Music processing method, music processing device, program product and electronic device

Abstract

The invention provides a music processing method, a music processing device, a program product and electronic equipment, and relates to the technical field of computers. The method comprises the following steps: displaying classification information of a first music set in response to a classification operation for the first music set; the classification information comprises one or more music subsets obtained by classifying music in the first music set through an artificial intelligence model; and playing music in a target subset in response to a playing operation for the target subset in the one or more music subsets. According to the invention, the operation process of music classification by the user is simplified, the dependence of the classification result on the label is reduced, and the diversity of the classification result is improved.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology. More specifically, embodiments of the present disclosure relate to a music processing method, a music processing apparatus, a program product, and an electronic device. Background Art

[0002] This section aims to provide background or context for the technical solutions stated in the claims. The description of the related content in this section does not imply an admission that it is prior art.

[0003] In a music application, if a user wants to classify music, they usually need to manually select classification tags. For example, after the user selects tags such as "Mandarin" and "Rap", the program filters out the music that matches both the "Mandarin" and "Rap" tags to form a classified playlist. Summary of the Invention

[0004] However, in the above classification method, the user needs to perform the operation of manually selecting classification tags, which increases the user's operation process, and the classification result depends on the richness of the tags, resulting in a relatively single classification result and affecting the user experience.

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

[0006] According to a first aspect of the present disclosure, there is provided a music processing method, the method comprising: in response to a classification operation on a first music set, displaying classification information of the first music set; the classification information includes: one or more music subsets obtained by classifying the music in the first music set through an artificial intelligence model; in response to a play operation on a target subset among the one or more music subsets, playing the music in the target subset.

[0007] In one embodiment, the step of in response to a classification operation on a first music set, displaying classification information of the first music set includes: providing a classification control on the information interface of the first music set; in response to a first trigger operation on the classification control, displaying the classification information of the first music set.

[0008] In one embodiment, the step of in response to a play operation on a target subset among the one or more music subsets, playing the music in the target subset includes: providing a play control corresponding to each of the music subsets in the classification information; in response to a second trigger operation on the play control corresponding to the target subset, playing the music in the target subset.

[0009] In one embodiment, providing a playback control corresponding to each of the music subsets in the classification information includes: determining a text area corresponding to each of the music subsets in the classification information; and providing a playback control in the text area corresponding to each of the music subsets respectively.

[0010] In one embodiment, playing the music in the target subset includes: determining the music information of the target subset from the classification information; and obtaining and playing the music in the target subset from the music library according to the music information of the target subset.

[0011] In one embodiment, determining the music information of the target subset from the classification information includes: extracting the text information corresponding to the target subset from the classification information; and determining the music information of the target subset according to the text information corresponding to the target subset.

[0012] In one embodiment, displaying the classification information of the first music set includes: generating classification prompt information about the first music set; and requesting an artificial intelligence model to process the classification prompt information to obtain and display the classification information.

[0013] In one embodiment, generating the classification prompt information about the first music set includes: generating the classification prompt information according to the music preference information of the user associated with the first music set and the music information of the first music set.

[0014] In one embodiment, the classification information includes historical classification information and / or current classification information; responding to a classification operation on the first music set and displaying the classification information of the first music set includes: in response to a classification operation on the first music set, if there is historical classification information of the first music set, displaying the historical classification information; the historical classification information is the classification information obtained by classifying the music in the first music set through an artificial intelligence model before the classification operation; in response to a classification operation on the first music set, if there is no historical classification information of the first music set, requesting the artificial intelligence model to classify the current music in the first music set to obtain and display the current classification information.

[0015] In one embodiment, the method further includes: in the case of displaying the historical classification information, in response to a classification update operation, requesting the artificial intelligence model to classify the current music in the first music set to obtain and display the current classification information.

[0016] In one embodiment, the method further includes: when displaying the current classification information, in response to a classification update operation, displaying the updated current classification information; the updated current classification information includes: one or more music subsets obtained by reclassifying the current music in the first music set through an artificial intelligence model.

[0017] In one embodiment, the classification update operation includes: a third trigger operation on a classification update control provided in the display interface of the classification information.

[0018] In one embodiment, the classification information includes historical classification information and / or current classification information; the step of displaying the classification information of the first music set in response to a classification operation on the first music set includes: in response to a classification operation on the first music set, if there is historical classification information of the first music set and the music corresponding to the historical classification information is the same as the current music in the first music set, then displaying the historical classification information; the historical classification information is classification information obtained by classifying the music in the first music set through an artificial intelligence model before the classification operation; in response to a classification operation on the first music set, if there is no historical classification information of the first music set, or there is historical classification information of the first music set but the music corresponding to the historical classification information is different from the current music in the first music set, then requesting the artificial intelligence model to classify the current music in the first music set, and obtaining and displaying the current classification information.

[0019] In one embodiment, playing the music in the target subset includes: using the target subset as the current playlist, or adding the music in the target subset to the playlist before the play operation to obtain the current playlist; playing the music in the current playlist.

[0020] In one embodiment, the first music set includes one or more of the following: a set of music for which the user has performed a preset operation; a music set selected by the user from a candidate music set during a classification operation; a set of music recommended for the user.

[0021] According to a second aspect of the present disclosure, there is provided a music processing apparatus, the apparatus includes: a classification information display module configured to display the classification information of the first music set in response to a classification operation on the first music set; the classification information includes: one or more music subsets obtained by classifying the music in the first music set through an artificial intelligence model; a music subset play module configured to play the music in the target subset in response to a play operation on the target subset among the one or more music subsets.

[0022] In one embodiment, in response to a classification operation on a first music set, displaying classification information of the first music set includes: providing a classification control on an information interface of the first music set; and in response to a first trigger operation on the classification control, displaying the classification information of the first music set.

[0023] In one embodiment, in response to a play operation on a target subset among the one or more music subsets, playing music in the target subset includes: providing a play control corresponding to each of the music subsets in the classification information; and in response to a second trigger operation on the play control corresponding to the target subset, playing music in the target subset.

[0024] In one embodiment, providing a play control corresponding to each of the music subsets in the classification information includes: determining a text area corresponding to each of the music subsets in the classification information; and respectively providing a play control in the text area corresponding to each of the music subsets.

