one implementation, the outputting of the recommendation value of the candidate music according to the third feature may include the following steps:

[0183] The third feature is combined with the second music feature of the candidate music and then input into the recommendation prediction model for processing to obtain the recommendation value of the candidate music.

[0184] For example, the third feature can be combined with the second music feature E t The concatenation is then input into a multi-layer perceptron as a high-order feature cross module to predict the current user's interest in the candidate music, that is, to obtain the recommendation value. The calculation formula is:

[0185]

[0186] In one embodiment, the cross entropy loss function is used for training, and the collection behavior of user u on sample music i is y u,i ∈{0,1}, the overall loss is:

[0187]

[0188] When the parameters of the feature alignment model are fixed, the parameters of models other than the language model and the feature alignment model (such as the similarity model, the multi-layer perceptron, etc.) can be updated through the above-mentioned overall loss.

[0189] Fig. 9 A schematic diagram of determining a recommendation value for candidate music is shown. The user information of the current user can be obtained, including the lyrics of the song currently browsed and the music reviews that have been interacted with recently. The text information is extracted and fused, and the first prompt information is combined to obtain the second prompt information. The second prompt information is segmented, encoded, and spliced ​​with additional word elements and then input into the language model, and the first feature is extracted from the language model. The k reference music that the current user has interacted with recently are obtained, and the first music feature is obtained through style enhancement processing (such as mapping according to a style mapping table), and the candidate music is subjected to style enhancement processing to obtain the second music feature. The first music feature, the second music feature, and the interactive feature formed by the interaction between the two are input into the similarity model to obtain the similarity. The weight is determined according to the similarity, and the first music feature is weightedly fused and pooled to obtain the second feature. The first feature and the second feature are spliced ​​and input into the feature alignment model to obtain the third feature. The third feature is then input into the multi-layer perceptron for processing to obtain the recommendation value of the candidate music.

[0190] Exemplary Devices

[0191] The exemplary embodiment of the present disclosure also provides a music playback control device. Fig.10 As shown, the music playing control device 1000 includes the following program modules:

[0192] The first playing module 1010 is configured to play the first music;

[0193] The music determination module 1020 is configured to determine a second music in response to a music recommendation operation for the first music; the second music is music recommended for the current user based on the first music;

[0194] The second playing module 1030 is configured to play the second music.

[0195] In one embodiment, the device is also used to: provide a first control in the playback interface of the first music; the music recommendation operation for the first music includes: a first preset operation for the first control.

[0196] In one embodiment, providing a first control in the playback interface of the first music includes: providing a first control in the playback interface of the first music when the first music meets a preset condition.

[0197] In one implementation, the first music meets a preset condition, including: the first music is music that has a preset association relationship with the current user.

[0198] In one embodiment, providing the first control in the playback interface of the first music also includes: when the first music does not meet a preset condition, in response to a second preset operation for the first music, providing the first control in the playback interface of the first music; the second preset operation is used to establish a preset association relationship between the first music and the current user.

[0199] In one embodiment, the device is also used to: display a first identifier in the playback interface of the first music; the first identifier has a first state and a second state, the first identifier being in the first state indicates that the first music meets a preset condition, and the first identifier being in the second state indicates that the first music does not meet the preset condition.

[0200] In one implementation, the playing of the second music includes: interrupting the playing of the first music and switching to playing the second music; or playing the second music after the playing of the first music ends.

[0201] In one embodiment, the device is also used to: provide a first control and a second control in the playback interface of the first music; the music recommendation operation for the first music includes: a first preset operation for the first control, or a third preset operation for the second control.

[0202] In one embodiment, the playing of the second music includes: in response to a first preset operation for the first control, when the second music is determined to be played, interrupting the playing of the first music and switching to playing the second music; in response to a third preset operation for the second control, when the second music is determined to be played, playing the second music after the playing of the first music is finished.

