WO2024001545A1 - 歌单展示信息生成方法、装置、电子设备及存储介质 - Google Patents

歌单展示信息生成方法、装置、电子设备及存储介质 Download PDF

Info

Publication number
WO2024001545A1
WO2024001545A1 PCT/CN2023/093667 CN2023093667W WO2024001545A1 WO 2024001545 A1 WO2024001545 A1 WO 2024001545A1 CN 2023093667 W CN2023093667 W CN 2023093667W WO 2024001545 A1 WO2024001545 A1 WO 2024001545A1
Authority
WO
WIPO (PCT)
Prior art keywords
song
target
playlist
title
unit data
Prior art date
Application number
PCT/CN2023/093667
Other languages
English (en)
French (fr)
Inventor
林晓慧
戴俊宇
张露曦
邓乐来
郭冠军
贺杰
陶传贵
宋旭晨
刘子恒
Original Assignee
北京字跳网络技术有限公司
脸萌有限公司
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 北京字跳网络技术有限公司, 脸萌有限公司 filed Critical 北京字跳网络技术有限公司
Publication of WO2024001545A1 publication Critical patent/WO2024001545A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
    • G06F16/63—Querying
    • G06F16/638—Presentation of query results
    • G06F16/639—Presentation of query results using playlists
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
    • G06F16/63—Querying
    • G06F16/635—Filtering based on additional data, e.g. user or group profiles

