Music generation method and apparatus, and computer device and storage medium

Abstract

Provided in the present disclosure are a music generation method and apparatus, and a computer device and a storage medium. The method comprises: in response to a music generation operation in an operation interface, displaying a production interface, wherein the production interface comprises at least one music type option; in response to a first operation on any music type option, displaying, in the production interface, at least one first category corresponding to the any music type option; in response to a second operation on any first category, displaying at least one first sub-category corresponding to the any first category, and determining a selection for the at least one first sub-category, so as to generate constraint information; and in response to a music generation operation, performing music generation on the basis of the constraint information.

Description

Music generation method and device, computer device, and storage medium

[0001] Cross-reference to Related Applications

[0002] This application claims priority to the Chinese Patent Application No. 202411304416.2, filed on September 18, 2024, and entitled "Music Generation Method and Device, Computer Device, and Storage Medium", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0003] The present disclosure relates to the technical field of computer, and particularly relates to a music generation method and device, a computer device, and a storage medium. BACKGROUND

[0004] In recent years, with the rapid development of the Internet, generative artificial intelligence technology has been gradually applied to the creation of various types of media content, such as image and video content generation and production. SUMMARY

[0005] Therefore, the present disclosure provides a music generation method and device, a computer device, and a storage medium.

[0006] To achieve the above object, in a first aspect, the present disclosure provides a music generation method, comprising:

[0007] In response to a music generation operation in an operation interface, a production interface is displayed; the production interface comprises at least one music type option;

[0008] In response to a first operation on any music type option, at least one first classification corresponding to the any music type option is displayed in the production interface;

[0009] In response to a second operation on any first classification, at least one first sub-classification corresponding to the any first classification is displayed, and selection of the at least one first sub-classification is determined to generate constraint information;

[0010] In response to a music generation operation, music is generated according to the constraint information.

[0011] In a second aspect, the present disclosure provides a music generation device, comprising:

[0012] A first module is configured to display a production interface in response to a music generation operation in an operation interface; the production interface comprises at least one music type option;

[0013] A second module is configured to display at least one first classification corresponding to any music type option in the production interface in response to a first operation on the any music type option;

[0014] The third module is configured to, in response to the second operation on any first category, display at least one first sub-category corresponding to the any first category, and determine selection of the at least one first sub-category, to generate constraint information.

[0015] The fourth module is configured to, in response to a music generation operation, generate music according to the constraint information.

[0016] In a third aspect, the present disclosure provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method in the first aspect.

[0017] In a fourth aspect, the present disclosure provides a non-transitory computer readable storage medium storing computer instructions for causing a computer to execute the method in the first aspect. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the related art, the drawings needed to be used in the embodiments or the related art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0019] FIG. 1 shows a schematic diagram of an exemplary system according to an embodiment of the present disclosure.

[0020] FIG. 2 shows a schematic diagram of an exemplary operation interface according to an embodiment of the present disclosure.

[0021] FIG. 3A shows a schematic diagram of an exemplary production interface according to an embodiment of the present disclosure.

[0022] FIG. 3B shows a partial schematic diagram of a functional area of an exemplary production interface according to an embodiment of the present disclosure.

[0023] FIG. 3C shows a partial schematic diagram of a functional area of another exemplary production interface according to an embodiment of the present disclosure.

[0024] FIG. 3D shows a partial schematic diagram of a functional area of another exemplary production interface according to an embodiment of the present disclosure.

[0025] FIG. 3E shows a partial schematic diagram of a functional area of another exemplary production interface according to an embodiment of the present disclosure.

[0026] FIG. 3F shows a partial schematic diagram of a first display area of an exemplary production interface according to an embodiment of the present disclosure.

[0027] FIG. 3G shows a partial schematic view of a second display area of an example operation interface according to embodiments of the present disclosure.

[0028] FIG. 3H shows a schematic view of a music playing floating area of an example operation interface according to embodiments of the present disclosure.

[0029] FIG. 4 shows a flow schematic view of an example method according to embodiments of the present disclosure.

[0030] FIG. 5 shows a schematic view of an example device according to embodiments of the present disclosure.

[0031] FIG. 6 shows a schematic view of an example computer device according to embodiments of the present disclosure. DETAILED DESCRIPTION

[0032] With the popularity of generative artificial intelligence technology, more and more users want to generate music content while making images or videos, which poses a certain challenge to the current production platform that provides comprehensive generative artificial intelligence technology.

[0033] To make the purpose, technical solutions and advantages of the present disclosure clearer, the present disclosure is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0034] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present disclosure should be understood as the usual meaning understood by those skilled in the art to which the present disclosure belongs. The terms "first", "second", and similar terms used in the examples of the present disclosure do not represent any order, quantity, or importance, but are only used to distinguish different components. The terms "include" or "contain" and similar terms mean that the elements or objects before the terms cover the elements or objects listed after the terms and their equivalents, without excluding other elements or objects. The terms "connect" or "connected" and similar terms are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. The terms "up", "down", "left", "right", and the like only represent relative positional relationships, which may change accordingly when the absolute position of the described object changes.

[0035] It can be understood that, before using the technical solutions disclosed in the embodiments of the present disclosure, the type of personal information involved in the present disclosure, the scope of use, the scene of use, and the like should be informed to the user and the authorization of the user should be obtained in accordance with relevant laws and regulations.

[0036] For example, in response to receiving an active request of a user, a prompt information is sent to the user to explicitly prompt the user that the operation requested to be performed will require obtaining and using personal information of the user. Thus, the user can autonomously select whether to provide the personal information to the software or hardware, such as an electronic device, an application program, a server or a storage medium, etc. performing the operation of the technical solution of the present disclosure according to the prompt information.

[0037] As an optional but non-limiting implementation, in response to receiving an active request of a user, the manner of sending a prompt information to the user may, for example, be a pop-up window manner, in which the prompt information can be presented in a text manner. In addition, the pop-up window can also carry a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0038] It can be understood that the above notification and obtaining user authorization process is only illustrative and does not limit the implementation of the present disclosure, and other manners meeting the relevant laws and regulations can also be applied to the implementation of the present disclosure.

[0039] It can be understood that the data (including but not limited to the data itself, the obtaining or use of the data) involved in the technical solution should comply with the requirements of the relevant laws and regulations and the relevant provisions.

[0040] For the purpose, technical solution and advantages of the present disclosure to be clearer and more apparent, the present disclosure is further described in detail below in combination with specific examples and with reference to the accompanying drawings.

[0041] FIG. 1 shows a schematic diagram of an exemplary system 100 according to an embodiment of the present disclosure. The system 100 can be a system for implementing music generation.