[0025] In one embodiment, playing music in the target subset includes: determining music information of the target subset from the classification information; and according to the music information of the target subset, obtaining and playing music in the target subset from a music library.

[0026] In one embodiment, determining music information of the target subset from the classification information includes: extracting text information corresponding to the target subset from the classification information; and determining the music information of the target subset according to the text information corresponding to the target subset.

[0027] In one embodiment, displaying the classification information of the first music set includes: generating classification prompt information about the first music set; requesting an artificial intelligence model to process the classification prompt information, and obtaining and displaying the classification information.

[0028] In one embodiment, generating classification prompt information about the first music set includes: generating the classification prompt information according to music preference information of a user associated with the first music set and music information of the first music set.

[0029] In one embodiment, the classification information includes historical classification information and / or current classification information; the displaying of the classification information of the first music set in response to a classification operation on the first music set includes: in response to a classification operation on the first music set, if there is historical classification information of the first music set, then display the historical classification information; the historical classification information is classification information obtained by classifying the music in the first music set through an artificial intelligence model before the classification operation; in response to a classification operation on the first music set, if there is no historical classification information of the first music set, then request the artificial intelligence model to classify the current music in the first music set, and obtain and display the current classification information.

[0030] In one embodiment, the classification information display module is further configured to: in the case of displaying the historical classification information, in response to a classification update operation, request the artificial intelligence model to classify the current music in the first music set, and obtain and display the current classification information.

[0031] In one embodiment, the classification information display module is further configured to: in the case of displaying the current classification information, in response to a classification update operation, display the updated current classification information; the updated current classification information includes: one or more music subsets obtained by reclassifying the current music in the first music set through an artificial intelligence model.

[0032] In one embodiment, the classification update operation includes: a third trigger operation on a classification update control provided in the display interface of the classification information.

[0033] In one embodiment, the classification information includes historical classification information and / or current classification information; the displaying of the classification information of the first music set in response to a classification operation on the first music set includes: in response to a classification operation on the first music set, if there is historical classification information of the first music set and the music corresponding to the historical classification information is the same as the current music in the first music set, then display the historical classification information; the historical classification information is classification information obtained by classifying the music in the first music set through an artificial intelligence model before the classification operation; in response to a classification operation on the first music set, if there is no historical classification information of the first music set, or there is historical classification information of the first music set but the music corresponding to the historical classification information is different from the current music in the first music set, then request the artificial intelligence model to classify the current music in the first music set, and obtain and display the current classification information.

[0034] In one embodiment, playing the music in the target subset includes: taking the target subset as the current playlist, or adding the music in the target subset to the playlist before the play operation to obtain the current playlist; and playing the music in the current playlist.

[0035] In one embodiment, the first music collection includes one or more of the following: a collection of music on which the user has performed preset operations; a collection of music selected by the user from a candidate music collection when performing a classification operation; and a collection of music recommended to the user.

[0036] According to a third aspect of the present disclosure, a computer program product 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.

[0037] 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.

[0038] The embodiments of the present disclosure have the following technical effects:

[0039] In response to a classification operation on a first music collection, classification information of the first music collection, which is obtained through classification by an artificial intelligence model, is displayed. In response to a play operation on a target subset, music in the target subset is played. An intelligent music classification function is provided. On the one hand, when performing a classification operation, the user does not need to manually select a classification label, and can quickly jump from the classification information to the target subset to be played, simplifying the user's operation process. On the other hand, the capabilities of the artificial intelligence model can be used to explore deep-level features in the music and classify it accordingly, reducing the dependence of the classification results on labels, which is conducive to increasing the diversity of the classification results and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 A system architecture diagram in an embodiment of the present disclosure is shown.

[0041] Figure 2 A flowchart of a music processing method in an embodiment of the present disclosure is shown.

[0042] Figure 3 A schematic diagram illustrating a first music collection in an embodiment of the present disclosure is shown.

[0043] Figure 4 A schematic diagram showing classification information in an embodiment of the present disclosure.

[0044] Figure 5A schematic diagram showing a playback interface in an embodiment of the present disclosure.

[0045] Figure 6 A schematic flowchart showing a music processing method in an embodiment of the present disclosure.

[0046] Figure 7 A schematic flowchart showing a music classification processing flow based on different technical layers in an embodiment of the present disclosure.

[0047] Figure 8 A schematic diagram showing a front-end component in an embodiment of the present disclosure.

[0048] Figure 9 A schematic structural diagram showing a music processing device in an embodiment of the present disclosure.

[0049] Figure 10 A schematic structural diagram showing an electronic device in an embodiment of the present disclosure.

[0050] In the drawings, the same or corresponding reference numerals indicate the same or corresponding parts. Detailed Embodiments

[0051] The principles and spirit of the present disclosure will be elaborated in detail below 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 do not 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 convey the scope of the present disclosure to those skilled in the art completely.

[0052] The embodiments of the present disclosure can be implemented as a system, a device, an apparatus, a method, or a computer program product. Therefore, the present disclosure can be specifically implemented in the following forms: completely in hardware, completely in software (including firmware, resident software, microcode, etc.), or in a form combining hardware and software. Summary of the Invention

[0054] In the related art, if a user wants to classify music in a music application, usually the user needs to manually select classification tags. For example, after the user selects the tags of "Mandarin" and "Rap", the program filters out the music that matches both the "Mandarin" and "Rap" tags to form a classified playlist.

[0055] However, in the above classification method, the user needs to perform the operation of manually selecting classification tags, which increases the user's operation process, and the classification result depends on the richness of the tags, resulting in a relatively single classification result and affecting the user experience.

[0056] In view of the above, the present disclosure provides a music processing method, a music processing device, a program product and an electronic device. In response to a classification operation on a first music set, the classification information of the first music set is displayed, which is obtained through classification by an artificial intelligence model. In response to a playback operation on a target subset, the music in the target subset is played. An intelligent music classification function is provided. On the one hand, when performing a classification operation, the user does not need to manually select a classification label, and can quickly jump from the classification information to the playback target subset, which simplifies the user's operation process. On the other hand, by utilizing the capabilities of the artificial intelligence model, it is possible to explore the deep-level features in the music and classify it accordingly, reducing the dependence of the classification results on labels, which is conducive to improving the diversity of the classification results and enhancing the user experience.

[0057] After introducing the basic principles of the present disclosure, various non-limiting embodiments of the present disclosure are described in detail below.

