WO2022160603A1 - 歌曲的推荐方法、装置、电子设备及存储介质 - Google Patents

歌曲的推荐方法、装置、电子设备及存储介质 Download PDF

Info

Publication number
WO2022160603A1
WO2022160603A1 PCT/CN2021/104110 CN2021104110W WO2022160603A1 WO 2022160603 A1 WO2022160603 A1 WO 2022160603A1 CN 2021104110 W CN2021104110 W CN 2021104110W WO 2022160603 A1 WO2022160603 A1 WO 2022160603A1
Authority
WO
WIPO (PCT)
Prior art keywords
song
songs
information
identified
release
Prior art date
Application number
PCT/CN2021/104110
Other languages
English (en)
French (fr)
Inventor
周志新
朱剑
吴旺文
徐嘉锐
郑炜明
朱碧磊
管培雯
Original Assignee
北京字节跳动网络技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京字节跳动网络技术有限公司 filed Critical 北京字节跳动网络技术有限公司
Priority to US17/600,323 priority Critical patent/US20240054157A1/en
Publication of WO2022160603A1 publication Critical patent/WO2022160603A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/60Information retrieval; Database structures therefor; File system structures therefor of audio data
    • G06F16/63Querying
    • G06F16/635Filtering based on additional data, e.g. user or group profiles
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/60Information retrieval; Database structures therefor; File system structures therefor of audio data
    • G06F16/63Querying
    • G06F16/638Presentation of query results
    • G06F16/639Presentation of query results using playlists
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/60Information retrieval; Database structures therefor; File system structures therefor of audio data
    • G06F16/68Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/686Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title or artist information, time, location or usage information, user ratings