[0042] As shown in FIG. 1, taking the terminal device and the server jointly performing an object display method as an example, the system 100 can include a terminal device 102, a server 104 and a database server 106. The terminal device 102 and the server 104 are connected through a network, such as a wired or wireless network connection, etc. Optionally, the apparatus for implementing music generation can be integrated in the terminal device 102. The database server 106 and the server 104 are connected through a network, such as a wired or wireless network connection, etc. The database server 106 can store various data related to the implementation of the music generation method, such as music parameters, generation algorithms, etc.

[0043] The terminal device 102 can be installed with various application programs (APPs) such as music processing application programs, video conference application programs, life service application programs, reading application programs, video application programs, social application programs, payment application programs, web browsers, and instant messaging tools, which can be used for music generation and / or display / play of the generated music. As an optional example, the application program (APP) installed on the terminal device 102 can be downloaded and installed from the server 104.

[0044] The terminal device 102 herein can be hardware or software. When the terminal device 102 is hardware, it can be various electronic devices with a display screen, including but not limited to a smart phone, a tablet computer, an e-book reader, an MP3 player, a laptop computer (Laptop), and a desktop computer (PC), and the like. When the terminal device 102 is software, it can be installed in the above-listed electronic devices. It can be implemented as multiple software or software modules (for example, for providing distributed services), or as a single software or software module, which is not specifically limited herein.

[0045] The server 104 can be a server providing various services. For example, a background server providing support for various application programs displayed on the terminal device 102. The database server 106 can also be a database server providing various services. It can be understood that in the case where the server 104 can implement the related functions of the database server 106, the database server 106 can not be provided in the system 100.

[0046] The server 104 and the database server 106 herein can also be hardware or software. When they are hardware, they can be implemented as a distributed server cluster composed of multiple servers, or as a single server. When they are software, they can be implemented as multiple software or software modules (for example, for providing distributed services), or as a single software or software module, which is not specifically limited herein.

[0047] It should be noted that the music generation method provided by the examples of the present disclosure can be executed by the system 100. Specifically, it can be executed by interaction between the terminal device 102, the server 104, and the database server 106. It can be understood that in the case where the terminal device 102 has the functions required by the server 104 and the database server 106 for executing the music generation method, it can also be executed by the terminal device 102 alone. It should be understood that the number of terminal devices 102, servers 104, database servers 106, and users 108 in FIG. 1 is only illustrative. According to actual needs, there can be any number of terminal devices, users, servers, and database servers.

[0048] In an example application scenario, the user 108 can input an instruction of making music through the terminal device 102, and the server 104 can provide a music generation service to the user 108 based on the instruction, and display an operation interface of the music generation service in a page through the terminal device 102.

[0049] As described in the background, in some examples, users can make production and manufacturing work of various products, such as pictures, videos, etc., through application generation artificial intelligence technology. Users can generate images using application generation artificial intelligence (AIGC, Artificial Intelligence Generated Content). After the user has a successful experience in visual products using generation artificial intelligence technology, the user gradually wants to get corresponding help in auditory products, that is, the user begins to have a corresponding demand for the generation and production of music content. Therefore, after learning from the corresponding settings of image generation, a corresponding music generation tool can be developed to perform music generation work. In some examples, the music generation tool can be presented to the user in the form of a separate APP; or it can be integrated into a generation artificial intelligence technology platform to provide users with a choice. The platform can provide users with various generation services, such as image generation, video generation, story generation, and music generation, etc. Herein, no specific limitation is made.

[0050] In some examples, the music generation tool can be a software or program with music generation function. However, no specific limitation is made herein. Specifically, a tool with music generation capability and capable of completing intelligent music generation through interaction with an operator can be considered as a music generation tool.

[0051] In a more specific scenario, when the user 108 uses the generation artificial intelligence technology platform, the user can generally perform generation operations of products such as image generation and video generation. It can be understood that in this scenario, as the user's demand gradually increases, the user will gradually be dissatisfied with only being able to generate images or videos, and on this basis, the user also hopes to be able to generate and produce music content, which poses a certain challenge to the current production platform that provides comprehensive generation artificial intelligence technology.

[0052] FIG. 2 shows a schematic diagram of an example operation interface 200 according to an embodiment of the present disclosure.

[0053] As shown in FIG. 2, the operation interface 200 can be a homepage interface of a platform providing generative artificial intelligence technology, which generally provides corresponding services for each user, so the homepage interface here can be a homepage interface of a user. Of course, in some other examples, the operation interface 200 can also be a public platform homepage, etc. Hereinafter, the operation interface 200 is taken as an example of a homepage interface of a user, which can be a page of an image processing application, a mini-program or a website page, etc. entering the user homepage of the platform. The user 108 can enter the corresponding platform website by opening the application or mini-program of the platform in the terminal device 102, or by entering the website of the platform through the website program, so that the operation interface 200 can be displayed on the terminal device 102. It can be understood that there are many ways to enter the operation interface 200, and here only the possible entering ways are described for a clearer illustration.

[0054] As shown in FIG. 2, after entering the operation interface 200, the corresponding ports for image generation and video generation can be set in the corresponding function areas, for example, the corresponding operation ports (such as the image generation control area and the video generation control area shown in FIG. 2) can be set in the function area 201 and / or the function area 202. Then, the main body area 203 of the operation interface 200 can display some products, for example, the products made by the user, the products followed or purchased by the user, or the products recommended according to the user's settings and / or the platform's recommendation algorithm. Through the operation interface 200, the user can conveniently generate image, video and text works. Furthermore, as the user's demand expands, more and more users hope to make music works while using the operation interface 200.

[0055] Furthermore, in combination with the above actual situation, as shown in FIG. 2, in some examples, in order to give the user more interactive options, especially the music making function, so as to provide the user with more diversified function capabilities, first, the corresponding music generation control area can be set on the operation interface 200, as shown in FIG. 2, the operation area for music generation can be set in the function area 201 and / or the function area 202, such as the music generation button area in FIG. 2. The user can select the control area by clicking the area (music generation) to perform music generation operation, thereby triggering the music generation workflow.

[0056] It should be noted that the selection operation appearing in the present example and the following examples can be a single-click, double-click, touch, etc. operation with a clear trigger signal on the object. This is only an exemplary illustration, and the selection operation is not specifically limited.