[0058] Application Scenario Overview

[0059] It should be noted that the following application scenarios are only shown to facilitate understanding of the spirit and principles of the present disclosure. The embodiments of the present disclosure are not limited in this respect and can be applied to any applicable scenarios.

[0060] The embodiments of the present disclosure are applicable to music applications, such as music apps (applications), music services provided through web pages (such as music websites), or music applets installed in other programs. The embodiments of the present disclosure implement an intelligent music classification function. When a user wants to classify a first music collection, the classification operation can trigger the display of classification information, which includes one or more classification subsets obtained by the artificial intelligence model. The user can then select any subset to play.

[0061] 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 device 110 and a server 120. The terminal device 110 may be a mobile phone, a personal computer, a tablet computer, a smart wearable device, etc., and has an audio function, which can run music-related applications, such as music apps, music websites, music applets, etc. In addition, the terminal device 110 has a display function, which can display classification information and other music-related information. The server 120 is a background for providing music-related services, which may be a server or a cluster formed by multiple servers. In one embodiment, the server 120 may include a first service system and a second service system, the first service system provides music services, and the second service system provides artificial intelligence services, such as providing music classification services based on artificial intelligence models. The terminal device 110 and the server 120 can be connected through a wired or wireless communication link to achieve information interaction.

[0062] The music processing method in the embodiments of the present disclosure can be executed independently by the terminal device 110 or the server 120, or jointly executed by the terminal device 110 and the server 120.

[0063] In one embodiment, the music processing method can be executed independently by the terminal device 110 without setting up the server 120. For example, an artificial intelligence model can be deployed locally on the terminal device 110, and the music App can be run by the terminal device 110 in a single-machine environment to provide music classification services through the local artificial intelligence model.

[0064] Exemplary method

[0065] The music processing method in the embodiments of the present disclosure will be described exemplarily below. Figure 2 The flowchart of the music processing method is shown, which may include steps S210 and S220. Each step will be described in detail below. Figure 2 in

[0066] In step S210, in response to a classification operation for the first music set, display the classification information of the first music set; the classification information includes: one or more music subsets obtained by classifying the music in the first music set through an artificial intelligence model.

[0067] Among them, a music set refers to a collection of music, which is composed of one or more pieces of music and may include, but is not limited to, forms such as playlists, albums, and playlists. The first music set is the music set that the user needs to classify and can be any music set. Exemplarily, the first music set includes one or more of the following:

[0068] ① A collection of music for which the user has performed a preset operation. Among them, the preset operation can be operations such as like and favorite. For example, when listening to music, the user can click the like control (such as a heart-shaped control) to add the music to the collection of "My Favorite Music", and this collection can be used as the first music set.

[0069] ② A music set selected by the user from the candidate music sets when performing the classification operation. Among them, the candidate music sets can include music sets created by the user, collected music sets, etc. For example, on the user's personal page, all the music sets created and collected by the user are displayed, and the user can select any one or more of them as the first music set for classification operations.

[0070] ③ A collection of music recommended for the user. Among them, the program can recommend music sets that match the user's music preference information, music sets that match the current environment, popular music sets, etc. The user can use one or more of these music sets as the first music set for classification operations.

[0071] It should be noted that the above user can be the user currently logged in to the music application.

[0072] The classification operation is an operation by which the user triggers the display of classification information. The present disclosure does not limit the specific operation manner of the classification operation. For example, the classification operation can be an operation performed through a specific control, or a voice instruction operation, etc.

[0073] In one implementation manner, the above-mentioned displaying the classification information of the first music set in response to the classification operation for the first music set may include the following steps:

[0074] Provide a classification control on the information interface of the first music set;

[0075] In response to a first trigger operation on the classification control, display the classification information of the first music set.

[0076] Exemplarily, the user can click on the first music set in their personal page to trigger entering the information interface of the first music set. This interface can refer to Figure 3 as shown, display information such as the name, cover image, and track list of the first music set, and provide a classification control 301. The first trigger operation can be an operation such as a single click, double click, long press, etc. When the user performs a first trigger operation on the classification control 301, it triggers the display of the classification information of the first music set. In this way, the user can complete the classification operation in the information interface of the first music set, which is relatively convenient.

[0077] In the implementation manner of the present disclosure, the music in the first music set is classified by an artificial intelligence model. The artificial intelligence model includes, but is not limited to, large language models (LLMs), generative models, general large models, domain-specific models, etc. It can be a pre-trained model or a model that has been fine-tuned for the music classification scenario. The artificial intelligence model can capture deep-level features such as semantics and emotions in music, does not rely on explicit labels such as language, artist, music type, etc., and can find the commonalities of different music at the semantic and emotional levels, realizing deep-level music classification, thereby breaking through the limitations of labels and bringing intelligent classification results.

[0078] The classification information can be the classification result provided by the artificial intelligence model, or the information generated based on the classification result, such as adding other explanatory content on the basis of the classification result to form the final classification information. The classification information includes one or more music subsets obtained by classification. Figure 4 shows a schematic diagram of the classification information. When the user clicks on the classification control 301 in the Figure 3 information interface as shown, it can jump to Figure 4The classification interface shown displays classification information. The classification information lists the names and track lists of each music subset, so that users can clearly see the classification results.

[0079] In one implementation, the above-displaying the classification information of the first music set may include the following steps:

[0080] Generate classification hint information about the first music set;

[0081] Request an artificial intelligence model to process the classification hint information, and obtain and display the classification information.

[0082] Among them, the classification hint information is information used to prompt the artificial intelligence model to classify the first music set, and can be the prompt information (prompt) input into the artificial intelligence model, describing the first music set and the user's classification requirements, etc. In one implementation, the music information of the first music set can be combined with a preset classification hint template to obtain the classification hint information. For example, the music information of the first music set includes, but is not limited to, the name, artist, album, etc. of each music in the first music set, and these information are filled into the fixed slots in the preset classification hint template to form the classification hint information.

[0083] In one implementation, the above-generating the classification hint information about the first music set may include the following steps:

[0084] Generate classification hint information according to the music preference information of the user associated with the first music set and the music information of the first music set.

