CN108205536B - Song list generation method and device - Google Patents
Song list generation method and device Download PDFInfo
- Publication number
- CN108205536B CN108205536B CN201611169320.5A CN201611169320A CN108205536B CN 108205536 B CN108205536 B CN 108205536B CN 201611169320 A CN201611169320 A CN 201611169320A CN 108205536 B CN108205536 B CN 108205536B
- Authority
- CN
- China
- Prior art keywords
- song
- growth rate
- score
- songs
- label
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
Images
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
- G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/686—Retrieval 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
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)
- Reverberation, Karaoke And Other Acoustics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention relates to a song list generation method and device. The method comprises the following steps: determining at least one label, wherein each label is used for identifying a song attribute, each song attribute corresponds to at least one song, each song corresponds to a score, and the score is calculated according to the heat of the song corresponding to the score; and selecting a first set number of songs from the plurality of songs corresponding to the at least one tag to generate a song list according to the scores of the plurality of songs corresponding to the at least one tag. The method and the device realize that the song list can be generated more accurately and conveniently based on the historical data of the songs listened by the user and the tags added to the songs.
Description
Technical Field
The invention relates to the technical field of audio data processing, in particular to a song list generation method and device.
Background
A music station refers to an online music broadcasting station application, which can recommend different music according to different themes for songs of different styles and types. Wherein the categories are mood, theme, crowd, scene, singer, musical instrument, language, music, and so on. In this way, the user can select a plurality of pieces of music suitable for the current time and place to enjoy through one operation, and therefore, the user is more and more favored.
However, the song list of the radio station is screened from the song library, and the problems that the sorting precision is not high or the manual screening is time-consuming and labor-consuming exist.
Disclosure of Invention
The embodiment of the invention provides a song list generation method and device. The method and the device realize that the song list can be generated more accurately and conveniently based on the historical data of the songs listened by the user and the tags added to the songs.
In one aspect, an embodiment of the present invention provides a method for generating a song list. The method comprises the following steps:
determining at least one label, wherein each label is used for identifying a song attribute, each song attribute corresponds to at least one song, each song corresponds to a score, and the score is calculated according to the heat of the song corresponding to the score;
and selecting a first set number of songs from the plurality of songs corresponding to the at least one tag to generate a song list according to the scores of the plurality of songs corresponding to the at least one tag.
Optionally, the song list is associated with the at least one tag, the method further comprising:
determining a second set number of songs with later scores in the song list and the second set number of songs with later scores, which are not contained in the song list, corresponding to the at least one label;
deleting the second set number of songs with the later scores from the song list, and increasing the second set number of songs with the later scores.
Optionally, the score is obtained by calculating according to the popularity of the song corresponding to the score, and the score includes:
counting the daily playing amount, comment number, praise number, collection number, download number and search number of the songs;
and respectively multiplying the playing growth rate, the comment growth rate, the like growth rate, the collection growth rate, the download growth rate and the search growth rate of the song by weights to obtain the score.
Optionally, the score comprises at least one or more of:
daily score, weekly score, monthly score, seasonal score, and yearly score.
Optionally, the weight corresponding to the play growth rate is 65, the weight corresponding to the comment growth rate is 5, the weight corresponding to the like growth rate is 5, the weight corresponding to the collection growth rate is 5, the weight corresponding to the download growth rate is 10, and the weight corresponding to the search growth rate is 10.
In another aspect, an embodiment of the present invention provides a song list generating apparatus. The method comprises the following steps:
the system comprises a first determining unit, a second determining unit and a searching unit, wherein the first determining unit is used for determining at least one label, each label is used for identifying one song attribute, each song attribute corresponds to at least one song, each song corresponds to a score, and the score is obtained by calculation according to the heat of the song corresponding to the score;
and the generating unit is used for selecting a first set number of songs from the plurality of songs corresponding to the at least one label to generate a song list according to the scores of the plurality of songs corresponding to the at least one label.
Optionally, the method further comprises:
a second determining unit, configured to determine a second set number of songs that are scored later in the song list, and the second set number of songs that are not included in the song list and that correspond to the at least one tag;
and the updating unit is used for deleting the second set number of songs with the later scores from the song list and increasing the second set number of songs with the later scores.