[0057] As shown in FIG. 3A, after the user performs the music generation operation, a production interface 300 can be displayed in the operation interface 200. The production interface 300 can be a brand new window, or the operation interface 200 can be replaced by the production interface 300, and the like. The production interface 300 can include a plurality of regions. The production interface 300 can include a function area 301 for performing the music generation operation, and can also include a display area 302 for displaying the generated work. The display area 302 can include only the music work corresponding to the production interface 300, or can include other works generated by the current user, such as image works, video works, and the like. The display form of the function area 301 and the display area 302 in the production interface 300 can be as shown in FIG. 3A, in which the function area 301 occupies the left part of the interface, and the display area 302 occupies the middle and right part of the interface. Alternatively, the function area 301 can occupy the upper part of the interface, and the display area 302 can occupy the middle and lower part of the interface. In different specific scenarios, the size, shape, and position of the function area 301 and the display area 302 can be adjusted in the production interface 300, and the like, which are not limited herein.

[0058] Further, first, only a partial region of the function area 301 is described. As shown in FIGS. 3B to 3E, the function area 301 of the production interface 300 according to an embodiment of the present disclosure is shown.

[0059] Afterwards, as shown in FIG. 3A, at least two music type options 310, specifically, song with lyrics 310A and pure music 310B, are displayed in the production interface 300, in other specific scenarios, other options can be set according to the scenario, or the number of music type options 310 can be increased or decreased, that is, at least one music type option 310 is included in the production interface 300. Taking the music type options 310 as an example of song with lyrics 310A and pure music 310B, when the production interface 300 is entered, the song with lyrics 310A and the pure music 310B can be selected (first operation), and after one of them is selected, the content corresponding to the selected option can be displayed in the production interface 300. As shown in FIG. 3A, when the user selects the song with lyrics 310A, the content corresponding to the song with lyrics 310A can be displayed in the production interface 300. In a more specific scenario, in order to highlight the selected option, the selected option can be displayed differently, for example, by highlighting, enlarging, color adjusting, or other methods. In a more specific scenario, for at least one music type option 310, the corresponding options can be displayed in the function area 301 in turn, or only part of the music type options 310 can be displayed according to the size of the function area 301, and the others can be omitted. The omitted music type options 310 can be displayed by sliding.

[0060] In some examples, first taking the selected song with lyrics 310A as an example, after the first operation is performed on the song with lyrics 310A, the content corresponding to the song with lyrics 310A can be displayed in the production interface 300, specifically can be displayed in the function area 301, and specifically can include at least one first classification 320. The first classification 320 here is mainly used to form a corresponding constraint on music generation, for example, as shown in FIG. 3A, the style, instrument, scene, etc. of the music can be specifically limited. For example, after the style is specifically limited to "jazz", the generated music will be based on jazz music, and other styles of music will no longer be generated. After selecting one first classification 320, at least one first sub-classification 330 belonging to the first classification 320 can be more specifically displayed, for example, after selecting the first classification "style", at least one first sub-classification 330 can be continuously displayed in the function area 301, and these first sub-classifications can be specific subdivision options of the selected first classification 320. Then, at least one first sub-classification 330 can be selected at least once to generate constraint information. Here, the number of first sub-classifications 330 that can be selected in each first classification 320 can be limited, for example, it can be limited to selecting 1, 3, etc. in one classification, or it can be limited to the total number of selected classifications, for example, a total of 10, 12 classifications can be selected as constraints, etc. Here, for the scenario of selecting multiple, taking the "style" classification as an example, if 2 or more are selected, the music generation can be selected from the selected styles, or the generated music style can include all or part of the styles. Here, it should be noted that the selection operation of any first classification can be considered as a second operation of any first classification, and in some other examples, similar to the first operation described above, the second operation (or the first operation) can be a selection operation, and the selection operation is not necessarily a second operation (or a first operation). In different scenarios, other operations can also be a second operation (or a first operation) as long as they meet the corresponding settings and needs, which are not specifically limited here. In a more specific scenario, for the first classification 320 and the first sub-classification 330, similar settings can also be performed as the music type option 310, that is, the corresponding options can be displayed in the function area 301 in turn, or only part of them can be displayed according to the size of the function area 301, and the others can be omitted. The omitted classifications can be displayed through sliding, etc.

[0061] For the selected category or subcategory, it can also be displayed in a manner distinguished from other unselected categories, that is, the selected item can be displayed in a distinguished manner. Of course, in some examples, a separate area can be provided for displaying the selected different subcategories, for example, as shown in FIG. 3A, a selected area 304 can be provided, and when a subcategory 330 is selected, the selected subcategory can be displayed in the selected area 304.

[0062] In a more specific scenario, when the user enters the production interface 300, a music type option 310 and the specific content of a first category 320 of the music type option 310 can be displayed in the function area 301 by default, and when the user selects other music type options 310, the content in the function area 301 is adjusted.

[0063] Further, after the selection of the first category 320 and the first subcategory 330 is completed, the corresponding constraint information can be generated according to the selected content, which is used to provide constraints for music generation. Then, the final music generation operation can be performed through the corresponding music generation operation, and the music generation operation, as shown in FIG. 3A, can be performed through the selection operation on the trigger area of "music generation", which is used as the music generation operation. The music generation operation can be used to confirm and submit the operation in the function area 301, and the related operation of music generation is performed. Therefore, the constraint information generated in the foregoing is provided to the model or algorithm used for music generation to perform the corresponding music generation work.

[0064] It should be noted that, regardless of the generated music being instrumental music or a song with lyrics, it is not necessarily necessary to obtain the corresponding lyrics information (or text information). In some examples, even if the generation of a song with lyrics is selected, it is not necessarily necessary to fill in the lyrics, but can use the corresponding model to automatically generate, for example, as shown in FIG. 3A, for the song with lyrics 310A option, although the text area 303 for text information input is set, it is not mandatory to fill in this area, when the music generation operation is performed, if there is no content in the text area 303, it can be automatically generated and filled in by the corresponding model, algorithm. Similarly, for instrumental music, a corresponding text input area, i.e. the text area 303, can be set to describe the music to be generated, thereby forming another form of constraint, for example, for instrumental music, the input text information can be used as a more detailed limitation on the scene of the music, thereby performing more specific constraints or assisting music generation as a reference when generating music. As shown in FIG. 3C, for the instrumental music option, a text area 303 can also be set, which allows the user to input text information to limit the music to be generated accordingly. Of course, this part can also be automatically generated (such as by triggering the "inspiration generation" function area shown in FIG. 3C).

[0065] Further, in some examples, the text area 303 can be set or not set. Of course, in order to better allow the user to express their ideas about the music, the text area 303 can be set in the production interface 300, specifically in the function area 301. Then, for the content of this area, it can be determined by obtaining the user's text input for this area; or a piece of text information can be automatically generated in the text area 303 by the user's third operation on this area. The third operation can be understood as an instruction operation to automatically generate, which can be triggered (or selected) by a corresponding function key or area set in the text area 303 (such as the "one-key song" function area shown in FIG. 3A); or it can be directly triggered by a corresponding gesture operation or stroke operation, for example, a certain touch track or mouse track can directly trigger automatic text generation in the text area 303. In the process of automatically generating text information, if the text area 303 already contains text, these texts can be used as a reference, or they can be ignored.