[0085] Among them, the user associated with the first music set can be the user who created or collected the first music set, or the user targeted by the system's recommendation of the first music set. When performing the classification operation for the first music set, the currently logged-in user is the user associated with the first music set. The user's music preference information may include: information statistically analyzed from the user's recent (such as the last month, the last half year, etc.) or long-term music listening behavior, or information obtained by feature extraction after statistics, etc. For example, the user's recent music listening time can be statistically analyzed to obtain the time when the user likes to listen to music (such as commuting time every day, early morning), the music genres and semantics that the user often listens to recently are statistically analyzed, and these statistically analyzed information are used as music preference information. Combine the music preference information and the music information of the first music set to generate the classification hint information. For example, fill the music preference information and the music information of the first music set into the fixed slots in the preset classification hint template to form the classification hint information.

[0086] After generating the classification prompt information, request the artificial intelligence model to process the classification prompt information. For example, the interface of the artificial intelligence model can be called, and the classification prompt information can be input into the interface, so that the artificial intelligence model processes the classification prompt information. The artificial intelligence model can feedback the classification information and display it in the graphical user interface of the terminal device, or after the terminal device receives the classification result feedback by the artificial intelligence model, obtain the classification information according to the classification result and display it in the graphical user interface.

[0087] Through the above method, after the user performs the classification operation, the classification prompt information can be automatically generated and the artificial intelligence model can be requested to process it, without the user inputting the classification prompt information and performing the operation of interacting with the model, which simplifies the operation process.

[0088] In one implementation, the music in the first music collection can be classified in the following way:

[0089] According to the user's music preference information, generate one or more groups of music preference features. For example, the music preference information can be encoded to obtain the music preference features.

[0090] According to the music information of the first music collection, extract features (such as semantic features, emotion features, etc.) for each music in the first music collection to obtain the music features of each music.

[0091] Match the music features of each music with each group of music preference features respectively. If the match is successful, the corresponding music is classified into the music subset corresponding to the music preference features. For example, the music preference features and music features can be represented in the form of vectors, matrices, etc. When matching the music features and music preference features, the similarity between the vectors and matrices can be calculated. If the similarity reaches the preset similarity threshold, it means that the music features and music preference features match successfully. Thus, deep music classification is achieved.

[0092] In one implementation, the information related to the artificial intelligence model can be not displayed. For example, only the classification information is displayed, and it is not displayed that the classification information is provided by the artificial intelligence model, so that the user has no perception of the artificial intelligence model and reduces the user's understanding cost.

[0093] In another implementation, the information related to the artificial intelligence model can be displayed. For example, it is displayed that the classification information is provided by a certain artificial intelligence model. Even the analysis process information of the artificial intelligence model can be displayed. This is convenient for the user to understand the classification logic and improves the user's recognition of the classification information.

[0094] Continue to refer to Figure 2 In step S220, in response to the play operation for the target subset in one or more music subsets, play the music in the target subset.

[0095] Among them, the target subset is the music subset selected by the user from the above one or more music subsets for current playback. The playback operation is an operation used to trigger the playback of the target subset. The present disclosure does not limit the specific operation manner of the playback operation. For example, the playback operation can be an operation performed through a specific control, or a voice instruction operation, etc. Exemplarily, the classification information includes the above one or more music subsets, and the user can select any one of the music subsets for the playback operation. For example, after selecting a certain music subset for the playback operation, the music subset selected by the user is the target subset, and the playback operation performed by the user can trigger the playback of the music in the target subset.

[0096] In one implementation manner, the above-mentioned playing the music in the target subset in response to the playback operation for the target subset in one or more music subsets may include the following steps:

[0097] Provide playback controls corresponding to each music subset in the classification information;

[0098] In response to a second trigger operation for the playback control corresponding to the target subset, play the music in the target subset.

[0099] Among them, the classification information is usually text information. Providing the playback controls corresponding to each music subset in the classification information enables the classification information to be operated by the user to achieve fast playback of the target subset. Refer to Figure 4 As shown, playback controls 3021, 3031, and 3041 corresponding to each music subset can be provided in the classification information.

[0100] In one implementation manner, the above-mentioned providing the playback controls corresponding to each music subset in the classification information may include the following steps:

[0101] Determine the text areas corresponding to each music subset in the classification information;

[0102] Provide playback controls in the text areas corresponding to each music subset respectively.

[0103] Among them, the text area corresponding to the music subset refers to the area where the text information used to describe the music subset is located in the classification information. For example, referring to Figure 4 the classification information shown, the music subset "Late Night Self-Healing Cabin" corresponds to the text area 3022, the music subset "Rock Painkiller" corresponds to the text area 3032, and the music subset "Rainy Day Shelter" corresponds to the text area 3042. In one implementation manner, the classification identifiers in the classification information can be recognized, such as Figure 4The classification numbers "1", "2", "3" in it, or the delimiters that divide different music subsets, etc. Determine the text area corresponding to each music subset according to the classification identifier. For example, the text area corresponding to each music subset is the text area between two adjacent classification numbers or delimiters.

[0104] In the case of determining the text area corresponding to each music subset, corresponding playback controls can be provided in each text area respectively. For example, in Figure 4 In the classification information shown, a playback control 3021 is provided in the text area 3022, a playback control 3031 is provided in the text area 3032, and a playback control 3041 is provided in the text area 3042. The correspondence between each playback control and each music subset is realized.

[0105] The second trigger operation can be an operation such as a single click, a double click, a long press, etc. Taking Figure 4 as an example, when the user performs a second trigger operation on the playback control 302, it is determined that the music subset "Late Night Self-Healing Cabin" corresponding to the playback control 3021 is the target subset, and the music in the target subset is played.

[0106] Through the above method, the correspondence between the playback control and the music subset can be clearly shown. When the user performs an operation using the playback control, the playback of the target subset can be triggered, further simplifying the operation process.

[0107] In one embodiment, playing the music in the above-mentioned target subset may include the following steps:

[0108] Determine the music information of the target subset from the classification information;

[0109] According to the music information of the target subset, obtain the music in the target subset from the music library and play it.

[0110] Among them, the classification information may include the music information of each music subset, such as which music each music subset includes. In the case of determining the target subset, the music information of the target subset can be determined from the classification information.

[0111] In one embodiment, the above-mentioned determining the music information of the target subset from the classification information may include the following steps:

[0112] Extract the text information corresponding to the target subset from the classification information;

[0113] Determine the music information of the target subset according to the text information corresponding to the target subset.