Definitions

  • the embodiments of the present disclosure relate to the field of computers, and in particular, to a method, apparatus, electronic device, storage medium, computer program product, and computer program for recommending songs.
  • the music platform will select newly released songs from the music library, and generate a new song recommendation list or a new song recommendation list for users to listen to.
  • embodiments of the present disclosure provide a method, apparatus, electronic device, storage medium, computer program product, and computer program for recommending songs.
  • the present disclosure provides a method for recommending songs, including:
  • the first page is switched to the second page of the selected target song
  • the song release date of the target song is determined according to the song release information and hearing information of the song.
  • the present disclosure provides a device for recommending songs, including:
  • a display module for displaying a first page, the first page including a target song selected according to the release date of the song
  • an interaction module configured to respond to a triggering operation on the target song on the first page, so that the display module switches the first page to the second page of the selected target song;
  • the song release date of the target song is determined according to the song release information and hearing information of the song.
  • an electronic device including:
  • the memory stores computer-executable instructions
  • the at least one processor executes the computer-executable instructions stored in the memory to cause the at least one processor to perform the method for recommending songs as described in the first aspect.
  • the present disclosure further provides a computer-readable storage medium, wherein computer-executable instructions are stored in the computer-readable storage medium, and when a processor executes the computer-executable instructions, the implementation of the first aspect is achieved.
  • the present disclosure provides a computer program product comprising computer instructions that, when executed by a processor, implement the method for recommending songs in the first aspect.
  • the present disclosure further provides a computer program, which, when executed by a processor, is used to implement the method for recommending songs according to the first aspect.
  • the method, device, electronic device, storage medium, computer program product, and computer program for recommending songs may firstly display a first page, where the first page includes a target song selected according to the release date of the song; then , in response to the triggering operation on the target song on the first page, switch the first page to the second page of the selected target song.
  • the song release date of the target song in this embodiment is determined according to the song release information and hearing information of the song, and in this way, the real song release date of the song can be effectively identified, so that the display on the first page can be done.
  • target songs were chosen based on their actual song release dates. Using this method can effectively improve the recognition accuracy of the new song, which is convenient for the user to use.
  • FIG. 1 is a schematic diagram of a network architecture on which the disclosure is based;
  • FIG. 2 is a schematic flowchart of a method for recommending songs according to an embodiment of the present disclosure
  • FIG. 3 is a schematic diagram of a first interaction of a method for recommending songs according to an embodiment of the present disclosure
  • FIG. 4 is a second interactive schematic diagram of a method for recommending songs according to an embodiment of the present disclosure
  • FIG. 5 is a third interactive schematic diagram of a method for recommending songs according to an embodiment of the present disclosure
  • FIG. 6 is a schematic flowchart of a method for determining the release date of a song provided by an embodiment of the present disclosure
  • FIG. 7 is a structural block diagram of an apparatus for recommending songs according to an embodiment of the present disclosure.
  • FIG. 8 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present disclosure.
  • the music platform will select newly released songs from the music library, and generate a new song recommendation list or a new song recommendation list for users to listen to.
  • a singer released album A which included song a
  • the singer released album B which included 20 years of classic songs, in which album B included song a.
  • the song a released in 2000 Based on the situation described in this example, and based on the existing method for identifying the release date of new songs, the music platform will identify song a in album B as a new song released in 2020, and put it into the new song recommendation list for recommendation.
  • the release date of the song can be determined according to the song release information and the hearing information of the song, that is, a series of judgment processing is performed through the release information and the hearing information of the song to determine the actual release of the song date, and the actual release date of the song will be used to play and recommend the song.
  • FIG. 1 is a schematic diagram of a network architecture on which the present disclosure is based.
  • the network architecture shown in FIG. 1 may specifically include a terminal 1 and a server 2 .
  • the terminal 1 can be a hardware device that can be used to play songs, such as a user's mobile phone, a desktop computer, a smart home device, a tablet computer, etc., and a music platform can be installed on the terminal 1 to play songs such as an APP and a client;
  • the server 2 can be An independent server or server cluster set in the cloud can be used to provide file and data support for the music platform of songs on the terminal 1, as well as page display services and interactive services.
  • the device for recommending songs provided by the present disclosure can be specifically carried in the server 2 shown in FIG. 1 , which recommends songs stored in the server 2 based on the release dates of the songs through the method for recommending songs based on the songs provided by the present disclosure.
  • FIG. 2 is a schematic flowchart of a method for recommending songs according to an embodiment of the present disclosure.
  • the method for recommending songs provided by the embodiments of the present disclosure includes:
  • Step 101 display a first page, the first page includes the target song selected according to the song release date; wherein, the song release date of the target song is determined according to the song release information and hearing information of the song;
  • Step 102 In response to the triggering operation on the target song on the first page, switch the first page to the second page of the selected target song.
  • the execution body of the recommendation method provided in this example is the aforementioned device for recommending songs.
  • it specifically refers to the client or display end of the music platform, which is the installation or display end of the music platform. It is integrated on the terminal and can be presented to the user through an application interface or a control display interface. The user can interact with the song recommendation device through the terminal, and control it to obtain the pages and songs it provides.
  • the song recommendation device can be a client of the music platform, it generally provides the user with the function of displaying and playing music. That is to say, a large number of songs can be displayed on the terminal, and the user can start playing, pause, switch and other different operations on these songs through different touch methods such as clicking, sliding, and pressing.
  • the terminal will display a first page on which the target song will be included, and the target song will be selected by the release date of the song.
  • the release date of the song is determined according to the song release information and hearing information of the song.
  • the terminal will switch the first page to the second page of the selected target song in response to the user's triggering operation on the target song on the first page.
  • the touch control of the trigger operation may be click, slide, press, etc., which is not limited in this embodiment.
  • This embodiment does not limit the specific forms of the aforementioned first page and second page, and the content presented on the pages and page functions may be determined based on the product requirements of the actual music platform.
  • FIG. 3 is a first interactive schematic diagram of a method for recommending songs according to an embodiment of the present disclosure.
  • the terminal is in the running state of using the client of the music platform to play songs.
  • the first page is shown as Play page of song A: On the play page, the user can control the play and pause of the song by triggering the play pause button of the song.
  • a new song identification indicating that song A belongs to a new song is also included.
  • song A it is obtained by filtering the song release date of each song from the music library, such as filtering new songs based on the song release date (that is, selecting the song release date from the music library and Songs that are closer to the current date are played in shuffle or in order).
  • how to determine the song release date of the song A may refer to the subsequent embodiments, which will not be described here for the time being.
  • the user can select the new song identifier on the first page (ie, the playback page of song A), and the terminal will respond to the trigger operation and display other songs with the same new song identifier as the song A.
  • the second page is a new song recommendation page.
  • the new song recommendation page includes one or more new songs, each of which can be obtained by filtering new songs based on the release date of the song, and The song release date of each new song may adopt the manner of determining the song release date in the subsequent implementation manner.
  • the interaction scenario shown in FIG. 3 shows that by using the song recommendation method provided by the present disclosure, the user can select the new song identifier of song A on the playback page (first page) of song A, so that the terminal can switch to this A new song recommendation page (second page) corresponding to song A, wherein other songs with the same new song identification as song A will be included on the new song recommendation page.
  • the song release date of each song is determined based on the method of determining the release date of the song mentioned in the follow-up method, and then the release date of each song is determined. It is obtained by screening new songs (that is, selecting songs whose release date is closer to the current date from the music library).
  • FIG. 4 is a second interactive schematic diagram of a method for recommending songs according to an embodiment of the present disclosure.
  • the terminal is in a locked screen state, but the client of the music platform in the background is still running and provides users with play service.
  • the lock screen page will be used as the first page mentioned in this disclosure, on which the song A selected based on the song release date and the corresponding new song identification (determined with the song A and the corresponding new song identification described in scene 1) are displayed. in a similar manner).
  • the page After the user triggers the new song logo on the lock screen page (the first page), the page will jump from the lock screen page (the first page) of the terminal to the second page.
  • the second page in this scenario 2 may specifically be a new song recommendation page, and the new song recommendation page will include other songs with the same new song ID as song A.
  • the song A involved in the interactive scene shown in FIG. 4 and other songs in the new song recommendation page are based on the method of determining the release date of the song mentioned in the follow-up method. Determine the song release date of each song, It is obtained by screening new songs (that is, selecting songs whose release date is closer to the current date from the music library).
  • FIG. 5 is a third interactive schematic diagram of a method for recommending songs according to an embodiment of the present disclosure.
  • the terminal is in a running state in which the client of the music platform provides users with song-related information browsing.
  • the first page is represented as a new song recommendation page including song A: on this new song recommendation page, the user can browse the songs, singers and related information provided on the new song recommendation page by dragging the page.
  • the new song recommendation page includes one or more new songs, each of which can be obtained by filtering new songs based on the release date of the song, and the release date of each new song.
  • the method of determining the release date of the song in the subsequent implementation manners may be adopted.
  • the terminal will respond to the trigger operation performed by the user on the song A (target song) on the new song recommendation page (the first page), and at this time, the terminal will switch from the new song recommendation page (the first page) to the song A (the first page).
  • the playing of the song A may be performed synchronously.
  • the switching of the first page and the second page involved in the embodiments of the present disclosure includes but is not limited to the above three scenarios. According to actual user needs, there will be more switching trigger modes and content representations between the first page and the second page.
  • FIG. 6 is a schematic flowchart of a method for determining the release date of a song provided by an embodiment of the present disclosure.
  • the release date of each song can also be determined, as shown in FIG. 6 , including:
  • Step 201 obtain the release information and hearing information of the song to be identified
  • Step 202 compare and analyze the release information and hearing information of the song to be identified with the release information and hearing information of each song in the music library;
  • Step 203 Determine the song release date of the to-be-identified song according to the comparison and analysis result.
  • the release date of the song required in each scenario can be determined, and based on the determined release date of the song, more scenario requirements can be realized.
  • the song release date of each song stored in the server 2 may be determined based on the method shown in FIG. 6 , and then the generation of the first page is performed based on the determined release date of each song.
  • the first page may specifically be the first page shown in any of the above three scenarios, and may also be other pages.
  • the determination of the release date of a song is generally determined based on the release date of the album to which the song belongs.
  • the album release date of the album will be used as the release date of each song included in the album; for example, the album release date of an album is December 15, 2020, then the album release date
  • the song release date of song a, song b and song c in it are all identified as December 15, 2020.
  • the music platform marks and pushes songs whose release date is later than December 14, 2020 as new songs, the above-mentioned song a, song b, and song c are all recognized as new songs, and corresponding pushes will be made.
  • steps 201 to 203 record the method for determining the release date of the song provided by the present disclosure.
  • the method for recommending songs provided by the present disclosure will also use the song information of the song to be identified and the existing songs in the music library to perform "duplication checking" processing to determine whether the song is a reissued song. .
  • any song will be selected as the song to be identified, so that the recommendation device can identify the release date of the song.
  • the recommending device will first acquire song information of the song to be identified, and the song information may specifically include release information and hearing information.
  • the release information may specifically come from the release of the album or the album recording information uploaded by the copyright owner, and the International Standard Recording Code (ISRC for short) of the album.
  • the release information may include one or more of song title information, artist information, song summary information, and song identification information.
  • Hearing information can be expressed as the audio-visual feeling of the user when listening to the song, which is generally associated with the audio characteristics of the song and/or the voiceprint characteristics, and is accompanied by the arrangement of the song, the singer's own voice, The singing technique is different.
  • the recommendation device will use the release information and hearing information of the song to be identified to compare and analyze the release information and hearing information of each song in the existing music library, so as to determine the song release date of the song to be identified:
  • the album release date in the release information of the song to be identified is used as the song release date of the song to be identified.
  • the album release date of album A to which it belongs is December 15, 2020.
  • the album release date "December 15, 2020" of the song b can be directly used as the song release date of the song b, and recorded in the song b on the corresponding field in the song information (for example, recorded in the field of the song release date of the song information).
  • the album release date of album A to which it belongs is December 15, 2020.
  • the comparative analysis of release information and listening information shows that in the existing music library, there are Song a1 and candidate song a2 have the same release information and the same hearing information.
  • the album release date of the album A1 to which the candidate song a1 belongs is "December 1, 2010”
  • the album release date of the album A2 to which the candidate song a2 belongs is "December 1, 2015”. Since the release date of the album A1 is earlier, at this time, the "December 1, 2010" can be used as the real release date of the song a, and recorded on the corresponding field in the song information of the song a (such as recording on the song release date field of the song information).
  • album A may be the same or different, and no restrictions are imposed here.
  • the real song release date of the song can be determined, thereby facilitating subsequent identification and recommendation of new songs.
  • the processing method of distributed identification can be adopted:
  • step 202 may specifically include:
  • Step 2021 Based on the release information, similar songs are divided between the to-be-identified song and each song in the music library to obtain similar songs similar to the to-be-identified song.
  • Step 2022 Perform clustering processing on the to-be-identified song and each of the similar songs based on the hearing information to obtain candidate songs.