[0066] In some examples, for the selection of at least one first sub-category 330, the selected first sub-category 330 can be displayed not only in the selected area 304, but also in the text area 303. As shown in FIGS. 3D and 3E, this is an example of displaying a selected first sub-category 330 in the selected area 304 and the text area 303, respectively.

[0067] Further, for the song with words, in the text area 303, the corresponding input can be more professional according to the common structure of the song, so that the generated music can be more in line with the needs of the user. Specifically, as shown in FIG. 3B, the user can input a set structure prompt to specify the specific structure, and in the example, the structure prompt is specifically a " / " symbol, and of course other structure prompts can also be set in other examples, which are not specifically limited. After the user inputs the corresponding structure prompt, the prompt information can be prompted, and the user can select or directly input according to the corresponding rules. As shown in FIG. 3B, after inputting " / ", a prompt area can be formed on the side of the structure prompt, and the prompt information is displayed in the prompt area. The user can select the prompt information (the fourth operation), such as selecting the intro in the prompt information, or directly inputting the corresponding input according to the prompt information, such as directly inputting the intro after " / ". Then, the corresponding structure word (such as the aforementioned intro) can be displayed in the text area 303, and the content after the structure word is considered as the limitation or description of the part indicated by the structure word. That is, according to the fourth operation of the prompt information or the input information corresponding to the prompt information, the structure word is displayed in the text area, and the input text after the structure word is considered as the specific content of the structure word; wherein the structure word corresponds to the specific content of the prompt information determined by the fourth operation, or corresponds to the specific content of the prompt information corresponding to the input information.

[0068] After that, for the example of setting the text area 303, if there is text information in the text area 303 when the music generation operation is performed, the text information can be merged into the constraint information as a kind of constraint and input into the corresponding music generation model or algorithm to constrain and limit the music generation.

[0069] Further, the first classification and the first sub-classification are more specifically described. As shown in FIG. 3A, the classification display area 305 can be further set in the production interface 300, specifically in the function area 301. The first classification 320 and the first sub-classification 330 are displayed in the classification display area 305. After that, for one selection method of the first classification 320 and the first sub-classification 330, part of the description has been made in the foregoing example, that is, the options of the first classification 320 can be displayed in the classification display area 305 first, and when the user selects one of the first classification 320, the first sub-classification 330 corresponding to the first classification 320 is continued to be displayed in the classification display area 305. After that, the user selects, and the selected classification can be displayed differently, or can be displayed in other areas (for example, the selected area 304 or the text area 303).

[0070] In another example, as shown in FIGS. 3C-3E, the first categories 320 can be displayed in the category display area 305 first, and after a user selects one of the first categories 320, the display of the first categories 320 in the category display area 305 is cancelled, and only the first sub-categories 330 corresponding to the selected first category 320 is displayed. As shown in FIGS. 3C-3E, after the first category 320 of “Dance” is selected, the other first categories in the category display area 305 are cancelled (and can be understood as not selectable), and then only the first sub-categories 330 corresponding to the first category 320 of “Dance” is displayed in the category display area 305.

[0071] Further, for such a selection mode, multiple sequences can be performed, i.e., after the selection of the first category 320 is completed, the first sub-categories 330 corresponding to the selected first category 320 is displayed, after a first sub-category 330 is selected, the second sub-categories corresponding to the selected first sub-category 330 can be further displayed, and after a second sub-category is selected, only the third sub-categories corresponding to the selected second sub-category is displayed, and so on, until the number of selected categories or options reaches a preset condition (e.g., reaches the bottom layer of categories or the number of selected categories reaches a certain number, etc.), or the user stops the selection and triggers the music generation operation, etc.

[0072] For the generation of songs with lyrics, the song length generally corresponds to the length of the lyrics, and thus the corresponding song length can not be set. For pure music without lyrics, the song length can need to be limited. Therefore, in some examples, as shown in FIGS. 3C-3E, the music type option 310 can further include a pure music option 310B, and in the function area 301 corresponding to the pure music option 310B, a time length input area (music time part in the figure) can be further displayed, and the user can set the music time length through the input in the area. The specific time length input area can be in the form of a text box, and the user can input the specific time in the text box; or as shown in FIGS. 3C-3E, the time can be selected through the drag input of the drag bar, and of course on one side of the drag bar, the display of the set time can be performed; or the time can be set through the scroll wheel, and the minute, second, etc. setting scroll wheel can be set in the time length input area, and the specific time can be set through the scrolling of the scroll wheel.

[0073] Finally, for music generation, an input port for song name and song cover can also be further set, for example, in the function area 301, set the corresponding input area, etc. Of course, similar to the lyrics, for the song name and the song cover, they can also not be input, but let the music generation model directly generate by means of the corresponding module. Specifically, the corresponding generation work can be performed according to the constraint information, which can or can not contain text information. That is, in some examples, music generation according to constraint information includes at least one of generating a music song, generating a music song name, and generating a music cover. In more specific scenarios, whether it is automatic generation of lyrics or generation of song names or covers, it may fail to generate due to insufficient content, etc.; or these automatically generated contents need to be audited, and if they cannot pass the audit, they may also cause the generation to fail. When the generation fails, the user can be prompted by forming a corresponding prompt information.

[0074] At this point, the music generation part is completed, and the generated music work can be displayed in the display area 302 of the production interface 300. Specifically, as shown in FIG. 3A, the display of a work can be performed in the first display area 306 in the display area 302. For the first display area 306, more specifically, as shown in FIG. 3F, at least part of the information of the music can be displayed in the first display area 306, such as the song cover, the text information in the constraint information, etc. After the user selects the music type option, the first classification, and the first sub-classification, the essence is to set the nature of the music, and then the contents of these options or classifications can be displayed in the first display area 306 in turn. In order to save space, only part or none of them can be displayed. For the above information that is not displayed, a trigger area 306A (or can be called an expansion identifier) can be set. When the trigger area 306A is triggered by selection, hovering, or other operations, the specific display of the above information can be performed separately. For example, as shown in FIG. 3F, only the identifier corresponding to the music type option is displayed after the text information, and the other classifications are not displayed, but an expansion identifier 306A of "song style" is set. When the user triggers the area by selection or hovering, etc., the specific information that has not been displayed before can be displayed by popping up a display box on one side or other forms.

