CN116108221A - Song recommendation method, song display method and device - Google Patents

Song recommendation method, song display method and device Download PDF

Info

Publication number
CN116108221A
CN116108221A CN202310006344.2A CN202310006344A CN116108221A CN 116108221 A CN116108221 A CN 116108221A CN 202310006344 A CN202310006344 A CN 202310006344A CN 116108221 A CN116108221 A CN 116108221A
Authority
CN
China
Prior art keywords
song
comment
search
target
recommendation
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
CN202310006344.2A
Other languages
Chinese (zh)
Inventor
吴庆双
吴敏
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.)
China Mobile Communications Group Co Ltd
MIGU Culture Technology Co Ltd
Original Assignee
China Mobile Communications Group Co Ltd
MIGU Culture 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 China Mobile Communications Group Co Ltd, MIGU Culture Technology Co Ltd filed Critical China Mobile Communications Group Co Ltd
Priority to CN202310006344.2A priority Critical patent/CN116108221A/en
Publication of CN116108221A publication Critical patent/CN116108221A/en
Pending legal-status Critical Current

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
    • G06F16/635—Filtering based on additional data, e.g. user or group profiles
    • 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
    • G06F16/632—Query formulation
    • 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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

The invention discloses a song recommending method, a song displaying method and a song displaying device, wherein the recommending method comprises the following steps: comment information of a target search song is obtained, and a popular characteristic value corresponding to at least one comment subject of the target search song is determined according to the comment information; determining target recommendation dimensions of songs to be recommended according to the popular feature values corresponding to the at least one evaluation subject matter; and searching the songs according to the target recommendation dimension to obtain the songs to be recommended. According to the technical scheme, the preference content searched by the user can be determined according to the song popularity characteristic value of the song searched by the user, and the song to be recommended is further obtained through retrieval according to the recommendation dimension formed by the preference content, so that the recommendation result can enable the user to generate resonance, and the satisfaction degree and the liveness degree of the user are improved.