  • candidate songs include but are not limited to: songs with the same release information as the songs to be identified (for example, songs in which the same artist sings the same song in different concerts, the same artist sings the same song in partnership with different artists songs, etc.), and may also include songs that are the same as the release information of the song to be identified (eg, cover songs of the same song by different artists, etc.).
  • the music library includes song c1 (cover song), song c2 (concert version), and song c3 (the earliest released song).
  • the song c1, the song c2 and the song c3 will be candidate songs similar to the song c.
  • the recommending device will also perform clustering processing based on the listening sensation information on each candidate song to determine that the candidate song and the song to be identified belong to the exact same candidate song.
  • the auditory information can be expressed as the audiovisual experience of the user when listening to the song, which is generally associated with the audio characteristics of the song and/or the voiceprint characteristics, and is associated with the composition of the song.
  • the song, the singer's own voice, and the singing technique are different.
  • the to-be-identified song may be compared with the audio features and/or voiceprint features of the similar songs, so as to select the The audio feature, and/or the voiceprint feature is the same candidate song as the to-be-identified song.
  • the audio feature refers to the characteristics of the song in terms of frequency, amplitude and phase.
  • the processing device can obtain the characteristics of the song in frequency, amplitude and phase by analyzing the audio characteristics of the song, and then convert the songs with the same frequency, amplitude and phase. clustered out as candidate songs.
  • the voiceprint feature refers to the feature obtained after converting the acoustic signal of the song into an electrical signal. By performing signal conversion and feature analysis on the song, the sound wave spectrum of the speech information carried in the song can be analyzed, and then the aggregation of the song can be realized. Class identification to get candidate songs.
  • the above-mentioned audio features and voiceprint features may also be combined during clustering to implement cluster analysis of songs, and identify candidate songs that are the same as the songs to be identified from the candidate songs of the songs to be identified.
  • the identification method further includes: from the songs in the music library, marking songs whose release date is earlier than a preset date as new songs; the target song is from songs marked as new songs selected.
  • a preset date when generating a new song recommendation page, can be first determined as a screening condition, and then, by reading the field of the song release date in the song information of the song, the real release date of the song can be obtained, In turn, whether the song is a new song is marked and filtered based on the actual release date.
  • Several songs whose real song release date is later than the preset date are obtained after filtering, and these songs will constitute a new song recommendation page to be pushed to the user.
  • the method for recommending songs provided by the embodiments of the present disclosure firstly obtains song information of the songs to be identified; wherein the song information includes release information and hearing information of the songs to be identified; then, the songs of the songs to be identified are The information is compared and analyzed with the song information of each song in the music library; finally, the release date of the song to be identified is determined according to the result of the comparison and analysis.
  • This method can effectively identify the real song release date of the song, avoid the occurrence of identifying the "old song” in the newly released album as a "new song”, effectively improve the recognition accuracy of the new song, and facilitate the use of the user. .
  • FIG. 7 is a structural block diagram of an apparatus for recommending songs according to an embodiment of the present disclosure.
  • the device for recommending songs includes:
  • the display module 10 is used for displaying the first page, and the first page includes the target song selected according to the release date of the song;
  • the interaction module 20 is configured to respond to the selection operation on the target song on the first page, so that the display module switches the first page to the second page of the selected target song;
  • the song release date of the target song is determined according to the song release information and hearing information of the song.
  • the device for recommending songs further includes: a processing module 30;
  • the processing module 30 is used to obtain release information and hearing information of the song to be identified; compare and analyze the release information and hearing information of the song to be identified and the release information and hearing information of each song in the music library; According to the comparative analysis result, the song release date of the to-be-identified song is determined.
  • the processing module 30 is further configured to: if there is no candidate song in the music library that is identical to the song information of the song to be identified, then use the album release date in the release information of the song to be identified as the song to be identified. song release date.
  • the processing module 30 is also used for: if there is a candidate song with the same song information as the song information of the song to be identified in the music library, then from the album release date in the release information of each candidate song, select a distance from the current date. The album release date with the largest time interval is taken as the song release date of the to-be-identified song.
  • the processing module 30 is further configured to: based on the release information, perform similar song division on the to-be-identified song and each song in the music library to obtain similar songs similar to the to-be-identified song; According to the hearing information, the to-be-identified song and each of the similar songs are clustered to obtain candidate songs.
  • the to-be-identified song and each of the similar songs are clustered to obtain candidate songs, including:
  • the release information includes one or more of song title information, artist information, song summary information, and song identification information.
  • the processing module 30 is also used to: from each song in the music library, mark the song whose release date is earlier than the preset date as a new song; the target song is selected from the songs marked as the new song. out.
  • the device for recommending songs may firstly display a first page, where the first page includes a target song selected according to the release date of the song; then, in response to triggering the target song on the first page operation to switch the first page to the second page of the selected target song.
  • the song release date of the target song in this embodiment is determined according to the song release information and hearing information of the song, and in this way, the real song release date of the song can be effectively identified, so that the display on the first page can be done.
  • target songs were chosen based on their actual song release dates. Using this method can effectively improve the recognition accuracy of the new song, which is convenient for the user to use.
  • the electronic device provided in this embodiment can be used to implement the technical solutions of the foregoing method embodiments, and the implementation principles and technical effects thereof are similar, and details are not described herein again in this embodiment.
  • the electronic device 900 may be a terminal device or a media library.
  • the terminal equipment may include, but is not limited to, such as mobile phones, notebook computers, digital broadcast receivers, personal digital assistants (Personal Digital Assistant, referred to as PDA), tablet computers (Portable Android Device, referred to as PAD), portable multimedia players (Portable Media Player, PMP for short), mobile terminals such as in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, and the like.
  • PDA Personal Digital Assistant
  • PAD Portable Android Device
  • PMP Portable Multimedia Player
  • mobile terminals such as in-vehicle terminals (such as in-vehicle navigation terminals), etc.
  • fixed terminals such as digital TVs, desktop computers, and the like.
  • the electronic device shown in FIG. 8 is only an example, and should not impose any limitation on the function and scope of use of the embodiments of the present disclosure.
  • the electronic device 900 may include a processing device (such as a central processing unit, a graphics processor, etc.) 901, which may be stored in a read only memory (Read Only Memory, ROM for short) 902 according to a program or from a storage device 908 is a program loaded into a random access memory (Random Access Memory, RAM for short) 903 to execute various appropriate actions and processes.
  • a processing device such as a central processing unit, a graphics processor, etc.
  • ROM Read Only Memory
  • RAM Random Access Memory
  • various programs and data necessary for the operation of the electronic device 900 are also stored.
  • the processing device 901, the ROM 902, and the RAM 903 are connected to each other through a bus 904.
  • An input/output (I/O) interface 905 is also connected to bus 904 .
  • the following devices can be connected to the I/O interface 905: input devices 906 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, a Liquid Crystal Display (LCD for short) ), speaker, vibrator, etc. output device 907; storage device 908 including, eg, magnetic tape, hard disk, etc.; and communication device 909.
  • the communication means 909 may allow the electronic device 900 to communicate wirelessly or by wire with other devices to exchange data. While FIG. 8 shows electronic device 900 having various means, it should be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.
  • embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the method illustrated in the flowchart.
  • the computer program may be downloaded and installed from the network via the communication device 909, or from the storage device 908, or from the ROM 902.
  • the processing apparatus 901 the above-mentioned functions defined in the methods of the embodiments of the present disclosure are executed.
  • the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above two.
  • the computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above. More specific examples of computer readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable Programmable Read Only Memory (EPROM), flash memory, optical fiber, portable Compact Disc-Read Only Memory (CD-ROM), optical storage device, magnetic storage device, or any suitable of the above The combination.
  • a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave with computer-readable program code embodied thereon. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device .
  • Program code embodied on a computer readable medium may be transmitted using any suitable medium including, but not limited to, electrical wire, optical fiber cable, RF (radio frequency), etc., or any suitable combination of the foregoing.
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or may exist alone without being assembled into the electronic device.
  • the aforementioned computer-readable medium carries one or more programs, and when the aforementioned one or more programs are executed by the electronic device, causes the electronic device to execute the methods shown in the foregoing embodiments.
  • Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages, including object-oriented programming languages—such as Java, Smalltalk, C++, but also conventional Procedural programming language - such as the "C" language or similar programming language.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or media library.
  • the remote computer can be connected to the user's computer through any kind of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or, can be connected to an external A computer (eg using an internet service provider to connect via the internet).
  • LAN Local Area Network
  • WAN Wide Area Network
  • Embodiments of the present disclosure provide a computer program product, including computer instructions, which, when executed by a processor, implement the method for recommending songs as described in any preceding item, and the implementation principles and technical effects thereof are similar. It is not repeated here.
  • Embodiments of the present disclosure also provide a computer program, which, when executed by a processor, is used to implement the method for recommending songs as described in any preceding item.
  • each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more logical functions for implementing the specified functions executable instructions.
  • the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations can be implemented in dedicated hardware-based systems that perform the specified functions or operations , or can be implemented in a combination of dedicated hardware and computer instructions.
  • the units involved in the embodiments of the present disclosure may be implemented in a software manner, and may also be implemented in a hardware manner.
  • the name of the unit does not constitute a limitation of the unit itself under certain circumstances, for example, the first obtaining unit may also be described as "a unit that obtains at least two Internet Protocol addresses".
  • exemplary types of hardware logic components include: Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (Application Specific Standard Products) Standard Product, ASSP), system on chip (System On Chip, SOC), complex programmable logic device (Complex Programmable Logic Device, CPLD) and so on.
  • FPGAs Field Programmable Gate Arrays
  • ASICs Application Specific Integrated Circuits
  • ASSP Application Specific Standard Products
  • ASOC System On Chip
  • complex programmable logic device Complex Programmable Logic Device, CPLD
  • a method for recommending songs includes:
  • the first page is switched to the second page of the selected target song
  • the song release date of the target song is determined according to the song release information and hearing information of the song.
  • the method before the displaying the first page, the method further includes:
  • the song release date of the to-be-identified song is determined.
  • determining the song release date of the to-be-identified song according to the comparison result including:
  • the album release date in the release information of the song to be identified is used as the song release date of the song to be identified.
  • determining the song release date of the to-be-identified song according to the comparison result including:
  • the song information of the to-be-identified song is compared and analyzed with the song information of each song in the music library, including:
  • similar songs are divided between the to-be-identified song and each song in the music library to obtain similar songs similar to the to-be-identified song;
  • the songs to be identified and each of the similar songs are clustered to obtain candidate songs.
  • the to-be-identified song and each of the similar songs are clustered based on the hearing information to obtain candidate songs, including:
  • the release information includes one or more of song title information, artist information, song summary information, and song identification information.
  • it also includes:
  • the target song is selected from songs marked as new songs.
  • an apparatus for recommending songs includes:
  • a display module for displaying a first page, the first page including a target song selected according to the release date of the song
  • an interaction module configured to respond to the selection operation on the target song on the first page, so that the display module switches the first page to the second page of the selected target song
  • the song release date of the target song is determined according to the song release information and hearing information of the song.
  • it also includes: a processing module
  • the processing module is used to obtain the release information and hearing information of the song to be identified; compare and analyze the release information and hearing information of the song to be identified with the release information and hearing information of each song in the music library; Comparing the analysis results, determine the song release date of the to-be-identified song.
  • the processing module is also used to: if there is no candidate song identical to the song information of the song to be identified in the music library, then use the album release date in the release information of the song to be identified as the date of the release of the song to be identified. Song release date.
  • the processing module is also used for: if there is a candidate song with the same song information as the song information of the song to be identified in the music library, then from the album release date in the release information of each said candidate song, select a distance from the current date. The release date of the album with the largest time interval is taken as the release date of the song to be identified.
  • the processing module is further configured to: based on the release information, perform similar song division on the to-be-identified song and each song in the music library to obtain similar songs similar to the to-be-identified song; The sensory information is obtained, and the songs to be identified and each of the similar songs are clustered to obtain candidate songs.
  • the to-be-identified song and each of the similar songs are clustered to obtain candidate songs, including:
  • the release information includes one or more of song title information, artist information, song summary information, and song identification information.
  • the processing module is also used to: from each song in the music library, mark the song whose release date is earlier than the preset date as a new song; the target song is selected from the songs marked as a new song. of.
  • an electronic device includes: at least one processor and a memory;
  • the memory stores computer-executable instructions
  • the at least one processor executes the computer-executable instructions stored in the memory to cause the at least one processor to perform the method for recommending songs as described in any preceding item.
  • a computer-readable storage medium stores computer-executable instructions, and when a processor executes the computer-executable instructions, the The recommended method for the song described in the previous item.
  • a computer program product includes computer instructions, the computer instructions being executed by a processor of the method for recommending songs as described in any preceding item.
  • a computer program when the computer program is executed by a processor, is used to implement the method for recommending songs as described in any preceding item.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Library & Information Science (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