Optionally, the method further comprises:
the statistical unit is used for counting the daily playing amount, comment number, praise number, collection number, download number and search number of the songs;
and the calculating unit is used for multiplying the playing growth rate, the comment growth rate, the like growth rate, the collection growth rate, the download growth rate and the search growth rate of the song by the weight respectively to obtain the score.
Optionally, the score comprises at least one or more of:
daily score, weekly score, monthly score, seasonal score, and yearly score.
Optionally, the weight corresponding to the play growth rate is 65, the weight corresponding to the comment growth rate is 5, the weight corresponding to the like growth rate is 5, the weight corresponding to the collection growth rate is 5, the weight corresponding to the download growth rate is 10, and the weight corresponding to the search growth rate is 10.
According to the embodiment of the invention, the song list can be generated more accurately and conveniently based on the historical data of the songs listened by the user and the tags added to the songs. The song list can be updated more accurately and conveniently according to the song listening history data of the user and the tags of the songs, and the user experience is higher.
Drawings
Fig. 1 is a flowchart of a song list generation method according to an embodiment of the present invention;
FIG. 2 provides an example of an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a song list generation apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Embodiments of the present invention associate each station with one or more tags by tagging songs and scoring them. And when the song list is generated, the songs corresponding to one or more labels associated with the radio station are screened according to the scores to obtain the song list. The classification precision is high, and is efficient. Meanwhile, the scores of the songs are obtained by counting the daily playing amount, the number of comments, the number of praise, the number of collections, the number of downloads and the number of searches, so that the popularity of the songs can be reflected more accurately.
For the purpose of facilitating understanding of the embodiments of the present invention, the following description will be further explained with reference to specific embodiments, which are not to be construed as limiting the embodiments of the present invention.
Fig. 1 is a flowchart of a song list generation method according to an embodiment of the present invention. As shown in fig. 1, the method specifically includes:
s110, determining at least one label, wherein each label is used for identifying one song attribute, each song attribute corresponds to at least one song, each song corresponds to a score, and the score is calculated according to the heat of the song corresponding to the score;
each song is tagged (tag) when it is entered into the library, which is used to identify attributes such as the genre or genre of the song. For example, the song "I am a little bird" may have the added tags: inspirations, rock and roll, and get up, etc.
The tag may be obtained by analyzing the identification information in the song file, for example, by analyzing the ID3 information in the MP3 file.
It can also be determined by big data analysis according to the behavior habit of the user, for example, the songs frequently listened to by the user while running can be counted, and further, the data can be obtained by combining with the sports software.
It can also be added manually. Specifically, the song without the added tag can be pushed to the user, the user adds the tag to the song according to the common knowledge of the user, and one or more tags with more adding times are selected as the tag of the song through statistics.
Each station may be associated with one or more tags. For example, the theme is a station for work, and the labels that can be associated with it may be piano music, light music, work and relax, and so on.
Songs may be scored according to song popularity, which may include any one or more of a daily score, a weekly score, a monthly score, a seasonal score, and an annual score.
Wherein the score can be calculated as shown in fig. 2, as described below.
And counting the daily playing amount, the number of comments, the number of praises, the number of collections, the number of downloads, the number of searches and the like of the songs based on the song playing log of the client.
The above data for each song is summarized by nature.
Daily growth rate, weekly growth rate, monthly growth rate, and seasonal growth rate of the popularity of the song are calculated, taking the play volume as an example.
The daily growth rate is calculated in a mode of (D2-D1)/D1, D1 is the song playing amount of the previous day, and D2 is the song playing amount of the current day;
the week growth rate is calculated in a mode of (W2-W1)/W1, wherein W1 is the song playing amount of the last week, and W2 is the song playing amount of the last week;
the monthly growth rate is calculated in the mode of (M2-M1)/M1, M1 is the song playing amount of the latest month, and M2 is the song monthly playing amount of the previous month;
the season growth rate is calculated as (Q2-Q1)/Q1, Q1 is the song playing volume in the latest season, and Q2 is the song playing volume in the previous season;
similarly, the number of comments, the number of praise, the number of collections, the number of downloads and the growth rate of the number of searches are calculated, and then the data are weighted and summed to calculate the total score, wherein the weighted and summed calculation mode is as follows:
song score (song play growth rate + comment growth rate + weight + praise growth rate + weight of collection growth rate + weight of download growth rate + weight of search growth rate)/100
The weights are adjustable and are configured as shown in table 1.