[0203] In one embodiment, the music recommendation operation for the first music includes one or more of the following operations: a preset gesture operation; a fourth preset operation for an external device associated with a terminal that plays the first music; an operation to control the terminal that plays the first music to make a preset motion trajectory.

[0204] In one embodiment, the determining the second music in response to the music recommendation operation for the first music includes: when the first music meets a preset condition, responding to the music recommendation operation for the first music and determining the second music; when the first music does not meet the preset condition, responding to the music recommendation operation for the first music, setting the first music to meet the preset condition and determining the second music.

[0205] In one implementation, the playing of the second music includes: generating a recommended playlist including at least one second music, and playing the second music according to the recommended playlist.

[0206] In one embodiment, the device is also used to: respond to an editing operation on the recommended playlist and adjust the recommended playlist according to the editing operation; the editing operation includes at least one of the following operations: deleting music from the recommended playlist; adjusting the order of music in the recommended playlist; and adjusting the playback mode of the recommended playlist.

[0207] In one embodiment, after the second music is finished playing, the device is also used to perform at least one of the following steps: presenting a prompt message or prompt effect for prompting the end of the second music playing; switching to playing the initial playlist; the initial playlist is the playlist before determining the second music.

[0208] In one embodiment, the response to the music recommendation operation for the first music determines the second music, including: responding to the music recommendation operation for the first music, sending a music recommendation request to a server; receiving feedback information from the server, and determining the second music based on the feedback information.

[0209] In one embodiment, the determining of the second music in response to the music recommendation operation for the first music includes: in response to the music recommendation operation for the first music, determining the second music based on user information of the current user and first music information of one or more reference music that the current user has recently interacted with.

[0210] In one embodiment, determining the second music based on user information of the current user and first music information of one or more reference music with which the current user has recently interacted includes: determining recommendation values ​​of one or more candidate music based on the user information and the first music information; and determining the second music from the candidate music based on the recommendation values.

[0211] In one embodiment, determining the recommendation value of one or more candidate music based on the user information and the first music information includes: extracting a first feature based on the user information; extracting a second feature based on the first music information and the second music information of the candidate music; fusing the first feature and the second feature to obtain a third feature; and outputting the recommendation value of the candidate music based on the third feature.

[0212] In one embodiment, extracting the first feature based on the user information includes: combining the user information and the first prompt information to obtain second prompt information; processing the second prompt information using a language model and extracting intermediate features from the language model; and obtaining the first feature based on the intermediate features.

[0213] In one embodiment, the second prompt information is processed using a language model and intermediate features are extracted from the language model, including: segmenting the second prompt information and encoding it to obtain a word unit encoding sequence; concatenating the word unit encoding sequence with additional word unit encoding and inputting it into the language model, and obtaining the intermediate features output by the language model.

[0214] In one embodiment, the extracting of the second feature based on the first music information and the second music information of the candidate music includes: extracting the first music feature based on the first music information; the first music feature includes the music features of each reference music; extracting the second music feature based on the candidate music; determining the similarity between the first music feature and the second music feature; and performing weighted fusion of the music features of each reference music based on the similarity to obtain the second feature.

[0215] In one embodiment, determining the similarity between the first music feature and the second music feature includes: determining the interaction feature between the first music feature and the second music feature; fusing the first music feature, the second music feature, and the interaction feature and inputting them into a similarity model for processing, and obtaining the similarity based on the processing result.

[0216] In one embodiment, weighted fusion of the music features of the respective reference music according to the similarity to obtain the second feature includes: determining the weights of the respective reference music according to the similarity, and adding an additional weight to the weight of the first music therein; the first music is the reference music with the most recent interaction time; and weighted fusion of the music features of the respective reference music according to the weights of the respective reference music to obtain the second feature.

[0217] In one implementation, fusing the first feature and the second feature to obtain a third feature includes: fusing the first feature and the second feature and inputting the fused features into a feature alignment model for processing to obtain the third feature.