Definitions

  • Embodiments of the present disclosure relate to the field of Internet technology, and in particular, to a method, device, electronic device, computer-readable storage medium, computer program product, and computer program for generating playlist display information.
  • APPs music applications
  • music platforms recommend songs to users includes not only recommendations for single songs, but also recommendations for collections of multiple songs, that is, playlist recommendations.
  • playlist recommendations it is also necessary to generate display information such as covers and titles that match the playlist to display the playlist, thereby attracting users to consume the playlist.
  • the display information generated for the playlist in the prior art has the problem of low matching with the playlist content and the inability to accurately display the characteristics of the playlist content.
  • Embodiments of the present disclosure provide a method, device, electronic device, computer-readable storage medium, computer program product, and computer program for generating playlist display information.
  • embodiments of the present disclosure provide a method for generating playlist display information, including:
  • Obtain a target playlist which includes at least one song to be played; generate display information corresponding to the target playlist, wherein the display information is generated based on song unit data of the target playlist,
  • the song unit data represents the multi-dimensional characteristics of the at least one song to be played, and the display information includes the song list title and/or song list cover corresponding to the target song list.
  • embodiments of the present disclosure provide a method of generating playlist display information, including:
  • An acquisition module is used to acquire a target song list, which includes at least one song to be played;
  • Generating module configured to generate display information corresponding to the target playlist, wherein the display information is generated based on the song unit data of the target playlist, and the song unit data represents the at least one song to be played.
  • the display information includes the song list title and/or the song list cover corresponding to the target song list.
  • an electronic device including:
  • a processor and a memory communicatively connected to the processor
  • the memory stores computer execution instructions
  • the processor executes the computer execution instructions stored in the memory to implement the method for generating playlist display information as described in the first aspect and various possible designs of the first aspect.
  • embodiments of the present disclosure provide a computer-readable storage medium.
  • Computer-executable instructions are stored in the computer-readable storage medium.
  • the processor executes the computer-executable instructions, the above first aspect and the first aspect are implemented.
  • embodiments of the present disclosure provide a computer program product, including a computer program that, when executed by a processor, implements the generation of playlist display information as described in the first aspect and various possible designs of the first aspect. method.
  • embodiments of the present disclosure provide a computer program that, when executed by a processor, implements the method for generating playlist display information as described in the first aspect and various possible designs of the first aspect.
  • Figure 1 is an application scenario diagram of the method for generating playlist display information provided by an embodiment of the present disclosure.
  • Figure 2 is another application scenario diagram of the method for generating playlist display information provided by an embodiment of the present disclosure.
  • Figure 3 is a schematic flowchart 1 of a method for generating playlist display information provided by an embodiment of the present disclosure.
  • FIG. 4 is a flow chart of specific implementation steps of step S102 in the embodiment shown in FIG. 3 .
  • FIG. 5 is a flow chart of specific implementation steps of step S1021 in step S102.
  • Figure 6 is a schematic diagram of a data structure expressing song features corresponding to a target song list provided by an embodiment of the present disclosure.
  • Figure 7 is a schematic diagram of a process of generating a song list cover provided by an embodiment of the present disclosure.
  • Figure 8 is a schematic flowchart 2 of a method for generating playlist display information provided by an embodiment of the present disclosure.
  • FIG. 9 is a flow chart of specific implementation steps of step S202 in the embodiment shown in FIG. 8 .
  • FIG. 10 is a flow chart of specific implementation steps of step S205 in the embodiment shown in FIG. 8 .
  • Figure 11 is a schematic diagram of a song list cover provided by an embodiment of the present disclosure.
  • Figure 12 is a structural block diagram of a device for generating playlist display information provided by an embodiment of the present disclosure.
  • FIG. 13 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure.
  • Figure 14 is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present disclosure.
  • FIG. 1 is an application scenario diagram of the method for generating playlist display information provided by an embodiment of the present disclosure. Specifically, as shown in Figure 1 It is shown that the method provided by the embodiment of the present disclosure can be applied to a server, such as a music platform server, and the server communicates with a terminal device, where the terminal device is a device operated by a user and used to run music APPs, such as a smart phone or a tablet computer. wait.
  • a server such as a music platform server
  • the server communicates with a terminal device, where the terminal device is a device operated by a user and used to run music APPs, such as a smart phone or a tablet computer. wait.
  • the server uses the playlist display information generation method provided by the embodiment of the present disclosure to generate display information corresponding to the recommended playlist, such as the playlist title and playlist cover corresponding to the recommended playlist.
  • the server will recommend the playlists (shown as playlist 1, playlist 2, and playlist 3 in the picture) and the corresponding playlist titles (shown as title 1, title 2, and title 3 in the picture), and the song list cover (shown in the picture) Cover 1, Cover 2, and Cover 3 are shown in the figure), and the recommended content as a whole (Recommended content 1, Recommended content 2, and Recommended content 3 are shown in the figure) are sent to the terminal device and displayed on the side of the terminal device to complete the song. Single recommendation process. Afterwards, the terminal device responds to the user's instructions, consumes the recommended playlist based on display information such as the playlist title, playlist cover, etc., and completes the playback of the songs in the recommended playlist.
  • FIG 2 is another application scenario diagram of the method for generating playlist display information provided by an embodiment of the present disclosure.
  • the method provided by an embodiment of the present disclosure It can be applied to terminal devices, such as smartphones, tablets, etc.
  • the terminal device communicates with the server (server) through the running music APP (client), and receives the recommended playlist sent by the server (the playlist is shown in the figure 1. Playlist 2, Playlist 3).
  • the terminal device After that, the terminal device generates display information corresponding to the recommended playlist on the side of the terminal device based on the method for generating playlist display information provided by the embodiment of the present disclosure, for example, corresponding to the recommended playlist.
  • the song list titles (shown as title 1, title 2, and title 3 in the picture) and song list covers (shown as cover 1, cover 2, and cover 3 in the picture) are displayed on the side of the terminal device to complete the process of song list recommendation. Afterwards, the terminal device responds to the user's instructions, consumes the recommended playlist based on display information such as the playlist title, playlist cover, etc., and completes the playback of the songs in the recommended playlist.
  • playlist display information is usually generated by generating corresponding text and pictures based on manually set playlist tags of recommended playlists after generating recommended playlists, thereby obtaining automatically generated playlist titles and playlist covers. .
  • the recommended playlist does not have a manually set playlist tag
  • the corresponding text and picture will be generated based on a certain dimension of the playlist, such as "language” and "singer”, thereby obtaining the playlist title and playlist. cover.
  • the recommended playlist is generated based on multiple dimensional features of songs, generating the corresponding playlist display information based on a single dimensional feature will result in a low matching degree between the generated display information and the content of the playlist. The problem of accurately displaying the characteristics of the playlist content.
  • Embodiments of the present disclosure provide a method for generating playlist display information to solve the above problems.
  • FIG 3 is a schematic flowchart 1 of a method for generating playlist display information provided by an embodiment of the present disclosure.
  • the method of this embodiment can be applied in a server or a terminal device.
  • the method embodiment is mainly introduced with the server as the execution subject.
  • the method for generating playlist display information includes:
  • Step S101 Obtain a target song list, which includes at least one song to be played.
  • the target playlist is a collection of songs generated by the server based on preset rules and a preset music library.
  • the songs included in the target playlist that is, the songs to be played, are based on the specific results of generating the target playlist.
  • the target playlist The songs to be played in can be one or more.
  • the target playlist is determined based on the multi-dimensional characteristics of the songs in the music library, for example, based on the song's "release year”, “language”, “genre”, “song subject”, etc. There are no specific restrictions on the specific generation method of the target playlist here.
  • the target playlist can be generated by the server based on a preset algorithm before acquiring the target playlist, or it can be obtained by communicating with other servers; similarly, when the execution subject of the method in this embodiment is When using a terminal device, the target playlist may be obtained by communicating with other servers.
  • Step S102 Generate display information corresponding to the target playlist, where the display information is generated based on the song unit data of the target playlist.
  • the song unit data represents the multi-dimensional characteristics of at least one song to be played, and the display information includes the corresponding target playlist.
  • display information matching the target song list can be generated based on the characteristics of the target song list, such as the song list title and song list cover of the target song list.
  • the above object can be achieved through the song unit data (metadata) of the target playlist, where the target playlist includes multiple songs to be played, and the song unit data represents the multi-dimensional characteristics of the songs to be played.
  • the display information includes the playlist title and playlist cover corresponding to the target playlist.
  • the playlist cover is generated based on the playlist title, as shown in Figure 4.
  • the specific implementation steps of step S102 include:
  • Step S1021 Obtain the song unit data of the target song list.
  • the server obtains the song unit data corresponding to the target song list at the same time or after obtaining the target song list.
  • the song unit data represents the multi-dimensional characteristics of at least one song to be played. More specifically, in one implementation, the song unit data includes the multi-dimensional characteristics of each song to be played. In another implementation, the song unit data includes The average value of the multi-dimensional features of each song to be played. Furthermore, the multi-dimensional characteristics of the songs to be played represent a collection of characteristics of the songs to be played in multiple dimensions, such as "release year”, “language”, “genre”, “song body” and other dimensions. gather.
  • the song unit data of the target song list can be obtained in the following two specific ways, including:
  • the server can directly read the song unit data, where the valid song unit data is Refers to song unit data that can express the main characteristics of each song to be played in the target song list.
  • the effective song unit data refers to the multi-dimensional song features represented by it.
  • the corresponding feature value corresponds to a certain proportion (for example, 70%) of the songs to be played in the target song list (for example, 70%). under this song feature) have the same feature values.
  • the target playlist information may be sent by other servers, or generated by this server in the previous step of generating the target playlist, and is not specifically limited this time.
  • the server can generate the song unit data of the target playlist through calculation.
  • the specific implementation steps include :
  • Step S1021A Obtain the song feature expression of each song to be played in the target song list, and the song feature expression represents the multi-dimensional characteristics of the song to be played.
  • Step S1021B Generate song unit data of the target song list based on the song feature expression of at least one song to be played.
  • each song to be played has a corresponding song feature expression (embedding), and the song feature expression represents the multi-dimensional characteristics of the song to be played.
  • Figure 6 is a schematic data structure diagram of song feature expression corresponding to a target playlist provided by an embodiment of the present disclosure.
  • the target playlist includes songs to be played m1, m2, m3...cN, which respectively correspond to songs.
  • Feature expressions c01, c02, c03 (the figure only shows the specific implementation of the song feature expression c1 corresponding to m1, others are similar).
  • the song feature expression c1 of the song m1 to be played includes 3-dimensional features, which are song features A, Song feature B, song feature C.
  • song feature A represents the "song genre” of the song
  • song feature B represents the “release year” of the song
  • song feature C represents the "singing language” of the song.
  • the feature value of song feature A is #01, which means (the song style is) "rock”
  • the feature value of song feature B is #03, which means (the release year is) "90s”
  • the feature value of song feature C is #05, which means (the singing language is) "French”.
  • the song unit data of the target playlist can be obtained by using the characteristic values of the corresponding dimensional features in the multi-dimensional features of the songs to be played.
  • the specific implementation of step S1021B includes: performing a weighted average based on the song feature expressions of at least two songs to be played to obtain a weighted average feature value; and generating a target song list based on the weighted average feature.
  • the feature dimensions included in the song unit data cover the feature dimensions included in the song feature expression, that is, the song unit data can include the feature dimensions: song feature A, song feature B, song feature C, It also includes feature dimensions: playlist feature F, for example, representing the number of songs in the playlist. In this way, a more accurate feature representation of the target playlist can be achieved.
  • the song unit data of the target song list can express the overall characteristics of each song to be played in each dimension, and the feature performance is more Balance to improve the accuracy and stability of song unit data.
  • the songs to be played include seed songs.
  • the specific implementation of step S1021B includes: obtaining the seed songs, and generating song unit data according to the song feature expression of the seed songs, where the seed songs are determined based on user instructions.
  • the seed songs are the songs used to generate the target playlist.
  • songs most similar to the multi-dimensional features of the seed song are selected from the music library as candidate songs, and then based on the candidate songs and a collection of seed songs to generate a target song list.
  • the target song list is generated based on the seed songs. Therefore, the song feature expression of the seed songs is the most representative (closest to the song unit data).
  • the song unit data of the target song list is generated through seed songs. While ensuring the accuracy of the song unit data, the calculation process of the song unit data is simplified, the calculation amount is reduced, and the song unit data is improved. generation speed.
  • Step S1022 Generate a song list title based on the song unit data.
  • the specific steps of generating a song list title include: obtaining a pre-selected set of titles, which includes at least one candidate title; calculating the matching degree between the title feature expression of each candidate title and the song unit data, where the title feature expression represents Multi-dimensional characteristics of the candidate titles; based on the matching degree of each candidate title, the target title is determined, and the playlist title is generated based on the target title.
  • the title pre-selection set is generated based on Natural Language Processing (NLP) technology and contains multiple sets of candidate titles used to express the multi-dimensional characteristics of different songs.
  • NLP Natural Language Processing
  • the title features of each candidate title express the multi-dimensional features of the representation, and the feature distance between the multi-dimensional graph features corresponding to the song unit data is calculated, thereby determining the matching degree between the candidate title and the song unit data, and then maximizing the matching degree.
  • the candidate title is determined as the target title, so that the target title is used as the playlist title, and the step of generating the playlist title is completed.
  • the title feature expression and the song unit data include the same target dimensional features, and the target dimensional features include, for example, "release year”, “language”, “genre”, and “song subject”; calculate the title feature expression and the song unit data
  • the steps of matching degree include: based on the target dimension feature, obtain the first feature value of the candidate title under the target dimension feature, and the second feature value of the target playlist under the target dimension feature; based on the first feature value and the second feature
  • the weighted distance of the value is used to obtain the matching degree between the title feature expression of the candidate title and the song unit data.
  • the target title that best matches the song unit data is determined, thereby obtaining the song list title, so that the song list title
  • the features are closest to the features of the target playlist in multiple dimensions, thereby improving the consistency of the playlist title and the content of the target playlist, and improving the accuracy of the playlist title.
  • Step S1023 Generate a song list cover based on the song list title.
  • Figure 7 is a schematic diagram of a process for generating a song list cover provided by an embodiment of the present disclosure.
  • feature extraction is first performed based on the song unit data and natural language processing technology is used.
  • the title of the song list is text used to describe the content characteristics and genre characteristics of the songs in the target song list, such as "French movie music" and "My dance party”.
  • the song list cover is generated based on the text information corresponding to the generated song list title. Specifically, for example, using a preset image generation algorithm, based on the text information corresponding to the song list title and the description of the target song list.
  • Information such as the characteristics of at least one dimension in the song unit data, determine the elements, main colors, composition, and other image features in the image, and render them to generate a text that can express the content contained in the text information corresponding to the song list title. Meaningful images, namely playlist covers.
  • Meaningful images, namely playlist covers it should be noted that in the step of this embodiment, because the target song list contained in the song list title has fewer features (the features have undergone dimensionality reduction in the process of generating the song list title), therefore, in the above-mentioned step based on the song list title, In the process of generating a playlist cover based on the corresponding text information, combined with the description information of the target playlist, the accuracy of the generated playlist cover can be further improved.
  • the characteristics of text information and image information are used to first generate text information that is easier, less difficult, and more accurate in information description based on the song unit data, and then obtain the song list title, and then construct the complexity based on the text information.
  • Higher image information can be used to obtain the song list cover, thereby improving the accuracy of the generated song list title and song list cover, so that the song list title and song list cover can better express the characteristics of the target song list content.
  • step S102 it also includes:
  • the server sends the display information corresponding to the target playlist to the terminal device, so that the terminal device displays the display information, that is, the playlist cover and/or the playlist title. Afterwards, the terminal device will play or display the songs to be played in the corresponding target song list based on the trigger instruction for the display information.
  • the terminal device after generating the display information corresponding to the target playlist, the terminal device displays the display information, that is, the playlist cover and/or the playlist title, and then the terminal device will display the playlist based on In response to the triggering instruction of the display information, the songs to be played in the corresponding target song list are played or displayed.
  • the target song list which includes at least one song to be played
  • display information corresponding to the target song list is generated, where the display information is generated based on the song unit data of the target song list.
  • the unit data represents the multi-dimensional characteristics of at least one song to be played
  • the display information includes the song list title and/or song list cover corresponding to the target song list.
  • FIG. 8 is a schematic flowchart 2 of a method for generating playlist display information provided by an embodiment of the present disclosure. Based on the embodiment shown in Figure 3, this embodiment provides another implementation step of step S102, and adds a step of checking the song unit data.
  • the method for generating song list display information includes:
  • Step S201 Obtain a target song list, which includes at least one song to be played.
  • Step S202 Detect valid song unit data of the target song list.
  • the target song list can be generated in the previous step, or obtained by receiving data sent by other servers.
  • the target song list can be valid song unit data, or invalid song list. Unit data, or unit data does not exist.
  • corresponding processing methods are performed, thereby accurately obtaining the song unit data of the target playlist. Therefore, after obtaining the target song list, the song unit data of the target song list is detected. Specifically, for example, whether the target song list has corresponding song unit data, and whether the song unit data is valid song unit data.
  • step S202 includes:
  • Step S2021 Obtain at least two target dimensional features of each song to be played in the target playlist
  • Step S2022 If for each target dimensional feature, the proportion of songs to be played with the same feature value is greater than the proportion threshold corresponding to the target dimensional feature, it is determined that valid song unit data of the target song list is detected.
  • the song feature expression of the songs m1, m2, and m3 to be played includes three-dimensional features, which are song feature A, song feature B, and song feature respectively. C.
  • For each song feature there is a corresponding feature value.
  • the proportion of the same feature values is greater than 50%, then This song feature works.
  • the feature values of songs m1 and m2 to be played are #1, and the feature value of song m3 to be played is #2; then for song feature A, the feature value is The proportion of #1 is 66.7% (more than 50%), and the proportion of feature value #2 is 33.3%. Therefore, the song feature A is a valid song feature.
  • the feature value of the song m1 to be played is #1, the feature value of the song m2 to be played is #2, and the feature value of the song m3 to be played is #3.
  • the target song list has valid song unit data. It should be noted that since the songs to be played in the target playlist correspond to the song unit data, and the song unit data is formed based on the songs to be played in the target playlist, therefore, if all song features are valid, the target playlist The corresponding song unit data can be used as valid song unit data for calculation in subsequent steps.
  • Step S203 Read or generate song unit data of the target song list according to the check result.
  • the valid song unit data is read, and the song list cover is generated based on the valid song unit data; if there is no valid song unit data corresponding to the target song list.
  • the song unit data is generated based on the song characteristic expression of each song to be played in the target song list, and then the song list cover is generated based on the valid song unit data.