[0075] Further, as shown in FIG. 3F, in order to facilitate the re-editing of the music work, a re-editing identifier 306B can be provided for the first display area 306. By triggering the re-editing identifier 306B, the music work can be re-edited, and the setting attributes corresponding to the music work can be recalled in the function area 301, so as to re-edit the music work. Similarly, the same setting as the music work displayed in the first display area 306 can be used to generate a music work again by using the music generation model or algorithm, that is, the same constraint information is used to generate a music work again by using the music generation model or algorithm. Due to the setting of the music generation model or algorithm itself, even if the input is completely consistent, the output can not be the same, so that at least one music work can be generated by using the same constraint information. In order to realize such a function, a re-generation identifier 306C can be provided for the first display area 306. By triggering the re-generation identifier 306C, the same constraint information of the music work displayed in the first display area 306 can be used to generate a music work again.

[0076] In some examples, similar to the first display area 306 described above, the display of the finished work can also be performed in the operation interface 200. As shown in FIG. 2, the display of the finished work can be performed in the main area 203, wherein the second display area 307 can be used to display the finished music work. As shown in FIG. 3G, a specific structure diagram of the second display area 307 is shown. The second display area 307 is mainly used to display the work information, and specifically for the finished music work, the music cover of the finished music work and the song information such as the song name and the author can be displayed, and the user can view more detailed information by clicking these information. Then, it is more important for the finished music work to be able to be played, so that the user can hear the specific content of the work, and then the first area 307A can be included in the second display area 307, and when the user triggers (such as clicking, etc.) the area, the music work can be played. At the same time, the song cover and other information can be displayed in the first area 307A, or the corresponding lyrics can be displayed when the music is played.

[0077] Further, after the user appreciates the work of the second display area 307, in order to meet the user's desire to make similar works with the finished music work of the second display area 307, or further modify and adjust the work based on the finished music work. A second area 307B can be set in the second display area 307. By triggering (such as clicking, etc.) the area, the attribute information corresponding to the finished music work can be directly displayed on the operation interface 200 or displayed through a newly created window. The displayed information form or layout form can be similar to the function area 301 of the production interface 300, except that the corresponding constraint information of the finished music work displayed in the second display area 307 is filled in or selected. At the same time, the area corresponding to the triggering area of the "music generation" of the function area 301 in the newly generated area is the third area. The specific third area can be a "make the same" triggering area. After the user checks the displayed constraint information, if you want to further "make the same" or improve it, you can trigger (select operation) the third area. After triggering the third area, it can jump to the production interface 300, and adjust the text area, classification display area and the like in the production interface 300 according to the constraint information of the finished music work, so that it is consistent with the constraint information of the finished music work. Then receive the user's adjustment, or directly perform music generation operation.

[0078] In some examples, the main area 203 of the operation interface 200 can contain information of many works, and it can be slidable or scrollable. After a user plays a finished music work in the operation interface 200, if the main area 203 is sliding or scrolling, and the second display area 307 of the playing finished music work is out of the display range of the main area 203 or the display range of the operation interface 200, the display of the music work can be terminated by stopping playing, for example, directly stopping, or fading out in a set time after being out of the display range, and finally stopping. However, in more scenarios, the user generally does not want the music work to stop displaying, so when there is no second display area 307 of the finished music work, a corresponding controller needs to be set to control the music work. Therefore, when the second display area 307 is out of the display range of the operation interface 200, a music playing floating area 308 can be displayed on the operation interface 200. As shown in FIG. 2, the music playing floating area 308 can be set at any position of the operation interface 200, for example, the lower right corner, etc. Specifically, the form of the music playing floating area 308 can be as shown in FIG. 3H. The music playing floating area 308 can be set at any position of the operation interface 200, and the user can move or adjust the size of the music playing floating area 308, etc. Then, the functions that can be realized by the music playing floating area 308 are as follows. First, the fourth area 308A of the music playing floating area 308 can jump back to the position of the second display area 307 of the music work. When the user triggers the fourth area 308A, the operation interface 200 can directly jump to the position of the second display area 307 of the finished music work, and cancel the music playing floating area 308. At the same time, the cover of the music work, the playing progress, and other information can be displayed in the fourth area 308A. Then, the music playing floating area 308 can set a control area, i.e., the fifth area 308B, to control whether to play the music or control the corresponding music attribute. When the user triggers the fifth area 308B, according to the function keys of the fifth area 308B triggered by the user, the music work can be played, paused, stopped, the volume can be adjusted, the music work can be fast forwarded or rewound, the previous work or the next work can be adjusted, etc. Further, the music playing floating area 308 can set a sixth area 308C to close the music playing floating area 308. By triggering (selecting, clicking, etc.) the sixth area 308C, the music playing floating area 308 can be cancelled, and the playing of the corresponding finished music can be stopped.

[0079] In some more specific scenarios, a music playlist can be generated according to the work content of the main area 203 of the operation interface 200, and the music work corresponding to the music playing floating area 308 can be changed according to the change of the playing music.

[0080] Further, the music playing floating area 308 is arranged to control the music work when the second display area 307 of the playing music work exceeds the display range, and the music playing floating area 308 is not necessary to be displayed when the second display area 307 of the music work re-enters the display range, and the music playing floating area 308 can be cancelled. Or the user selects another music work and wants to play the selected music work, and the playing of the current music work is stopped and the selected music work is played. At the same time, the second display area 307 of the selected music work is in the display range when the user selects the music work, and the music playing floating area 308 is not necessary to be displayed and can be cancelled.

[0081] Finally, FIG. 4 shows a flow diagram of an exemplary method 400 according to an embodiment of the present disclosure.

[0082] The method 400 is used for music generation and can be implemented by the terminal device 102 alone or by the system 100. As shown in FIG. 4, the method 400 can include the following steps.

[0083] At step 402, in response to a music generation operation in an operation interface, a production interface is displayed; the production interface includes at least one music type option.

[0084] At step 404, in response to a first operation on any music type option, at least one first category corresponding to the any music type option is displayed in the production interface.

[0085] At step 406, in response to a second operation on any first category, at least one first subcategory corresponding to the any first category is displayed, and selection of the at least one first subcategory is determined to generate constraint information.

[0086] At step 408, in response to a music generation operation, music generation is performed according to the constraint information.

[0087] In some exemplary embodiments, after the response to the first operation on any music type option, the method further includes:

[0088] displaying a text area in the production interface;

[0089] obtaining input text information through the text area;

[0090] or

[0091] in response to a third operation in the text area, automatically generating the text information in the text area.

[0092] In some example embodiments, the music generation according to the constraint information comprises:

[0093] In response to the existence of the text information, the music generation is performed with the text information as a constraint.