一种歌曲的推荐方法、装置、电子设备、存储介质、计算机程序产品及计算机程序,首先可显示第一页面,所述第一页面包括根据歌曲发行日期选出的目标歌曲;然后,响应对所述第一页面上的目标歌曲进行的触发操作,将所述第一页面切换至被选中的目标歌曲的第二页面。目标歌曲的歌曲发行日期是根据歌曲的歌曲发行信息和听感信息确定的,而通过这样的方式能够有效对于歌曲的真实歌曲发行日期进行识别,进而使得在第一页面所展示的目标歌曲是基于其真实歌曲发行日期而选出的。而利用该方式能有效提高对于新歌的识别准确率,便于用户使用。

Description

歌曲的推荐方法、装置、电子设备及存储介质
本申请要求于2021年1月28日提交的申请号为202110117713.6、名称为“歌曲的推荐方法、装置、电子设备及存储介质”的中国专利申请的优先权,此申请的内容通过引用并入本文。
技术领域
本公开实施例涉及计算机领域,尤其涉及一种歌曲的推荐方法、装置、电子设备、存储介质、计算机程序产品及计算机程序。
背景技术
随着网络的普及,每天都有很多新发行的歌曲涌入包括音乐应用程序(Application,APP)等在内的音乐平台。为了便于用户快速获取这些新歌,音乐平台会从曲库中选出新发行的歌曲,并生成新歌推荐列表或新歌推荐榜单,以供用户收听。
现有技术中,对于歌曲是否属于新歌是基于其发行日期来确定的,而歌曲的发行日期是根据其所属的专辑的发行日期来确定的。但是,这样的对于新歌的识别方式,会误将一些发行在新合辑中的“老歌”也识别为“新歌”,从而出现推送的新歌推荐榜单中存在“老歌”的情况,不利于用户使用。
发明内容
针对上述问题,本公开实施例提供了一种歌曲的推荐方法、装置、电子设备、存储介质、计算机程序产品及计算机程序。
第一方面,本公开提供了一种歌曲的推荐方法,包括:
显示第一页面,所述第一页面包括根据歌曲发行日期选出的目标歌曲;
响应对所述第一页面上的目标歌曲进行的触发操作,将所述第一页面切换至被选中的目标歌曲的第二页面;
其中,所述目标歌曲的歌曲发行日期是根据歌曲的歌曲发行信息和听感信息确定的。
第二方面,本公开提供了一种歌曲的推荐装置,包括:
显示模块,用于显示第一页面,所述第一页面包括根据歌曲发行日期选出的目标歌曲;
交互模块,用于响应对所述第一页面上的目标歌曲进行的触发操作,以使所述显示模块将所述第一页面切换至被选中的目标歌曲的第二页面;
其中,所述目标歌曲的歌曲发行日期是根据歌曲的歌曲发行信息和听感信息确定的。
第三方面,本公开提供了一种电子设备,其中,包括:
至少一个处理器;以及
存储器;
所述存储器存储计算机执行指令;
所述至少一个处理器执行所述存储器存储的计算机执行指令,使得所述至少一个处理器执行如第一方面所述歌曲的推荐方法。
第四方面,本公开还提供了一种计算机可读存储介质,其中,所述计算机可读存储介质中存储有计算机执行指令,当处理器执行所述计算机执行指令时,实现如第一方面所述歌曲的推荐方法。
第五方面,本公开提供了一种计算机程序产品,包括计算机指令,该计算机指令被处理器执行时实现第一方面所述歌曲的推荐方法。
第六方面,本公开还提供了一种计算机程序,所述计算机程序被处理器执行时,用于实现如第一方面所述歌曲的推荐方法。
本公开实施例提供的歌曲的推荐方法、装置、电子设备、存储介质、计算机程序产品及计算机程序,首先可显示第一页面,所述第一页面包括根据歌曲发行日期选出的目标歌曲;然后,响应对所述第一页面上的目标歌曲进行的触发操作,将所述第一页面切换至被选中的目标歌曲的第二页面。本实施例中的目标歌曲的歌曲发行日期是根据歌曲的歌曲发行信息和听感信息确定的,而通过这样的方式能够有效对于歌曲的真实歌曲发行日期进行识别,进而使得在第一页面所展示的目标歌曲是基于其真实歌曲发行日期而选出的。而利用该方式能有效提高对于新歌的识别准确率,便于用户使用。
附图说明
为了更清楚地说明本公开实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍,显而易见地,下面描述中的附图是本公开的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。
图1为本公开所基于的一种网络架构的示意图;
图2为本公开实施例提供的一种歌曲的推荐方法的流程示意图;
图3为本公开实施例提供的一种歌曲的推荐方法的第一交互示意图;
图4为本公开实施例提供的一种歌曲的推荐方法的第二交互示意图;
图5为本公开实施例提供的一种歌曲的推荐方法的第三交互示意图;
图6为本公开实施例提供的一种歌曲发行日期的确定方法的流程示意图;
图7为本公开实施例提供的歌曲的推荐装置的结构框图;
图8为本公开实施例提供的电子设备的硬件结构示意图。
具体实施方式
为使本公开实施例的目的、技术方案和优点更加清楚,下面将结合本公开实施例中的附图,对本公开实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例是本公开一部分实施例,而不是全部的实施例。基于本公开中的实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例,都属于本公开保护的范围。
随着网络的普及,每天都有很多新发行的歌曲涌入包括音乐APP等在内的音乐平台。为了便于用户快速获取这些新歌,音乐平台会从曲库中选出新发行的歌曲,并生成新歌推荐列表或新歌推荐榜单,以供用户收听。
现有技术中,对于歌曲是否属于新歌是基于其发行日期来确定的,而歌曲的发行日期是根据其所属的专辑的发行日期来确定的。但是,这样的对于新歌的识别方式,会误将一些发行在新合辑中的“老歌”也识别为“新歌”。
举例来说,在2000年,某歌手发行了专辑A,该专辑A中包括歌曲a;而在2020年,该歌手发行了收录了20年经典歌曲的专辑B,在该专辑B中,收录了发行于2000年的歌曲a。基于该举例所述的情况,基于现有的新歌发行日期的识别方法,音乐平台会将专辑B中的歌曲a认定为发行于2020年的新歌,并置入新歌推荐列表以进行推荐。
这样的新歌推荐的准确率不高,即被音乐平台确定为新歌的歌曲实际上是老歌,十分影响用户的视听体验。
针对这样的问题,根据本公开的实施例,可根据歌曲的歌曲发行信息和听感信息确定歌曲发行日期,即通过歌曲的发行信息和听感信息进行一系列判定处理以确定出歌曲的实际发行日期,而该歌曲的实际发行日期将用于对歌曲的播放和推荐。
特别的,基于本公开实施例提供的方式所实现的对新歌的推荐,不会出现将新发行专辑中的“老歌”识别为“新歌”的情况,便于用户使用。
参考图1,图1为本公开所基于的一种网络架构的示意图,该图1所示网络架构具体可包括终端1以及服务器2。
其中,终端1具体可为用户手机、台式电脑、智能家居设备、平板电脑等可用于播放歌曲的硬件设备,终端1上可安装有播放APP、收听客户端等歌曲的音乐平台;服务器2可为设置在云端的独立服务器或服务器集群,其可用于为终端1上的歌曲的音乐平台提供文件和数据支持,以及页面的显示服务和交互服务。
本公开提供的歌曲的推荐装置具体可承载于图1所示的服务器2中,其通过基于本公开提供的歌曲的推荐方法,对服务器2中所存储的歌曲基于歌曲发行日期进行推荐。
基于前述的网络架构,针对前述提及的现有技术中由于直接将歌曲所属专辑的专辑发行日期作为歌曲发行日期而导致的对于歌曲的推送,特别是对于新歌的推送不准确的问题。第一方面,参考图2,图2为本公开实施例提供的一种歌曲的推荐方法的流程示意图。本公开实施例提供的歌曲的推荐方法,包括:
步骤101、显示第一页面,所述第一页面包括根据歌曲发行日期选出的目标歌曲;其中,所述目标歌曲的歌曲发行日期是根据歌曲的歌曲发行信息和听感信息确定的;
步骤102、响应对所述第一页面上的目标歌曲进行的触发操作,将所述第一页面切换至被选中的目标歌曲的第二页面。
需要说明的是,本示例提供的推荐方法的执行主体为前述的歌曲的推荐装置,在本公开的一些实施例中,其具体指代的是音乐平台的客户端或展示端,其是安装或集成在终端上的,并可通过应用界面或控制显示界面的方式呈现给用户。用户可通过终端与歌曲的推荐装置进行交互,并对其进行控制以获取其提供的页面和歌曲。
在终端上,由于歌曲推荐装置具体可为音乐平台的客户端,其一般会向用户提供对于音乐的显示播放功能。也就是说,终端上可显示有大量的歌曲,用户可通过点击、滑动、按压等不同的触控方式对这些歌曲进行开始播放、播放暂停、切换等不同操作。
在本公开所基于的实施方式中,终端将显示第一页面,在该第一页面上将包括目标歌曲,而该目标歌曲是通过歌曲发行日期选出的。而与现有技术不同的是,本实施方式中,歌曲发行日期是根据歌曲的歌曲发行信息和听感信息确定的。
随后,终端将响应用户对第一页面上的目标歌曲进行的触发操作,将所述第一页面切换至被选中的目标歌曲的第二页面。其中的触发操作的触控控制可为点击、滑动、按压等,本实施方式对其不进行限制。
本实施例对前述的第一页面和第二页面的具体形态不进行限定,其页面所呈现的内容和页面功能可基于实际音乐平台的产品需求而定。
为了便于理解,下面将以目标歌曲为基于歌曲发行日期而选出的“新歌”为例,针对几种可能的页面切换类型进行简单描述:
场景一:
图3为本公开实施例提供的一种歌曲的推荐方法的第一交互示意图,如图3所示的,终端处于利用音乐平台的客户端播放歌曲的运行状态,此时,第一页面表现为歌曲A的播放页面:在播放页面上,用户可通过触发歌曲的播放暂停按钮,以对歌曲的播放和暂停播放进行控制。
此外,在该播放页面上,还包括有歌曲A属于新歌的新歌标识。特别的,对于歌曲A来说,其是通过从曲库中,对各歌曲的歌曲发行日期进行筛选而得到的,如基于歌曲发行日期进行新歌筛选(即从曲库中选出歌曲发行日期与当前日期较为接近的歌曲,以随机播放或采用顺序播放)。其中,如何确定该歌曲A的歌曲发行日期则可参见后续实施方式,在此处暂不进行描述。
而此时,用户可选中第一页面(即歌曲A的播放页面)上的新歌标识,终端将会响应该触发操作,并将与该歌曲A具有相同新歌标识的其他歌曲一并进行展示。如图3中所示的,第二页面表现为新歌推荐页,示例性的,新歌推荐页中包括一首或多首新歌,其每一新歌均可通过基于歌曲发行日期的新歌筛选得到,且每一新歌的歌曲发行日期均可采用后续实施方式中的歌曲发行日期的确定方式。
图3所示的交互场景展示出,利用本公开提供的歌曲的推荐方法,用户可通过对歌曲A的播放页面(第一页面)上的歌曲A的新歌标识进行选中,以使终端切换至该歌曲A相应的新歌推荐页(第二页面),其中,在该新歌推荐页上将包括有与歌曲A具有相同的新歌标识的其他歌曲。而在图3所示的交互场景中所涉及的歌曲A以及新歌推荐页中的其他歌曲,均是先基于后续方式中提及的歌曲发行日期的确定方式,确定各歌曲的歌曲发行日期,再进行新歌筛选而得到的(即从曲库中选出歌曲发行日期与当前日期较为接近的歌曲)。
场景二:
图4为本公开实施例提供的一种歌曲的推荐方法的第二交互示意图,如图4所示的,终端处于锁屏状态,但其后台的音乐平台的客户端还在运行并为用户提供播放服务。此时, 锁屏页面将作为本公开提及的第一页面,其上显示有基于歌曲发行日期选出的歌曲A以及相应的新歌标识(与场景一所述的歌曲A和相应的新歌标识确定方式类似)。
当用户触发该锁屏页面(第一页面)上的新歌标识之后,页面将从终端的锁屏页面(第一页面)跳转至第二页面。此时,与前述场景一类似的是,本场景二中的第二页面具体可为新歌推荐页,在该新歌推荐页上将包括有与歌曲A具有相同的新歌标识的其他歌曲。
同时,在图4所示的交互场景中所涉及的歌曲A以及新歌推荐页中的其他歌曲,均是先基于后续方式中提及的歌曲发行日期的确定方式,确定各歌曲的歌曲发行日期,再进行新歌筛选而得到的(即从曲库中选出歌曲发行日期与当前日期较为接近的歌曲)。
场景三:
图5为本公开实施例提供的一种歌曲的推荐方法的第三交互示意图,如图5所示的,终端处于利用音乐平台的客户端为用户提供歌曲相关信息浏览的运行状态,此时,第一页面表现为包括有歌曲A的新歌推荐页:在该新歌推荐页上,用户可通过拖动页面的方式,对新歌推荐页上提供的歌曲、歌手以及相关信息进行浏览。
当然,与之前场景一和场景二类似的是,新歌推荐页中包括一首或多首新歌,其每一新歌均可通过基于歌曲发行日期的新歌筛选得到的,且每一新歌的歌曲发行日期均可采用后续实施方式中的歌曲发行日期的确定方式。
随后,终端将响应用户在该新歌推荐页(第一页面)上对歌曲A(目标歌曲)所进行的触发操作,此时,终端会从新歌推荐页(第一页面)切换至该歌曲A(目标歌曲)的歌曲播放页(第二页面)。可选的,在该歌曲A被选中并切换至相应的歌曲播放页时,可同步执行对歌曲A的播放。
