CN110647653A - Song recommendation method and device and computer storage medium - Google Patents

Song recommendation method and device and computer storage medium Download PDF

Info

Publication number
CN110647653A
CN110647653A CN201910944368.6A CN201910944368A CN110647653A CN 110647653 A CN110647653 A CN 110647653A CN 201910944368 A CN201910944368 A CN 201910944368A CN 110647653 A CN110647653 A CN 110647653A
Authority
CN
China
Prior art keywords
song
recommended
user
songs
matching degree
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.)
Pending
Application number
CN201910944368.6A
Other languages
Chinese (zh)
Inventor
李子豪
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Kugou Computer Technology Co Ltd
Original Assignee
Guangzhou Kugou Computer Technology Co Ltd
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 Guangzhou Kugou Computer Technology Co Ltd filed Critical Guangzhou Kugou Computer Technology Co Ltd
Priority to CN201910944368.6A priority Critical patent/CN110647653A/en
Publication of CN110647653A publication Critical patent/CN110647653A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/60Information retrieval; Database structures therefor; File system structures therefor of audio data
    • G06F16/63Querying
    • G06F16/635Filtering based on additional data, e.g. user or group profiles

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)

Abstract

The application discloses a song recommendation method and device and a computer storage medium, and belongs to the technical field of multimedia. The method comprises the following steps: when songs are required to be recommended by a user to be recommended, for a first history song in a plurality of history songs listened to by the user to be recommended, according to the recommended songs configured for the first history song by each reference user, determining the user matching degree of each recommended song, and according to the user matching degree of each recommended song, determining the recommended song of the first history song. The user matching degree may be used to indicate a matching degree between the user to be recommended and the reference user, and therefore, the song recommended for the first history song according to the user matching degree of each recommended song may be a recommended song manually configured by the reference user having a higher matching degree with the user to be recommended. And the subjective preferences of the two users with higher matching degree are generally consistent, so that the finally determined recommended song is more in line with the subjective preferences of the user to be recommended.

Description

Song recommendation method and device and computer storage medium
Technical Field
The present application relates to the field of multimedia technologies, and in particular, to a song recommendation method, an apparatus, and a computer storage medium.
Background
With the development of multimedia technology, more and more users listen to or download songs online through the internet. In addition, the server can also recommend songs to the user, so that the user can listen to the songs more conveniently. In this case, how to ensure that the songs recommended by the server meet the user's preferences has become one of the problems that needs to be solved currently.
In the related art, the server may determine a favorite category of the user to listen to the song according to the song that the user has listened to, and then recommend the song to the user according to the favorite category of the user to listen to the song. However, songs recommended in this way still have difficulty meeting the user's needs, thereby affecting the user's interest in listening to the songs.
Disclosure of Invention
The embodiment of the application provides a song recommendation method, a song recommendation device and a computer storage medium, which can enable recommended songs to meet the requirements of users better. The technical scheme is as follows:
in one aspect, a song recommendation method is provided, and the method includes:
for a first history song in a plurality of history songs listened to by a user to be recommended before the current time, acquiring a recommended song configured for the first history song by each reference user in a plurality of reference users to obtain a plurality of recommended songs corresponding to the plurality of reference users one by one, wherein the plurality of reference users are other users except the user to be recommended, and the first history song is any one of the plurality of history songs;
for a first recommended song in the plurality of recommended songs, determining the user matching degree of the first recommended song according to the user characteristics of the user to be recommended and the user characteristics of a first reference user corresponding to the first recommended song, wherein the first recommended song is any one of the plurality of recommended songs;
and determining the recommended songs of the first history songs according to the user matching degree of each first recommended song in the plurality of recommended songs.
Optionally, after obtaining the recommended song configured for the first history song by each of the multiple reference users, the method further includes:
determining the song matching degree of the first recommended song according to the first historical song;
correspondingly, the determining the recommendation list of the first history song according to the user matching degree of each first recommendation song in the plurality of recommendation songs includes:
and determining the recommended songs of the first historical songs according to the user matching degree and the song matching degree of each first recommended song in the plurality of recommended songs.
Optionally, the determining the recommended songs of the first history songs according to the user matching degree and the song matching degree of each first recommended song in the plurality of recommended songs includes:
for a first recommended song in the plurality of recommended songs, determining a recommended value of the first recommended song according to the user matching degree and the song matching degree of the first recommended song;
and determining a song recommendation list according to the recommendation value of each first recommended song in the plurality of recommended songs, wherein the recommendation value of the recommended song in the front ranking in the plurality of recommended songs included in the song recommendation list is greater than the recommendation value of the recommended song in the back ranking.
Optionally, the determining the recommendation value of the first recommended song according to the user matching degree and the song matching degree of the first recommended song includes:
and multiplying the user matching degree of the first recommended song and the song matching degree, or performing weighted addition on the user matching degree and the song matching degree of the first recommended song to obtain a recommended value of the first recommended song.
Optionally, the user characteristics of the first reference user include one or more of personal information of the first reference user, a historical song listening record of the first reference user, and an affinity between the first reference user and the user to be recommended.
Optionally, when the user characteristics of the first reference user include personal information of the first reference user, a historical song listening record of the first reference user, and an affinity between the first reference user and the user to be recommended, determining the user matching degree of the first recommended song according to the user characteristics of the user to be recommended and the user characteristics of the first reference user corresponding to the first recommended song includes:
determining a user similarity value of the first reference user according to the personal information of the user to be recommended and the personal information of the first reference user;
determining a historical song listening similarity value of the first reference user according to the historical song listening record of the user to be recommended and the historical song listening record of the first reference user;
determining the affinity value of the first reference user according to the affinity relationship between the user to be recommended and the first reference user;
and determining the user matching degree with the first recommended song according to the user similarity value of the first reference user, the historical song listening similarity value of the first reference user and the affinity value of the first reference user.
Optionally, the method further includes:
receiving a song recommendation request sent by the first reference user, wherein the song recommendation request carries a recommended song configured for the first historical song by the first reference user, a display interface of a terminal held by the first reference user comprises a song recommendation option, and the song recommendation request is triggered by the first reference user through the song recommendation option.
In another aspect, there is provided a song recommendation apparatus, the apparatus including:
the device comprises an acquisition module, a recommendation module and a recommendation module, wherein the acquisition module is used for acquiring a recommended song configured for a first historical song by each reference user in a plurality of reference users for the first historical song, and acquiring a plurality of recommended songs corresponding to the reference users one by one, the reference users are other users except for a user to be recommended, and the first historical song is any one of the plurality of historical songs;
the first determining module is used for determining the user matching degree of a first recommended song in the plurality of recommended songs according to the user characteristics of the user to be recommended and the user characteristics of a first reference user corresponding to the first recommended song, wherein the first recommended song is any one of the plurality of recommended songs;
and the second determination module is used for determining the recommended songs of the first history songs according to the user matching degree of each first recommended song in the plurality of recommended songs.
Optionally, the apparatus further comprises:
a third determining module, configured to determine a song matching degree of the first recommended song according to the first historical song;
accordingly, the second determining module comprises:
and the determining submodule is used for determining the recommended songs of the first historical songs according to the user matching degree and the song matching degree of each first recommended song in the plurality of recommended songs.
Optionally, the determining sub-module is configured to:
the first determining unit is used for determining a recommendation value of a first recommended song in the plurality of recommended songs according to the user matching degree and the song matching degree of the first recommended song;
and the second determining unit is used for determining a song recommendation list according to the recommendation value of each first recommended song in the plurality of recommended songs, wherein the recommendation value of the recommended song ranked at the front in the song recommendation list is greater than the recommendation value of the recommended song ranked at the back.
Optionally, the first determining unit is configured to:
and multiplying the user matching degree of the first recommended song and the song matching degree, or performing weighted addition on the user matching degree and the song matching degree of the first recommended song to obtain a recommended value of the first recommended song.
Optionally, the user characteristics of the first reference user include one or more of personal information of the first reference user, a historical song listening record of the first reference user, and an affinity between the first reference user and the user to be recommended.
Optionally, when the user characteristics of the first reference user include personal information of the first reference user, historical song listening records of the first reference user, and an affinity between the first reference user and the user to be recommended, the first determining module is configured to:
determining a user similarity value of the first reference user according to the personal information of the user to be recommended and the personal information of the first reference user;
a sixth determining module, configured to determine a historical song listening similarity value of the first reference user according to the historical song listening record of the user to be recommended and the historical song listening record of the first reference user;
determining the affinity value of the first reference user according to the affinity relationship between the user to be recommended and the first reference user;
and determining the user matching degree with the first recommended song according to the user similarity value of the first reference user, the historical song listening similarity value of the first reference user and the affinity value of the first reference user.
Optionally, the apparatus further comprises:
a receiving module, configured to receive a song recommendation request sent by the first reference user, where the song recommendation request carries a recommended song configured for the first history song by the first reference user, a display interface of a terminal held by the first reference user includes a song recommendation option, and the song recommendation request is triggered by the first reference user through the song recommendation option.
In another aspect, a song recommendation apparatus is provided that includes a processor and a memory for storing processor-executable instructions;
wherein the processor is configured to load the executable instructions and perform the aforementioned method of providing song recommendations.
In another aspect, a computer-readable storage medium is provided, having instructions stored therein, which when executed by a processor, implement the steps of the song recommendation method provided above.
The beneficial effects brought by the technical scheme provided by the embodiment of the application at least comprise:
in the embodiment of the application, since each reference user can manually configure the recommended song for a certain song, the recommended song configured by each reference user obviously conforms to the subjective preference of each reference user. In this case, when songs are required to be recommended by the user to be recommended, for a first history song in the plurality of history songs listened to by the user to be recommended, according to the recommended songs configured for the first history song by the respective reference users, the user matching degree of each recommended song is determined, and the recommended song of the first history song is determined according to the user matching degree of each recommended song. The user matching degree can be used for indicating the matching degree between the user to be recommended and the reference user, and therefore the song recommended for the first history song according to the user matching degree of each recommended song can be a recommended song manually configured by the reference user with higher matching degree with the user to be recommended. And the subjective preferences of the two users with higher matching degree are generally consistent, so that the finally determined recommended song is more consistent with the subjective preference of the user to be recommended, the song recommendation method provided by the application is higher in accuracy, and the interest of the user in listening to the song is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is an architecture diagram of a song recommendation system according to an embodiment of the present application;
FIG. 2 is a flowchart of a song recommendation method provided by an embodiment of the present application;
FIG. 3 is a flow chart of another song recommendation method provided by an embodiment of the present application;
FIG. 4 is a schematic diagram of a display interface provided by an embodiment of the present application;
fig. 5 is a schematic structural diagram of a song recommending apparatus according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a server according to an embodiment of the present application.
Detailed Description
To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
Before explaining the embodiments of the present application in detail, a system architecture related to the embodiments of the present application will be described.
Fig. 1 is an architecture diagram of a song recommendation system according to an embodiment of the present application. As shown in fig. 1, the system includes a to-be-recommended client 101, a server 102, and a plurality of reference clients 103.
The user terminal 101 to be recommended may be connected to the server 102 in a wireless or wired manner for communication, and any one of the reference user terminals 103 may be connected to the server 102 in a wireless or wired manner for communication.
At present, a song application is usually installed on a device such as a mobile phone or a computer, and the server 102 may be a server corresponding to the song application. The user terminal 101 to be recommended and any reference user terminal 103 can be a mobile phone or a computer. The user side 101 to be recommended corresponds to a user to be recommended, and the user to be recommended refers to a user who needs to recommend songs through the server at the current time. Any reference user terminal 103 corresponds to a reference user, which refers to a user that the server needs to refer to when recommending songs to a user to be recommended.
The server 102 may obtain a historical song listening record of the user terminal 101 to be recommended, where the historical song listening record includes a plurality of historical songs. For the sake of convenience in the following description, any one of the plurality of history songs is referred to as a first history song. The server 102 may obtain, by each reference user terminal 103 of the plurality of reference user terminals 103, a recommended song configured for the first history song by the corresponding reference user, and recommend a song for the first history song according to the obtained recommended song. Wherein, recommending songs for the first history song according to the obtained recommended songs will be described in detail in the following embodiments, which will not be explained first.
Fig. 2 is a flowchart of a song recommendation method according to an embodiment of the present application, where the song recommendation method may include the following steps:
step 201: the server acquires recommended songs configured for the first history songs by each reference user in a plurality of reference users for the first history songs in the plurality of history songs listened to by the user to be recommended before the current time, and acquires a plurality of recommended songs corresponding to the plurality of reference users one by one.
Step 202: the server determines the user matching degree of a first recommended song in the plurality of recommended songs according to the user characteristics of the user to be recommended and the user characteristics of a first reference user corresponding to the first recommended song.
Step 203: the server determines recommended songs of the first history songs according to the user matching degree of each first recommended song in the plurality of recommended songs.
In the embodiment of the application, since each reference user can manually configure the recommended song for a certain song, the recommended song configured by each reference user obviously conforms to the subjective preference of each reference user. In this case, when songs are required to be recommended by the user to be recommended, for a first history song in the plurality of history songs listened to by the user to be recommended, according to the recommended songs configured for the first history song by the respective reference users, the user matching degree of each recommended song is determined, and the recommended song of the first history song is determined according to the user matching degree of each recommended song. The user matching degree can be used for indicating the matching degree between the user to be recommended and the reference user, and therefore the song recommended for the first history song according to the user matching degree of each recommended song can be a recommended song manually configured by the reference user with higher matching degree with the user to be recommended. And the subjective preferences of the two users with higher matching degree are generally consistent, so that the finally determined recommended song is more consistent with the subjective preference of the user to be recommended, the song recommendation method provided by the application is higher in accuracy, and the interest of the user in listening to the song is improved.
Fig. 3 is a flowchart of another song recommendation method provided in an embodiment of the present application, and this embodiment illustrates that the song recommendation method is applied to a server, where the song recommendation method may include the following steps:
step 301: and for a first history song in the plurality of history songs listened to by the user to be recommended before the current time, acquiring a recommended song configured for the first history song by each reference user in the plurality of reference users, and acquiring a plurality of recommended songs corresponding to the plurality of reference users one by one.
When a user to be recommended needs to recommend songs through the server, a user side corresponding to the user to be recommended sends a recommended song obtaining request to the server, and the recommended song obtaining request carries a plurality of historical songs listened by the user to be recommended before the current time. The server may recommend songs based on each of the plurality of history songs so that the recommended songs can meet the user's needs.
Steps 301 to 304 are explained by the server for recommending songs for a first history song, and all implementations of the server for recommending other history songs can refer to the first history song, which is not explained herein.
The first history song is any one of a plurality of history songs listened to by the user to be recommended before, and the plurality of history songs are all songs listened to by the user to be recommended through the song application program in a reference time period before the current time. The reference time period may be set for the server. For example, the reference time period may be one week or one month.
In addition, the recommended songs configured for the first history song by each of the plurality of reference users are configured before the current time of the respective reference user. The implementation manner of referring to the user configuration recommended songs may be: for a first reference user of the multiple reference users, as shown in fig. 4, a display interface of a terminal held by the first reference user includes a song recommendation option, and when the first reference user needs to configure a recommended song for a first history song, the first reference user may trigger a song recommendation request through the song recommendation option, where the song recommendation request carries the recommended song configured by the first reference user for the first history song. And the user side corresponding to the first reference user sends the song recommendation request to the server, and the server receives the song recommendation request sent by the first reference user. The aforementioned song recommendation options may also be referred to as song recommendation entries.
After receiving the song recommendation request sent by the first reference user, the server can store the recommended songs configured for the first history songs by the first reference user. When a plurality of reference users configure recommended songs for the first history song, a plurality of recommended songs aiming at the first history song are stored in the server, and the recommended songs are in one-to-one correspondence with the reference users. When different reference users configure the recommended songs for different songs, the server stores the recommended songs for each of the plurality of songs. Therefore, when the server needs to recommend songs for the first history song, the recommended songs for the first history song can be obtained from the stored recommended songs for each of the plurality of songs, resulting in the plurality of recommended songs in step 301.
For example, when the current server needs to recommend a song for li, the server obtains all the history songs listened to in a week before the current time of li, and selects any one of the history songs as the first history song, which may be song xx. The reference users stored in the server sequentially include a recommended song 1, a recommended song 2, a recommended song 3, a recommended song 4, a recommended song 5, a recommended song 6, a recommended song 7, a recommended song 8, a recommended song 9, and a recommended song 10 for the xxxmiummended recommended song. The 10 reference users corresponding to the 10 recommended songs are user 1, user 2, user 3, user 4, user 5, user 6, user 7, user 8, user 9, and user 10, respectively.
Step 302: and for a first recommended song in the plurality of recommended songs, determining the user matching degree of the first recommended song according to the user characteristics of the user to be recommended and the user characteristics of a first reference user corresponding to the first recommended song.
The user matching degree of the first recommended song refers to the degree of similarity between the user characteristics of the first reference user and the user characteristics of the user to be recommended. The user characteristics comprise one or more of personal information of the first reference user, historical song listening records of the first reference user, and intimacy between the first reference user and the user to be recommended. Thus, step 302 can be implemented by at least the following three possible implementations.
(1) When the user characteristics of the first reference user include personal information of the first reference user, a historical song listening record of the first reference user, and an affinity between the first reference user and the user to be recommended, the implementation process of step 302 may be: determining a user similarity value of a first reference user according to the personal information of the user to be recommended and the personal information of the first reference user; determining a historical song listening similarity value of a first reference user according to the historical song listening record of the user to be recommended and the historical song listening record of the first reference user; determining the affinity value of a first reference user according to the affinity relationship between the user to be recommended and the first reference user; and determining the user matching degree of the first recommended song according to the user similarity value of the first reference user, the historical song listening similarity value of the first reference user and the intimacy value of the first reference user.
The user similarity value is used for indicating the similarity degree of the personal information of the first reference user and the personal information of the user to be recommended. The personal information may include age, region, hobbyist, personality label, etc. For example, the personal information of the user to be recommended including a certain personal information may be: age "20", hobbyist "zhouxixx", territory "xx province", personality label "homeman".
The historical song listening similarity value is used for indicating the similarity degree of the song characteristics in the historical song listening record of any reference user and the song characteristics in the historical song listening record of the user to be recommended. Song characteristics include the melody of the song, the artist of the song, etc.
The intimacy between the user to be recommended and the first reference user is used for indicating the intimacy degree between the user to be recommended and the first reference user. The intimate relationship may include whether the user to be recommended and the first reference user are in a friend relationship.
In addition, the determining of the user similarity value of the first reference user according to the personal information of the user to be recommended and the personal information of the first reference user may be determined by a first model. The first model is used to determine a similarity value between different personal information. That is, when different personal information is input to the first model, the first model may output a similarity between the two personal information, which may be a user similarity value between the two personal information. The first model may be pre-trained by the server, or may be obtained by the server from a database.
In addition, the determining of the historical song listening similarity value of the first reference user according to the historical song listening record of the user to be recommended and the historical song listening record of the first reference user can also be determined through the trained second model. The second model is used for determining similarity values among different historical song listening records. That is, when different historical song listening records are input to the second model, the second model can output the similarity between the two historical song listening records, and the similarity can be used as the similarity value of the historical songs between the two historical song listening records. The second model may be pre-trained by the server, or may be obtained from the database by the server.
In addition, according to the affinity relationship between the user to be recommended and the first reference user, the implementation manner of determining the affinity value of the first reference user may be: when the recommendation user and the first reference user are in a friend relationship, the intimacy value of the first reference user may be a first intimacy value, and when the recommendation user and the first reference user are not in a friend relationship, the intimacy value of the first reference user may be a second intimacy value. Wherein the first affinity value is greater than the second affinity value. For example, the first affinity is 100 and the second affinity is 5. In addition, the server may also determine the affinity value of the first reference user in other manners, which is not specifically limited in this embodiment of the application.
After the server determines the user similarity value of the first reference user, the historical song listening similarity value of the first reference user and the affinity value of the first reference user, the user matching degree of the first recommended song can be determined according to the user similarity value of the first reference user, the historical song listening similarity value of the first reference user and the affinity value of the first reference user.
In a possible implementation manner, the user similarity value of the first reference user, the historical song listening similarity value of the first reference user, and the intimacy value of the first reference user may be directly added or weighted added, and the obtained numerical value is the user matching degree of the first recommended song.
In another possible implementation manner, the user similarity value of the first reference user, the historical song listening similarity value of the first reference user, and the intimacy value of the first reference user may also be directly multiplied, and the obtained numerical value is the user matching degree of the first recommended song.
In another possible implementation manner, the server may preset a corresponding relationship between the numerical range and the user matching degree, and at this time, after the server may perform numerical operation on the user similarity value of the first reference user, the historical singing similarity value of the first reference user, and the intimacy value of the first reference user, the user matching degree corresponding to the numerical value obtained after the numerical operation may be searched according to the corresponding relationship between the numerical range and the user matching degree. The aforementioned numerical operation may be addition, weighted addition, or phase, etc.
For example, the preset corresponding relationship between the numerical range and the user matching degree is as follows: the user matching degree corresponding to the numerical range [0-100 ] is S1, the user matching degree corresponding to the numerical range [ 100-. If the value obtained by performing numerical operation on the user similarity value of the first reference user, the historical listening song similarity value of the first reference user, and the intimacy value of the first reference user is 260, the user matching degree of the first recommended song is S3.
(2) When the user characteristics of the first reference user include both the personal information of the first reference user and the affinity between the first reference user and the user to be recommended, the implementation process of step 302 may be: determining a user similarity value of a first reference user according to the personal information of the user to be recommended and the personal information of the first reference user; determining the affinity value of a first reference user according to the affinity relationship between the user to be recommended and the first reference user; and determining the user matching degree of the first recommended song according to the user similarity value of the first reference user and the affinity value of the first reference user.
(3) When the user characteristics of the first reference user include the historical song listening record of the first reference user and the affinity between the first reference user and the user to be recommended, the implementation process of step 302 may be: determining a historical song listening similarity value of a first reference user according to the historical song listening record of the user to be recommended and the historical song listening record of the first reference user; determining the affinity value of a first reference user according to the affinity relationship between the user to be recommended and the first reference user; and determining the user matching degree of the first recommended song according to the historical song listening similarity value of the first reference user and the affinity value of the first reference user.
The implementation processes of determining the user similarity value, the historical song listening similarity value, the intimacy value and the user matching degree in the implementation manners (2) and (3) can refer to the implementation manner (1), and are not elaborated herein.
In addition, when the user characteristics of the first reference user include other types of information, the user matching degree of the first recommended song can be determined by referring to the three implementation manners described above, and will not be elaborated herein again.
Step 303: and determining the song matching degree of the first recommended song according to the first historical song.
The song matching degree is used to indicate the degree of similarity between two songs. Therefore, in one possible implementation manner, the implementation procedure of step 303 is: a song match score between the first recommended song and the first historical song is determined based on the mixed music feature model.
Wherein, the mixed music characteristic model is a model for detecting music similarity. When two pieces of audio are input to the mixed music feature model, the mixed music feature model can analyze the two pieces of audio and output a similarity, and the similarity can be used as the song matching degree of the two pieces of audio. In addition, the mixed music feature model may be obtained by training in advance by the server, or may be obtained from a database by the server, and will not be described in detail herein.
Step 304: and determining the recommended songs of the first historical songs according to the user matching degree and the song matching degree of each first recommended song in the plurality of recommended songs.
In one possible implementation manner, the implementation procedure of step 304 may be: and for a first recommended song in the plurality of recommended songs, determining a recommended value of the first recommended song according to the user matching degree and the song matching degree of the first recommended song. And determining a song recommendation list according to the recommendation value of each first recommended song in the plurality of recommended songs, wherein the recommendation value of the recommended song in the front ranking in the plurality of recommended songs included in the song recommendation list is greater than the recommendation value of the recommended song in the back ranking.
The song recommendation list may include one recommendation song with the largest recommendation value, or may include a plurality of recommendation songs with the highest recommendation values. That is, the song recommendation list presented to the user to be recommended may include one recommendation song or may include a plurality of recommendation songs.
In the implementation manner, the songs recommended as the first history songs are displayed to the user to be recommended in a song recommendation list mode. Optionally, after determining the recommendation value of each recommendation song in the plurality of recommendation songs, the server may also recommend a song to the user to be recommended in other manners. For example, a recommended song with the largest recommendation value is directly pushed to the user to be recommended, and the description is not repeated here.
In addition, in a possible implementation manner, the implementation process of determining the recommended value of the first recommended song according to the user matching degree and the song matching degree of the first recommended song includes: and for a first recommended song in the plurality of recommended songs, multiplying the user matching degree and the song matching degree of the first recommended song to obtain a recommended value of the first recommended song.
In another possible implementation manner, the implementation process of determining the recommendation value of the first recommended song according to the user matching degree and the song matching degree of the first recommended song includes: and for a first recommended song in the plurality of recommended songs, carrying out weighted addition on the user matching degree and the song matching degree of the first recommended song to obtain a recommended value of the first recommended song. The server sets a weight for the user matching degree and the song matching degree respectively, so that the user matching degree and the song matching degree of the first recommended song can be weighted and added according to the two weights subsequently.
Step 304 is to determine a recommended song for the first history song based on the user matching degree and the song matching degree for each recommended song of the plurality of recommended songs. In addition, when the song recommendation method according to the embodiment of the application is applied, the recommended song of the first history song may be determined only according to the user matching degree of each recommended song in the plurality of recommended songs, and details are not described here.
In the embodiment of the application, since each reference user can manually configure the recommended song for a certain song, the recommended song configured by each reference user obviously conforms to the subjective preference of each reference user. In this case, when songs are required to be recommended by the user to be recommended, for a first history song in the plurality of history songs listened to by the user to be recommended, according to the recommended songs configured for the first history song by the respective reference users, the user matching degree of each recommended song is determined, and the recommended song of the first history song is determined according to the user matching degree of each recommended song. The user matching degree can be used for indicating the matching degree between the user to be recommended and the reference user, and therefore the song recommended for the first history song according to the user matching degree of each recommended song can be a recommended song manually configured by the reference user with higher matching degree with the user to be recommended. And the subjective preferences of the two users with higher matching degree are generally consistent, so that the finally determined recommended song is more consistent with the subjective preference of the user to be recommended, the song recommendation method provided by the application is higher in accuracy, and the interest of the user in listening to the song is improved.
Fig. 5 is a schematic structural diagram of a song recommending apparatus provided in an embodiment of the present application, where the song recommending apparatus may be implemented by software, hardware, or a combination of the two. The song recommending apparatus may include:
an obtaining module 501, configured to obtain, for a first history song of multiple history songs listened to by a user to be recommended before the current time, a recommended song configured for the first history song by each reference user of multiple reference users to obtain multiple recommended songs corresponding to the multiple reference users one to one, where the multiple reference users are other users except the user to be recommended, and the first history song is any one of the multiple history songs;
a first determining module 502, configured to determine, for a first recommended song of the multiple recommended songs, a user matching degree of the first recommended song according to a user characteristic of a user to be recommended and a user characteristic of a first reference user corresponding to the first recommended song, where the first recommended song is any one of the multiple recommended songs;
the second determining module 503 is configured to determine recommended songs of the first history song according to the user matching degree of each first recommended song in the plurality of recommended songs.
Optionally, the apparatus 500 further comprises:
the third determining module is used for determining the song matching degree of the first recommended song according to the first historical song;
accordingly, the second determining module comprises:
and the determining submodule is used for determining the recommended songs of the first historical song according to the user matching degree and the song matching degree of each first recommended song in the plurality of recommended songs.
Optionally, the determining submodule is configured to:
the first determining unit is used for determining a recommendation value of a first recommended song in the plurality of recommended songs according to the user matching degree and the song matching degree of the first recommended song;
and the second determining unit is used for determining a song recommendation list according to the recommendation value of each first recommended song in the plurality of recommended songs, wherein the recommendation value of the recommended song in the front ranking in the plurality of recommended songs included in the song recommendation list is greater than the recommendation value of the recommended song in the back ranking.
Optionally, the first determining unit is configured to:
and multiplying the user matching degree of the first recommended song and the song matching degree, or weighting and adding the user matching degree of the first recommended song and the song matching degree to obtain a recommended value of the first recommended song.
Optionally, the user characteristics of the first reference user include one or more of personal information of the first reference user, a historical song listening record of the first reference user, and an affinity between the first reference user and the user to be recommended.
Optionally, when the user characteristics of the first reference user include personal information of the first reference user, a historical song listening record of the first reference user, and an affinity between the first reference user and the user to be recommended, the first determining module is configured to:
determining a user similarity value of a first reference user according to the personal information of the user to be recommended and the personal information of the first reference user;
the sixth determining module is used for determining the historical song listening similarity value of the first reference user according to the historical song listening record of the user to be recommended and the historical song listening record of the first reference user;
determining the affinity value of a first reference user according to the affinity relationship between the user to be recommended and the first reference user;
and determining the user matching degree of the first recommended song according to the user similarity value of the first reference user, the historical song listening similarity value of the first reference user and the intimacy value of the first reference user.
Optionally, the apparatus further comprises:
the receiving module is used for receiving a song recommendation request sent by a first reference user, the song recommendation request carries recommended songs configured for the first historical song by the first reference user, a display interface of a terminal held by the first reference user comprises song recommendation options, and the song recommendation request is triggered by the first reference user through the song recommendation options.
In the embodiment of the present application, since each reference user may manually configure a recommended song for a certain song, the recommended song configured by each reference user obviously conforms to the subjective preference of each reference user. In this case, when songs are required to be recommended by the user to be recommended, for a first history song in the plurality of history songs listened to by the user to be recommended, according to the recommended songs configured for the first history song by the respective reference users, the user matching degree of each recommended song is determined, and the recommended song of the first history song is determined according to the user matching degree of each recommended song. The user matching degree can be used for indicating the matching degree between the user to be recommended and the reference user, and therefore the song recommended for the first history song according to the user matching degree of each recommended song can be a recommended song manually configured by the reference user with higher matching degree with the user to be recommended. And the subjective preferences of the two users with higher matching degree are generally consistent, so that the finally determined recommended song is more consistent with the subjective preference of the user to be recommended, the song recommendation method provided by the application is higher in accuracy, and the interest of the user in listening to the song is improved.
It should be noted that: in the song recommending device provided in the above embodiment, only the division of the functional modules is illustrated when recommending songs, and in practical applications, the function distribution may be completed by different functional modules according to needs, that is, the internal structure of the apparatus is divided into different functional modules to complete all or part of the functions described above. In addition, the song recommending device and the song recommending method provided by the above embodiments belong to the same concept, and the specific implementation process is described in the method embodiments in detail, which is not described herein again.
Fig. 6 is a schematic structural diagram of a server according to an embodiment of the present application. The server may be a server in a cluster of background servers. Specifically, the method comprises the following steps:
the server 600 includes a Central Processing Unit (CPU)601, a system memory 604 including a Random Access Memory (RAM)602 and a Read Only Memory (ROM)603, and a system bus 605 connecting the system memory 604 and the central processing unit 601. The server 600 also includes a basic input/output system (I/O system) 606, which facilitates the transfer of information between devices within the computer, and a mass storage device 607, which stores an operating system 613, application programs 614, and other program modules 615.
The basic input/output system 606 includes a display 608 for displaying information and an input device 609 such as a mouse, keyboard, etc. for user input of information. Wherein a display 608 and an input device 609 are connected to the central processing unit 601 through an input output controller 610 connected to the system bus 605. The basic input/output system 606 may also include an input/output controller 610 for receiving and processing input from a number of other devices, such as a keyboard, mouse, or electronic stylus. Similarly, input/output controller 610 may also provide output to a display screen, a printer, or other type of output device.
The mass storage device 607 is connected to the central processing unit 601 through a mass storage controller (not shown) connected to the system bus 605. The mass storage device 607 and its associated computer-readable media provide non-volatile storage for the server 600. That is, mass storage device 607 may include a computer-readable medium (not shown), such as a hard disk or CD-ROM drive.
Computer-readable media may include computer storage media and communication media. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes RAM, ROM, EPROM, EEPROM, flash memory or other solid state memory technology, CD-ROM, DVD, or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices. Of course, those skilled in the art will appreciate that computer storage media is not limited to the foregoing. The system memory 604 and mass storage device 607 described above may be collectively referred to as memory.
According to various embodiments of the present application, the server 600 may also operate as a remote computer connected to a network through a network, such as the Internet. That is, the server 600 may be connected to the network 612 through the network interface unit 611 connected to the system bus 605, or may be connected to other types of networks or remote computer systems (not shown) using the network interface unit 611.
The memory further includes one or more programs, and the one or more programs are stored in the memory and configured to be executed by the CPU. The one or more programs include instructions for performing the song recommendation method provided by embodiments of the present application as described below.
Embodiments of the present application further provide a non-transitory computer-readable storage medium, and when instructions in the storage medium are executed by a processor of a server, the server is enabled to execute the song recommendation method provided in the foregoing embodiments.
Embodiments of the present application further provide a computer program product containing instructions, which when run on a server, cause the server to execute the song recommendation method provided in the above embodiments.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims (10)

1. A song recommendation method, the method comprising:
for a first history song in a plurality of history songs listened to by a user to be recommended before the current time, acquiring a recommended song configured for the first history song by each reference user in a plurality of reference users to obtain a plurality of recommended songs corresponding to the plurality of reference users one by one, wherein the plurality of reference users are other users except the user to be recommended, and the first history song is any one of the plurality of history songs;
for a first recommended song in the plurality of recommended songs, determining the user matching degree of the first recommended song according to the user characteristics of the user to be recommended and the user characteristics of a first reference user corresponding to the first recommended song, wherein the first recommended song is any one of the plurality of recommended songs;
and determining the recommended songs of the first history songs according to the user matching degree of each first recommended song in the plurality of recommended songs.
2. The method of claim 1, wherein after obtaining the recommended songs configured for the first historical song by each of the plurality of reference users, further comprising:
determining the song matching degree of the first recommended song according to the first historical song;
correspondingly, the determining the recommended songs of the first history songs according to the user matching degree of each first recommended song in the plurality of recommended songs includes:
and determining the recommended songs of the first historical songs according to the user matching degree and the song matching degree of each first recommended song in the plurality of recommended songs.
3. The method of claim 2, wherein determining the recommended songs for the first history song based on the user match and the song match for each first recommended song in the plurality of recommended songs comprises:
for a first recommended song in the plurality of recommended songs, determining a recommended value of the first recommended song according to the user matching degree and the song matching degree of the first recommended song;
and determining a song recommendation list according to the recommendation value of each first recommended song in the plurality of recommended songs, wherein the recommendation value of the recommended song in the front ranking in the plurality of recommended songs included in the song recommendation list is greater than the recommendation value of the recommended song in the back ranking.
4. The method of claim 3, wherein determining the recommendation value for the first recommended song based on the user match and the song match for the first recommended song comprises:
and multiplying the user matching degree of the first recommended song and the song matching degree, or performing weighted addition on the user matching degree and the song matching degree of the first recommended song to obtain a recommended value of the first recommended song.
5. The method of any one of claims 1 to 4, wherein the user characteristics of the first reference user comprise one or more of personal information of the first reference user, historical song listening records of the first reference user, and intimacy between the first reference user and the user to be recommended.
6. The method of claim 5, wherein when the user characteristics of the first reference user include personal information of the first reference user, a historical song listening record of the first reference user, and an affinity between the first reference user and the user to be recommended, the determining the user matching degree of the first recommended song according to the user characteristics of the user to be recommended and the user characteristics of the first reference user corresponding to the first recommended song comprises:
determining a user similarity value of the first reference user according to the personal information of the user to be recommended and the personal information of the first reference user;
determining a historical song listening similarity value of the first reference user according to the historical song listening record of the user to be recommended and the historical song listening record of the first reference user;
determining the affinity value of the first reference user according to the affinity relationship between the user to be recommended and the first reference user;
and determining the user matching degree with the first recommended song according to the user similarity value of the first reference user, the historical song listening similarity value of the first reference user and the affinity value of the first reference user.
7. The method of claim 1, wherein the method further comprises:
receiving a song recommendation request sent by the first reference user, wherein the song recommendation request carries a recommended song configured for the first historical song by the first reference user, a display interface of a terminal held by the first reference user comprises a song recommendation option, and the song recommendation request is triggered by the first reference user through the song recommendation option.
8. A song recommendation apparatus, characterized in that the apparatus comprises:
the device comprises an acquisition module, a recommendation module and a recommendation module, wherein the acquisition module is used for acquiring a recommended song configured for a first historical song by each reference user in a plurality of reference users for the first historical song, and acquiring a plurality of recommended songs corresponding to the reference users one by one, the reference users are other users except for a user to be recommended, and the first historical song is any one of the plurality of historical songs;
the first determining module is used for determining the user matching degree of a first recommended song in the plurality of recommended songs according to the user characteristics of the user to be recommended and the user characteristics of a first reference user corresponding to the first recommended song, wherein the first recommended song is any one of the plurality of recommended songs;
and the second determination module is used for determining the recommended songs of the first history songs according to the user matching degree of each first recommended song in the plurality of recommended songs.
9. An apparatus for song recommendation, the apparatus comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to load the executable instructions and to perform the steps of the method of any of the above claims 1 to 7.
10. A computer-readable storage medium having stored thereon instructions which, when executed by a processor, carry out the steps of the method of any of claims 1 to 7.
CN201910944368.6A 2019-09-30 2019-09-30 Song recommendation method and device and computer storage medium Pending CN110647653A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910944368.6A CN110647653A (en) 2019-09-30 2019-09-30 Song recommendation method and device and computer storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910944368.6A CN110647653A (en) 2019-09-30 2019-09-30 Song recommendation method and device and computer storage medium

Publications (1)

Publication Number Publication Date
CN110647653A true CN110647653A (en) 2020-01-03

Family

ID=69012271

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910944368.6A Pending CN110647653A (en) 2019-09-30 2019-09-30 Song recommendation method and device and computer storage medium

Country Status (1)

Country Link
CN (1) CN110647653A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112364244A (en) * 2020-11-16 2021-02-12 广州酷狗计算机科技有限公司 Multimedia data recommendation method, device, server and storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2009090358A1 (en) * 2008-01-15 2009-07-23 Music Technology Limited Playlist manager
CN107977373A (en) * 2016-10-21 2018-05-01 北京酷我科技有限公司 A kind of recommendation method of song
CN108228882A (en) * 2018-01-26 2018-06-29 维沃移动通信有限公司 The recommendation method and terminal device of a kind of audition for the songs segment
CN109299317A (en) * 2018-11-12 2019-02-01 百度在线网络技术(北京)有限公司 Method, apparatus, storage medium and the terminal device that musical works is recommended
CN109461012A (en) * 2017-09-06 2019-03-12 中国移动通信有限公司研究院 A kind of Products Show method, apparatus and terminal

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2009090358A1 (en) * 2008-01-15 2009-07-23 Music Technology Limited Playlist manager
CN107977373A (en) * 2016-10-21 2018-05-01 北京酷我科技有限公司 A kind of recommendation method of song
CN109461012A (en) * 2017-09-06 2019-03-12 中国移动通信有限公司研究院 A kind of Products Show method, apparatus and terminal
CN108228882A (en) * 2018-01-26 2018-06-29 维沃移动通信有限公司 The recommendation method and terminal device of a kind of audition for the songs segment
CN109299317A (en) * 2018-11-12 2019-02-01 百度在线网络技术(北京)有限公司 Method, apparatus, storage medium and the terminal device that musical works is recommended

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112364244A (en) * 2020-11-16 2021-02-12 广州酷狗计算机科技有限公司 Multimedia data recommendation method, device, server and storage medium

Similar Documents

Publication Publication Date Title
US11128582B2 (en) Emoji recommendation method and apparatus
CN108763502B (en) Information recommendation method and system
US11222273B2 (en) Service recommendation method, apparatus, and device
CN111432226B (en) Live broadcast recommendation method and device, server, terminal and storage medium
US20150363061A1 (en) System and method for providing related digital content
CN112868004B (en) Resource recommendation method and device, electronic equipment and storage medium
CN109582872B (en) Information pushing method and device, electronic equipment and storage medium
CN107734031B (en) Information interaction method and system based on electronic book
CN108491540B (en) Text information pushing method and device and intelligent terminal
CN107729578B (en) Music recommendation method and device
JP2023520483A (en) SEARCH CONTENT DISPLAY METHOD, DEVICE, ELECTRONIC DEVICE, AND STORAGE MEDIUM
CN113592535B (en) Advertisement recommendation method and device, electronic equipment and storage medium
CN112104505B (en) Application recommendation method, device, server and computer readable storage medium
CN111209477A (en) Information recommendation method and device, electronic equipment and storage medium
CN110225407A (en) The acquisition methods and device and computer readable storage medium of a kind of played data
CN110677267A (en) Information processing method and device
CN111464826B (en) List updating method and device for virtual resources, electronic equipment and storage medium
CN111274415A (en) Method, apparatus and computer storage medium for determining alternate video material
CN103488669A (en) Information processing apparatus, information processing method and program
CN110647653A (en) Song recommendation method and device and computer storage medium
CN113010790A (en) Content recommendation method, device, server and storage medium
CN111124209A (en) Interface display adjustment method and device
CN114741594A (en) Information pushing method and device, computer equipment and storage medium
CN110333927B (en) Interface skipping method and device, server and storage medium
CN113934938A (en) Information display method and device, readable medium and electronic equipment

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20200103