[0094] In some example embodiments, the obtaining of the input text information through the text area comprises:

[0095] In response to the obtaining of a preset structure prompt, displaying prompt information corresponding to the structure prompt;

[0096] According to a fourth operation on the prompt information or the obtaining of input information corresponding to the prompt information, displaying a structure word in the text area and taking the input text after the structure word as the specific content of the structure word; wherein the structure word corresponds to the specific content of the prompt information determined by the fourth operation or the specific content of the prompt information corresponding to the input information.

[0097] In some example embodiments, the production interface comprises a classification display area; and the displaying of at least one first sub-category corresponding to any first category comprises:

[0098] According to the second operation, determining the selected any first category, and displaying all first sub-categories corresponding to the selected any first category in the classification display area.

[0099] In some example embodiments, the production interface comprises a classification display area; and the displaying of at least one first sub-category corresponding to any first category comprises:

[0100] In the classification display area, canceling the display of the at least one first category and displaying the at least one first sub-category in the classification display area;

[0101] In response to the selection of any first sub-category, canceling the display of the at least one first sub-category in the classification display area and displaying second sub-categories corresponding to the selected first sub-category in the classification display area, and repeating the above operations until the number of selected options reaches a preset condition or a music generation operation is obtained.

[0102] In some example embodiments, the music type options at least comprise a pure music option;

[0103] In response to the first operation on any music type option, the method further comprises:

[0104] In response to the pure music option determined by the first operation, a duration input area is displayed in the production interface to set a music duration through the duration input area.

[0105] In some example embodiments, the music generation according to the constraint information includes at least one of generating a music song, generating a music title, and generating a music cover.

[0106] In some example embodiments, after the music generation according to the constraint information, the method further includes:

[0107] displaying a first display area of the generated music in the production interface;

[0108] displaying content of the constraint information in the first display area in sequence;

[0109] or

[0110] displaying at least part of the content of the constraint information and an expansion identifier in the first display area; wherein the expansion identifier is used to display the omitted content of the constraint information when triggered.

[0111] In some example embodiments, after the music generation according to the constraint information, the method further includes:

[0112] displaying a first display area of the generated music in the production interface;

[0113] adding a re-editing identifier and / or a re-generation identifier to the first display area.

[0114] In some example embodiments, the operation interface further includes a second display area for displaying a finished music; the second display area includes at least a first area and a second area.

[0115] In response to a triggering operation on the first area, the finished music is played.

[0116] In response to a triggering operation on the second area, the constraint information corresponding to the finished music and a third area are displayed.

[0117] In response to a triggering operation on the third area, the production interface is displayed and adjusted according to the constraint information corresponding to the finished music.

[0118] In some example embodiments, the operation interface further includes a music playing floating area; the music playing floating area includes at least one of a fourth area, a fifth area, and a sixth area.

[0119] After the finished music is played, the method further includes:

[0120] displaying the music playing floating area on the operation interface in response to the second display area exceeding the display range of the operation interface;

[0121] redisplaying the second display area in the display range of the operation interface and canceling the music playing floating area in response to the triggering operation on the fourth area;

[0122] controlling the playing state of the finished music and / or adjusting the playing attribute in response to the triggering operation on the fifth area;

[0123] closing the music playing floating area and stopping the playing of the finished music in response to the triggering operation on the sixth area.

[0124] In some example embodiments, after displaying the music playing floating area on the operation interface, the method further comprises:

[0125] canceling the music playing floating area in response to the second display area re-entering the display range of the operation interface or receiving a selection of other finished music.

[0126] As can be seen from the above embodiments, the music generation method provided by the embodiments of the present disclosure displays a production interface for music generation on the operation interface of the user, so that the user can generate music while producing images or videos, and can set constraints for the generated music by selecting different categories and different subcategories when generating music, so as to limit the type, timbre, musical instrument, scene and other elements of music generation, so that the music can be more suitable for the needs of the user, and provide more diverse functions for the user to create using generative artificial intelligence technology, and significantly improve the user experience.

[0127] It should be noted that the method of the embodiments of the present disclosure can be executed by a single device, such as a computer or a server, etc. The method of the embodiments of the present disclosure can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only execute one or more steps in the method of the embodiments of the present disclosure, and the multiple devices will interact with each other to complete the method.

[0128] It is to be understood that the foregoing description is directed to particular embodiments of the disclosure. Various changes can be made to the application claimed without departing from the scope of the application. It can be understood that the drawings and detailed description thereto are not intended to limit the scope of the application to the particular embodiments described in the specification. The actions or steps described in the claims can be performed in different order than described in the examples and still achieve desirable results.

[0129] According to the same technical concept, the disclosure also provides a music generation device corresponding to the method of any of the above embodiments.

[0130] Referring to FIG. 5, the music generation device 500 includes:

[0131] A first module 510 is configured to display a production interface in response to a music generation operation in an operation interface; the production interface includes at least one music type option.

[0132] A second module 520 is configured to display at least one first classification corresponding to any music type option in the production interface in response to a first operation on the any music type option.

[0133] A third module 530 is configured to display at least one first sub-classification corresponding to any first classification in response to a second operation on the any first classification, and determine a selection of the at least one first sub-classification to generate constraint information.

[0134] A fourth module 540 is configured to generate music according to the constraint information in response to a music generation operation.

[0135] In some example embodiments, the second module 520 is further configured to:

[0136] display a text area in the production interface;

[0137] obtain input text information through the text area;

[0138] or

[0139] automatically generate the text information in the text area in response to a third operation in the text area.

[0140] In some example embodiments, the fourth module 540 is further configured to:

[0141] generate music with the text information as a constraint in response to the presence of the text information.

[0142] In some example embodiments, the second module 520 is further configured to:

[0143] in response to obtaining the preset structure prompt, display prompt information corresponding to the structure prompt;

[0144] in response to a fourth operation on the prompt information or obtaining input information corresponding to the prompt information, display a structure word in the text area, and take the input text after the structure word as the specific content of the structure word; wherein the structure word corresponds to the specific content of the prompt information determined by the fourth operation, or the specific content of the prompt information corresponding to the input information.

[0145] In some example embodiments, the production interface includes a category display area; the third module 530 is further configured to:

[0146] determine the selected any first category according to the second operation, and display all first sub-categories corresponding to the any first category in the category display area.

[0147] In some example embodiments, the production interface includes a category display area; the third module 530 is further configured to:

[0148] cancel the display of the at least one first category in the category display area, and display the at least one first sub-category in the category display area.

[0149] in response to the selection of any first sub-category, cancel the display of the at least one first sub-category in the category display area, and display second sub-categories corresponding to the selected first sub-category in the category display area, and repeat the above process until the number of selected options reaches a preset condition or a music generation operation is obtained.