当然,需要说明的是,本公开实施例中所涉及的第一页面和第二页面的切换包括但不限于上述三种场景。根据实际的用户需求,第一页面和第二页面之间将有着更多的切换触发方式和内容表现形式。
在上述方式的基础上,下面将针对上述提及的歌曲发行日期的确定方式进行进一步说明:
与现有技术不同的是,在本实施方式中采用了不同的对于歌曲发行日期的确定方式,图6为本公开实施例提供的一种歌曲发行日期的确定方法的流程示意图。在图2所示的步骤101之前,还可先确定出各歌曲的歌曲发行日期,如图6所示的,包括:
步骤201、获取待识别歌曲的发行信息和听感信息;
步骤202、将所述待识别歌曲的发行信息和听感信息与曲库中各歌曲的发行信息和听感信息进行比对分析;
步骤203、根据比对分析结果,确定所述待识别歌曲的歌曲发行日期。
其中,如前述各场景所述的,通过图6提供的方法,可确定各场景中所需的歌曲发行日期,而基于确定的歌曲发行日期可实现更多场景需求。
示例的,可基于图6所示方法对服务器2中所存储的各歌曲的歌曲发行日期进行确定,然后基于确定的各歌曲的发行日期执行第一页面的生成。其中的第一页面具体可为上述三种场景中的任一场景所示的第一页面,也可为其他页面。
在现有技术中,对于音乐平台来说,对于歌曲发行日期的确定一般都是基于歌曲所归属的专辑发行日期而定的。当音乐平台收录有一张新发行的专辑时,会将该专辑的专辑发行日期作为专辑所收录的各歌曲的发行日期;如,某专辑的专辑发行日期为2020年12月15日,那么该专辑内的歌曲a、歌曲b以及歌曲c的歌曲发行日期均被认定为2020年12月15日。
此时,若音乐平台将发行日期晚于2020年12月14日的歌曲作为新歌进行标记和推送时,上述的歌曲a、歌曲b以及歌曲c均被识别为新歌,并进行相应的推送。
但是,正如之前背景技术所述的,在很多情况下,经典老歌会被重新收录并发行,如前述的歌曲a已经收录在2010年12月1日发行的专辑中,本次发行是对该歌曲a的再次发行。但是,由于歌曲a被收录到专辑发行日期为2020年12月15日的专辑中,其依旧将被当做新歌进行标记和推送,导致了用户接收到的新歌推送页面中,会包括歌曲a在内的老歌新发行的歌曲,使得用户收听体验较差。
而本公开提供的技术方案正是为了解决该问题,使得歌曲的真实歌曲发行日期可被识别,并被歌曲的音乐平台获取,使得生成新歌推荐列表中的歌曲均为真实新歌。其中,步骤201至步骤203记录了本公开提供的歌曲发行日期的确定方法。
与现有技术不同的是,本公开提供的歌曲的推荐方法中还将利用待识别歌曲的歌曲信息与曲库中已有歌曲进行“查重”处理,以判定该歌曲是否为重新发行的歌曲。
本公开实施例中,当音乐平台收录有某一新发行的专辑之后,会从中选取任一歌曲作为待识别歌曲,以使推荐装置对其进行歌曲发行日期的识别。
具体来说,推荐装置首先将会获取到待识别歌曲的歌曲信息,歌曲信息具体可包括有发行信息和听感信息。
其中的发行信息具体可来自于专辑的发行发或版权方上传的专辑收录信息、专辑的国际标准音像制品编码(International Standard Recording Code,简称ISRC)。其发行信息可包括有歌名信息、艺人信息、歌曲摘要信息、歌曲标识信息中的一种或多种。
听感信息则可表示为用户在听到歌曲时的视听感受,其一般与歌曲的音频特征,和/或,声纹特征相关联,并随着的歌曲的编曲、演唱者自身声线、演唱技法的不同而不同。
推荐装置将利用待识别歌曲的发行信息和听感信息与已有曲库中各歌曲的发行信息和听感信息进行比对分析,以确定所述待识别歌曲的歌曲发行日期:
若曲库中不存在与待识别歌曲的歌曲信息相同的候选歌曲,则将所述待识别歌曲的发行信息中的专辑发行日期作为所述待识别歌曲的歌曲发行日期。
举例来说,以歌曲b为例,其所属专辑A的专辑发行日期为2020年12月15日,经发行信息和听感信息的比对分析可知,在已有的曲库中,不存在与该歌曲b发行信息相同、听感信息相同的歌曲,此时,可直接将该歌曲b的专辑发行日期“2020年12月15日”作为该歌曲b的歌曲发行日期,并记录在该歌曲b的歌曲信息中的相应字段上(如记录在歌曲信息的歌曲发行日期这一字段上)。
若曲库中存在与待识别歌曲的歌曲信息相同的候选歌曲,则从各所述候选歌曲的发行信息中的专辑发行日期中,选出距离当前日期的时间间隔最大的专辑发行日期作为所述待识别歌曲的歌曲发行日期。
举例来说,以歌曲a为例,其所属专辑A的专辑发行日期为2020年12月15日,经发行信息和听感信息的比对分析可知,在已有的曲库中,存在与该歌曲a发行信息相同,听感信息相同的候选歌曲a1和候选歌曲a2。
此时,该候选歌曲a1所属专辑A1的专辑发行日期为“2010年12月1日”,该候选歌曲a2所属专辑A2的专辑发行日期为“2015年12月1日”。由于专辑A1的发行日期更早,此时,可将该“2010年12月1日”作为歌曲a的真实的歌曲发行日期,并记录在该歌曲a的歌曲信息中的相应字段上(如记录在歌曲信息的歌曲发行日期这一字段上)。
需要说明的是,上述的专辑A、专辑A1、以及专辑A2的发行商、版权方、发行方式、发行平台可相同,也可不同,在此不进行任何限制。
通过上述方式可实现对于歌曲真实的歌曲发行日期的确定,从而便于后续对于新歌的识别和推荐。
为了提高对于歌曲发行日期的识别效率和识别速度,在可选实施方式中,可采用分布识别的处理方式:
其中,步骤202具体可包括:
步骤2021、基于发行信息,对所述待识别歌曲和所述曲库中的各歌曲进行相似歌曲划分,得到与所述待识别歌曲相似的相似歌曲。
步骤2022、基于听感信息,对所述待识别歌曲和各所述相似歌曲进行聚类处理,得到候选歌曲。
具体来说,针对歌曲来说,通过对于其发行信息的分析,可将与待识别歌曲相似的歌曲筛选出来,以得到候选歌曲。其中,候选歌曲包括但不限于:与待识别歌曲的发行信息相同的歌曲(如,同一艺人在不同演唱会上对同一首歌曲进行演唱的歌曲,同一艺人与不同艺人进行搭档对同一歌曲进行演唱的歌曲等),也可包括与待识别歌曲的发行信息相同的歌曲(如,不同艺人对同一歌曲的翻唱歌曲等)。
例如,针对歌曲c来说,通过对于发行信息的分析,可识别出曲库中包括歌曲c1(翻唱歌曲),歌曲c2(演唱会版本),歌曲c3(最早发行的歌曲)。此时,该歌曲c1,歌曲c2以及歌曲c3将作为歌曲c相似的候选歌曲。
随后,推荐装置还将对各候选歌曲进行基于听感信息的聚类处理,以确定与待识别歌曲属于完全相同的候选歌曲。
具体的,如前所述的,听感信息则可表示为用户在听到歌曲时的视听感受,其一般与歌曲的音频特征,和/或,声纹特征相关联,并随着歌曲的编曲、演唱者自身声线、演唱技法的不同而不同。
在推荐装置进行聚类处理时,可将所述待识别歌曲和各所述相似歌曲的音频特征,和/或,声纹特征进行比对处理,以从各所述相似歌曲中选出所述音频特征,和/或,所述声纹特征与所述待识别歌曲相同的候选歌曲。
其中,音频特征是指歌曲在频率、振幅、相位上的特征,处理装置通过对歌曲进行音频特征分析,可获取到歌曲在频率、振幅、相位的特性,进而将频率、振幅、相位相同的歌曲聚类出来,以作为候选歌曲。
声纹特征是指将歌曲的声信号转换成电信号后所得到的特征,通过对歌曲进行信号转换和特征分析,能够对歌曲中所携带言语信息的声波频谱进行分析,进而实现对于歌曲的聚类识别,以得到候选歌曲。
或者,在聚类时还可结合上述的音频特征以及声纹特征,以实现对于歌曲的聚类分析,从待识别歌曲的候选歌曲中识别出与待识别歌曲相同的候选歌曲。
在本公开实施例提供的实施方式中,由于曲库中歌曲数量较大,直接利用听感信息进行候选歌曲的识别容易使得识别所需时间较长,识别成本较大;直接利用发行信息进行识别又容易出现识别准确率受限和误识别的情况发生。因此,在本实施方式中,通过先利用发行信息进行相似的候选歌曲的识别,再利用听感信息从候选歌曲中聚类得到与待识别歌曲相同的候选歌曲,从而在保证识别准确率的情况下提高了识别效率。
在可选实施例中,识别方法还包括:从所述曲库中各歌曲中,将歌曲发行日期早于预设日期的歌曲标注为新歌;所述目标歌曲是从被标注为新歌的歌曲中选出的。
参考前述场景图,在生成新歌推荐页时,可首先确定一预设日期,以作为筛选条件,然后,通过读取歌曲的歌曲信息中歌曲发行日期这一字段,以得到歌曲的真实发行日期,进而基于真实发行日期对歌曲是否为新歌进行标记和筛选。经筛选得到歌曲的真实歌曲发行日期晚于所述预设日期的若干歌曲,这些歌曲将构成新歌推荐页,以被推送至用户。
本公开实施例提供的歌曲的推荐方法,首先获取待识别歌曲的歌曲信息;其中所述歌曲信息中包括所述待识别歌曲的发行信息和听感信息;然后,将所述待识别歌曲的歌曲信息与曲库中各歌曲的歌曲信息进行比对分析;最后,根据比对分析结果,确定所述待识别歌曲的歌曲发行日期。通过这样的方式能够有效对于歌曲的真实歌曲发行日期进行识别,避免出现将新发行专辑中的“老歌”识别为“新歌”的情况发生,有效提高了对于新歌的识别准确率,便于用户使用。
对应于上文实施例的歌曲的推荐方法,图7为本公开实施例提供的歌曲的推荐装置的结构框图。为了便于说明,仅示出了与本公开实施例相关的部分。参照图7,所述歌曲的推荐装置包括:
显示模块10,用于显示第一页面,所述第一页面包括根据歌曲发行日期选出的目标歌曲;
交互模块20,用于响应对所述第一页面上的目标歌曲进行的选中操作,以使所述显示模块将所述第一页面切换至被选中的目标歌曲的第二页面;
其中,所述目标歌曲的歌曲发行日期是根据歌曲的歌曲发行信息和听感信息确定的。
可选的,所述歌曲的推荐装置还包括:处理模块30;
所述处理模块30用于获取待识别歌曲的发行信息和听感信息;将所述待识别歌曲的发行信息和听感信息与曲库中各歌曲的发行信息和听感信息进行比对分析;根据比对分析结果,确定所述待识别歌曲的歌曲发行日期。
可选的,处理模块30还用于:若曲库中不存在与待识别歌曲的歌曲信息相同的候选歌曲,则将所述待识别歌曲的发行信息中的专辑发行日期作为所述待识别歌曲的歌曲发行日期。
可选的,处理模块30还用于:若曲库中存在与待识别歌曲的歌曲信息相同的候选歌曲,则从各所述候选歌曲的发行信息中的专辑发行日期中,选出距离当前日期的时间间隔最大的专辑发行日期作为所述待识别歌曲的歌曲发行日期。
可选的,处理模块30还用于:基于发行信息,对所述待识别歌曲和所述曲库中的各歌曲进行相似歌曲划分,得到与所述待识别歌曲相似的相似歌曲;以及,基于听感信息,对所述待识别歌曲和各所述相似歌曲进行聚类处理,得到候选歌曲。
其中,所述基于听感信息,对所述待识别歌曲和各所述相似歌曲进行聚类处理,得到候选歌曲,包括:
将所述待识别歌曲和各所述相似歌曲的音频特征,和/或,声纹特征进行比对处理,以从各所述相似歌曲中选出所述音频特征,和/或,所述声纹特征与所述待识别歌曲相同的候选歌曲。
可选的,所述发行信息包括:歌名信息、艺人信息、歌曲摘要信息、歌曲标识信息中的一种或多种。
可选的,处理模块30还用于:从所述曲库中各歌曲中,将歌曲发行日期早于预设日期的歌曲标注为新歌;所述目标歌曲是从被标注为新歌的歌曲中选出的。
本公开实施例提供的歌曲的推荐装置,首先可显示第一页面,所述第一页面包括根据歌曲发行日期选出的目标歌曲;然后,响应对所述第一页面上的目标歌曲进行的触发操作,将所述第一页面切换至被选中的目标歌曲的第二页面。本实施例中的目标歌曲的歌曲发行日期是根据歌曲的歌曲发行信息和听感信息确定的,而通过这样的方式能够有效对于歌曲的真实歌曲发行日期进行识别,进而使得在第一页面所展示的目标歌曲是基于其真实歌曲发行日期而选出的。而利用该方式能有效提高对于新歌的识别准确率,便于用户使用。
本实施例提供的电子设备,可用于执行上述方法实施例的技术方案,其实现原理和技术效果类似,本实施例此处不再赘述。
参考图8,其示出了适于用来实现本公开实施例的电子设备900的结构示意图,该电子设备900可以为终端设备或媒体库。其中,终端设备可以包括但不限于诸如移动电话、笔记本电脑、数字广播接收器、个人数字助理(Personal Digital Assistant,简称PDA)、平 板电脑(Portable Android Device,简称PAD)、便携式多媒体播放器(Portable Media Player,简称PMP)、车载终端(例如车载导航终端)等等的移动终端以及诸如数字TV、台式计算机等等的固定终端。图8示出的电子设备仅仅是一个示例,不应对本公开实施例的功能和使用范围带来任何限制。