[0218] In one embodiment, outputting the recommendation value of the candidate music according to the third feature includes: combining the third feature with the second music feature of the candidate music and inputting the combined features into a recommendation prediction model for processing to obtain the recommendation value of the candidate music.

[0219] In addition, other specific details of the embodiments of the present disclosure have been described in detail in the embodiments of the above method and will not be repeated here.

[0220] Exemplary Program Products

[0221] The exemplary embodiments of the present disclosure also provide a computer program product, which includes a computer program, and when the computer program is executed by a processor, the above-mentioned virtual action editing method is implemented.

[0222] In one embodiment, the computer program product may be a tangible product containing a computer program, such as a computer-readable storage medium storing a computer program. The readable storage medium may be a storage medium based on electrical, magnetic, optical, electromagnetic, infrared, or other signals, including but not limited to: random access memory (RAM), read-only memory (ROM), magnetic tape, floppy disk, flash memory (Flash), mechanical hard disk (HDD), solid-state drive (SSD), and the like. Exemplarily, the computer program product may be implemented as a non-volatile storage medium storing a computer program, such as a read-only memory, a NAND flash memory, and the like.

[0223] In one embodiment, the computer program product may be an intangible product including a computer program. Exemplarily, the computer program product may be implemented as a virtual digital product, such as a digital file storing an executable file, an installation package, etc. of the computer program.

[0224] The code of the computer program can be written in one or more programming languages. Programming languages ​​such as C language, Java, C++, etc. The program code can be executed entirely on the user computing device, or partially on the user computing device, or as a separate software package, or partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, such as a local area network (LAN), a wide area network (WAN), etc., or can be connected to an external computing device (e.g., an Internet connection provided by an operator).

[0225] Computer programs can be carried or transmitted through electrical, magnetic, optical, electromagnetic, infrared and other signals. Electronic devices can convert signals carrying computer programs into digital signals to run the computer programs. When a computer program is run on an electronic device, its code is used to enable the electronic device to execute (more specifically, the processor of the electronic device can execute) the method steps of various exemplary embodiments of the present disclosure, such as the following steps: S210, play the first music; S220, in response to the music recommendation operation for the first music, determine the second music; the second music is the music recommended for the current user based on the first music; S230, play the second music.

[0226] By executing the above steps on a computer level, a music recommendation function is provided to support users to perform music recommendation operations. The program recommends and plays a second music for the user based on the first music currently being played, thereby broadening the scope of listening to music in addition to the music or playlist selected by the user and enriching the user experience. The time spent by users actively searching for music of interest is reduced, and related user operations, as well as browsing pages, auditioning music, etc., are reduced, thereby reducing the resource consumption of the server or terminal.

[0227] Exemplary Electronic Devices

[0228] The exemplary embodiment of the present disclosure also provides an electronic device. The electronic device includes a processor and a memory, and the memory is used to store executable instructions of the processor. The processor is configured to execute the above method of the present disclosure by executing the executable instructions.

[0229] refer to Fig.11 An electronic device according to an exemplary embodiment of the present disclosure is described. Fig.11 The electronic device 1100 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0230] like Fig.11As shown, the electronic device 1100 is in the form of a general-purpose computing device. The components of the electronic device 1100 may include, but are not limited to: at least one processing unit 1110, at least one storage unit 1120, a bus 1130 connecting different system components (including the storage unit 1120 and the processing unit 1110), an I / O (input / output) interface 1140, a network adapter 1150, a display 1160, and an audio unit 1170.

[0231] The storage unit stores program codes, which can be executed by the processing unit 1110, so that the processing unit 1110 executes the steps according to various exemplary embodiments of the present disclosure described in the above “Exemplary Method” section of this specification. For example, the processing unit 1110 can execute the following steps: S210, play the first music; S220, in response to the music recommendation operation for the first music, determine the second music; the second music is the music recommended for the current user based on the first music; S230, play the second music.