[0150] In some example embodiments, the music type option includes at least a pure music option.

[0151] The second module 520 is further configured to:

[0152] in response to the first operation determining the pure music option, display a duration input area in the production interface to set the music duration through the duration input area.

[0153] In some example embodiments, the fourth module 540 generates music according to the constraint information, including at least one of generating a music song, generating a music song name, and generating a music cover.

[0154] In some example embodiments, the fourth module 540 is further configured to:

[0155] display a first display area of the generated music in the production interface.

[0156] displaying content of the constraint information in the first display area in sequence;

[0157] or

[0158] displaying at least part of the content of the constraint information and an expansion mark in the first display area; wherein the expansion mark is used to display the omitted content of the constraint information when triggered.

[0159] In some example embodiments, the fourth module 540 is further configured to:

[0160] displaying a first display area of the generated music in the production interface;

[0161] adding a re-editing mark and / or a re-generation mark to the first display area.

[0162] In some example embodiments, the operation interface further comprises a second display area for displaying the finished music; the second display area comprises at least a first area and a second area;

[0163] playing the finished music in response to a triggering operation on the first area;

[0164] displaying constraint information corresponding to the finished music and a third area in response to a triggering operation on the second area;

[0165] displaying the production interface and adjusting the production interface according to the constraint information corresponding to the finished music in response to a triggering operation on the third area.

[0166] In some example embodiments, the operation interface further comprises a music playing floating area; the music playing floating area comprises at least one of a fourth area, a fifth area and a sixth area;

[0167] After playing the finished music, the operation further comprises:

[0168] displaying the music playing floating area on the operation interface in response to the second display area exceeding the display range of the operation interface;

[0169] redisplaying the second display area in the display range of the operation interface and canceling the music playing floating area in response to a triggering operation on the fourth area;

[0170] controlling the playing state of the finished music and / or adjusting the playing attribute in response to a triggering operation on the fifth area;

[0171] In response to the triggering operation on the sixth region, the music playing floating area is closed and the playing of the finished music is stopped.

[0172] In some example embodiments, after displaying the music playing floating area on the operation interface, the method further includes:

[0173] In response to the second display region re-entering the display range of the operation interface or receiving a selection of other finished music, the music playing floating area is cancelled.

[0174] For the convenience of description, the above apparatus is described in various modules according to functions. Of course, the functions of the modules can be implemented in one or more software and / or hardware when implementing the embodiments of the present disclosure.

[0175] The apparatus of the above embodiments is used to implement the corresponding method 400 in the foregoing embodiments, and has the beneficial effects of the corresponding method 400 embodiments, which are not described here again.

[0176] Based on the same technical concept, corresponding to the method of any of the above embodiments, the embodiments of the present disclosure also provide a computer device for implementing the method 400 described above. FIG. 6 shows a hardware structure schematic diagram of an example computer device 600 provided by the embodiments of the present disclosure. The computer device 600 can be used to implement the terminal device 102 of FIG. 1. In some scenarios, the computer device 600 can also be used to implement the server 104, the database server 106 of FIG. 1.

[0177] As shown in FIG. 6, the computer device 600 can include a processor 602, a memory 604, a network module 606, a peripheral interface 608, and a bus 610. Among them, the processor 602, the memory 604, the network module 606, and the peripheral interface 608 are connected to each other through the bus 610 for internal communication connection in the computer device 600.

[0178] The processor 602 can be a central processing unit (CPU), an image processor, a neural network processor (NPU), a microcontroller (MCU), a programmable logic device, a digital signal processor (DSP), an application specific integrated circuit (ASIC), or one or more integrated circuits. The processor 602 can be used to perform functions related to the techniques described in the present disclosure. In some embodiments, the processor 602 can also include multiple processors integrated as a single logic component. For example, as shown in FIG. 6, the processor 602 can include multiple processors 602a, 602b, and 602c.

[0179] The memory 604 can be configured to store data (e.g., instructions, computer code, etc.). As shown in FIG. 6, the data stored by the memory 604 can include program instructions (e.g., program instructions for implementing the method 400 of the embodiments of the present disclosure) and data to be processed (e.g., the memory can store configuration files of other modules, etc.). The processor 602 can also access the program instructions and data stored by the memory 604 and execute the program instructions to operate on the data to be processed. The memory 604 can include volatile storage or nonvolatile storage. In some embodiments, the memory 604 can include random access memory (RAM), read only memory (ROM), optical disc, magnetic disc, hard disc, solid state disc (SSD), flash memory, memory stick, etc.

[0180] The network interface 606 can be configured to provide communication with other external devices to the computer device 600 via a network. The network can be any wired or wireless network capable of transmitting and receiving data. For example, the network can be a wired network, a local wireless network (e.g., Bluetooth, WiFi, near field communication (NFC), etc.), a cellular network, the Internet, or a combination thereof. It can be understood that the type of network is not limited to the specific examples described above.

[0181] The peripheral interface 608 can be configured to connect the computer device 600 with one or more peripheral devices to enable information input and output. For example, the peripheral devices can include input devices such as a keyboard, a mouse, a touchpad, a touch screen, a microphone, various sensors, etc. and output devices such as a display, a speaker, a vibrator, an indicator light, etc.

[0182] The bus 610 can be configured to transmit information between various components (e.g., the processor 602, the memory 604, the network interface 606, and the peripheral interface 608) of the computer device 600, such as an internal bus (e.g., a processor-memory bus), an external bus (a USB port, a PCI-E bus), etc.

[0183] It should be noted that although the architecture of the computer device 600 described above only shows the processor 602, the memory 604, the network interface 606, the peripheral interface 608, and the bus 610, in the specific implementation process, the architecture of the computer device 600 can also include other components necessary for normal operation. In addition, those skilled in the art can understand that the architecture of the computer device 600 described above can also only include components necessary for implementing the embodiments of the present disclosure, and does not necessarily include all the components shown in the figure.

[0184] The computer device 600 of the above embodiments is used to implement the method 400 as described in any of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which are not described here again.

[0185] Based on the same technical concept, the disclosure also provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method 400 of any of the above embodiments.

[0186] The computer-readable medium of the embodiments can include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device.

[0187] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to perform the method 400 of any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which are not repeated here.

[0188] Based on the same technical concept, the disclosure also provides a computer program product including computer program instructions that, when executed on a computer, cause the computer to perform the method 400 of any of the above embodiments. In some embodiments, the computer program instructions can be executed by one or more processors of a computer to cause the computer and / or the processor to perform the method 400. Corresponding to the execution subject of each step in each embodiment of the method 400, the processor performing the corresponding step can belong to the corresponding execution subject.