  • Step S204 Generate a song list cover based on the valid song unit data of the target song list.
  • the pre-trained image generation model can be used for rendering, and the multi-dimensional song features represented by the valid song unit data can be used as parameters to generate the image, thereby obtaining the song list cover.
  • the image generation model has the ability to map multi-dimensional song features into image features, and render based on the image features to obtain the corresponding image.
  • the image features include elements, main colors, composition, etc.
  • the image generation model (generator model) can be trained by using manually annotated images as samples, which will not be described again here.
  • Step S205 Generate a song list title based on the song list cover.
  • step S205 After obtaining the playlist cover, a corresponding playlist title is generated based on the playlist cover.
  • the specific implementation steps of step S205 include:
  • Step S2051 Determine the title space according to the song list cover.
  • the title space is the area within the song list cover used to render the song list title.
  • Step S2052 Generate a playlist title based on the size of the title space.
  • Figure 11 is a schematic diagram of a song list cover provided by an embodiment of the present disclosure.
  • a song list cover In the upper right part of the song list cover (image), there is a blank area that can be used to render a title, that is, a title space.
  • the position and size of the title space may be different.
  • the playlist title is usually set on the previous layer of the playlist cover (that is, the playlist title will cover the playlist cover).
  • Occlusion of effective information in the cover renders the playlist title to the title space, and based on the size of the title space, such as the length (shown as L in the figure) and height (shown as H in the figure), from the title pre-selection set Among the multiple target titles determined, based on the length of the target title (the more words in the title, the greater the length and/or width of the title space), select a target title that matches the size of the title space, thereby further avoiding playlist titles.
  • the cover of the song list improves the overall visual effect of the song list cover and the song list title.
  • the song list cover is first determined based on the song unit data, and then the song list title is determined based on the song list cover. Since the song unit data (relative to the song list title) is high-dimensional data, it has richer features for the target song list. expression ability, so the song list cover generated based on the song unit data can better express the richer features of the target song list and improve the visual expressiveness of the song list cover. At the same time, after the song list cover is determined, the song list cover is determined based on the song list cover. Single title can make the layout of the song list title and song list cover more reasonable, avoid the problem of the song list cover being blocked, and improve the overall visual effect of the song list cover and song list title.
  • step S201 is consistent with step S101 in the above-mentioned embodiment.
  • step S101 please refer to the discussion of step S101, which will not be described again here.
  • FIG. 12 is a structural block diagram of a device for generating playlist display information provided by an embodiment of the present disclosure. For convenience of explanation, only parts related to the embodiments of the present disclosure are shown.
  • the song list display information generating device 3 includes:
  • the acquisition module 31 is used to acquire a target song list, which includes at least one song to be played;
  • the generation module 32 is used to generate display information corresponding to the target playlist, where the display information is generated based on the song unit data of the target playlist.
  • the song unit data represents the multi-dimensional characteristics of at least one song to be played, and the display information includes the target The playlist title and/or playlist cover corresponding to the playlist.
  • the display information includes a playlist title and a playlist cover corresponding to the target playlist, where the playlist cover is related to the playlist title.
  • the generation module 32 is specifically used to: obtain the song unit data of the target song list; Generate a song list title based on the song unit data; generate a song list cover based on the song list title.
  • the generation module 32 when obtaining the song unit data of the target playlist, is specifically used to: obtain the song feature expressions of each song to be played in the target playlist, and the song feature expressions represent the characteristics of the songs to be played. Multi-dimensional features; generate song unit data of the target song list based on the song feature expression of at least one song to be played.
  • the songs to be played include seed songs.
  • the generation module 32 is specifically used to: obtain the seed songs, and Song unit data is generated based on the song feature expression of the seed song; the seed song is determined based on user instructions.
  • the generation module 32 when generating the song unit data of the target song list based on at least one song feature expression of the song to be played, is specifically configured to: perform the following steps based on the song feature expressions of at least two songs to be played. Weighted average is used to obtain the weighted average feature value; based on the weighted average feature, the song unit data of the target song list is generated.
  • the generation module 32 when generating a song list title based on the song unit data, is specifically used to: obtain a pre-selected set of titles, which includes at least one candidate title; and calculate the title characteristics of each candidate title. Express the matching degree with the song unit data, in which the title feature expresses the multi-dimensional characteristics of the candidate title; based on the matching degree corresponding to each candidate title, the target title is determined, and the song list title is generated based on the target title.
  • the title feature expression and the song unit data include the same target dimension feature.
  • the generation module 32 is specifically used to: based on the target dimension Features, obtain the first feature value of the candidate title under the target dimension feature, and the second feature value of the target playlist under the target dimension feature; based on the weighted distance between the first feature value and the second feature value, obtain the title of the candidate title Matching degree of feature expression and song unit data.
  • the display information includes the playlist title and playlist cover corresponding to the target playlist.
  • the generation module 32 is specifically used to: obtain the song unit data of the target playlist. ; Generate a song list cover based on the song unit data of the target song list; generate a song list title based on the song list cover.
  • the generation module 32 when generating a playlist title based on the playlist cover, is specifically used to: determine the title space based on the playlist cover, and the title space is within the playlist cover for rendering the playlist title. area; based on the size of the title space, generate the playlist title.
  • the generation module 32 when generating a playlist title based on the playlist cover, is specifically used to: obtain a pre-selected set of titles, which includes at least one candidate title; and calculate the title feature expression of each candidate title.
  • the generation module 32 is also used to: detect the valid song unit data of the target song list; if the song unit data of the target song list is detected, generate the target song list based on the valid song unit data. , generate display information corresponding to the target playlist; if the song unit data of the target playlist is not detected, generate the song unit data of the target playlist based on the song unit data of the song to be played.
  • the generation module 32 when detecting the valid song unit data of the target playlist, is specifically used to: obtain at least two target dimension features of each song to be played in the target playlist; if for each target Dimension feature, if the proportion of songs to be played with the same feature value is greater than the proportion threshold corresponding to the target dimensional feature, then it is determined that the detection Valid song unit data of the target song list is detected.
  • the playlist display information generating device 3 provided in this embodiment can execute the technical solution of the above method embodiment. Its implementation principles and technical effects are similar, and will not be described again in this embodiment.
  • FIG 13 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure. As shown in Figure 13, the electronic device 4 includes:
  • Processor 41 and memory 42 communicatively connected to processor 41;
  • Memory 42 stores computer execution instructions
  • the processor 41 executes the computer execution instructions stored in the memory 42 to implement the method for generating playlist display information in the embodiment shown in Figure 3-11.
  • processor 41 and the memory 42 are connected through the bus 43 .
  • the electronic device 900 may be a terminal device or a server.
  • terminal devices may include but are not limited to mobile phones, laptops, digital broadcast receivers, personal digital assistants (Personal Digital Assistant, PDA for short), tablet computers (Portable Android Device, PAD for short), portable multimedia players (Portable Mobile terminals such as Media Player (PMP for short), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc.
  • PDA Personal Digital Assistant
  • PAD Personal Android Device
  • portable multimedia players Portable Mobile terminals such as Media Player (PMP for short
  • vehicle-mounted terminals such as vehicle-mounted navigation terminals
  • fixed terminals such as digital TVs, desktop computers, etc.
  • the electronic device shown in FIG. 14 is only an example and should not impose any limitations on the functions 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 process data according to a program stored in a read-only memory (Read Only Memory, ROM for short) 902 or from a storage device. 908 loads the program in the random access memory (Random Access Memory, RAM for short) 903 to perform various appropriate actions and processing. In the RAM 903, various programs and data required for the operation of the electronic device 900 are also stored.
  • the processing device 901, ROM 902 and RAM 903 are connected to each other via a bus 904.
  • An input/output (I/O for short) 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). ), an output device 907 such as a speaker, a vibrator, etc.; a storage device 908 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 909.
  • the communication device 909 may allow the electronic device 900 to communicate wirelessly or wiredly with other devices to exchange data.
  • FIG. 14 illustrates electronic device 900 with various means, it should be understood that implementation or availability of all illustrated means is not required. More or fewer means may alternatively be implemented or provided.
  • embodiments of the present disclosure include a computer program product including 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 communication device 909, or from storage device 908, or from ROM 902.
  • the processing device 901 the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.
  • 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 may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples of computer readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard drives, RAM, ROM, Erasable Programmable Read Only Memory (EPROM for short) or flash memory, optical fiber, portable compact disk read-only memory (Compact Disk Read Only Memory (CD-ROM for short)), optical storage device, magnetic storage device, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program for use by or in connection 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, carrying computer-readable program code therein. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above.
  • a computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device .
  • Program code contained on a computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, radio frequency (Radio Frequency, RF for short), etc., or any suitable combination of the above.
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device; it may also exist independently without being assembled into the electronic device.
  • the computer-readable medium carries one or more programs.
  • the electronic device When the one or more programs are executed by the electronic device, the electronic device performs the method shown in the above embodiment.
  • Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional Procedural programming language—such as "C" or a 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 server.
  • 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 it can be connected to an external computer Computer (e.g. connected via the Internet using an Internet service provider).
  • LAN Local Area Network
  • WAN Wide Area Network
  • each block in the flowchart or block diagram may represent a module, segment, or portion of code that contains one or more logic functions that implement the specified executable instructions.
  • the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown one after another may actually execute substantially in parallel, or they may sometimes execute in the reverse order, depending on the functionality involved.
  • each block of the block diagram and/or flowchart illustration, and combinations of blocks in the block diagram and/or flowchart illustration can be implemented by special purpose hardware-based systems that perform the specified functions or operations. , or can be implemented using a combination of specialized hardware and computer instructions.
  • the units involved in the embodiments of the present disclosure can be implemented in software or hardware. way to achieve it.
  • the name of the unit does not constitute a limitation on the unit itself under certain circumstances.
  • the first acquisition module can also be described as "a unit that acquires at least two Internet Protocol addresses.”
  • exemplary types of hardware logic components include: Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), Application Specific Standard Products ( Application Specific Standard Parts (ASSP for short), System on Chip (SOC for short), Complex Programmable Logic Device (CPLD for short), etc.
  • FPGA Field Programmable Gate Array
  • ASIC Application Specific Integrated Circuit
  • ASSP Application Specific Standard Parts
  • SOC System on Chip
  • CPLD Complex Programmable Logic Device
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with an instruction execution system, apparatus, or device.
  • the machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, RAM, ROM, EPROM or flash memory, optical fiber, CD-ROM, optical storage device, magnetic storage device , or any suitable combination of the above.
  • a method for generating playlist display information including:
  • Obtain a target playlist which includes at least one song to be played; generate display information corresponding to the target playlist, wherein the display information is generated based on song unit data of the target playlist,
  • the song unit data represents the multi-dimensional characteristics of the at least one song to be played, and the display information includes the song list title and/or song list cover corresponding to the target song list.
  • the display information includes a playlist title and a playlist cover corresponding to the target playlist, wherein the playlist cover is related to the playlist title.
  • generating display information corresponding to the target playlist includes: obtaining song unit data of the target playlist; generating a playlist title according to the song unit data; The song list title generates a song list cover.
  • obtaining the song unit data of the target playlist includes: obtaining song feature expressions of each song to be played in the target playlist, where the song feature expression represents the The multi-dimensional characteristics of the songs to be played are described; and the song unit data of the target song list is generated according to the song characteristic expression of at least one song to be played.
  • the songs to be played include seed songs, and generating the song unit data of the target song list according to the song feature expression of at least one song to be played includes: obtaining the seed songs, And generate the song unit data according to the song feature expression of the seed song; wherein the seed song is determined based on user instructions.
  • generating the song unit data of the target playlist based on at least one song feature expression of the song to be played includes: based on at least two song feature expressions of the song to be played. A weighted average is performed to obtain a weighted average feature value; based on the weighted average feature, song unit data of the target song list is generated.
  • the song list title is generated according to the song unit data, including
  • the method includes: obtaining a pre-selected set of titles, the pre-selected set of titles including at least one candidate title; calculating a matching degree between the title feature expression of each candidate title and the song unit data, wherein the title feature expression represents the candidate title Multi-dimensional features of the title; determine the target title based on the matching degree corresponding to each candidate title, and generate the playlist title based on the target title.
  • the title feature expression and the song unit data include the same target dimension feature
  • the calculating degree of matching between the title feature expression of each candidate title and the song unit data is , including: based on the target dimension characteristics, obtaining the first characteristic value of the candidate title under the target dimension characteristics, and the second characteristic value of the target playlist under the target dimension characteristics; based on the The weighted distance between the first feature value and the second feature value obtains the matching degree between the title feature expression of the candidate title and the song unit data.
  • the display information includes a playlist title and a playlist cover corresponding to the target playlist
  • generating the display information corresponding to the target playlist includes: obtaining the target song The song unit data of the target song list is generated; the song list cover is generated based on the song unit data of the target song list; and the song list title is generated based on the song list cover.
  • generating a playlist title based on the playlist cover includes: determining a title space based on the playlist cover, and the title space is used within the playlist cover. In an area where the playlist title is rendered; based on the size of the title space, the playlist title is generated.
  • generating a playlist title based on the playlist cover includes: obtaining a pre-selected set of titles, the pre-selected set of titles including at least one candidate title; and calculating the number of each candidate title.
  • a target title is determined, and the playlist title is generated based on the target title.
  • the method further includes: detecting valid song unit data of the target playlist; if the song unit data of the target playlist is detected, based on The effective song unit data generates display information corresponding to the target song list; if the song unit data of the target song list is not detected, the target song list is generated based on the song unit data of the song to be played. song unit data.
  • detecting the effective song unit data of the target playlist includes: obtaining at least two target dimension features of each song to be played in the target playlist; if for each target dimension feature, the proportion of songs to be played with the same feature value is greater than the proportion threshold corresponding to the target dimension feature, then it is determined that the valid song unit data of the target song list is detected.
  • a device for generating playlist display information including:
  • An acquisition module is used to acquire a target song list, which includes at least one song to be played;
  • Generating module configured to generate display information corresponding to the target playlist, wherein the display information is generated based on the song unit data of the target playlist, and the song unit data represents the at least one song to be played.
  • the display information includes the song list title and/or the song list cover corresponding to the target song list.
  • the display information includes a playlist title and a playlist cover corresponding to the target playlist, wherein the playlist cover is related to the playlist title.
  • the generation module is specifically configured to: obtain song unit data of the target playlist; generate a playlist title based on the song unit data; and generate a playlist cover based on the song list title.
  • the generation module when obtaining the song unit data of the target playlist, is specifically used to: obtain the song feature expression of each song to be played in the target playlist, and the song feature expression represents the song to be played. Multi-dimensional features; generate song unit data of the target song list based on the song feature expression of at least one song to be played.
  • the songs to be played include seed songs
  • the generation module is specifically used to: obtain the seed songs when generating the song unit data of the target song list according to the song feature expression of at least one song to be played, And based on the song feature expression of the seed song, song unit data is generated; where the seed song is determined based on user instructions.
  • the generation module when generating the song unit data of the target playlist based on at least one song feature expression of the song to be played, is specifically configured to: based on at least two song feature expressions of the songs to be played. A weighted average is performed to obtain a weighted average feature value; based on the weighted average feature, the song unit data of the target song list is generated.
  • the generation module when the generation module generates a playlist title based on the song unit data, it is specifically used to: obtain a pre-selected set of titles, which includes at least one candidate title; and calculate the title of each candidate title.
  • the title feature expression and the song unit data include the same target dimension feature.
  • the generation module is specifically used to: based on the target Dimension features, obtain the first feature value of the candidate title under the target dimension feature, and the second feature value of the target playlist under the target dimension feature; based on the weighted distance between the first feature value and the second feature value, obtain the candidate title's The matching degree between the title feature expression and the song unit data.
  • the display information includes the playlist title and playlist cover corresponding to the target playlist.
  • the generation module When the generation module generates the display information corresponding to the target playlist, it is specifically used to: obtain the song unit of the target playlist. Data; generate a song list cover based on the song unit data of the target song list; generate a song list title based on the song list cover.
  • the generation module when generating a song list title based on the song list cover, is specifically used to: determine the title space based on the song list cover, and the title space is within the song list cover for rendering the song list. The area of the title; based on the size of the title space, the playlist title is generated.
  • the generation module when the generation module generates a playlist title based on the playlist cover, it is specifically used to: obtain a pre-selected set of titles, which includes at least one candidate title; and calculate the title features of each candidate title.
  • the generation module is further configured to: detect valid song unit data of the target song list; if the song unit data of the target song list is detected, generate the target song list based on the valid song unit data. data to generate display information corresponding to the target playlist; if the song unit data of the target playlist is not detected, the song unit data of the target playlist is generated based on the song unit data of the song to be played.
  • the generation module when detecting the valid song unit data of the target playlist, is specifically used to: obtain at least two target dimension features of each song to be played in the target playlist; if for each Target dimension feature, the proportion of songs to be played with the same feature value is greater than the proportion threshold corresponding to the target dimension feature, then it is determined Valid song unit data of the target song list must be detected.
  • an electronic device including: a processor, and a memory communicatively connected to the processor;
  • the memory stores computer execution instructions
  • the processor executes the computer execution instructions stored in the memory to implement the method for generating playlist display information as described in the first aspect and various possible designs of the first aspect.
  • a computer-readable storage medium is provided.
  • Computer-executable instructions are stored in the computer-readable storage medium.
  • a processor executes the computer-executed instructions, Implement the method for generating playlist display information as described in the first aspect and various possible designs of the first aspect.
  • a computer program product including a computer program that, when executed by a processor, implements the above first aspect and various possible designs of the first aspect.
  • the method for generating playlist display information is provided.
  • a computer program which when executed by a processor implements the playlist described in the first aspect and various possible designs of the first aspect. Demonstrate information generation methods.