TABLE 1
| Parameter(s) | Weight of |
| Play volume growth rate | 65 |
| Rate of increase of number of comments | 5 |
| Growth rate of praise | 5 |
| Percentage increase of collection | 5 |
| Download number growth rate | 10 |
| Search number growth rate | 10 |
| … | … |
For example, the growth rate of playing, the growth rate of commenting, the growth rate of praise, the growth rate of collecting, the growth rate of downloading and the growth rate of searching are respectively 150%, 10%, 20%, 5%, 20% and 15% of a certain song according to monthly statistics. The result is calculated by weight:
(150％*65+10％*5+20％*5+5％*5+20％*10+15％*10)/100＝1.0275。
wherein the daily score, the weekly score, the monthly score, the seasonal score and the annual score are calculated according to the daily growth rate, the weekly growth rate, the monthly growth rate, the seasonal growth rate and the annual growth rate respectively.
In the embodiment of the invention, the time and the times of song cutting of the user can be counted, wherein the time of song cutting can be counted in a percentage mode. For example, the number of times a song is cut 50% before the song is played may be counted.
And calculating the growth rate according to the song cutting time and the times, and subtracting the growth rate of the song cutting multiplied by the weight when calculating the final score. And the statistical song-cutting times can be multiplied by the weight corresponding to the song-cutting time. For example, the total number of song-cutting times is 1/the first song-cutting time (percentage) + … … 1/the nth song-cutting time.
And S120, selecting a first set number of songs from the plurality of songs corresponding to the at least one tag to generate a song list according to the scores of the plurality of songs corresponding to the at least one tag.
The scores of the songs corresponding to at least one label can be ranked from large to small, and a first set number of songs with higher scores are selected to generate a song list.
At least one label corresponding to the radio station can also be assigned with a weight, the scores of a plurality of songs can be multiplied by the weight and then ranked, and the weight can be determined according to the relevance of the label and the radio station theme. For example, the theme is a station for work, and its associated tags may be piano music, soft music, work, and relax. Wherein, the weights corresponding to the piano music, the soft music, the work and the relax tags can be respectively 80%, 90%, 95% and 85%.
According to the embodiment of the invention, the song list can be generated more accurately and conveniently based on the historical data of the songs listened by the user and the tags added to the songs.
In another embodiment, the songs in the song list can be updated, the interval time for updating the song list can be flexibly adjusted, and corresponding growth rate weights are respectively applied to score according to weekly, monthly and quarterly updating.
The following list update is further described with reference to specific steps.
S130 determines a second set number of songs from the song list after the score, and the second set number of songs from the song list after the score that is not included in the at least one tag.
S140, deleting the second set number of songs with the later scores from the song list, and increasing the second set number of songs with the later scores.
In one example, taking monthly update as an example, after the score of each song is obtained, the 5% of the songs with the lowest score in a certain type of radio station songs are screened out and replaced by the same type of songs with the highest score and which are not in the current radio station song list.
For example, in a station labeled "light music", there are 20 million songs in the song library in the monthly song score, and 1000 "light music" played in the station. After the statistics of the scores, the later 5% of the scores in the station, namely 50 songs with the scores at the top are replaced to complete the updating.
The song list updating period can be configured, and the configuration period can be updated according to one or more of the period of week, month, quarter and year. And when the song list is updated in a plurality of updating periods, updating according to the updating mode corresponding to the larger updating period when the updating condition of the larger updating period is reached.
For example, when the song list is selected to be updated according to the week and the month as the update period, when the month update period and the week update period are reached at the same time, the song list may be updated according to the calculation manner of the month update period. The data of the larger updating period is more comprehensive, the calculated result is more accurate, the smaller updating period has more real-time performance, and the advantages of both the larger updating period and the smaller updating period can be considered for updating by adopting various updating period modes.
Therefore, when a user selects a radio station, the song list corresponding to the radio station can be played.
According to the embodiment of the invention, the song list can be updated more accurately and conveniently according to the song listening history data of the user and the tags of the songs, and the user experience is higher.
Fig. 3 is a schematic structural diagram of a song list generation apparatus according to an embodiment of the present invention. As shown in fig. 3, the apparatus specifically includes:
a first determining unit 301, configured to determine at least one tag, where each of the at least one tag is used to identify one song attribute, each song attribute corresponds to at least one song, each of the at least one song corresponds to a score, and the score is calculated according to a popularity of the song corresponding to the score;
a generating unit 302, configured to select, according to scores of multiple songs corresponding to the at least one tag, a first set number of songs from the multiple songs corresponding to the at least one tag to generate a song list.