[0114] Exemplarily, in the case of identifying the classification identifier in the classification information, the text regions corresponding to each music subset are determined according to the classification identifier. The text information corresponding to the target subset is extracted from the text region corresponding to the target subset. For example, when the user performs a second trigger operation on a certain playback control, according to the region where the playback control is located in the classification information, the text region corresponding to the target subset is determined, and the text information corresponding to the target subset is extracted from the text region corresponding to the target subset. This text information describes the music information of the target subset, so the music information of the target subset can be determined according to this text information, for example, determining which music the target subset includes.

[0115] Furthermore, according to the music information of the target subset, the corresponding music is obtained from the music library. For example, according to the music information of the target subset, the corresponding audio resources are searched in the music library and played.

[0116] Since the classification information is usually text information and is not a music resource itself or does not include music resources, through the above method, the classification information is associated with the music resources, realizing the jump to play the target subset according to the classification information, and simplifying the user operation process.

[0117] In one implementation, the corresponding music resource information, such as a music resource identifier, can be carried in the classification information or the playback control. Exemplarily, the first music set includes the music resource identifiers of each music. The music resource identifier is not the music name and can be a unique identifier in the music library, usually invisible to the user. When the artificial intelligence model performs music classification on the first music set, it can obtain the music information of the first music set, including the music resource identifier. When generating the classification information, it can add the music resource identifier to the classification information. The music resource identifier may not be displayed in the classification information in the form of text, etc., but is associated with a specific text region or statement in the classification information through a link, etc. For example, referring to Figure 4 As shown, the text "Late Night Self-Healing Cabin" can be associated with the music resource identifiers of each music it contains. When the user clicks on the text "Late Night Self-Healing Cabin", according to the associated music resource identifier, the corresponding music resources are obtained from the music library and played. Or, when providing a playback control for the classification information generated by the artificial intelligence model, according to the music resource identifiers of each music in the first music set, each playback control is associated with the corresponding music resource identifier. For example, referring to Figure 4 As shown, the playback control 3021 can be associated with the music resource identifiers of each music in the music subset "Late Night Self-Healing Cabin". When the user clicks on the playback control 3021, according to the associated music resource identifier, the corresponding music resources are obtained from the music library and played.

[0118] In one embodiment, the classification information includes music information (such as music names and artists, etc.) of one or more pieces of music in the first music collection. The user can perform a play operation on the music information of a single piece of music in the classification information, and this play operation can be equivalent to the play operation on the music subset where the music is located, triggering the music subset where the music is located as the target subset and playing the music in the target subset. For example, referring to Figure 4 As shown, the classification information includes the music information of a single piece of music. If the user clicks on the text "Artist AA's Track 1", it triggers the music subset "Late Night Self-Healing Cabin" where "Artist AA's Track 1" is located as the target subset and plays the music in the target subset.

[0119] In one embodiment, playing the music in the above-mentioned target subset may include the following steps:

[0120] Taking the target subset as the current playlist, or adding the music in the target subset to the playlist before the play operation to obtain the current playlist;

[0121] Playing the music in the current playlist.

[0122] Among them, the target subset can be taken as the current playlist, and this current playlist only includes the music in the target subset. It is also possible to add the target subset to the playlist before the user performs the play operation to obtain the current playlist, and this current playlist includes the music in the target subset and the music in the playlist that the user was originally listening to. One of these methods can be selected according to requirements to determine the current playlist. Furthermore, playing the music in the current playlist can be performed in ways such as sequential play, random play, loop play, etc.

[0123] In one embodiment, referring to Figure 5 As described, in response to the play operation on the target subset, it jumps to the music play interface. Exemplarily, in response to the play operation on the target subset, the music to be initially played is determined in sequence or randomly in the target subset, or the music selected by the user during the play operation is used as the initially played music. It jumps to the play interface of this music and starts playing from this music.

[0124] In one embodiment, the classification information includes historical classification information and / or current classification information. The above-mentioned step of displaying the classification information of the first music collection in response to the classification operation on the first music collection may include the following steps:

[0125] In response to the classification operation on the first music collection, if there is historical classification information of the first music collection, the historical classification information is displayed; the historical classification information is the classification information obtained by classifying the music in the first music collection through an artificial intelligence model before the classification operation;

[0126] In response to a classification operation on the first music set, if there is no historical classification information of the first music set, request the artificial intelligence model to classify the current music in the first music set, and obtain and display the current classification information.

[0127] Among them, the classification information obtained by classifying the first music set can be saved locally on the terminal device or on the server. When the user performs a classification operation on the first music set subsequently, the saved classification information, that is, the historical classification information, can be displayed. Exemplarily, only the historical classification information of the most recent classification can be saved, or the historical classification information within a certain period of time can be saved, or all the historical classification information can be saved. In the case of displaying the historical classification information, there is no need to currently call the artificial intelligence model to execute the music classification process, which can reduce the overhead of calling the artificial intelligence model and quickly provide classification information for the user.

[0128] If the user performs a classification operation on the first music set for the first time, or although the user has performed a classification operation on the first music set previously, the corresponding historical classification information has been cleared due to reasons such as being too early in time or the user manually clearing the information, resulting in the non-existence of the historical classification information of the first music set. In this case, request the artificial intelligence model to execute the music classification process to obtain the current classification information and display it. It should be understood that this current classification information can be used as the historical classification information when the user performs a classification operation subsequently.

[0129] In one implementation, the music processing method may further include the following steps:

[0130] In the case of displaying the historical classification information, in response to a classification update operation, request the artificial intelligence model to classify the current music in the first music set, and obtain and display the current classification information.

[0131] Among them, the classification update operation is an operation used to request an update of the currently displayed classification information. For example, as shown in Figure 4 In the display interface of the classification information (this interface can be used to display historical classification information or current classification information), a classification update control 305 is provided. The classification update operation may include a third trigger operation on the classification update control 305, such as a click, double-click, long-press operation, etc.

[0132] When displaying historical classification information, the historical classification information may not meet the user's needs. For example, the music corresponding to the historical classification information is different from the current music in the first music collection, that is, the music in the first music collection when generating the historical classification information is inconsistent with the music in the current first music collection. The user can trigger reclassification through a classification update operation. Specifically, request the artificial intelligence model to classify the current music in the first music collection, and obtain and display the current classification information. This current classification information can overwrite the originally displayed historical classification information or be located after the historical classification information.