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)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

本公开实施例提供一种歌单展示信息生成方法、装置、电子设备、计算机可读存储介质、计算机程序产品及计算机程序，通过获取目标歌单，目标歌单内包括至少一首待播放歌曲；生成目标歌单对应的展示信息，其中，展示信息是基于目标歌单的歌单元数据生成的，歌单元数据表征至少一首待播放歌曲的多维度特征，展示信息包括目标歌单对应的歌单标题和/或歌单封面，由于通过获取目标歌单，并针对性的利用目标歌单的歌单元数据来生成展示信息，可以使生成的展示信息与目标歌单在多维度上相匹配，从而提高生成的展示信息与歌单内容的一致性，实现对歌单内容的特征的准确展示。

Description

歌单展示信息生成方法、装置、电子设备及存储介质
相关申请的交叉引用
本申请要求于2022年07月01日提交中国专利局、申请号为202210774585.7、申请名称为“歌单展示信息生成方法、装置、电子设备及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本公开实施例涉及互联网技术领域，尤其涉及一种歌单展示信息生成方法、装置、电子设备、计算机可读存储介质、计算机程序产品及计算机程序。
背景技术
当前，音乐类应用(Application，简称APP)和音乐平台向用户推荐歌曲的方式，不仅包括针对单首歌曲的推荐，还包括针对由多首歌曲组成的合集的推荐，即歌单推荐。同时，还需要生成与歌单匹配的封面、标题等展示信息对歌单进行展示，从而吸引用户对歌单的消费。
然而，现有技术中针对歌单生成的展示信息，存在与歌单内容匹配度低、无法准确展示歌单内容的特征的问题。
发明内容
本公开实施例提供一种歌单展示信息生成方法、装置、电子设备、计算机可读存储介质、计算机程序产品及计算机程序。
第一方面，本公开实施例提供一种歌单展示信息生成方法，包括：
获取目标歌单，所述目标歌单内包括至少一首待播放歌曲；生成所述目标歌单对应的展示信息，其中，所述展示信息是基于所述目标歌单的歌单元数据生成的，所述歌单元数据表征所述至少一首待播放歌曲的多维度特征，所述展示信息包括所述目标歌单对应的歌单标题和/或歌单封面。
第二方面，本公开实施例提供一种歌单展示信息生成，包括：
获取模块，用于获取目标歌单，所述目标歌单内包括至少一首待播放歌曲；
生成模块，用于生成所述目标歌单对应的展示信息，其中，所述展示信息是基于所述目标歌单的歌单元数据生成的，所述歌单元数据表征所述至少一首待播放歌曲的多维度特征，所述展示信息包括所述目标歌单对应的歌单标题和/或歌单封面。
第三方面，本公开实施例提供一种电子设备，包括：
处理器，以及与所述处理器通信连接的存储器；
所述存储器存储计算机执行指令；
所述处理器执行所述存储器存储的计算机执行指令，以实现如上第一方面以及第一方面各种可能的设计所述的歌单展示信息生成方法。
第四方面，本公开实施例提供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，实现如上第一方面以及第一方面各种可能的设计所述的歌单展示信息生成方法。
第五方面，本公开实施例提供一种计算机程序产品，包括计算机程序，所述计算机程序被处理器执行时实现如上第一方面以及第一方面各种可能的设计所述的歌单展示信息生成方法。
第六方面，本公开实施例提供一种计算机程序，所述计算机程序被处理器执行时实现如上第一方面以及第一方面各种可能的设计所述的歌单展示信息生成方法。
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为本公开实施例提供的歌单展示信息生成方法的一种应用场景图。
图2为本公开实施例提供的歌单展示信息生成方法的另一种应用场景图。
图3为本公开实施例提供的歌单展示信息生成方法流程示意图一。
图4为图3所示实施例中步骤S102的具体实现步骤流程图。
图5为步骤S102中的步骤S1021的具体实现步骤流程图。
图6为本公开实施例提供的一种目标歌单对应的歌曲特征表达的数据结构示意图。
图7为本公开实施例提供的一种生成歌单封面的过程示意图。
图8为本公开实施例提供的歌单展示信息生成方法的流程示意图二。
图9为图8所示实施例中步骤S202的具体实现步骤流程图。
图10为图8所示实施例中步骤S205的具体实现步骤流程图。
图11为本公开实施例提供的一种歌单封面的示意图。
图12为本公开实施例提供的歌单展示信息生成装置的结构框图。
图13为本公开实施例提供的一种电子设备的结构示意图。
图14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。
下面对本公开实施例的应用场景进行解释：
本公开实施例提供的歌单展示信息生成方法，可以应用于歌单推荐的应用场景。图1为本公开实施例提供的歌单展示信息生成方法的一种应用场景图，具体地，如图1所 示，本公开实施例提供的方法，可以应用于服务器，例如音乐平台服务器，服务器与终端设备通信，其中，终端设备为由用户操作，用于运行音乐类APP的设备，例如智能手机、平板电脑等。服务器在基于预设规则，生成推荐歌单后，通过本公开实施例提供的歌单展示信息生成方法，生成与推荐歌单对应的展示信息，例如推荐歌单对应的歌单标题和歌单封面。之后，服务器将推荐歌单(图中示为歌单1、歌单2、歌单3)以及对应的歌单标题(图中示为标题1、标题2、标题3)、歌单封面(图中示为封面1、封面2、封面3)，作为整体的推荐内容(图中示为推荐内容1、推荐内容2、推荐内容3)发送至终端设备，并在终端设备一侧展示，完成歌单推荐的过程。之后，终端设备响应于用户指令，基于歌单标题、歌单封面等展示信息对推荐歌单进行消费，完成推荐歌单内歌曲的播放。
图2为本公开实施例提供的歌单展示信息生成方法的另一种应用场景图，具体地，如图2所示，在另一种可能的实现方式中，本公开实施例提供的方法，可以应用于终端设备，例如智能手机、平板电脑等，终端设备通过运行的音乐类APP(客户端)与服务器(服务端)进行通信，并接收服务器发送的推荐歌单(图中示为歌单1、歌单2、歌单3)，之后，终端设备基于本公开实施例提供的歌单展示信息生成方法，在终端设备一侧生成与推荐歌单对应的展示信息，例如推荐歌单对应的歌单标题(图中示为标题1、标题2、标题3)和歌单封面(图中示为封面1、封面2、封面3)，并在终端设备一侧展示，完成歌单推荐的过程。之后，终端设备响应于用户指令，基于歌单标题、歌单封面等展示信息对推荐歌单进行消费，完成推荐歌单内歌曲的播放。
现有技术中，歌单展示信息的生成，通常是在生成推荐歌单后，基于推荐歌单人工设置的歌单标签，生成对应的文字和图片，从而得到自动生成的歌单标题和歌单封面。而当推荐歌单无人工设置的歌单标签时，则会基于歌单的某一维度的特征，例如“语言”、“演唱者”，生成对应的文字和图片，从而得到歌单标题和歌单封面。然而，当推荐歌单是基于歌曲的多个维度特征共同生成的情况下，基于其中的单一维度的特征生成对应的歌单展示信息，会导致生成的展示信息与歌单内容匹配度低、无法准确展示歌单内容的特征的问题。
本公开实施例提供一种歌单展示信息生成方法以解决上述问题。
参考图3，图3为本公开实施例提供的歌单展示信息生成方法流程示意图一。本实施例的方法可以应用在服务器或终端设备中，本实施例中，主要以服务器为执行主体对该方法实施例进行介绍，该歌单展示信息生成方法包括：
步骤S101：获取目标歌单，目标歌单内包括至少一首待播放歌曲。
示例性地，目标歌单是服务器基于预设规则和预设曲库生成的歌曲集合，其中，目标歌单中包括的歌曲，即待播放歌曲，基于生成目标歌单的具体结果，目标歌单中的待播放歌曲可以为一首或多首。目标歌单是基于曲库内歌曲的多维度特征进行筛选而确定的，例如，基于歌曲的“发行年份”、“语言”、“曲风”、“歌曲主体”等。对于目标歌单的具体生成方法，此处不进行具体限制。其中，示例性地，目标歌单可以是服务器在获取目标歌单之前基于预设的算法生成的，也可以是通过与其他服务器通信而获得的；类似地，当本实施例方法的执行主体为终端设备时，该目标歌单可以是通过与其他服务器通信而获得的。
步骤S102：生成目标歌单对应的展示信息，其中，展示信息是基于目标歌单的歌单元数据生成的，歌单元数据表征至少一首待播放歌曲的多维度特征，展示信息包括目标歌单对应的歌单标题和/或歌单封面。
进一步地，在获得目标歌单之后，可以基于目标歌单的特征来生成与其匹配的展示信息，例如目标歌单的歌单标题、歌单封面。具体地，可以通过目标歌单的歌单元数据(metadata)来实现上述目的，其中，目标歌单中包括多个待播放歌曲，歌单元数据表征待播放歌曲的多维度特征。
在一种可能的实现方式中，展示信息包括目标歌单对应的歌单标题和歌单封面，歌单封面是基于歌单标题生成的，如图4所示，步骤S102的具体实现步骤包括：
步骤S1021：获取目标歌单的歌单元数据。
示例性地，服务器在得到目标歌单的同时或之后，获得目标歌单对应的歌单元数据。歌单元数据表征至少一首待播放歌曲的多维度特征，更具体地，一种实现方式中，歌单元数据包括每一待播放歌曲的多维度特征，另一种实现方式中，歌单元数据包括各待播放歌曲的多维度特征的平均值。进一步地，待播放歌曲的多维度特征，表征待播放歌曲在多个维度上的特征的集合，例如，“发行年份”、“语言”、“曲风”、“歌曲主体”等维度的特征的集合。
进一步地，基于歌单元数据不同的存在状态，可以通过以下两种具体方式获得目标歌单的歌单元数据，包括：
一种可能的实现方式中，若目标歌单的歌单元数据有效，即目标歌单的歌单元数据为有效歌单元数据，则服务器可以直接读取该歌单元数据，其中，有效歌单元数据是指能够表现出目标歌单中各待播放歌曲的主体特征的歌单元数据。具体地，例如，有效歌单元数据是指其所表征的多个维度的歌曲特征中，针对每一歌曲特征，对应的特征值与目标歌单内一定比例(例如70％)的待播放歌曲(在该歌曲特征下)的特征值相同。其中，目标歌单信息可以是由其他服务器发送的，或者由本服务器在之前生成目标歌单的步骤中生成的，此次不进行具体限定。
在另一种可能的实现方式中，若目标歌单的歌单元数据不存在，则服务器可以通过计算而生成目标歌单的歌单元数据，示例性地，如图5所示，具体实现步骤包括：
步骤S1021A：获取目标歌单内的各待播放歌曲的歌曲特征表达，歌曲特征表达表征待播放歌曲的多维度特征。
步骤S1021B：根据至少一个待播放歌曲的歌曲特征表达，生成目标歌单的歌单元数据。
示例性地，目标歌单内包含的一首或多首待播放歌曲中，每一首待播放歌曲均具有对应的歌曲特征表达(embedding)，歌曲特征表达表征待播放歌曲的多维度特征。图6为本公开实施例提供的一种目标歌单对应的歌曲特征表达的数据结构示意图，如图6所示，目标歌单内，包括待播放歌曲m1、m2、m3…cN，分别对应歌曲特征表达c01、c02、c03(图中仅示出m1对应的歌曲特征表达c1的具体实现，其他类似)，待播放歌曲m1的歌曲特征表达c1包括3个维度的特征，分别为歌曲特征A、歌曲特征B、歌曲特征C。其中，示例性地，歌曲特征A表征歌曲的“歌曲曲风”、歌曲特征B表征歌曲的“发行年代”、歌曲特征C表征歌曲的“演唱语言”。针对每一维度的特征，待播放 歌曲m1均对应一个特征值，如图所示，即歌曲特征A的特征值为#01，表示(歌曲风为)“摇滚”；歌曲特征B的特征值为#03，表示(发行年代为)“90年代”；歌曲特征C的特征值为#05，表示(演唱语言为)“法语”。
基于目标歌单中待播放歌曲的歌曲特征表达，利用待播放歌曲的多维度特征中对应维度特征的特征值进行计算，即可得到目标歌单的歌单元数据。在一种可能的实现方式中，步骤S1021B的具体实现方式包括，包括：基于至少两个待播放歌曲的歌曲特征表达进行加权平均，得到加权平均特征值；根据加权平均特征，生成目标歌单的歌单元数据。具体地，基于图6所示，例如，将播放歌曲m1、m2、m3各自的歌曲特征A的特征值取平均，得到歌曲特征A的平均特征值aver_1；将播放歌曲m1、m2、m3各自的歌曲特征B取平均，得到歌曲特征B的平均特征值aver_2，将播放歌曲m1、m2、m3各自的歌曲特征C取平均，得到歌曲特征C的平均特征值aver_3。之后，基于歌曲特征A的平均特征值aver_1、歌曲特征B的平均特征值aver_2、歌曲特征C的平均特征值aver_3的组合，得到目标歌单的歌单元数据。其中，示例性地，歌单元数据中包括的特征维度，覆盖歌曲特征表达中包括的特征维度，即歌单元数据可以在包括特征维度：歌曲特征A、歌曲特征B、歌曲特征C的基础上，还包括特征维度：歌单特征F，例如表示歌单内的歌曲数量。从而实现对目标歌单更加准确的特征表现。
本实施例中，通过利用待播放歌曲的多维度特征中对应维度特征的特征值进行计算，使目标歌单的歌单元数据能够表现出各待播放歌曲在各维度上的整体特征，特征表现更加均衡，提高歌单元数据的准确性和稳定性。
在另一种实现方式中，待播放歌曲包括种子歌曲，步骤S1021B的具体实现方式包括：获取种子歌曲，并根据种子歌曲的歌曲特征表达，生成歌单元数据，其中，种子歌曲基于用户指令确定。