[0232] By executing the above steps by the processing unit 1110, a music recommendation function is provided to support the user to perform music recommendation operations. The program recommends and plays a second music for the user based on the first music currently being played, thereby broadening the scope of listening to music in addition to the music or playlist selected by the user and enriching the user experience. The time spent by the user actively searching for music of interest is reduced, and related user operations, as well as browsing pages, auditioning music, etc., are reduced, thereby reducing the resource consumption of the server or terminal.

[0233] The storage unit 1120 may include a volatile storage unit, such as a random access storage unit (RAM) 1121 and / or a cache storage unit 1122 , and may further include a read-only storage unit (ROM) 1123 .

[0234] The storage unit 1120 may also include a program / utility 1124 having a set (at least one) of program modules 1125, such program modules 1125 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0235] The bus 1130 is used to connect different parts of the electronic device 1100 and may include a data bus, an address bus, a control bus, and the like.

[0236] The electronic device 1100 may also communicate with one or more external devices 1200 (eg, a keyboard, a pointing device, a Bluetooth device, etc.), and such communication may be performed through the I / O interface 1140 .

[0237] Electronic device 1100 can also communicate with one or more networks (such as local area network (LAN), wide area network (WAN) and / or public network, such as the Internet) through network adapter 1150. As shown in the figure, network adapter 1150 communicates with other modules of electronic device 1100 through bus 1130.

[0238] The display 1160 is used to display a graphical user interface, such as a playback interface.

[0239] The audio unit 1170 is used to play audio, such as playing the first music, the second music, etc. It can also be used to receive audio signals.

[0240] It should be understood that although not shown in the figures, other hardware and / or software modules may be used in conjunction with the electronic device 1100, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0241] It should be noted that, although several modules or submodules of the device are mentioned in the above detailed description, such division is merely exemplary and not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules to be embodied.

[0242] In addition, although the operations of the disclosed method are described in a specific order in the drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0243] Although the spirit and principle of the present disclosure have been described with reference to several specific embodiments, it should be understood that the present disclosure is not limited to the disclosed specific embodiments, and the division of various aspects does not mean that the features in these aspects cannot be combined to benefit, and such division is only for the convenience of expression. The present disclosure is intended to cover various modifications and equivalent arrangements included in the spirit and scope of the attached claims.

Claims

1. A music playing control method, characterized in that: include: Play the first music; In response to a music recommendation operation for the first music, determining a second music; The second music is music recommended to the current user based on the first music; Play the second music.

2. The method according to claim 1, characterized in that The method further comprises: Providing a first control in the playback interface of the first music; The music recommendation operation for the first music includes: a first preset operation for the first control.

3. The method according to claim 2, characterized in that The providing a first control in the playback interface of the first music includes: When the first music meets a preset condition, a first control is provided in a playback interface of the first music.

4. The method according to claim 3, characterized in that The first music meets a preset condition, including: the first music is music having a preset association relationship with the current user.

5. The method according to claim 4, characterized in that The providing a first control in the playback interface of the first music further includes: When the first music does not meet the preset condition, in response to a second preset operation for the first music, the first control is provided in the playback interface of the first music; the second preset operation is used to establish a preset association relationship between the first music and the current user.

6. The method according to claim 3, characterized in that The method further comprises: A first identifier is displayed in the playback interface of the first music; the first identifier has a first state and a second state, the first identifier being in the first state indicates that the first music meets a preset condition, and the first identifier being in the second state indicates that the first music does not meet the preset condition.

7. The method according to claim 1, characterized in that The playing of the second music comprises: interrupt the playing of the first music and switch to playing the second music; or After the first music is finished playing, the second music is played.

8. A music playing control device, characterized in that: include: A first playing module is configured to play a first music; a music determination module, configured to determine second music in response to a music recommendation operation for the first music; The second music is music recommended to the current user based on the first music; The second playing module is configured to play the second music.

9. A computer program product having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 7 by executing the executable instructions.

Images