[0133] In one implementation, the music processing method may further include the following steps:

[0134] When displaying the current classification information, in response to the classification update operation, display the updated current classification information; the updated current classification information includes: one or more music subsets obtained by reclassifying the current music in the first music collection through the artificial intelligence model.

[0135] Among them, after the artificial intelligence model performs the current classification, if the user is not satisfied with the current classification information, reclassification can be triggered through the classification update operation. Specifically, the artificial intelligence model can be requested again to classify the current music in the first music collection, and the updated current classification information is obtained and displayed.

[0136] It should be understood that when the artificial intelligence model performs the music classification process, certain random information is usually added. For example, the artificial intelligence model has a temperature parameter (temperature). When the temperature parameter is greater than 0, the generation process of the artificial intelligence model is random. Even if the text prompt information input to the artificial intelligence model is not changed, the artificial intelligence model can output different classification results in the previous and subsequent music classification processes. Or, in response to the classification update operation, adjust the classification prompt information, such as adding the content that the user is not satisfied with the previous classification result, or adjusting the relevant description content of the classification logic, and input the adjusted classification prompt information into the artificial intelligence model, so that the artificial intelligence model outputs a classification result different from the previous one, thereby obtaining the updated current classification information.

[0137] In one implementation, the classification information includes historical classification information and / or current classification information. The above-mentioned response to the classification operation for the first music collection and display of the classification information of the first music collection includes:

[0138] In response to the classification operation for the first music collection, if there is historical classification information of the first music collection and the music corresponding to the historical classification information is the same as the current music in the first music collection, then display the historical classification information; the historical classification information is the classification information obtained by classifying the music in the first music collection through the artificial intelligence model before the classification operation;

[0139] In response to a classification operation for a first music set, if there is no historical classification information for the first music set, or if there is historical classification information for the first music set but the music corresponding to the historical classification information is different from the current music in the first music set, then request the artificial intelligence model to classify the current music in the first music set, and obtain and display the current classification information.

[0140] That is, if there is historical classification information and the first music set when the historical classification information was generated is the same as the music in the current first music set, which means the historical classification information is applicable to the current first music set, then display the historical classification information. If there is no historical classification information, then request the artificial intelligence model to perform the music classification process to obtain and display the current classification information. Or, if there is historical classification information but the first music set when the historical classification information was generated is different from the music in the current first music set, which means the historical classification information may not be applicable to the current first music set, then request the artificial intelligence model to perform the music classification process to obtain and display the current classification information. In this way, different classification information display strategies are adopted according to whether the historical classification information corresponds to the current first music set, which is beneficial to meeting the classification needs of users.

[0141] In one implementation, in response to a classification operation for a first music set, regardless of whether there is historical classification information, request the artificial intelligence model to classify the current music in the first music set, and obtain and display the current classification information. This ensures that after the user performs a classification operation, the classification information seen is the latest classification information, which conforms to the current first music set and has a high probability of meeting the classification needs of the user.

[0142] Figure 6 The schematic flowchart of the music processing method is shown and may include the following steps:

[0143] Step S601, receive a classification operation of the user for the first music set, such as the operation of the user clicking on the classification control in the first music set;

[0144] Step S602, detect whether there is historical classification information for the first music set. If so, execute step S603; if not, execute step S605;

[0145] Step S603, display the historical classification information;

[0146] Step S604, receive a classification update operation of the user, such as the operation of the user clicking on the classification update control in the display interface of the classification information;

[0147] Step S605, call the artificial intelligence model to classify the current music in the first music set;

[0148] Step S606, detect whether the current classification information fed back by the artificial intelligence model is obtained. If so, execute step S607; if not, execute step S611;

[0149] Step S607, continuously add the current classification information to the display interface of the classification information;

[0150] Step S608, detect whether the display of the current classification information is completed. If so, execute step S609; if not, execute step S611;

[0151] Step S609, add a playback control in the historical classification information or the current classification information;

[0152] Step S610; in response to a second trigger operation on the playback control, play the music in the corresponding target subset;

[0153] Step S611, display an exception message according to the exception situation, such as displaying messages like "Server response timeout".

[0154] Figure 7 Shows the music classification processing flow based on different technical layers. At the function layer, when the user enters the first music set, the entry control of the music intelligent classification function is provided through the policy configuration ability, such as providing a classification control. In response to the classification operation, at the streaming entry layer, the domain name of the music intelligent classification function is provided through proxy services such as nginx (a reverse proxy server), and is maintained through an SseEmitter (SSE emitter, SSE (Server-Sent Events) is a technology for real-time communication between the server and the client) connection pool, providing an SSE streaming API (Application Programming Interface), to achieve accessing the service of the artificial intelligence model in an SSE streaming manner. At the business layer, prompt processing is performed through a scenario SPI (Service Provider Interface, a service discovery mechanism provided by Java) to generate classification prompt information. At the model access layer, through model interface adaptation, an application layer streaming call component can be implemented, and the architecture of Netty (a Java open-source framework) and RxJava (Reactive Extensions for Java, a library for building asynchronous programs and event-driven programs) can be adopted, and timeout control (such as when the model returns information and times out, it will not wait indefinitely, but perform timeout exception handling) and anti-spam mechanisms (such as filtering spam information in the input and output information of the model) are adopted. At the streaming entry layer, through the response of the SseEmitter, the information returned through streaming is obtained, so as to display the classification information.

[0155] Figure 8 A schematic diagram of a front - end component is shown. The front - end component can be divided into a UI (User Interface) layer, a logic layer, and a data layer. Among them, the data layer includes an SSE request module, enabling request interaction between the terminal device and the server through the SSE method. For example, the terminal device requests the server to call an artificial intelligence model for music classification through the SSE method. The logic layer includes a data processing module, a display control module, and an exception handling module. The data processing module is used to perform data processing during music classification and playback, such as obtaining music information of the first music set, obtaining the user's music preference information, generating classification prompt information, etc. The display control module is used to control the information displayed in the graphical user interface. The exception handling module is used for handling in abnormal situations, such as displaying exception information when the information returned by the artificial intelligence model times out. The UI layer includes a MarkDown (mark) display module, which can edit the classification information returned by the artificial intelligence model, such as adding play controls, adding links, etc. Through the design of the above - mentioned front - end component, the music intelligent classification function can be efficiently implemented, and the display and control of classification information can be realized.