[0189] The computer program product of the above embodiments is used to cause the computer and / or the processor to perform the method 400 of any of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which are not repeated here.

[0190] Those of ordinary skill in the art will realize that the foregoing discussion of any of the embodiments has been presented for the purpose of illustration and description and is not intended to be exhaustive or to limit the disclosure to the precise forms described. Many modifications and variations will be apparent to those of ordinary skill in the art. For example, the above-described embodiments can be implemented in conjunction with other memory architectures (e.g., dynamic RAM (DRAM)).

[0191] In addition, to simplify the description and discussion, and so as not to make the embodiments of the disclosure difficult to understand, the well-known power / ground connections to integrated circuit (IC) chips and other components can or can not be shown in the provided drawings. Further, devices can be shown in block diagram form in order to avoid making the embodiments of the disclosure difficult to understand, and this also takes into account the fact that details regarding implementation of these block diagram devices are highly dependent on the platform in which the embodiments of the disclosure are to be implemented (i.e., these details should be well within the understanding of one of ordinary skill in the art). Where specific details (e.g., circuitry) are set forth in order to describe an illustrative embodiment of the disclosure, it will be apparent to those of ordinary skill in the art that the embodiments of the disclosure can be practiced without these specific details or with an equivalent arrangement. Therefore, these descriptions should be considered in a descriptive sense only and not limiting.

[0192] Although the disclosure has been described in conjunction with specific embodiments thereof, many alternatives, modifications and variations will be apparent to those of ordinary skill in the art. For example, other memory architectures (e.g., dynamic RAM (DRAM)) can use the embodiments discussed.

[0193] The embodiments of the disclosure are intended to cover all such alternatives, modifications and variations as falling within the broad scope of the appended claims. Accordingly, any one of the steps of the disclosed embodiments can be performed in any order, and many of the steps can be performed in any order or in parallel, unless otherwise specified.

Claims

1. A music generation method, comprising: displaying a production interface in response to a music generation operation in an operation interface; the production interface comprising at least one music type option; displaying at least one first category corresponding to any music type option in the production interface in response to a first operation on the any music type option; displaying at least one first subcategory corresponding to any first category in response to a second operation on the any first category, determining selection of the at least one first subcategory, and generating constraint information in this way; generating music according to the constraint information in response to the music generation operation.

2. The method of claim 1, wherein, After the response to the first operation on the any music type option, the method further comprises: displaying a text area in the production interface; obtaining input text information through the text area; or automatically generating the text information in the text area in response to a third operation in the text area. The music generation according to the constraint information comprises:

3. The method of claim 2, wherein, in response to the existence of the text information, taking the text information as a constraint for the music generation. The obtaining of the input text information through the text area comprises:

4. The method of claim 2, wherein, in response to obtaining a preset structure prompt, displaying prompt information corresponding to the structure prompt; displaying a structure word in the text area according to a fourth operation on the prompt information or obtaining input information corresponding to the prompt information, and taking input text after the structure word as specific content of the structure word; wherein the structure word corresponds to specific content of the prompt information determined by the fourth operation or to specific content of the prompt information corresponding to the input information. The production interface comprises a category display area; and the displaying of the at least one first subcategory corresponding to the any first category comprises:

5. The method of claim 1, wherein, determining the any first category selected according to the second operation, and displaying all first subcategories corresponding to the any first category in the category display area. The production interface comprises a category display area; and the displaying of the at least one first subcategory corresponding to the any first category comprises:

6. The method of claim 1, wherein, canceling display of the at least one first category in the category display area, and displaying the at least one first subcategory in the category display area; in response to selection of any first subcategory, canceling display of the at least one first subcategory in the category display area, and displaying second subcategories corresponding to the selected first subcategory in the category display area, and repeating this in a loop until the number of selected options reaches a preset condition or a music generation operation is obtained. The music type option at least comprises a pure music option; 7. The method of claim 1, wherein, After the response to the first operation on the any music type option, the method further comprises: in response to the first operation determining the pure music option, displaying a duration input area in the production interface to set music duration through the duration input area. The music generation according to the constraint information comprises at least one of generating a music song, generating a music song name, and generating a music cover.

8. The method according to any one of claims 1 to 7, wherein, ​ 9. The method of claim 1, wherein, After the music generation according to the constraint information, the method further comprises: displaying a first display area of the generated music in the production interface; displaying the content of the constraint information in the first display area in sequence; or displaying at least part of the content of the constraint information and an expansion mark in the first display area; wherein the expansion mark is used to display the omitted content of the constraint information when triggered.

10. The method of claim 1, wherein, After the music generation according to the constraint information, the method further comprises: displaying a first display area of the generated music in the production interface; adding a re-editing mark and / or a re-generation mark to the first display area.

11. The method of claim 1, wherein, The operation interface further comprises a second display area for displaying the finished music; the second display area comprises at least a first area and a second area; in response to a triggering operation on the first area, playing the finished music; in response to a triggering operation on the second area, displaying the constraint information corresponding to the finished music and a third area; in response to a triggering operation on the third area, displaying the production interface and adjusting the production interface according to the constraint information corresponding to the finished music.

12. The method of claim 11, wherein, The operation interface further comprises a music playing floating area; the music playing floating area comprises at least one of a fourth area, a fifth area and a sixth area; After the playing of the finished music, the method further comprises: in response to the second display area exceeding the display range of the operation interface, displaying the music playing floating area on the operation interface; in response to a triggering operation on the fourth area, redisplaying the second display area in the display range of the operation interface and canceling the music playing floating area; in response to a triggering operation on the fifth area, controlling the playing state of the finished music and / or adjusting the playing attribute; in response to a triggering operation on the sixth area, closing the music playing floating area and stopping the playing of the finished music.

13. The method of claim 12, wherein, After the displaying of the music playing floating area on the operation interface, the method further comprises: in response to the second display area re-entering the display range of the operation interface or receiving a selection of other finished music, canceling the music playing floating area.

14. A music generation device, comprising: a first module for displaying a production interface in response to a music generation operation in an operation interface; the production interface comprises at least one music type option; a second module for displaying at least one first classification corresponding to any music type option in the production interface in response to a first operation on the any music type option; a third module for displaying at least one first sub-classification corresponding to any first classification in response to a second operation on the any first classification, determining a selection of the at least one first sub-classification to generate constraint information; a fourth module for generating music according to the constraint information in response to a music generation operation.

15. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein, The processor implements the method of any one of claims 1 to 13 when executing the program.

16. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are for causing a computer to perform the method of any one of claims 1 to 13.

Images