Description

Song recommendation method, song display method and device
Technical Field
The invention relates to the technical field of multimedia, in particular to a song recommendation method, a song display method and device, computing equipment and a computer storage medium.
Background
When a user searches songs, the existing music application program (APP) only returns searched target songs to the user, the mode does not further expand and consider the demand preference of the user based on the user searching behavior, the aim that the client pursues humanization and intellectualization cannot be embodied, more demands of the user during searching cannot be perceived, resonance is difficult to generate with the user, and the user experience of the client is reduced.
Disclosure of Invention
The present invention has been made in view of the above problems, and provides a song recommendation method, song presentation method and apparatus, a computing device, a computer storage medium, which overcome or at least partially solve the above problems.
According to one aspect of the present invention, there is provided a song recommendation method, the method comprising:
comment information of a target search song is obtained, and a popular characteristic value corresponding to at least one comment subject of the target search song is determined according to the comment information;
determining target recommendation dimensions of songs to be recommended according to the popular feature values corresponding to the at least one evaluation subject matter;
and searching the songs according to the target recommendation dimension to obtain the songs to be recommended.
Optionally, the determining, according to the comment information, a popularity feature value corresponding to at least one comment gist of the target search song further includes:
according to comment content in each comment information, respectively determining comment types and comment gist of each comment information;
and determining the popularity characteristic value of the target search song under each comment subject according to the comment type of each comment information and the statistical information of the comment subject.
Optionally, the determining the popularity characteristic value of the target search song under each comment subject according to the comment type of each comment information and the statistical information of the comment subject further includes:
selecting at least one forward comment type aiming at any comment subject matter, counting the first probability that the target search song belongs to any selected forward comment type, and counting the second probability that the target search song belongs to the comment subject matter and any selected forward comment type;
and calculating the popularity characteristic value of the target search song under the comment gist according to the first probability and the second probability.
Optionally, the comment subject includes melody, lyrics and/or singer, and the forward comment type includes: liking and/or neutrality;
determining a target recommendation dimension of the song to be recommended according to the popular feature value corresponding to the at least one evaluation subject matter, and searching the song according to the target recommendation dimension, wherein the obtaining the song to be recommended further comprises:
if the target recommendation dimension is determined to be the melody, song searching is carried out according to the composition artificial search information of the target search song;
if the target recommendation dimension is determined to be lyrics, performing song search by using artificial search information of words of the target search song;
and if the target recommendation dimension is determined to be the singer, performing song search by taking the singer of the target search song as search information.
According to another aspect of the present invention, there is provided a song presentation method, the method comprising:
receiving search information input by a user in an interface;
the search information is sent to a server side, so that the server side can determine target search songs according to the search information, and can determine popular feature values corresponding to at least one evaluation subject of the target search songs according to comment information of the target search songs, further determine target recommendation dimensions of songs to be recommended, and perform song search according to the target recommendation dimensions to obtain and return the songs to be recommended;
and receiving the target search song and the song to be recommended returned from the server, and displaying the target search song and the song to be recommended in the interface.
Optionally, the interface includes a search result display area and a recommendation result display area, where the search result display area is used to display the target search song and the recommendation result display area is used to display the song to be recommended.
Optionally, the search result display area and the recommendation result display area are each composed of at least one block;
the presenting the target search song and the song to be recommended to the user in the interface further comprises:
and respectively displaying the target search songs in at least one block corresponding to the search result display area, and respectively displaying the songs to be recommended in at least one block corresponding to the recommendation result display area, wherein each block respectively displays song information of the corresponding song.
Optionally, the interface further includes a continue recommendation trigger area, and the method further includes:
responding to the operation of the user on the continuous recommendation triggering area, sending a continuous recommendation request to a server side so that the server side can search songs according to recommendation dimensions except for target recommendation dimensions to obtain and return other songs to be recommended;
and receiving the other songs to be recommended returned from the server, and refreshing and displaying the other songs to be recommended in a recommendation result display area.
According to still another aspect of the present invention, there is provided a song recommendation apparatus, the apparatus comprising:
the characteristic value determining module is suitable for acquiring comment information of the target search song and determining a popular characteristic value corresponding to at least one comment subject of the target search song according to the comment information;
the recommendation dimension determining module is suitable for determining target recommendation dimensions of songs to be recommended according to the popular feature values corresponding to the at least one evaluation subject matter;
and the song recommendation module is suitable for searching songs according to the target recommendation dimension to obtain the songs to be recommended.
According to yet another aspect of the present invention, there is provided a song display apparatus, the apparatus comprising:
the information receiving module is suitable for receiving search information input by a user in the interface;
the information processing module is suitable for sending the search information to a server side so that the server side can determine target search songs according to the search information, determine popular characteristic values corresponding to at least one evaluation subject of the target search songs according to comment information of the target search songs, further determine target recommendation dimensions of songs to be recommended, search the songs according to the target recommendation dimensions, and obtain and return the songs to be recommended;
and the song display module is suitable for receiving the target search song and the song to be recommended returned from the server and displaying the target search song and the song to be recommended in the interface.
According to yet another aspect of the present invention, there is provided a computing device comprising: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation corresponding to the song recommendation method or the song display method.
According to still another aspect of the present invention, there is provided a computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the song recommendation method or the song presentation method described above.
According to the song recommendation technical scheme, firstly, comment information of a target search song from a plurality of users is obtained, and a popular characteristic value of the target search song is determined according to the comment information, wherein the popular characteristic value is associated with comment subjects reflecting the inherent category of the song; then, determining a target recommendation dimension of the song to be recommended according to at least one popular characteristic value corresponding to the evaluation subject, for example, according to the characteristics of the characteristic value and the like; and searching the songs according to the target recommendation dimension to obtain the songs to be recommended. According to the technical scheme, the preference content searched by the user can be determined according to the song popularity characteristic value of the song searched by the user, and the song to be recommended is further obtained through retrieval according to the recommendation dimension formed by the preference content, so that the recommendation result can enable the user to generate resonance, and the satisfaction degree and the liveness degree of the user are improved.
The foregoing description is only an overview of the present invention, and is intended to be implemented in accordance with the teachings of the present invention in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present invention more readily apparent.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
FIG. 1 is a flowchart of a song recommendation method according to an embodiment of the present invention;
FIG. 2 is a flow chart of a song presentation method according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a song presentation interface according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a song recommendation apparatus according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a song display apparatus according to an embodiment of the present invention;
FIG. 6 illustrates a schematic diagram of a computing device provided by an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
FIG. 1 shows a flowchart of an embodiment of a song recommendation method of the present invention, which is applied to a computing device as a server. The computing device is a computer device and/or cloud, the computer device including, but not limited to, a personal computer, a notebook computer, an industrial computer, a network host, a single network server, a plurality of network server sets; the Cloud is composed of a large number of computers or network servers based on Cloud Computing (Cloud Computing), which is one of distributed Computing, a virtual supercomputer composed of a group of loosely coupled computer sets.
As shown in fig. 1, the song recommendation method includes the steps of:
step 110: and obtaining comment information of the target search song, and determining a popular characteristic value corresponding to at least one comment subject of the target search song according to the comment information.
Wherein the comment information may be comments from a plurality of applications in order to obtain a comprehensive evaluation. The main point of the evaluation is specifically that the main angle of the user to the song evaluation, such as the attraction angle of the song, can be melody, lyrics, singer, etc., or other aspects. Of course, the above is merely an example, and the specific comment gist may be set according to actual needs without specific limitation.
The popular characteristic value of the song is a quantification of the tendency of the user to listen to the song when searching or browsing the target search song, and a comment subject corresponds to the popular characteristic value, and the specific quantification mode can be determined according to the processing mode of comment information.
Step 120: and determining the target recommendation dimension of the song to be recommended according to the popular feature value corresponding to the comment subject.
The comment themes are generally multiple, and the best comment theme among the comment themes can be determined as the target recommendation dimension in a manner of sorting by using the magnitude of the popular feature value.
Step 130: and searching the songs according to the target recommendation dimension to obtain the songs to be recommended.
For example, the determined target recommendation dimension may be a recommendation angle of the song (such as the name of the singer, etc.), and then the list of the song to be recommended is obtained by searching the database according to the type and the specific information.
In summary, when recommending songs, the embodiment of the invention fully considers the song listening tendency of the user when searching or browsing a certain song, determines a target recommending dimension according to comment information, and then recommends songs by utilizing the target recommending dimension, thereby better grasping the emotion and preference of the user and improving the satisfaction degree and the liveness degree of the user.
In one or some embodiments, step 110 of determining, according to the comment information, a popularity feature value corresponding to at least one comment gist of the target search song further includes:
according to comment content in each comment information, respectively determining comment types and comment gist of each comment information;
and determining the popularity characteristic value of the target search song under each comment subject according to the comment type of each comment information and the statistical information of the comment subject.
In the embodiment, comment information is further analyzed and processed, so that probability statistics is performed according to classification information of the comment information, and popular feature values of the comments are calculated and obtained.
Specifically, the comment information may be divided into comment content, comment type, and comment subject matter, which may be determined in association with the comment content. In addition, the embodiment of the invention preferably takes comment themes as recommendation dimensions, and the tendency of the user to search the song is quantitatively expressed by calculating the popular characteristic value of each comment theme.
For example, the comment content is collated according to the comment information to obtain the following table 1:
TABLE 1
ID Comment content Comment type (T) Comment gist (M)
1 Too like la Xi Huan Others
2 Melody brain washing Xi Huan Melody
3 Singing voice Zhenmei Xi Huan Singer
... ... ... ...
N Lyrics are too beautiful Xi Huan Lyrics
The comment types can obtain the emotion expressed by the comment according to a text emotion algorithm, and mainly comprise three types of likes, dislikes and neutrality, the comment subject comprises melody, lyrics, singers and other four types, namely, the effective evaluation of the user on songs can be basically classified into three types of melody, lyrics and singers, and of course, any one, two or three types of the three types can be included for a certain song. For example, a comment "too good for listening to a bar, and very pleasant for feeling lyrics" may include both melody and lyrics.
In one or some embodiments, the determining the song popularity feature value of the target search song under each comment gist according to the comment type of each comment information and the statistical information of the comment gist further includes:
selecting at least one forward comment type aiming at any comment subject matter, counting the first probability that the target search song belongs to any selected forward comment type, and counting the second probability that the target search song belongs to the comment subject matter and any selected forward comment type;
and calculating the popularity characteristic value of the target search song under the comment gist according to the first probability and the second probability.
In order to characterize the like degree of a comment subject (such as singer), a corresponding probability value can be obtained by carrying out statistical analysis on the number of times of occurrence of a forward comment (such as like) and the number of times of occurrence of the comment subject in the comment type, and the trend sequence of the comment subject is determined according to the size of the probability value.
For example, in this embodiment, the tendency of the user to comment on the comment subject may be determined only according to the second probability that the target search song belongs to the comment subject and any selected forward comment type, or the specific tendency may be determined according to the difference between the first probability and the second probability that the target search song belongs to any selected forward comment type.
Specifically, the comment subject includes melody, lyrics and/or singer, and the forward comment type includes: liking and/or neutrality; determining a target recommendation dimension of the song to be recommended according to the popular feature value corresponding to the at least one evaluation subject matter, and searching the song according to the target recommendation dimension, wherein the obtaining the song to be recommended further comprises:
if the target recommendation dimension is determined to be the melody, song searching is carried out according to the composition artificial search information of the target search song;
if the target recommendation dimension is determined to be lyrics, performing song search by using artificial search information of words of the target search song;
and if the target recommendation dimension is determined to be the singer, performing song search by taking the singer of the target search song as search information.
In an alternative embodiment, with comment subject matter as recommendation dimension, the popularity characteristic value of the song is calculated, and the popularity characteristic value can be judged according to the influence of three factors of melody, lyrics and singer in favorite user comments.
Specifically, M represents the comment category, T represents the comment category, and m_f (M) represents a popularity characteristic value of a specified subject of a song, that is, the influence of the comment subject of the song on the popularity of the song. The popularity characteristic value of whether a song is recommended or not can be determined as the accumulation of the favorite characteristic value and the neutral characteristic value, if other condition types are more or are more strict, the like and neutral types can be increased or decreased accordingly, for example, the like can be classified into general like, preferred and very popular, and the like.
Optionally, the popularity feature value (m_f (T)) of a single comment gist is a difference between a first probability value (C (T)) of comment data of the comment and a second probability value (C (M)) of the single comment gist. The smaller the resulting value, the greater the impact of the melody on whether the listener likes the song. The specific calculation formula is as follows:
Figure BDA0004036982400000091
wherein, m_f (M) is a popularity characteristic value of the song under the comment gist M, where p (T) represents a probability that the comment type T is liked in the data of table 1, and p (m|t) represents a probability that the comment type is liked in the data of table 1, and the comment gist M is lyric. n is a recommended content threshold set by the system, and assuming that both like and neutral can be recommended, n=2, and the enumerated value of comment type T is a result in the like and neutral range.
According to the formula, popular characteristic values of the melody, the lyrics and the singer are calculated in turn, and the smaller the value is, the larger the influence of the characteristic on the popularity of the song is indicated, so that the probability that the user searches the song and is attracted by the characteristic is inferred to be larger.
For example, if the popular feature value of the finally obtained melody is minimum, searching recommended content according to the composer of the song; if the obtained song popularity characteristic value of the lyrics is minimum, searching recommended content according to a word maker of the song; if the song popularity characteristic value of the obtained singer is minimum, searching recommended content according to the singer of the song.
FIG. 2 shows a flow chart of an embodiment of a song presentation method of the present invention as applied to a computing device as a client. A song presentation method as shown in connection with fig. 2, the method comprising:
step 210: search information input by a user in an interface is received.
Wherein, in combination with the interface structure shown in fig. 3, when the user reminds a certain well-known song, the user wants to search through the lyrics with high singing degree of a certain sentence. After the user logs in the client, approximately the interface shown in fig. 3, lyrics or other song information are input in the search box, and the search is submitted.
Step 220: and sending the search information to a server side, so that the server side can determine a target search song according to the search information, determine a popular characteristic value corresponding to at least one comment subject of the target search song according to comment information of the target search song, further determine a target recommendation dimension of a song to be recommended, and perform song search according to the target recommendation dimension to obtain the song to be recommended.
Specifically, after the client sends the search information to the server of the system background, the server searches to obtain the resource and information of the song to be recommended according to the song recommendation method in any embodiment, and then returns the song to be recommended to the client.
Step 230: and receiving the target search song and the song to be recommended returned from the server, and displaying the target search song and the song to be recommended in the interface.
In one embodiment, the interface includes a search result display area for displaying the target search song and a recommendation result display area for displaying the song to be recommended. The display classification and region display of each song is shown in combination with fig. 3, wherein the upper left part region mainly displays songs of search results, and the lower right part mainly displays songs of recommendation results.
In one embodiment, the search result presentation area and the recommendation result presentation area are each comprised of at least one block; the presenting the target search song and the song to be recommended to the user in the interface further comprises: and respectively displaying the target search songs in at least one block corresponding to the search result display area, and respectively displaying the songs to be recommended in at least one block corresponding to the recommendation result display area, wherein each block respectively displays song information of the corresponding song. And expressing the information of each song to be recommended through each block, and in the playing process, each block can also change the display form according to the setting to show the playing state of the block, so that the user experience is improved.
Specifically, the displaying of each song in the interface may be formed by blocks in various shapes, for example, each block may be arranged in a straight line or in a curved line, and optionally, may be in a ring shape as shown in fig. 3, etc.
In one embodiment, the interface further comprises a continue recommendation trigger area, the method further comprising:
responding to the operation of the user on the continuous recommendation triggering area, sending a continuous recommendation request to a server side so that the server side can search songs according to recommendation dimensions except for target recommendation dimensions to obtain and return other songs to be recommended;
and receiving the other songs to be recommended returned from the server, and refreshing and displaying the other songs to be recommended in a recommendation result display area.
Specifically, in order to make more songs played later fit the user's tendency, sub-optimal results may be further recommended to the user in addition to optimal recommended results.
In combination with the illustration example shown in fig. 3, each sector in the page may have different colors, and specific colors may be freely switched according to the style of APP or user preference, and each area may be replaced by a promotional photograph of a song, etc., without being limited to a color block. The search result display area and the recommendation result display area can dynamically load data results with front search reliability.
The method comprises the steps of loading more similar page turning functions, replacing the current display result, and enabling a gradual change page turning effect to appear when data are switched. "recommendation based on other features" is a further choice provided to the user; alternatively, if the result of searching for popular feature values calculated according to the above embodiments does not meet the user's expectations, the user may select more, such as by pressing the result recommended by the speaker, the user clicks "continue recommendation", and the system recommends new results based on the singer and composer.
Within the circle in the center of fig. 3, an advertisement animation or MV picture of the currently playing song, or a play button, etc. may be embedded.
Further, when the user clicks the round play button in the center, the search result starts to play according to the list, and each sector in the page can switch colors or brightness according to the rhythm of music or the style of song, so as to realize the call between the page and the music. When a song is played, the sector corresponding to the song may highlight or design a separate style, highlighting the music being played.
Optionally, after the user submits the search term, the blocks in the circle are displayed in sequence, the color system can be changed from shallow to deep, and the like, so that the whole style is changeable, the interface is more novel, the attraction to the user is increased, and the viscosity of the application program is improved.
Fig. 4 shows a schematic structural diagram of an embodiment of the song recommendation apparatus of the present invention. As shown in fig. 4, the apparatus 400 includes:
the feature value determining module 410 is adapted to obtain comment information of a target search song, and determine a popular feature value corresponding to at least one comment subject of the target search song according to the comment information;
the recommendation dimension determining module 420 is adapted to determine a target recommendation dimension of the song to be recommended according to the popularity feature value corresponding to the at least one comment subject;
and the song recommendation module 430 is adapted to perform song search according to the target recommendation dimension to obtain the song to be recommended.
In one or some embodiments, the feature value determination module 410 is further adapted to:
according to comment content in each comment information, respectively determining comment types and comment gist of each comment information;
and determining the popularity characteristic value of the target search song under each comment subject according to the comment type of each comment information and the statistical information of the comment subject.
In one or some embodiments, the feature value determination module 410 is further adapted to:
selecting at least one forward comment type aiming at any comment subject matter, counting the first probability that the target search song belongs to any selected forward comment type, and counting the second probability that the target search song belongs to the comment subject matter and any selected forward comment type;
and calculating the song popularity characteristic value of the target search song under the comment gist according to the first probability and the second probability.
In one embodiment, the comment gist includes melody, lyrics, and/or singer, and the forward comment type includes: liking and/or neutrality;
the song recommendation module 430 is further adapted to:
if the target recommendation dimension is determined to be the melody, song searching is carried out according to the composition artificial search information of the target search song;
if the target recommendation dimension is determined to be lyrics, performing song search by using artificial search information of words of the target search song;
and if the target recommendation dimension is determined to be the singer, performing song search by taking the singer of the target search song as search information.
Fig. 5 shows a schematic structural diagram of an embodiment of the song presentation apparatus of the present invention. As shown in fig. 5, the apparatus 500 includes:
an information receiving module 510 adapted to receive search information input in an interface by a user;
the information processing module 520 is adapted to send the search information to a server, so that the server determines a target search song according to the search information, determines a popular feature value corresponding to at least one comment subject of the target search song according to comment information of the target search song, further determines a target recommendation dimension of a song to be recommended, and performs song search according to the target recommendation dimension to obtain the song to be recommended;
the song display module 530 is adapted to receive the target search song and the song to be recommended returned from the server, and display the target search song and the song to be recommended in the interface.
In one embodiment, the interface includes a search result display area for displaying the target search song and a recommendation result display area for displaying the song to be recommended.
In one embodiment, the search result presentation area and the recommendation result presentation area are each comprised of at least one block;
the song presentation module 530 is further adapted to:
and respectively displaying the target search songs in at least one block corresponding to the search result display area, and respectively displaying the songs to be recommended in at least one block corresponding to the recommendation result display area, wherein each block respectively displays song information of the corresponding song.
In one embodiment, the interface further comprises a continue recommendation trigger, and the song presentation module 530 is further adapted to:
responding to the operation of the user on the continuous recommendation triggering area, sending a continuous recommendation request to a server side so that the server side can search songs according to recommendation dimensions except for target recommendation dimensions to obtain and return other songs to be recommended;
and receiving the other songs to be recommended returned from the server, and refreshing and displaying the other songs to be recommended in a recommendation result display area.
In summary, the key points and advantages of the above embodiments of the present invention are as follows:
1. according to the embodiment of the invention, the popular characteristic value of the song can be searched by the target of the user, the preference content (recommendation dimension) searched by the user can be determined, the song to be recommended is determined according to the preference content, the preference of the user can be better mastered, and the liveness of the user on the application program is improved;
2. the display style of the front end interface of the search and recommendation results breaks through the convention, is more novel, improves the use experience of the user, and can also avoid the influence of redundant data on the search experience of the user.
The embodiment of the invention provides a non-volatile computer storage medium, which stores at least one executable instruction, and the computer executable instruction can execute the song recommendation method or the song display method in any of the method embodiments.
FIG. 6 illustrates a schematic diagram of an embodiment of a computing device of the present invention, and the embodiments of the present invention are not limited to a particular implementation of the computing device.
As shown in fig. 6, the computing device may include: a processor 602, a communication interface (Communications Interface), a memory 606, and a communication bus 608.
Wherein: processor 602, communication interface 604, and memory 606 perform communication with each other via communication bus 608. Communication interface 604 is used to communicate with network elements of other devices, such as clients or other servers. The processor 602 is configured to execute the program 610, and may specifically perform relevant steps in the embodiments of the song recommendation method or song presentation method for a computing device described above.
In particular, program 610 may include program code including computer-operating instructions.
The processor 602 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or at least one integrated circuit configured to implement an embodiment of the present invention. The at least one processor included in the computing device may be the same type of processor, such as at least one CPU; but may also be different types of processors such as at least one CPU and at least one ASIC.
A memory 606 for storing a program 610. The memory 606 may comprise high-speed RAM memory or may further comprise non-volatile memory (non-volatile memory), such as at least one disk memory.
The program 610 may be specifically configured to cause the processor 62 to perform operations corresponding to the above-described song recommendation method or song presentation method embodiment.
The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems may also be used with the teachings herein. The required structure for a construction of such a system is apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It will be appreciated that the teachings of the present invention described herein may be implemented in a variety of programming languages, and the above description of specific languages is provided for disclosure of enablement and best mode of the present invention.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the above description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of at least one of the various inventive aspects. However, the disclosed method should not be construed as reflecting the intention that: i.e., the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in at least one apparatus different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component and, furthermore, they may be divided into a plurality of sub-modules or sub-units or sub-components. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.
Various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functionality of some or all of the components according to embodiments of the present invention may be implemented in practice using a microprocessor or Digital Signal Processor (DSP). The present invention can also be implemented as an apparatus or device program (e.g., a computer program and a computer program product) for performing a portion or all of the methods described herein. Such a program embodying the present invention may be stored on a computer readable medium, or may have the form of one or more signals. Such signals may be downloaded from an internet website, provided on a carrier signal, or provided in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specifically stated.

Claims (11)

1. A song recommendation method, the method comprising:
comment information of a target search song is obtained, and a popular characteristic value corresponding to at least one comment subject of the target search song is determined according to the comment information;
determining target recommendation dimensions of songs to be recommended according to the popular feature values corresponding to the at least one evaluation subject matter;
and searching the songs according to the target recommendation dimension to obtain the songs to be recommended.
2. The method of claim 1, wherein the determining, from the ratings information, a popularity feature corresponding to at least one ratings gist of the target search song further comprises:
according to comment content in each comment information, respectively determining comment types and comment gist of each comment information;
and determining the popularity characteristic value of the target search song under each comment subject according to the comment type of each comment information and the statistical information of the comment subject.
3. The method of claim 2, wherein the determining the popularity feature of the target search song under each of the comment topics based on the comment type of each of the comment information and the statistical information of the comment topics further comprises:
selecting at least one forward comment type aiming at any comment subject matter, counting the first probability that the target search song belongs to any selected forward comment type, and counting the second probability that the target search song belongs to the comment subject matter and any selected forward comment type;
and calculating the popularity characteristic value of the target search song under the comment gist according to the first probability and the second probability.
4. The method of claim 3, wherein the comment subject matter includes melody, lyrics, and/or singer, and the forward comment type includes: liking and/or neutrality;
determining a target recommendation dimension of the song to be recommended according to the popular feature value corresponding to the at least one evaluation subject matter, and searching the song according to the target recommendation dimension, wherein the obtaining the song to be recommended further comprises:
if the target recommendation dimension is determined to be the melody, song searching is carried out according to the composition artificial search information of the target search song;
if the target recommendation dimension is determined to be lyrics, performing song search by using artificial search information of words of the target search song;
and if the target recommendation dimension is determined to be the singer, performing song search by taking the singer of the target search song as search information.
5. A song presentation method, the method comprising:
receiving search information input by a user in an interface;
the search information is sent to a server side, so that the server side can determine target search songs according to the search information, and can determine popular feature values corresponding to at least one evaluation subject of the target search songs according to comment information of the target search songs, further determine target recommendation dimensions of songs to be recommended, and perform song search according to the target recommendation dimensions to obtain and return the songs to be recommended;
and receiving the target search song and the song to be recommended returned from the server, and displaying the target search song and the song to be recommended in the interface.
6. The method of claim 5, wherein the interface comprises a search results display area for displaying the target search song and a recommendation results display area for displaying the song to be recommended.
7. The method of claim 6, wherein the search result presentation area and the recommendation result presentation area each consist of at least one tile;
the presenting the target search song and the song to be recommended to the user in the interface further comprises:
and respectively displaying the target search songs in at least one block corresponding to the search result display area, and respectively displaying the songs to be recommended in at least one block corresponding to the recommendation result display area, wherein each block respectively displays song information of the corresponding song.
8. The method of claim 6, wherein the interface further comprises a continue recommendation trigger, the method further comprising:
responding to the operation of the user on the continuous recommendation triggering area, sending a continuous recommendation request to a server side so that the server side can search songs according to recommendation dimensions except for target recommendation dimensions to obtain and return other songs to be recommended;
and receiving the other songs to be recommended returned from the server, and refreshing and displaying the other songs to be recommended in a recommendation result display area.
9. A song presentation apparatus, the apparatus comprising:
the information receiving module is suitable for receiving search information input by a user in the interface;
the information processing module is suitable for sending the search information to a server side so that the server side can determine target search songs according to the search information, determine popular characteristic values corresponding to at least one evaluation subject of the target search songs according to comment information of the target search songs, further determine target recommendation dimensions of songs to be recommended, and perform song search according to the target recommendation dimensions to obtain the songs to be recommended;
and the song display module is suitable for receiving the target search song and the song to be recommended returned from the server and displaying the target search song and the song to be recommended in the interface.
10. A computing device, the computing device comprising: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;
the memory is configured to store at least one executable instruction that causes the processor to perform operations corresponding to the song recommendation method according to any one of claims 1-4 or the song presentation method according to any one of claims 5-8.
11. A computer storage medium, wherein at least one executable instruction is stored in the storage medium, and the executable instruction causes a processor to perform operations corresponding to the song recommendation method according to any one of claims 1 to 4 or the song presentation method according to any one of claims 5 to 8.
CN202310006344.2A 2023-01-04 2023-01-04 Song recommendation method, song display method and device Pending CN116108221A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310006344.2A CN116108221A (en) 2023-01-04 2023-01-04 Song recommendation method, song display method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310006344.2A CN116108221A (en) 2023-01-04 2023-01-04 Song recommendation method, song display method and device

Publications (1)

Publication Number Publication Date
CN116108221A true CN116108221A (en) 2023-05-12

Family

ID=86259254

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310006344.2A Pending CN116108221A (en) 2023-01-04 2023-01-04 Song recommendation method, song display method and device

Country Status (1)

Country Link
CN (1) CN116108221A (en)

Similar Documents

Publication Publication Date Title
US11030202B2 (en) Method and device for recommendation of media content
US7533091B2 (en) Methods, systems, and computer-readable media for generating a suggested list of media items based upon a seed
CN105808685B (en) Promotion information pushing method and device
Kaminskas et al. Location-aware music recommendation using auto-tagging and hybrid matching
Mandel et al. A web-based game for collecting music metadata
JP4524709B2 (en) Information processing apparatus and method, and program
Hyung et al. Music recommendation using text analysis on song requests to radio stations
CN106302085B (en) Recommendation method and system for instant messaging group
CN106416263B (en) The method and apparatus that intelligent automatic high speed for media caches
US20140317105A1 (en) Live recommendation generation
US8688615B2 (en) Content selection based on consumer interactions
CN110175245A (en) Multimedia recommendation method, device, equipment and storage medium
CN106708817B (en) Information searching method and device
US20090138457A1 (en) Grouping and weighting media categories with time periods
WO2013184957A1 (en) Systems and methods of classifying content items
US20220122147A1 (en) Emotion calculation device, emotion calculation method, and program
JP5594532B2 (en) Information processing apparatus and method, information processing system, and program
CN101884042A (en) Using reputation measures to improve search relevance
WO2017067156A1 (en) Playlist list determining method, device, electronic device and storage medium
CN105512178B (en) A kind of entity recommended method and device
US20210034661A1 (en) Systems and methods for recommending collaborative content
Hyung et al. Utilizing context-relevant keywords extracted from a large collection of user-generated documents for music discovery
JP5854275B2 (en) Information processing apparatus and program
CN105898426A (en) Multimedia content processing method and device and server
CN108604250A (en) Identify the classification of content item and method, system and medium according to classification organising content items to present

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