如图8所示,电子设备900可以包括处理装置(例如中央处理器、图形处理器等)901,其可以根据存储在只读存储器(Read Only Memory,简称ROM)902中的程序或者从存储装置908加载到随机访问存储器(Random Access Memory,简称RAM)903中的程序而执行各种适当的动作和处理。在RAM 903中,还存储有电子设备900操作所需的各种程序和数据。处理装置901、ROM 902以及RAM 903通过总线904彼此相连。输入/输出(I/O)接口905也连接至总线904。
通常,以下装置可以连接至I/O接口905:包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置906;包括例如液晶显示器(Liquid Crystal Display,简称LCD)、扬声器、振动器等的输出装置907;包括例如磁带、硬盘等的存储装置908;以及通信装置909。通信装置909可以允许电子设备900与其他设备进行无线或有线通信以交换数据。虽然图8示出了具有各种装置的电子设备900,但是应理解的是,并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。
特别地,根据本公开的实施例,上文参考流程图描述的过程可以被实现为计算机软件程序。例如,本公开的实施例包括一种计算机程序产品,其包括承载在计算机可读介质上的计算机程序,该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中,该计算机程序可以通过通信装置909从网络上被下载和安装,或者从存储装置908被安装,或者从ROM 902被安装。在该计算机程序被处理装置901执行时,执行本公开实施例的方法中限定的上述功能。
需要说明的是,本公开上述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的***、装置或器件,或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于:具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(Electrically Programmable Read Only Memory,EPROM)、闪存、光纤、便携式紧凑磁盘只读存储器(Compact Disc-Read Only Memory,CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中,计算机可读存储介质可以是任何 包含或存储程序的有形介质,该程序可以被指令执行***、装置或者器件使用或者与其结合使用。而在本公开中,计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号,其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式,包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质,该计算机可读信号介质可以发送、传播或者传输用于由指令执行***、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输,包括但不限于:电线、光缆、RF(射频)等等,或者上述的任意合适的组合。
上述计算机可读介质可以是上述电子设备中所包含的;也可以是单独存在,而未装配入该电子设备中。
上述计算机可读介质承载有一个或者多个程序,当上述一个或者多个程序被该电子设备执行时,使得该电子设备执行上述实施例所示的方法。
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的操作的计算机程序代码,上述程序设计语言包括面向对象的程序设计语言—诸如Java、Smalltalk、C++,还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或媒体库上执行。在涉及远程计算机的情形中,远程计算机可以通过任意种类的网络——包括局域网(Local Area Network,简称LAN)或广域网(Wide Area Network,简称WAN)—连接到用户计算机,或者,可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
本公开的实施例提供一种计算机程序产品,包括计算机指令,该计算机指令被处理器执行时,实现如前任一项所述的歌曲的推荐方法,其实现原理和技术效果类似,本实施例此处不再赘述。
本公开的实施例还提供一种计算机程序,所述计算机程序被处理器执行时,用于实现如前任一项所述的歌曲的推荐方法。
附图中的流程图和框图图示了按照本公开各种实施例的***、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上,流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分,该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意,在有些作为替换的实现中,方框中所 标注的功能也可以以不同于附图中所标注的顺序发生。例如,两个接连地表示的方框实际上可以基本并行地执行,它们有时也可以按相反的顺序执行,这依所涉及的功能而定。也要注意的是,框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合,可以用执行规定的功能或操作的专用的基于硬件的***来实现,或者可以用专用硬件与计算机指令的组合来实现。
本公开实施例中所涉及到的单元可以通过软件的方式实现,也可以通过硬件的方式来实现。其中,单元的名称在某种情况下并不构成对该单元本身的限定,例如,第一获取单元还可以被描述为“获取至少两个网际协议地址的单元”。
本文中以上描述的功能可以至少部分地由一个或多个硬件逻辑部件来执行。例如,非限制性地,可以使用的示范类型的硬件逻辑部件包括:现场可编程门阵列(Field Programmable Gate Array,FPGA)、专用集成电路(Application Specific Integrated Circuit,ASIC)、专用标准产品(Application Specific Standard Product,ASSP)、片上***(System On Chip,SOC)、复杂可编程逻辑设备(Complex Programmable Logic Device,CPLD)等等。
以下是本公开的一些实施例。
第一方面,根据本公开的一个或多个实施例,一种歌曲的推荐方法,包括:
显示第一页面,所述第一页面包括根据歌曲发行日期选出的目标歌曲;
响应对所述第一页面上的目标歌曲进行的选中操作,将所述第一页面切换至被选中的目标歌曲的第二页面;
其中,所述目标歌曲的歌曲发行日期是根据歌曲的歌曲发行信息和听感信息确定的。
可选实施例中,所述显示第一页面之前,还包括:
获取待识别歌曲的发行信息和听感信息;
将所述待识别歌曲的发行信息和听感信息与曲库中各歌曲的发行信息和听感信息进行比对分析;
根据比对分析结果,确定所述待识别歌曲的歌曲发行日期。
可选实施例中,所述根据比对结果,确定所述待识别歌曲的歌曲发行日期,包括:
若曲库中不存在与待识别歌曲的歌曲信息相同的候选歌曲,则将所述待识别歌曲的发行信息中的专辑发行日期作为所述待识别歌曲的歌曲发行日期。
可选实施例中,所述根据比对结果,确定所述待识别歌曲的歌曲发行日期,包括:
若曲库中存在与待识别歌曲的歌曲信息相同的候选歌曲,则从各所述候选歌曲的发行信息中的专辑发行日期中,选出距离当前日期的时间间隔最大的专辑发行日期作为所述待识别歌曲的歌曲发行日期。
可选实施例中,将所述待识别歌曲的歌曲信息与曲库中各歌曲的歌曲信息进行比对分析,包括:
基于发行信息,对所述待识别歌曲和所述曲库中的各歌曲进行相似歌曲划分,得到与所述待识别歌曲相似的相似歌曲;以及,
基于听感信息,对所述待识别歌曲和各所述相似歌曲进行聚类处理,得到候选歌曲。
可选实施例中,所述基于听感信息,对所述待识别歌曲和各所述相似歌曲进行聚类处理,得到候选歌曲,包括:
将所述待识别歌曲和各所述相似歌曲的音频特征,和/或,声纹特征进行比对处理,以从各所述相似歌曲中选出所述音频特征,和/或,所述声纹特征与所述待识别歌曲相同的候选歌曲。
可选实施例中,所述发行信息包括:歌名信息、艺人信息、歌曲摘要信息、歌曲标识信息中的一种或多种。
可选实施例中,还包括:
从所述曲库中各歌曲中,将歌曲发行日期早于预设日期的歌曲标注为新歌;
所述目标歌曲是从被标注为新歌的歌曲中选出的。
第二方面,根据本公开的一个或多个实施例,一种歌曲的推荐装置,包括:
显示模块,用于显示第一页面,所述第一页面包括根据歌曲发行日期选出的目标歌曲;
交互模块,用于响应对所述第一页面上的目标歌曲进行的选中操作,以使所述显示模块将所述第一页面切换至被选中的目标歌曲的第二页面;
其中,所述目标歌曲的歌曲发行日期是根据歌曲的歌曲发行信息和听感信息确定的。
可选的,还包括:处理模块;
所述处理模块用于获取待识别歌曲的发行信息和听感信息;将所述待识别歌曲的发行信息和听感信息与曲库中各歌曲的发行信息和听感信息进行比对分析;根据比对分析结果,确定所述待识别歌曲的歌曲发行日期。
可选的,处理模块还用于:若曲库中不存在与待识别歌曲的歌曲信息相同的候选歌曲,则将所述待识别歌曲的发行信息中的专辑发行日期作为所述待识别歌曲的歌曲发行日期。
可选的,处理模块还用于:若曲库中存在与待识别歌曲的歌曲信息相同的候选歌曲,则从各所述候选歌曲的发行信息中的专辑发行日期中,选出距离当前日期的时间间隔最大的专辑发行日期作为所述待识别歌曲的歌曲发行日期。
可选的,处理模块还用于:基于发行信息,对所述待识别歌曲和所述曲库中的各歌曲进行相似歌曲划分,得到与所述待识别歌曲相似的相似歌曲;以及,基于听感信息,对所述待识别歌曲和各所述相似歌曲进行聚类处理,得到候选歌曲。
其中,所述基于听感信息,对所述待识别歌曲和各所述相似歌曲进行聚类处理,得到候选歌曲,包括:
将所述待识别歌曲和各所述相似歌曲的音频特征,和/或,声纹特征进行比对处理,以从各所述相似歌曲中选出所述音频特征,和/或,所述声纹特征与所述待识别歌曲相同的候选歌曲。
可选的,所述发行信息包括:歌名信息、艺人信息、歌曲摘要信息、歌曲标识信息中的一种或多种。
可选的,处理模块还用于:从所述曲库中各歌曲中,将歌曲发行日期早于预设日期的歌曲标注为新歌;所述目标歌曲是从被标注为新歌的歌曲中选出的。
第三方面,根据本公开的一个或多个实施例,一种电子设备,包括:至少一个处理器和存储器;
所述存储器存储计算机执行指令;
所述至少一个处理器执行所述存储器存储的计算机执行指令,使得所述至少一个处理器执行如前任一项所述的歌曲的推荐方法。
第四方面,根据本公开的一个或多个实施例,一种计算机可读存储介质,所述计算机可读存储介质中存储有计算机执行指令,当处理器执行所述计算机执行指令时,实现如前任一项所述的歌曲的推荐方法。
第五方面,根据本公开的一个或多个实施例,一种计算机程序产品,包括计算机指令,该计算机指令被处理器执行如前任一项所述的歌曲的推荐方法。
第六方面,根据本公开的一个或多个实施例,一种计算机程序,当所述计算机程序被处理器执行时,用于实现如前任一项所述的歌曲的推荐方法。
以上描述仅为本公开的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解,本公开中所涉及的公开范围,并不限于上述技术特征的特定组合而成的技术方案, 同时也应涵盖在不脱离上述公开构思的情况下,由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本公开中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。
此外,虽然采用特定次序描绘了各操作,但是这不应当理解为要求这些操作以所示出的特定次序或以顺序次序执行来执行。在一定环境下,多任务和并行处理可能是有利的。同样地,虽然在上面论述中包含了若干具体实现细节,但是这些不应当被解释为对本公开的范围的限制。在单独的实施例的上下文中描述的某些特征还可以组合地实现在单个实施例中。相反地,在单个实施例的上下文中描述的各种特征也可以单独地或以任何合适的子组合的方式实现在多个实施例中。
尽管已经采用特定于结构特征和/或方法逻辑动作的语言描述了本主题,但是应当理解所附权利要求书中所限定的主题未必局限于上面描述的特定特征或动作。相反,上面所描述的特定特征和动作仅仅是实现权利要求书的示例形式。

Claims (20)

  1. 一种歌曲的推荐方法,其特征在于,包括:
    显示第一页面,所述第一页面包括根据歌曲发行日期选出的目标歌曲;
    响应对所述第一页面上的所述目标歌曲进行的触发操作,将所述第一页面切换至被选中的目标歌曲的第二页面;
    其中,所述目标歌曲的歌曲发行日期是根据歌曲的歌曲发行信息和听感信息确定的。
  2. 根据权利要求1所述的歌曲的推荐方法,其特征在于,所述显示第一页面之前,还包括:
    获取待识别歌曲的发行信息和听感信息;
    将所述待识别歌曲的发行信息和听感信息与曲库中各歌曲的发行信息和听感信息进行比对分析;
    根据比对分析结果,确定所述待识别歌曲的歌曲发行日期。
  3. 根据权利要求2所述的歌曲的推荐方法,其特征在于,所述根据比对分析结果,确定所述待识别歌曲的歌曲发行日期,包括:
    若所述曲库中不存在与所述待识别歌曲的歌曲信息相同的候选歌曲,则将所述待识别歌曲的发行信息中的专辑发行日期作为所述待识别歌曲的歌曲发行日期。
  4. 根据权利要求2所述的歌曲的推荐方法,其特征在于,所述根据比对分析结果,确定所述待识别歌曲的歌曲发行日期,包括:
    若所述曲库中存在与所述待识别歌曲的歌曲信息相同的候选歌曲,则从各所述候选歌曲的发行信息中的专辑发行日期中,选出距离当前日期的时间间隔最大的专辑发行日期作为所述待识别歌曲的歌曲发行日期。
  5. 根据权利要求2-4任一项所述的歌曲的推荐方法,其特征在于,所述将所述待识别歌曲的歌曲信息与曲库中各歌曲的歌曲信息进行比对分析,包括:
    基于所述待识别歌曲和所述曲库中的各歌曲的发行信息,对所述待识别歌曲和所述曲库中的各歌曲进行相似歌曲划分,得到与所述待识别歌曲相似的相似歌曲;以及,
    基于所述待识别歌曲和所述曲库中的各歌曲的听感信息,对所述待识别歌曲和各所述相似歌曲进行聚类处理,得到候选歌曲。
  6. 根据权利要求5所述的歌曲的推荐方法,其特征在于,所述基于所述待识别歌曲和所述曲库中的各歌曲的听感信息,对所述待识别歌曲和各所述相似歌曲进行聚类处理,得到候选歌曲,包括:
    将所述待识别歌曲和各所述相似歌曲的音频特征,和/或,声纹特征进行比对处理,以从各所述相似歌曲中选出音频特征,和/或,声纹特征与所述待识别歌曲相同的所述候选歌曲。
  7. 根据权利要求1-6任一项所述的歌曲的推荐方法,其特征在于,所述发行信息包括:歌名信息、艺人信息、歌曲摘要信息、歌曲标识信息中的一种或多种。
  8. 根据权利要求1-7任一项所述的歌曲的推荐方法,其特征在于,还包括:
    从所述曲库中各歌曲中,将歌曲发行日期早于预设日期的歌曲标注为新歌;
    所述目标歌曲是从被标注为新歌的歌曲中选出的。
  9. 一种歌曲的推荐装置,其特征在于,包括:
    显示模块,用于显示第一页面,所述第一页面包括根据歌曲发行日期选出的目标歌曲;
    交互模块,用于响应对所述第一页面上的目标歌曲进行的触发操作,以使所述显示模块将所述第一页面切换至被选中的目标歌曲的第二页面;
    其中,所述目标歌曲的歌曲发行日期是根据歌曲的歌曲发行信息和听感信息确定的。
  10. 根据权利要求9所述的歌曲的推荐装置,其特征在于,还包括:
    处理模块;所述处理模块用于:
    获取待识别歌曲的发行信息和听感信息;
    将所述待识别歌曲的发行信息和听感信息与曲库中各歌曲的发行信息和听感信息进行比对分析;根据比对分析结果,确定所述待识别歌曲的歌曲发行日期。
  11. 根据权利要求10所述的歌曲的推荐装置,其特征在于,所述处理模块还用于:
    若所述曲库中不存在与所述待识别歌曲的歌曲信息相同的候选歌曲,则将所述待识别歌曲的发行信息中的专辑发行日期作为所述待识别歌曲的歌曲发行日期。
  12. 根据权利要求10所述的歌曲的推荐装置,其特征在于,所述处理模块还用于:
    若所述曲库中存在与所述待识别歌曲的歌曲信息相同的候选歌曲,则从各所述候选歌曲的发行信息中的专辑发行日期中,选出距离当前日期的时间间隔最大的专辑发行日期作为所述待识别歌曲的歌曲发行日期。
  13. 根据权利要求10-12任一项所述的歌曲的推荐装置,其特征在于,所述处理模块还用于:
    基于所述待识别歌曲和所述曲库中的各歌曲的发行信息,对所述待识别歌曲和所述曲库中的各歌曲进行相似歌曲划分,得到与所述待识别歌曲相似的相似歌曲;以及,
    基于所述待识别歌曲和所述曲库中的各歌曲的听感信息,对所述待识别歌曲和各所述 相似歌曲进行聚类处理,得到候选歌曲。
  14. 根据权利要求13所述的歌曲的推荐装置,其特征在于,所述基于所述待识别歌曲和所述曲库中的各歌曲的听感信息,对所述待识别歌曲和各所述相似歌曲进行聚类处理,得到候选歌曲,包括:
    将所述待识别歌曲和各所述相似歌曲的音频特征,和/或,声纹特征进行比对处理,以从各所述相似歌曲中选出音频特征,和/或,声纹特征与所述待识别歌曲相同的所述候选歌曲。
  15. 根据权利要求9-14任一项所述的歌曲的推荐装置,其特征在于,所述发行信息包括:歌名信息、艺人信息、歌曲摘要信息、歌曲标识信息中的一种或多种。
  16. 根据权利要求9-15任一项所述的歌曲的推荐装置,其特征在于,所述处理模块还用于:从所述曲库中各歌曲中,将歌曲发行日期早于预设日期的歌曲标注为新歌;所述目标歌曲是从被标注为新歌的歌曲中选出的。
  17. 一种电子设备,其特征在于,包括:
    至少一个处理器;以及
    存储器;
    所述存储器存储计算机执行指令;
    所述至少一个处理器执行所述存储器存储的计算机执行指令,使得所述至少一个处理器执行如权利要求1-8任一项所述的歌曲的推荐方法。
  18. 一种计算机可读存储介质,其特征在于,所述计算机可读存储介质中存储有计算机执行指令,当处理器执行所述计算机执行指令时,实现如权利要求1-8任一项所述的歌曲的推荐方法。
  19. 一种计算机程序产品,包括计算机指令,其特征在于,所述计算机指令被处理器执行时实现权利要求1-8任一项所述的歌曲的推荐方法。
  20. 一种计算机程序,其特征在于,所述计算机程序被处理器执行时,实现如权利要求1-8任一项所述的歌曲的推荐方法。
PCT/CN2021/104110 2021-01-28 2021-07-01 歌曲的推荐方法、装置、电子设备及存储介质 WO2022160603A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/600,323 US20240054157A1 (en) 2021-01-28 2021-07-01 Song recommendation method and apparatus, electronic device, and storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110117713.6A CN112765396A (zh) 2021-01-28 2021-01-28 歌曲的推荐方法、装置、电子设备及存储介质
CN202110117713.6 2021-01-28