具体地，种子歌曲即用于生成目标歌单的歌曲。在一种实现方式中，通过提取种子歌曲的多维度特征，并基于种子歌曲的多维度特征，从曲库中筛选与种子歌曲的多维度特征最相近的歌曲，作为候选歌曲，进而基于候选歌曲和种子歌曲的集合，生成目标歌单。在上述实现方式中，目标歌单是基于种子歌曲生成的，因此，种子歌曲的歌曲特征表达是最具代表性的(与歌单元数据最接近)。基于上述原因，本实施例步骤中，通过种子歌曲，生成目标歌单的歌单元数据，在保证歌单元数据的准确性的同时，简化歌单元数据的计算过程，降低计算量，提高歌单元数据的生成速度。
步骤S1022：根据歌单元数据，生成歌单标题。
示例性地，生成歌单标题的具体步骤包括：获取标题预选集，标题预选集内包括至少一个候选标题；计算各候选标题的标题特征表达与歌单元数据的匹配度，其中，标题特征表达表征候选标题的多维度特征；基于各候选标题对应的匹配度，确定目标标题，并基于目标标题生成歌单标题。其中，标题预选集是基于自然语言处理(Natural Language Processing，简称NLP)技术生成的，包含多个用于表达不同歌曲多维度特征的候选标题的集合，在获得歌单元数据后，基于标题预选集内各候选标题的标题特征表达表征的多维度特征，计算与歌单元数据对应的多维图特征之间的特征距离，从而确定候选标题与歌单元数据之间的匹配度，进而，将匹配度最大的候选标题确定为目标标题，从而将目标标题作为歌单标题，完成生成歌单标题的步骤。
进一步地，其中，标题特征表达和歌单元数据包括相同的目标维度特征，目标维度特征例如包括“发行年份”、“语言”、“曲风”、“歌曲主体”；计算标题特征表达与歌单元数据的匹配度的步骤包括：基于目标维度特征，获得候选标题在目标维度特征下的第一特征值，以及目标歌单在目标维度特征下的第二特征值；基于第一特征值和第二特征值的加权距离，得到候选标题的标题特征表达与歌单元数据的匹配度。
本实施例中，通过获取标题预选集，并通过计算歌单元数据与标题预选集内的候选标题的特征距离，确定与歌单元数据最匹配的目标标题，从而得到歌单标题，使歌单标题的特征与目标歌单的特征在多个维度上最接近，从而提高歌单标题与目标歌单的内容的一致性，提高歌单标题的精确度。
步骤S1023：根据歌单标题生成歌单封面。
图7为本公开实施例提供的一种生成歌单封面的过程示意图，如图7所示，示例性地，在获得歌单元数据后，首先基于歌单元数据进行特征提取，利用自然语言处理技术，从歌单候选集中生成目标歌单的歌单标题。其中，歌单标题为用于描述目标歌单中歌曲的内容特征、曲风特征的文字，例如“法语电影音乐”、“我的热舞派对”。之后，在基于生成的歌单标题对应的文字信息，进行歌单封面的生成，具体地，例如，利用预设的图像生成算法，基于歌单标题对应的文字信息以及对针对目标歌单的描述信息，例如歌单元数据中至少一个维度的特征，确定图像中的元素、主色调、构图、等图像特征，并进行渲染，从而生成一张能够表达歌单标题对应的文字信息所包含的内容、意义的图像，即歌单封面。其中，需要说明的是，本实施例步骤中，由于歌单标题中包含的目标歌单的特征较少(生成歌单标题的过程中特征经过了降维)，因此，在上述基于歌单标题对应的文字信息生成歌单封面的过程中，结合针对目标歌单的描述信息，可以进一步提高所生成的歌单封面的准确性。
本实施例步骤中，利用文字信息和图像信息的特点，首先基于歌单元数据生成更容易难度更低、信息描述准确性更好的文字信息，得到歌单标题，之后再基于文字信息构造复杂性更高的图像信息，得到歌单封面，从而提高生成的歌单标题和歌单封面的准确性，使歌单标题和歌单封面能够更好的表现目标歌单内容的特征。
可选地，步骤S102之后，还包括：
服务器将目标歌单对应的展示信息发送至终端设备，以使终端设备显示该展示信息，即歌单封面和/或歌单标题。之后，终端设备会基于针对该显示信息的触发指令，播放或显示对应的目标歌单内的待播放歌曲。
类似地，若以终端设备作为本方法实施例的执行主体，在生成目标歌单对应的展示信息后，终端设备显示该展示信息，即歌单封面和/或歌单标题，之后终端设备会基于针对该显示信息的触发指令，播放或显示对应的目标歌单内的待播放歌曲。
在本实施例中，通过获取目标歌单，目标歌单内包括至少一首待播放歌曲；生成目标歌单对应的展示信息，其中，展示信息是基于目标歌单的歌单元数据生成的，歌单元数据表征至少一首待播放歌曲的多维度特征，展示信息包括目标歌单对应的歌单标题和/或歌单封面，由于通过获取目标歌单，并针对性的利用目标歌单的歌单元数据来生成展示信息，可以使生成的展示信息与目标歌单在多维度上相匹配，从而提高生成的展示信息与歌单内容的一致性，实现对歌单内容的特征的准确展示。
参考图8，图8为本公开实施例提供的歌单展示信息生成方法的流程示意图二。本实施例在图3所示实施例的基础上，提供了另外一种步骤S102的实现步骤，并增加了对歌单元数据进行检查的步骤，该歌单展示信息生成方法包括：
步骤S201：获取目标歌单，目标歌单内包括至少一首待播放歌曲。
步骤S202：检测目标歌单的有效歌单元数据。
示例性地，目标歌单可以是在之前的步骤中生成，或者接收其他服务器发送的数据而获得，基于获得目标歌单的具体实现方式，目标歌单可以为有效歌单元数据，或者，无效歌单元数据，或者，不存在歌单元数据。基于目标歌单的歌单元数据的不同的存在状态，进行对应的处理方式，从而准确的得到目标歌单的歌单元数据。因此，在获得目标歌单之后，检测目标歌单的歌单元数据，具体地，例如，目标歌单是否存在对应的歌单元数据，以及，歌单元数据是否为有效歌单元数据。
如图9所示，步骤S202的具体实现步骤包括：
步骤S2021：获取目标歌单内各待播放歌曲的至少两个目标维度特征；
步骤S2022：若针对每一目标维度特征，特征值相同的待播放歌曲的比例均大于与目标维度特征对应的比例阈值，则确定检测到目标歌单的有效歌单元数据。
示例性地，参考图6所示的歌曲特征表达的数据结构，例如，待播放歌曲m1、m2、m3的歌曲特征表达包括3个维度的特征，分别为歌曲特征A、歌曲特征B、歌曲特征C，对于每一歌曲特征，分别对应一个特征值。其中，若在歌曲特征A、歌曲特征B、歌曲特征C中，针对每一歌曲特征，各待播放歌曲在该歌曲特征下的特征值，存在主体类型，例如特征值相同比例大于50％，则该歌曲特征有效。例如，针对歌曲特征A，待播放歌曲m1、m2、m3中，待播放歌曲m1、m2的特征值为#1，待播放歌曲m3的特征值为#2；则针对歌曲特征A，特征值为#1的比例为66.7％(大于50％)，特征值为#2的比例为33.3％，因此，该歌曲特征A为有效歌曲特征。再例如，针对歌曲特征B，待播放歌曲m1、m2、m3中，待播放歌曲m1的特征值为#1、待播放歌曲m2的特征值为#2、待播放歌曲m3的特征值为#3；则针对歌曲特征B，特征值为#1的比例为33.3％，特征值为#2的比例为33.3％，特征值为#3的比例为33.3％，均小于50％，因此，该歌曲特征B为无效歌曲特征。进一步的，若全部歌曲特征有效，则目标歌单具有有效歌单元数据。需要说明的是，由于目标歌单中的待播放歌曲与歌单元数据是对应的，歌单元数据是基于目标歌单中的待播放歌曲形成的，因此，若全部歌曲特征有效，则目标歌单对应的歌单元数据可以作为有效歌单元数据进行后续步骤的计算。
步骤S203：根据检查结果，读取或生成目标歌单的歌单元数据。
示例性地，根据检查结果，若存在目标歌单对应的有效歌单元数据，则读取该有效歌单元数据，并基于该有效歌单元数据生成歌单封面；若不存在目标歌单对应的有效歌单元数据，则基于目标歌单中各待播放歌曲的歌曲特征表达，来生成有效歌单元数据，之后基于该有效歌单元数据生成歌单封面。具体实现方式可参见图3所示实施例中步骤S1021中相关介绍，此处不再赘述。
步骤S204：根据目标歌单的有效歌单元数据，生成歌单封面。
示例性地，在得到有效歌单元数据后，可以利用预训练的图像生成模型进行渲染，以有效歌单元数据所表征的多维度歌曲特征作为参数进行图像生成，从而得到歌单封 面，其中，图像生成模型具有将多维度歌曲特征映射成图像特征，并基于图像特征进行渲染而得到对应的图像的能力，其中，图像特征包括元素、主色调、构图等。该图像生成模型(生成器模型)可以通过人工标注的图像作为样本进行训练而得到，此处不再赘述。
步骤S205：根据歌单封面，生成歌单标题。
进一步地，在得到歌单封面后，基于歌单封面来生成对应的歌单标题，示例性地，如图10所示，步骤S205的具体实现步骤包括：
步骤S2051：根据歌单封面，确定标题空间，标题空间为歌单封面内用于渲染歌单标题的区域。
步骤S2052：基于标题空间的大小，生成歌单标题。
图11为本公开实施例提供的一种歌单封面的示意图，如图11所示，在该歌单封面(图像)的右上部，存在一个可以用于渲染标题的空白区域，即标题空间。对于不同的歌单封面，其标题空间的位置以及大小均可能不同。为了实现更好的视觉效果，通常歌单标题是设置在歌单封面的上一图层(即歌单标题会遮盖歌单封面)，因此，本实施例中，为了避免歌单标题对歌单封面中有效信息的遮挡，将歌单标题渲染至标题空间，并基于标题空间的大小，例如标题空间的长度(图中示为L)和高度(图中示为H)，从标题预选集内确定的多个目标标题中，基于目标标题的长度(标题字数越多，则标题空间的长度和/或宽度越大)，选择与标题空间的大小匹配的目标标题，从而进一步的避免歌单标题对歌单封面的遮挡，提高歌单封面与歌单标题构成的整体的视觉效果。其中，从标题预选集内确定的多个目标标题的具体实现方式，可参见图3所示实施例中步骤S1022中的相关介绍，此处不再赘述。
本公开实施例中，通过歌单元数据先确定歌单封面，再基于歌单封面确定歌单标题，由于歌单元数据(相对歌单标题)是高维数据，具有针对目标歌单更丰富的特征表达能力，因此基于歌单元数据生成的歌单封面，能够更好的表现目标歌单更加丰富的特征，提高歌单封面的视觉表现力，同时在确定歌单封面后，基于歌单封面确定歌单标题，可以使歌单标题与歌单封面的布局更加合理，避免歌单封面被遮挡的问题，提高歌单封面与歌单标题构成的整体的视觉效果。
在本公开实施例中，步骤S201与上述实施例中步骤S101的一致，详细论述请参考步骤S101的论述，这里不再赘述。
对应于上文实施例的歌单展示信息生成方法，图12为本公开实施例提供的歌单展示信息生成装置的结构框图。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12，歌单展示信息生成装置3，包括：
获取模块31，用于获取目标歌单，目标歌单内包括至少一首待播放歌曲；
生成模块32，用于生成目标歌单对应的展示信息，其中，展示信息是基于目标歌单的歌单元数据生成的，歌单元数据表征至少一首待播放歌曲的多维度特征，展示信息包括目标歌单对应的歌单标题和/或歌单封面.
在本公开的一个实施例中，展示信息包括目标歌单对应的歌单标题和歌单封面，其中，歌单封面与歌单标题相关。
在本公开的一个实施例中，生成模块32，具体用于：获取目标歌单的歌单元数据； 根据歌单元数据，生成歌单标题；根据歌单标题生成歌单封面。
在本公开的一个实施例中，生成模块32在获取目标歌单的歌单元数据时，具体用于：获取目标歌单内的各待播放歌曲的歌曲特征表达，歌曲特征表达表征待播放歌曲的多维度特征；根据至少一个待播放歌曲的歌曲特征表达，生成目标歌单的歌单元数据。
在本公开的一个实施例中，待播放歌曲包括种子歌曲，生成模块32在根据至少一个待播放歌曲的歌曲特征表达，生成目标歌单的歌单元数据时，具体用于：获取种子歌曲，并根据种子歌曲的歌曲特征表达，生成歌单元数据；其中，种子歌曲基于用户指令确定。
在本公开的一个实施例中，生成模块32在根据至少一个待播放歌曲的歌曲特征表达，生成目标歌单的歌单元数据时，具体用于：基于至少两个待播放歌曲的歌曲特征表达进行加权平均，得到加权平均特征值；根据加权平均特征，生成目标歌单的歌单元数据。
在本公开的一个实施例中，生成模块32在根据歌单元数据，生成歌单标题时，具体用于：获取标题预选集，标题预选集内包括至少一个候选标题；计算各候选标题的标题特征表达与歌单元数据的匹配度，其中，标题特征表达表征候选标题的多维度特征；基于各候选标题对应的匹配度，确定目标标题，并基于目标标题生成歌单标题。
在本公开的一个实施例中，标题特征表达和歌单元数据包括相同的目标维度特征，生成模块32在计算各候选标题的标题特征表达与歌单元数据的匹配度时，具体用于：基于目标维度特征，获得候选标题在目标维度特征下的第一特征值，以及目标歌单在目标维度特征下的第二特征值；基于第一特征值和第二特征值的加权距离，得到候选标题的标题特征表达与歌单元数据的匹配度。
在本公开的一个实施例中，展示信息包括目标歌单对应的歌单标题和歌单封面，生成模块32在生成目标歌单对应的展示信息时，具体用于：获取目标歌单的歌单元数据；根据目标歌单的歌单元数据，生成歌单封面；根据歌单封面，生成歌单标题。
在本公开的一个实施例中，生成模块32在根据歌单封面，生成歌单标题时，具体用于：根据歌单封面，确定标题空间，标题空间为歌单封面内用于渲染歌单标题的区域；基于标题空间的大小，生成歌单标题。
在本公开的一个实施例中，生成模块32在根据歌单封面，生成歌单标题时，具体用于：获取标题预选集，标题预选集包括至少一个候选标题；计算各候选标题的标题特征表达与歌单封面的封面特征表达的匹配度，其中，标题特征表达表征候选标题的多维度特征，封面特征表达表征歌单封面的多维度特征；基于各候选标题对应的匹配度，确定目标标题，并基于目标标题生成歌单标题。
在本公开的一个实施例中，在获取目标歌单之后，生成模块32还用于：检测目标歌单的有效歌单元数据；若检测到目标歌单的歌单元数据，则基于有效歌单元数据，生成目标歌单对应的展示信息；若未检测到目标歌单的歌单元数据，则基于待播放歌曲的歌单元数据，生成目标歌单的歌单元数据。
在本公开的一个实施例中，生成模块32在检测目标歌单的有效歌单元数据时，具体用于：获取目标歌单内各待播放歌曲的至少两个目标维度特征；若针对每一目标维度特征，特征值相同的待播放歌曲的比例均大于与目标维度特征对应的比例阈值，则确定检 测到目标歌单的有效歌单元数据。
其中，获取模块31、生成模块32连接。本实施例提供的歌单展示信息生成装置3可以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。
图13为本公开实施例提供的一种电子设备的结构示意图，如图13所示，该电子设备4包括：
处理器41，以及与处理器41通信连接的存储器42；
存储器42存储计算机执行指令；
处理器41执行存储器42存储的计算机执行指令，以实现如图3-11所示实施例中的歌单展示信息生成方法。
其中，可选地，处理器41和存储器42通过总线43连接。
相关说明可以对应参见图3-11所对应的实施例中的步骤所对应的相关描述和效果进行理解，此处不做过多赘述。
参考图14，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可以为终端设备或服务器。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14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14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(Input/Output，简称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14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、或半导体的系统、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、RAM、ROM、可擦式可编程只读存储器(Erasable Programmable Read Only Memory，简称EPROM)或闪存、光纤、便携式紧凑磁盘只读存储器(Compact Disk Read Only Memory，简称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系统、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系统、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、射频(Radio Frequency，简称RF)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服务器上执行。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)。
附图中的流程图和框图，图示了按照本公开各种实施例的系统、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系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于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，第一获取模块还可以被描述为“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，简称FPGA)、专用集成电路(Application Specific Integrated Circuit，简称ASIC)、专用标准产品(Application Specific Standard Parts，简称ASSP)、片上系统(System on Chip，简称SOC)、复杂可编程逻辑设备(Complex Programmable Logic Device，简称CPLD)等等。
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、RAM、ROM、EPROM或快闪存储器、光纤、CD-ROM、光学储存设备、磁储存设备、或上述内容的任何合适组合。
第一方面，根据本公开的一个或多个实施例，提供了一种歌单展示信息生成方法，包括：
获取目标歌单，所述目标歌单内包括至少一首待播放歌曲；生成所述目标歌单对应的展示信息，其中，所述展示信息是基于所述目标歌单的歌单元数据生成的，所述歌单元数据表征所述至少一首待播放歌曲的多维度特征，所述展示信息包括所述目标歌单对应的歌单标题和/或歌单封面。
根据本公开的一个或多个实施例，所述展示信息包括所述目标歌单对应的歌单标题和歌单封面，其中，所述歌单封面与所述歌单标题相关。
根据本公开的一个或多个实施例，所述生成所述目标歌单对应的展示信息，包括：获取所述目标歌单的歌单元数据；根据所述歌单元数据，生成歌单标题；根据所述歌单标题生成歌单封面。
根据本公开的一个或多个实施例，所述获取所述目标歌单的歌单元数据，包括：获取所述目标歌单内的各待播放歌曲的歌曲特征表达，所述歌曲特征表达表征所述待播放歌曲的多维度特征；根据至少一个待播放歌曲的歌曲特征表达，生成所述目标歌单的歌单元数据。
根据本公开的一个或多个实施例，所述待播放歌曲包括种子歌曲，根据至少一个待播放歌曲的歌曲特征表达，生成所述目标歌单的歌单元数据，包括：获取所述种子歌曲，并根据所述种子歌曲的歌曲特征表达，生成所述歌单元数据；其中，所述种子歌曲基于用户指令确定。
根据本公开的一个或多个实施例，所述根据至少一个待播放歌曲的歌曲特征表达，生成所述目标歌单的歌单元数据，包括：基于至少两个所述待播放歌曲的歌曲特征表达进行加权平均，得到加权平均特征值；根据所述加权平均特征，生成所述目标歌单的歌单元数据。
根据本公开的一个或多个实施例，所述根据所述歌单元数据，生成歌单标题，包 括：获取标题预选集，所述标题预选集内包括至少一个候选标题；计算各所述候选标题的标题特征表达与所述歌单元数据的匹配度，其中，所述标题特征表达表征所述候选标题的多维度特征；基于各所述候选标题对应的匹配度，确定目标标题，并基于所述目标标题生成所述歌单标题。
根据本公开的一个或多个实施例，所述标题特征表达和所述歌单元数据包括相同的目标维度特征，所述计算各所述候选标题的标题特征表达与所述歌单元数据的匹配度，包括：基于所述目标维度特征，获得所述候选标题在所述目标维度特征下的第一特征值，以及所述目标歌单在所述目标维度特征下的第二特征值；基于所述第一特征值和所述第二特征值的加权距离，得到所述候选标题的标题特征表达与歌单元数据的匹配度。
根据本公开的一个或多个实施例，所述展示信息包括所述目标歌单对应的歌单标题和歌单封面，所述生成所述目标歌单对应的展示信息，包括：获取所述目标歌单的歌单元数据；根据所述目标歌单的歌单元数据，生成歌单封面；根据所述歌单封面，生成歌单标题。
根据本公开的一个或多个实施例，所述根据所述歌单封面，生成歌单标题，包括：根据所述歌单封面，确定标题空间，所述标题空间为所述歌单封面内用于渲染所述歌单标题的区域；基于所述标题空间的大小，生成所述歌单标题。
根据本公开的一个或多个实施例，所述根据所述歌单封面，生成歌单标题，包括：获取标题预选集，所述标题预选集包括至少一个候选标题；计算各所述候选标题的标题特征表达与所述歌单封面的封面特征表达的匹配度，其中，所述标题特征表达表征所述候选标题的多维度特征，所述封面特征表达表征所述歌单封面的多维度特征；基于各所述候选标题对应的匹配度，确定目标标题，并基于所述目标标题生成所述歌单标题。
根据本公开的一个或多个实施例，在所述获取目标歌单之后，还包括：检测所述目标歌单的有效歌单元数据；若检测到所述目标歌单的歌单元数据，则基于所述有效歌单元数据，生成所述目标歌单对应的展示信息；若未检测到所述目标歌单的歌单元数据，则基于所述待播放歌曲的歌单元数据，生成所述目标歌单的歌单元数据。
根据本公开的一个或多个实施例，所述检测所述目标歌单的有效歌单元数据，包括：获取目标歌单内各待播放歌曲的至少两个目标维度特征；若针对每一目标维度特征，特征值相同的待播放歌曲的比例均大于与目标维度特征对应的比例阈值，则确定检测到所述目标歌单的有效歌单元数据。
第二方面，根据本公开的一个或多个实施例，提供了一种歌单展示信息生成装置，包括：
获取模块，用于获取目标歌单，所述目标歌单内包括至少一首待播放歌曲；
生成模块，用于生成所述目标歌单对应的展示信息，其中，所述展示信息是基于所述目标歌单的歌单元数据生成的，所述歌单元数据表征所述至少一首待播放歌曲的多维度特征，所述展示信息包括所述目标歌单对应的歌单标题和/或歌单封面。
根据本公开的一个或多个实施例，展示信息包括目标歌单对应的歌单标题和歌单封面，其中，所述歌单封面与所述歌单标题相关。
根据本公开的一个或多个实施例，生成模块，具体用于：获取目标歌单的歌单元数据；根据歌单元数据，生成歌单标题；根据歌单标题生成歌单封面。
根据本公开的一个或多个实施例，生成模块在获取目标歌单的歌单元数据时，具体用于：获取目标歌单内的各待播放歌曲的歌曲特征表达，歌曲特征表达表征待播放歌曲的多维度特征；根据至少一个待播放歌曲的歌曲特征表达，生成目标歌单的歌单元数据。
根据本公开的一个或多个实施例，待播放歌曲包括种子歌曲，生成模块在根据至少一个待播放歌曲的歌曲特征表达，生成目标歌单的歌单元数据时，具体用于：获取种子歌曲，并根据种子歌曲的歌曲特征表达，生成歌单元数据；其中，种子歌曲基于用户指令确定。
根据本公开的一个或多个实施例，生成模块在根据至少一个待播放歌曲的歌曲特征表达，生成目标歌单的歌单元数据时，具体用于：基于至少两个待播放歌曲的歌曲特征表达进行加权平均，得到加权平均特征值；根据加权平均特征，生成目标歌单的歌单元数据。
根据本公开的一个或多个实施例，生成模块在根据歌单元数据，生成歌单标题时，具体用于：获取标题预选集，标题预选集内包括至少一个候选标题；计算各候选标题的标题特征表达与歌单元数据的匹配度，其中，标题特征表达表征候选标题的多维度特征；基于各候选标题对应的匹配度，确定目标标题，并基于目标标题生成歌单标题。
根据本公开的一个或多个实施例，标题特征表达和歌单元数据包括相同的目标维度特征，生成模块在计算各候选标题的标题特征表达与歌单元数据的匹配度时，具体用于：基于目标维度特征，获得候选标题在目标维度特征下的第一特征值，以及目标歌单在目标维度特征下的第二特征值；基于第一特征值和第二特征值的加权距离，得到候选标题的标题特征表达与歌单元数据的匹配度。
根据本公开的一个或多个实施例，展示信息包括目标歌单对应的歌单标题和歌单封面，生成模块在生成目标歌单对应的展示信息时，具体用于：获取目标歌单的歌单元数据；根据目标歌单的歌单元数据，生成歌单封面；根据歌单封面，生成歌单标题。
根据本公开的一个或多个实施例，生成模块在根据歌单封面，生成歌单标题时，具体用于：根据歌单封面，确定标题空间，标题空间为歌单封面内用于渲染歌单标题的区域；基于标题空间的大小，生成歌单标题。
根据本公开的一个或多个实施例，生成模块在根据歌单封面，生成歌单标题时，具体用于：获取标题预选集，标题预选集包括至少一个候选标题；计算各候选标题的标题特征表达与歌单封面的封面特征表达的匹配度，其中，标题特征表达表征候选标题的多维度特征，封面特征表达表征歌单封面的多维度特征；基于各候选标题对应的匹配度，确定目标标题，并基于目标标题生成歌单标题。
根据本公开的一个或多个实施例，在获取目标歌单之后，生成模块还用于：检测目标歌单的有效歌单元数据；若检测到目标歌单的歌单元数据，则基于有效歌单元数据，生成目标歌单对应的展示信息；若未检测到目标歌单的歌单元数据，则基于待播放歌曲的歌单元数据，生成目标歌单的歌单元数据。
根据本公开的一个或多个实施例，生成模块在检测目标歌单的有效歌单元数据时，具体用于：获取目标歌单内各待播放歌曲的至少两个目标维度特征；若针对每一目标维度特征，特征值相同的待播放歌曲的比例均大于与目标维度特征对应的比例阈值，则确 定检测到目标歌单的有效歌单元数据。
第三方面，根据本公开的一个或多个实施例，提供了一种电子设备，包括：处理器，以及与所述处理器通信连接的存储器；
所述存储器存储计算机执行指令；
所述处理器执行所述存储器存储的计算机执行指令，以实现如上第一方面以及第一方面各种可能的设计所述的歌单展示信息生成方法。
第四方面，根据本公开的一个或多个实施例，提供了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，实现如上第一方面以及第一方面各种可能的设计所述的歌单展示信息生成方法。
第五方面，根据本公开的一个或多个实施例，提供了一种计算机程序产品，包括计算机程序，所述计算机程序被处理器执行时实现如上第一方面以及第一方面各种可能的设计所述的歌单展示信息生成方法。
第六方面，根据本公开的一个或多个实施例，提供了一种计算机程序，所述计算机程序被处理器执行时实现如上第一方面以及第一方面各种可能的设计所述的歌单展示信息生成方法。
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 (18)

  1. 一种歌单展示信息生成方法，包括：
    获取目标歌单，所述目标歌单内包括至少一首待播放歌曲；
    生成所述目标歌单对应的展示信息，其中，所述展示信息是基于所述目标歌单的歌单元数据生成的，所述歌单元数据表征所述至少一首待播放歌曲的多维度特征，所述展示信息包括所述目标歌单对应的歌单标题和/或歌单封面。
  2. 根据权利要求1所述的方法，其中，所述展示信息包括所述目标歌单对应的歌单标题和歌单封面，其中，所述歌单封面与所述歌单标题相关。
  3. 根据权利要求1所述的方法，其中，所述生成所述目标歌单对应的展示信息，包括：
    获取所述目标歌单的歌单元数据；
    根据所述歌单元数据，生成歌单标题；
    根据所述歌单标题生成歌单封面。
  4. 根据权利要求3所述的方法，其中，所述获取所述目标歌单的歌单元数据，包括：
    获取所述目标歌单内的各待播放歌曲的歌曲特征表达，所述歌曲特征表达表征所述待播放歌曲的多维度特征；
    根据至少一个待播放歌曲的歌曲特征表达，生成所述目标歌单的歌单元数据。
  5. 根据权利要求4所述的方法，其中，所述待播放歌曲包括种子歌曲，根据至少一个待播放歌曲的歌曲特征表达，生成所述目标歌单的歌单元数据，包括：
    获取所述种子歌曲，并根据所述种子歌曲的歌曲特征表达，生成所述歌单元数据；
    其中，所述种子歌曲基于用户指令确定。
  6. 根据权利要求4所述的方法，其中，所述根据至少一个待播放歌曲的歌曲特征表达，生成所述目标歌单的歌单元数据，包括：
    基于至少两个所述待播放歌曲的歌曲特征表达进行加权平均，得到加权平均特征值；
    根据所述加权平均特征，生成所述目标歌单的歌单元数据。
  7. 根据权利要求3所述的方法，其中，所述根据所述歌单元数据，生成歌单标题，包括：
    获取标题预选集，所述标题预选集内包括至少一个候选标题；
    计算各所述候选标题的标题特征表达与所述歌单元数据的匹配度，其中，所述标题特征表达表征所述候选标题的多维度特征；
    基于各所述候选标题对应的匹配度，确定目标标题，并基于所述目标标题生成所述歌单标题。
  8. 根据权利要求7所述的方法，其中，所述标题特征表达和所述歌单元数据包括相同的目标维度特征，所述计算各所述候选标题的标题特征表达与所述歌单元数据的匹配度，包括：
    基于所述目标维度特征，获得所述候选标题在所述目标维度特征下的第一特征值，以及所述目标歌单在所述目标维度特征下的第二特征值；
    基于所述第一特征值和所述第二特征值的加权距离，得到所述候选标题的标题特征表达与歌单元数据的匹配度。
  9. 根据权利要求1所述的方法，其中，所述展示信息包括所述目标歌单对应的歌单标题和歌单封面，所述生成所述目标歌单对应的展示信息，包括：
    获取所述目标歌单的歌单元数据；
    根据所述目标歌单的歌单元数据，生成歌单封面；
    根据所述歌单封面，生成歌单标题。
  10. 根据权利要求9所述的方法，其中，所述根据所述歌单封面，生成歌单标题，包括：
    根据所述歌单封面，确定标题空间，所述标题空间为所述歌单封面内用于渲染所述歌单标题的区域；
    基于所述标题空间的大小，生成所述歌单标题。
  11. 根据权利要求9所述的方法，其中，所述根据所述歌单封面，生成歌单标题，包括：
    获取标题预选集，所述标题预选集包括至少一个候选标题；
    计算各所述候选标题的标题特征表达与所述歌单封面的封面特征表达的匹配度，其中，所述标题特征表达表征所述候选标题的多维度特征，所述封面特征表达表征所述歌单封面的多维度特征；
    基于各所述候选标题对应的匹配度，确定目标标题，并基于所述目标标题生成所述歌单标题。
  12. 根据权利要求1至11中任一项所述的方法，其中，在所述获取目标歌单之后，还包括：
    检测所述目标歌单的有效歌单元数据；
    若检测到所述目标歌单的歌单元数据，则基于所述有效歌单元数据，生成所述目标歌单对应的展示信息；
    若未检测到所述目标歌单的歌单元数据，则基于所述待播放歌曲的歌单元数据，生成所述目标歌单的歌单元数据。
  13. 根据权利要求12所述的方法，其中，所述检测所述目标歌单的有效歌单元数据，包括：
    获取目标歌单内各待播放歌曲的至少两个目标维度特征；
    若针对每一目标维度特征，特征值相同的待播放歌曲的比例均大于与目标维度特征对应的比例阈值，则确定检测到所述目标歌单的有效歌单元数据。
  14. 一种歌单展示信息生成装置，包括：
    获取模块，用于获取目标歌单，所述目标歌单内包括至少一首待播放歌曲；
    生成模块，用于生成所述目标歌单对应的展示信息，其中，所述展示信息是基于所述目标歌单的歌单元数据生成的，所述歌单元数据表征所述至少一首待播放歌曲的多维度特征，所述展示信息包括所述目标歌单对应的歌单标题和/或歌单封面。
  15. 一种电子设备，包括：处理器，以及与所述处理器通信连接的存储器；
    所述存储器存储计算机执行指令；
    所述处理器执行所述存储器存储的计算机执行指令，以实现如权利要求1至13中任一项所述的歌单展示信息生成方法。
  16. 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，实现如权利要求1至13中任一项所述的歌单展示信息生成方法。
  17. 一种计算机程序产品，包括计算机程序，所述计算机程序被处理器执行时实现权利要求1至13中任一项所述的歌单展示信息生成方法。
  18. 一种计算机程序，所述计算机程序被处理器执行时实现权利要求1至13中任一项所述的歌单展示信息生成方法。
PCT/CN2023/093667 2022-07-01 2023-05-11 歌单展示信息生成方法、装置、电子设备及存储介质 WO2024001545A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210774585.7 2022-07-01
CN202210774585.7A CN114943006A (zh) 2022-07-01 2022-07-01 歌单展示信息生成方法、装置、电子设备及存储介质

Publications (1)

Publication Number Publication Date
WO2024001545A1 true WO2024001545A1 (zh) 2024-01-04

Family

ID=82910252

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/093667 WO2024001545A1 (zh) 2022-07-01 2023-05-11 歌单展示信息生成方法、装置、电子设备及存储介质

Country Status (2)

Country Link
CN (1) CN114943006A (zh)
WO (1) WO2024001545A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114943006A (zh) * 2022-07-01 2022-08-26 北京字跳网络技术有限公司 歌单展示信息生成方法、装置、电子设备及存储介质
CN117850643A (zh) * 2022-09-30 2024-04-09 华为技术有限公司 一种系统、歌单生成方法以及电子设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060230331A1 (en) * 2005-04-07 2006-10-12 Microsoft Corporation Generating stylistically relevant placeholder covers for media items
CN107203624A (zh) * 2017-05-26 2017-09-26 维沃移动通信有限公司 一种歌单生成方法及移动终端
US10346470B1 (en) * 2014-01-20 2019-07-09 Beats Music, Llc Systems and methods for generating playlists in a music service
CN112989104A (zh) * 2021-03-17 2021-06-18 杭州网易云音乐科技有限公司 信息展示方法及装置、计算机可读存储介质、电子设备
CN114943006A (zh) * 2022-07-01 2022-08-26 北京字跳网络技术有限公司 歌单展示信息生成方法、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
US20060230331A1 (en) * 2005-04-07 2006-10-12 Microsoft Corporation Generating stylistically relevant placeholder covers for media items
US10346470B1 (en) * 2014-01-20 2019-07-09 Beats Music, Llc Systems and methods for generating playlists in a music service
CN107203624A (zh) * 2017-05-26 2017-09-26 维沃移动通信有限公司 一种歌单生成方法及移动终端
CN112989104A (zh) * 2021-03-17 2021-06-18 杭州网易云音乐科技有限公司 信息展示方法及装置、计算机可读存储介质、电子设备
CN114943006A (zh) * 2022-07-01 2022-08-26 北京字跳网络技术有限公司 歌单展示信息生成方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
CN114943006A (zh) 2022-08-26

Similar Documents

Publication Publication Date Title
WO2024001545A1 (zh) 歌单展示信息生成方法、装置、电子设备及存储介质
CN109543064B (zh) 歌词显示处理方法、装置、电子设备及计算机存储介质
WO2020233444A1 (zh) 在线文档插入信息方法及装置
WO2022089115A1 (zh) 图像分割方法、装置、设备及存储介质
WO2021135319A1 (zh) 基于深度学习的文案生成方法、装置及电子设备
WO2020107625A1 (zh) 视频分类方法、装置、电子设备及计算机可读存储介质
WO2022007565A1 (zh) 增强现实的图像处理方法、装置、电子设备及存储介质
WO2020244487A1 (zh) 彩蛋的展示方法、装置、电子设备和计算机可读存储介质
US20240143684A1 (en) Information presentation method and apparatus, and device and medium
WO2023088006A1 (zh) 云游戏交互方法、装置、可读介质和电子设备
CN110188782B (zh) 图像相似性确定方法、装置、电子设备及可读存储介质
CN111652675A (zh) 展示方法、装置和电子设备
CN112182255A (zh) 用于存储媒体文件和用于检索媒体文件的方法和装置
US20230315990A1 (en) Text detection method and apparatus, electronic device, and storage medium
CN113763931B (zh) 波形特征提取方法、装置、计算机设备及存储介质
CN112990176B (zh) 书写质量评价方法、装置和电子设备
WO2024001548A1 (zh) 歌单生成方法、装置、电子设备及存储介质
CN113835948A (zh) 温度检测方法、温度检测装置及电子设备
WO2023061229A1 (zh) 视频生成方法及设备
WO2022213801A1 (zh) 视频处理方法、装置及设备
CN112492399A (zh) 信息显示方法、装置及电子设备
CN110222590B (zh) 图像差异判断方法、装置及电子设备
CN114066721B (zh) 显示方法、装置和电子设备
CN111461227B (zh) 样本生成方法、装置、电子设备和计算机可读介质
CN114625876B (zh) 作者特征模型的生成方法、作者信息处理方法和装置

Legal Events

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

Ref document number: 23829731

Country of ref document: EP

Kind code of ref document: A1