[0156] Exemplary device

[0157] The music processing device in the embodiments of the present disclosure will be described below. Refer to Figure 9 As shown, the music processing device 900 may include the following modules:

[0158] A classification information display module 910, configured to display classification information of a first music set in response to a classification operation on the first music set; the classification information includes: one or more music subsets obtained by classifying the music in the first music set through an artificial intelligence model;

[0159] A music subset playback module 920, configured to play the music in the target subset in response to a playback operation on the target subset among one or more music subsets.

[0160] In one embodiment, displaying the classification information of the first music set in response to a classification operation on the first music set includes: providing a classification control on the information interface of the first music set; and displaying the classification information of the first music set in response to a first trigger operation on the classification control.

[0161] In one embodiment, playing the music in the target subset in response to a playback operation on the target subset among one or more music subsets includes: providing playback controls corresponding to each music subset in the classification information; and playing the music in the target subset in response to a second trigger operation on the playback control corresponding to the target subset.

[0162] In one embodiment, playback controls corresponding to each music subset are provided in classification information, including: determining text areas corresponding to each music subset in the classification information; and providing playback controls in the text areas corresponding to each music subset respectively.

[0163] In one embodiment, playing music in a target subset includes: determining music information of the target subset from classification information; and obtaining and playing the music in the target subset from a music library according to the music information of the target subset.

[0164] In one embodiment, determining music information of a target subset from classification information includes: extracting text information corresponding to the target subset from the classification information; and determining the music information of the target subset according to the text information corresponding to the target subset.

[0165] In one embodiment, displaying classification information of a first music set includes: generating classification prompt information about the first music set; and requesting an artificial intelligence model to process the classification prompt information to obtain and display the classification information.

[0166] In one embodiment, generating classification prompt information about a first music set includes: generating classification prompt information according to music preference information of a user associated with the first music set and music information of the first music set.

[0167] In one embodiment, classification information includes historical classification information and / or current classification information; responding to a classification operation on a first music set, displaying classification information of the first music set includes: in response to a classification operation on the first music set, if there is historical classification information of the first music set, displaying the historical classification information; the historical classification information is classification information obtained by classifying the music in the first music set by an artificial intelligence model before the classification operation; in response to a classification operation on the first music set, if there is no historical classification information of the first music set, requesting the artificial intelligence model to classify the current music in the first music set to obtain and display the current classification information.

[0168] In one embodiment, the classification information display module 910 is further configured to: in the case of displaying historical classification information, in response to a classification update operation, request the artificial intelligence model to classify the current music in the first music set to obtain and display the current classification information.

[0169] In one embodiment, the classification information display module 910 is further configured to: in the case of displaying current classification information, in response to a classification update operation, display the updated current classification information; the updated current classification information includes: one or more music subsets obtained by reclassifying the current music in the first music set by the artificial intelligence model.

[0170] In one embodiment, the classification update operation includes: a third triggering operation on a classification update control provided in the display interface of the classification information.

[0171] In one embodiment, the classification information includes historical classification information and / or current classification information; in response to a classification operation on a first music set, the classification information of the first music set is displayed, including: in response to a classification operation on the first music set, if there is historical classification information of the first music set and the music corresponding to the historical classification information is the same as the current music in the first music set, then the historical classification information is displayed; the historical classification information is the classification information obtained by classifying the music in the first music set through an artificial intelligence model before the classification operation; in response to a classification operation on the first music set, if there is no historical classification information of the first music set, or there is historical classification information of the first music set, but the music corresponding to the historical classification information is different from the current music in the first music set, then the artificial intelligence model is requested to classify the current music in the first music set, and the obtained and displayed current classification information is obtained.

[0172] In one embodiment, playing the music in the target subset includes: using the target subset as the current playlist, or adding the music in the target subset to the playlist before the play operation to obtain the current playlist; playing the music in the current playlist.

[0173] In one embodiment, the first music set includes one or more of the following: a set of music for which the user has performed a preset operation; a music set selected by the user from a candidate music set when performing a classification operation; a set of music recommended for the user.

[0174] 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.

[0175] Exemplary program product

[0176] The computer program product in the embodiments of the present disclosure will be described below. The computer program product includes a computer program, and when the computer program is executed by a processor, it implements the above method of the present disclosure.

[0177] In one embodiment, the computer program product may be a tangible product, such as a computer-readable storage medium storing a computer program. The readable storage medium may be based on signals such as electricity, magnetism, light, electromagnetic, infrared, etc., 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), etc. Exemplarily, the computer program product may be a non-volatile storage medium storing a computer program, such as read only memory, NAND flash memory, etc.

[0178] In one embodiment, the computer program product may be an intangible product. For example, the computer program product may be a virtual digital product, such as an executable file or installation package containing a computer program.

[0179] The code of the computer program can be written in one or more programming languages. Programming languages include, but are not limited to, C, 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 via 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., via an Internet connection provided by a carrier).

[0180] 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, and then run the computer programs. When the computer program is running on an electronic device, its code is used to enable the electronic device to execute (more specifically, it can enable the processor of the electronic device to execute) the method steps of various embodiments of the present disclosure, for example: step S210, in response to the classification operation for the first music set, display the classification information of the first music set; the classification information includes: one or more music subsets obtained by classifying the music in the first music set through an artificial intelligence model; step S220, in response to the play operation for the target subset in the one or more music subsets, play the music in the target subset.

[0181] The above steps are executed by a computer program. In response to a classification operation on the first music collection, classification information of the first music collection, which is obtained by classification using the artificial intelligence model, is displayed. In response to a play operation on the target subset, the music in the target subset is played. This provides an intelligent music classification function. On the one hand, when performing a classification operation, the user does not need to manually select a classification label and can quickly jump from the classification information to the target subset to be played, simplifying the user's operation process. On the other hand, the capabilities of the artificial intelligence model can be used to explore deep-level features in the music and classify it accordingly, reducing the dependence of the classification results on labels, which is conducive to increasing the diversity of the classification results and improving the user experience.

[0182] Exemplary electronic devices

[0183] The electronic device in the embodiment of the present disclosure is described below. The electronic device includes a processor and a memory, wherein the memory is used to store executable instructions of the processor. The processor is configured to execute the above-mentioned method of the present disclosure by executing the executable instructions.

[0184] refer to Figure 10 An electronic device according to an embodiment of the present disclosure will be exemplified. Figure 10 The electronic device 1000 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0185] like Figure 10 As shown, electronic device 1000 is presented in the form of a general-purpose computing device. Components of electronic device 1000 may include, but are not limited to, a processor 1010, a memory 1020, a bus 1030 connecting various system components (including memory 1020 and processor 1010), an I / O (input / output) interface 1040, a network adapter 1050, a display 1060, and an audio unit 1070.

[0186] Among them, the memory 1020 stores program code, and the program code can be executed by the processor 1010, so that the processor 1010 executes the method steps of the embodiment of the present disclosure, for example: step S210, in response to the classification operation for the first music set, displaying the classification information of the first music set; the classification information includes: one or more music subsets obtained by classifying the music in the first music set through the artificial intelligence model; step S220, in response to the playback operation for the target subset in one or more music subsets, playing the music in the target subset.

[0187] The above steps are performed by processor 1010. In response to a classification operation for the first music collection, classification information of the first music collection is displayed, which is obtained by classification by the artificial intelligence model. In response to a play operation for the target subset, the music in the target subset is played. An intelligent music classification function is provided. On the one hand, when performing a classification operation, the user does not need to manually select a classification label, and can quickly jump from the classification information to the target subset to be played, simplifying the user's operation process. On the other hand, the ability of the artificial intelligence model can be used to explore the deep-level features in the music and classify it accordingly, reducing the dependence of the classification results on labels, which is conducive to increasing the diversity of the classification results and improving the user experience.

[0188] The memory 1020 may include volatile memory, such as random access memory (RAM) 1021 and / or cache unit 1022, and may also include non-volatile memory, such as read-only memory (ROM) 1023. The memory 1020 may also include one or more program modules 1024, and such program modules 1024 include but are not limited to: operating systems, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment. For example, the program module 1024 may include each module in the above device.

[0189] The processor 1010 may include processing units such as an AP (Application Processor), a modem processor, a GPU (Graphics Processing Unit), an ISP (Image Signal Processor), a controller, an encoder, a decoder, a DSP (Digital Signal Processor), a baseband processor, and / or an NPU (Neural-Network Processing Unit).

[0190] The bus 1030 is used to connect different parts of the electronic device 1000 and may include a data bus, an address bus, a control bus, etc.

[0191] The electronic device 1000 may also communicate with one or more external devices 1100 (such as a keyboard, a pointing device, a Bluetooth device, etc.), and such communication may be carried out through the I / O interface 1040.

[0192] The electronic device 1000 may also communicate with one or more networks through the network adapter 1050. For example, the network adapter 1050 may provide mobile communication solutions such as 3G / 4G / 5G, or provide wireless communication solutions such as wireless local area network, Bluetooth, near field communication, etc. The network adapter 1050 may communicate with other modules of the electronic device 1000 through the bus 1030.

[0193] The electronic device 1000 may also display a graphical user interface through the display 1060 and display information in the graphical user interface, such as displaying classification information, etc.

[0194] The electronic device 1000 may also play audio through the audio unit 1070, such as playing music in a target subset.

[0195] Although not shown in the figures, other hardware and / or software modules may also be provided in the electronic device 1000, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID (Redundant Arrays of Independent Disks) systems, tape drives, and data backup storage systems, etc.

[0196] It should be noted that although several modules or sub-modules of the apparatus are mentioned in the above detailed description, this 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 of the above-described units / modules may be embodied in one unit / module. Conversely, the features and functions of one unit / module described above may be further divided and embodied by multiple units / modules.

[0197] In addition, although the operations of the method of the present disclosure are described in a specific order in the drawings, this does not require or imply that these operations must be performed in that specific order, or that all of the illustrated operations must be performed to achieve the desired result. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution.

[0198] Although the spirit and principles 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 specific embodiments disclosed, and the division of each aspect does not mean that the features in these aspects cannot be combined for benefit. This division is only for the convenience of description. The present disclosure aims to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.

Claims

1. A music processing method, characterized in that, The method includes: In response to a classification operation for a first music set, displaying classification information of the first music set; the classification information includes: one or more music subsets obtained by classifying the music in the first music set through an artificial intelligence model; In response to a play operation for a target subset among the one or more music subsets, playing the music in the target subset.

2. The method according to claim 1, wherein The step of, in response to a classification operation for a first music set, displaying classification information of the first music set, includes: Providing a classification control on the information interface of the first music set; In response to a first trigger operation for the classification control, displaying the classification information of the first music set.

3. The method according to claim 1, characterized in that, The step of, in response to a play operation for a target subset among the one or more music subsets, playing the music in the target subset, includes: Providing play controls corresponding to each of the music subsets in the classification information; In response to a second trigger operation for the play control corresponding to the target subset, playing the music in the target subset.

4. The method according to claim 3, characterized in that, The step of providing play controls corresponding to each of the music subsets in the classification information includes: Determining text areas corresponding to each of the music subsets in the classification information; Respectively providing play controls in the text areas corresponding to each of the music subsets.

5. The method according to claim 1, wherein The step of playing the music in the target subset includes: Determining music information of the target subset from the classification information; According to the music information of the target subset, obtaining and playing the music in the target subset from a music library.

6. The method according to claim 5, characterized in that, The step of determining music information of the target subset from the classification information includes: Extracting text information corresponding to the target subset from the classification information; Determining the music information of the target subset according to the text information corresponding to the target subset.

7. The method according to claim 1, wherein The step of displaying the classification information of the first music set includes: Generating classification prompt information about the first music set; Requesting the artificial intelligence model to process the classification prompt information, obtaining and displaying the classification information.

8. A music processing device, characterized in that, The apparatus includes: A classification information display module configured to, in response to a classification operation for a first music set, display classification information of the first music set; the classification information includes: one or more music subsets obtained by classifying the music in the first music set through an artificial intelligence model; A music subset play module configured to, in response to a play operation for a target subset among the one or more music subsets, play the music in the target subset.

9. A computer program product comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that, Including: A processor; And A memory for storing executable instructions of the processor; Wherein, the processor is configured to execute the method according to any one of claims 1 to 7 by executing the executable instructions.

Images