Optionally, the method further comprises:
a second determining unit 303, configured to determine a second set number of songs that are scored later in the song list, and the second set number of songs that are not scored later and correspond to the at least one tag;
an updating unit 304, configured to delete the second set number of songs after the rating is later in the song list, and increase the second set number of songs after the rating is later.
Optionally, the method further comprises:
the statistical unit is used for counting the daily playing amount, comment number, praise number, collection number, download number and search number of the songs;
and the calculating unit is used for multiplying the playing growth rate, the comment growth rate, the like growth rate, the collection growth rate, the download growth rate and the search growth rate of the song by the weight respectively to obtain the score.
Optionally, the score comprises at least one or more of:
daily score, weekly score, monthly score, seasonal score, and yearly score.
Optionally, the weight corresponding to the play growth rate is 65, the weight corresponding to the comment growth rate is 5, the weight corresponding to the like growth rate is 5, the weight corresponding to the collection growth rate is 5, the weight corresponding to the download growth rate is 10, and the weight corresponding to the search growth rate is 10.
Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied in hardware, a software module executed by a processor, or a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only illustrative of the present invention and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the scope of the present invention should be included in the scope of the present invention.
Claims (8)
1. A song list generation method, comprising:
determining at least one label, wherein each label is used for identifying a song attribute, each song attribute corresponds to at least one song, each song corresponds to a score, and the score is calculated according to the heat of the song corresponding to the score;
assigning a weight to the at least one label, and ranking the scores of the plurality of songs corresponding to the at least one label by multiplying the weights of the labels corresponding to the plurality of songs; selecting a plurality of songs corresponding to the at least one label according to the sorting, wherein a song list is generated by a first set number of songs;
determining a second set number of songs with later scores in the song list and the second set number of songs with later scores, which are not contained in the song list, corresponding to the at least one label;
deleting the second set number of songs with the later scores from the song list, and increasing the second set number of songs with the later scores which are not contained in the song list.
2. The method of claim 1, wherein the score is calculated based on the popularity of the song to which the score corresponds and comprises:
counting the daily playing amount, comment number, praise number, collection number, download number and search number of the songs;
and respectively multiplying the playing growth rate, the comment growth rate, the like growth rate, the collection growth rate, the download growth rate and the search growth rate of the song by weights to obtain the score.
3. The method of claim 2, wherein the scoring comprises at least one or more of:
daily score, weekly score, monthly score, seasonal score, and yearly score.
4. The method according to claim 2, wherein the weight corresponding to the play growth rate is 65, the weight corresponding to the comment growth rate is 5, the weight corresponding to the like growth rate is 5, the weight corresponding to the favorite growth rate is 5, the weight corresponding to the download growth rate is 10, and the weight corresponding to the search growth rate is 10.
5. A song list generation apparatus, comprising:
the system comprises a first determining unit, a second determining unit and a searching unit, wherein the first determining unit is used for determining at least one label, each label is used for identifying one song attribute, each song attribute corresponds to at least one song, each song corresponds to a score, and the score is obtained by calculation according to the heat of the song corresponding to the score;
assigning a weight to the at least one label, and ranking the scores of the plurality of songs corresponding to the at least one label by multiplying the weights of the labels corresponding to the plurality of songs;
the generating unit is used for selecting a first set number of songs from a plurality of songs corresponding to the at least one label to generate a song list according to the sorting;
a second determining unit, configured to determine a second set number of songs that are scored later in the song list, and the second set number of songs that are not included in the song list and that correspond to the at least one tag;
and the updating unit is used for deleting the second set number of songs with the later scores in the song list and increasing the second set number of songs with the later scores, which are not contained in the song list.
6. The apparatus of claim 5, further comprising:
the statistical unit is used for counting the daily playing amount, comment number, praise number, collection number, download number and search number of the songs;
and the calculating unit is used for multiplying the playing growth rate, the comment growth rate, the like growth rate, the collection growth rate, the download growth rate and the search growth rate of the song by the weight respectively to obtain the score.
7. The apparatus of claim 6, wherein the score comprises at least one or more of:
daily score, weekly score, monthly score, seasonal score, and yearly score.