Publications (1)

Publication Number Publication Date
WO2022160603A1 true WO2022160603A1 (zh) 2022-08-04

Family

ID=75706406

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/104110 WO2022160603A1 (zh) 2021-01-28 2021-07-01 歌曲的推荐方法、装置、电子设备及存储介质

Country Status (3)

Country Link
US (1) US20240054157A1 (zh)
CN (1) CN112765396A (zh)
WO (1) WO2022160603A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112765396A (zh) * 2021-01-28 2021-05-07 北京字节跳动网络技术有限公司 歌曲的推荐方法、装置、电子设备及存储介质
CN113569086B (zh) * 2021-08-05 2024-01-26 深圳墨世科技有限公司 曲库聚合方法、装置、终端设备和可读存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102902759A (zh) * 2012-09-24 2013-01-30 北京宜搜天下科技有限公司 一种歌曲处理方法及***
CN108428441A (zh) * 2018-02-09 2018-08-21 咪咕音乐有限公司 多媒体文件生成方法、电子设备和存储介质
US20180349493A1 (en) * 2016-09-27 2018-12-06 Tencent Technology (Shenzhen) Company Limited Dual sound source audio data processing method and apparatus
CN109376265A (zh) * 2018-12-12 2019-02-22 杭州网易云音乐科技有限公司 歌曲推荐列表生成方法、介质、装置和计算设备
CN112765396A (zh) * 2021-01-28 2021-05-07 北京字节跳动网络技术有限公司 歌曲的推荐方法、装置、电子设备及存储介质

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7783623B2 (en) * 2007-08-31 2010-08-24 Yahoo! Inc. System and method for recommending songs
JP2012226617A (ja) * 2011-04-20 2012-11-15 Sony Corp 情報処理装置、情報処理方法、及び、プログラム
CN102402625A (zh) * 2011-12-28 2012-04-04 深圳市五巨科技有限公司 一种音乐推荐的方法及***
US9098508B2 (en) * 2012-11-21 2015-08-04 Electronic Arts Inc. Aggregating identifiers for media items
US20170193100A1 (en) * 2016-01-06 2017-07-06 Marcus Bowery Music distribution system
CN108334623B (zh) * 2018-02-09 2021-02-12 广州酷狗计算机科技有限公司 歌曲的显示方法、装置和***
CN109857900B (zh) * 2019-02-14 2024-02-09 腾讯音乐娱乐科技(深圳)有限公司 一种相似歌曲推荐方法以及相关设备
CN111858974B (zh) * 2020-07-17 2022-03-15 北京字节跳动网络技术有限公司 信息推送方法、装置、电子设备及存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102902759A (zh) * 2012-09-24 2013-01-30 北京宜搜天下科技有限公司 一种歌曲处理方法及***
US20180349493A1 (en) * 2016-09-27 2018-12-06 Tencent Technology (Shenzhen) Company Limited Dual sound source audio data processing method and apparatus
CN108428441A (zh) * 2018-02-09 2018-08-21 咪咕音乐有限公司 多媒体文件生成方法、电子设备和存储介质
CN109376265A (zh) * 2018-12-12 2019-02-22 杭州网易云音乐科技有限公司 歌曲推荐列表生成方法、介质、装置和计算设备
CN112765396A (zh) * 2021-01-28 2021-05-07 北京字节跳动网络技术有限公司 歌曲的推荐方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
US20240054157A1 (en) 2024-02-15
CN112765396A (zh) 2021-05-07

Similar Documents

Publication Publication Date Title
WO2020113733A1 (zh) 动画生成方法、装置、电子设备及计算机可读存储介质
CN109543064B (zh) 歌词显示处理方法、装置、电子设备及计算机存储介质
WO2021093737A1 (zh) 生成视频的方法、装置、电子设备和计算机可读介质
WO2022095475A1 (zh) 音频播放方法、装置、电子设备及存储介质
CN108900768A (zh) 视频拍摄方法、装置、终端、服务器和存储介质
US20050147256A1 (en) Automated presentation of entertainment content in response to received ambient audio
WO2022160603A1 (zh) 歌曲的推荐方法、装置、电子设备及存储介质
US20230307004A1 (en) Audio data processing method and apparatus, and device and storage medium
WO2016112841A1 (zh) 一种信息处理方法及客户端、计算机存储介质
US20210304776A1 (en) Method and apparatus for filtering out background audio signal and storage medium
US20240007718A1 (en) Multimedia browsing method and apparatus, device and mediuim
US11272136B2 (en) Method and device for processing multimedia information, electronic equipment and computer-readable storage medium
CN110223677A (zh) 空间音频信号滤波
WO2023051293A1 (zh) 一种音频处理方法、装置、电子设备和存储介质
CN105808780A (zh) 歌曲识别方法及设备
WO2022100582A1 (zh) 搜索内容的匹配方法, 装置, 电子设备及存储介质
CN112380362B (zh) 基于用户交互的音乐播放方法、装置、设备及存储介质
WO2022048323A1 (zh) 信息处理方法及设备
US20240103802A1 (en) Method, apparatus, device and medium for multimedia processing
CN113923390A (zh) 视频录制方法、装置、设备及存储介质
WO2024001548A1 (zh) 歌单生成方法、装置、电子设备及存储介质
JP2024507734A (ja) 音声類似度決定方法及び装置、プログラム製品
CN105373585B (zh) 歌曲收藏方法和装置
KR101551968B1 (ko) 차량에 적용된 미디어를 통한 음원 정보 제공 방법
CN109495786B (zh) 视频处理参数信息的预配置方法、装置及电子设备

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 17600323

Country of ref document: US

REG Reference to national code

Ref country code: BR

Ref legal event code: B01A

Ref document number: 112021019598

Country of ref document: BR

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21922200

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 112021019598

Country of ref document: BR

Kind code of ref document: A2

Effective date: 20210929

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 08.11.2023)

122 Ep: pct application non-entry in european phase

Ref document number: 21922200

Country of ref document: EP

Kind code of ref document: A1