8. The apparatus according to claim 6, wherein the weight corresponding to the play growth rate is 65, the weight corresponding to the comment growth rate is 5, the weight corresponding to the like growth rate is 5, the weight corresponding to the favorite growth rate is 5, the weight corresponding to the download growth rate is 10, and the weight corresponding to the search growth rate is 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611169320.5A CN108205536B (en) | 2016-12-16 | 2016-12-16 | Song list generation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611169320.5A CN108205536B (en) | 2016-12-16 | 2016-12-16 | Song list generation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108205536A CN108205536A (en) | 2018-06-26 |
| CN108205536B true CN108205536B (en) | 2020-12-04 |
Family
ID=62602457
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611169320.5A Active CN108205536B (en) | 2016-12-16 | 2016-12-16 | Song list generation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108205536B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110458360B (en) * | 2019-08-13 | 2023-07-18 | 腾讯科技（深圳）有限公司 | Method, device, equipment and storage medium for predicting hot resources |
| CN112836082B (en) * | 2021-02-08 | 2023-01-10 | 咪咕音乐有限公司 | Method and device for generating song list, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103023971A (en) * | 2012-11-15 | 2013-04-03 | 广州酷狗计算机科技有限公司 | Information pushing method and system of music sharing radio stations |
| CN104077339A (en) * | 2013-07-09 | 2014-10-01 | 腾讯科技（深圳）有限公司 | Multimedia data user preference degree acquiring method, device and system |
| CN105915653A (en) * | 2016-06-24 | 2016-08-31 | 腾讯科技（深圳）有限公司 | Downloading method and device of media file |
| CN106227816A (en) * | 2016-07-22 | 2016-12-14 | 北京小米移动软件有限公司 | Push the method and device that song is single |
-
2016
- 2016-12-16 CN CN201611169320.5A patent/CN108205536B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103023971A (en) * | 2012-11-15 | 2013-04-03 | 广州酷狗计算机科技有限公司 | Information pushing method and system of music sharing radio stations |
| CN104077339A (en) * | 2013-07-09 | 2014-10-01 | 腾讯科技（深圳）有限公司 | Multimedia data user preference degree acquiring method, device and system |
| CN105915653A (en) * | 2016-06-24 | 2016-08-31 | 腾讯科技（深圳）有限公司 | Downloading method and device of media file |
| CN106227816A (en) * | 2016-07-22 | 2016-12-14 | 北京小米移动软件有限公司 | Push the method and device that song is single |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108205536A (en) | 2018-06-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107885745B (en) | Song recommendation method and device | |
| Knees et al. | Two data sets for tempo estimation and key detection in electronic dance music annotated from user corrections | |
| US8280889B2 (en) | Automatically acquiring acoustic information about music | |
| CN108304512B (en) | Video search engine coarse sorting method and device and electronic equipment | |
| CN107832437B (en) | Audio/video pushing method, device, equipment and storage medium | |
| CN102654860B (en) | Personalized music recommendation method and system | |
| US8548996B2 (en) | Ranking content items related to an event | |
| CN108021568B (en) | Singing bill recommendation method and device | |
| US20140180762A1 (en) | Systems and methods for customized music selection | |
| CN107977373B (en) | Song recommendation method | |
| US20140074884A1 (en) | Determining word information entropies | |
| JP5066963B2 (en) | Database construction device | |
| KR20040029452A (en) | Playlist generation, delivery and navigation | |
| JP5910316B2 (en) | Information processing apparatus, information processing method, and program | |
| Flexer et al. | Effects of album and artist filters in audio similarity computed for very large music databases | |
| CN111444380B (en) | Music search ordering method, device, equipment and storage medium | |
| CN111753124B (en) | Music recommendation method and server | |
| CN108205536B (en) | Song list generation method and device | |
| Caparrini et al. | Automatic subgenre classification in an electronic dance music taxonomy | |
| Hubáček et al. | Forty years of score-based soccer match outcome prediction: an experimental review | |
| CN107679236B (en) | Hot content pool maintenance method and device | |
| Chen et al. | Music recommendation based on multiple contextual similarity information | |
| CN113515663A (en) | Comment information display method and device, electronic equipment and storage medium | |
| CN108140034B (en) | Selecting content items based on received terms using a topic model | |
| CN106775567B (en) | Sound effect matching method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |