CN108804609A - Song recommendation method and device - Google Patents
Song recommendation method and device Download PDFInfo
- Publication number
- CN108804609A CN108804609A CN201810537968.6A CN201810537968A CN108804609A CN 108804609 A CN108804609 A CN 108804609A CN 201810537968 A CN201810537968 A CN 201810537968A CN 108804609 A CN108804609 A CN 108804609A
- Authority
- CN
- China
- Prior art keywords
- song
- user
- type
- current emotional
- songs
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000004458 analytical method Methods 0.000 claims abstract description 26
- 238000013507 mapping Methods 0.000 claims abstract description 21
- 230000002996 emotional effect Effects 0.000 claims description 63
- 230000036651 mood Effects 0.000 claims description 38
- 230000015654 memory Effects 0.000 claims description 19
- 238000004891 communication Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 7
- 230000009466 transformation Effects 0.000 claims description 3
- 230000008451 emotion Effects 0.000 abstract 5
- 230000006870 function Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 238000005314 correlation function Methods 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000008676 import Effects 0.000 description 2
- 208000019901 Anxiety disease Diseases 0.000 description 1
- 241001269238 Data Species 0.000 description 1
- 230000036506 anxiety Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 210000004709 eyebrow Anatomy 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000002889 sympathetic effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
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 provides a song recommendation method and device, and the method comprises the following steps: acquiring at least one of text information, audio information and image information of a user; determining the current emotion of the user according to the at least one piece of information and an emotion analysis model, wherein the emotion analysis model is used for representing the mapping relation between the at least one piece of information and the current emotion; determining a target song type recommended for the user according to the current emotion; and recommending the at least one song for the user according to the target song type, wherein the song type of the at least one song belongs to the target song type. By the adoption of the song recommending method and device, songs can be flexibly recommended to the user, and therefore user experience is improved.
Description
Technical field
This application involves music commending system fields, and more particularly, to the song in music commending system field
Recommend method and apparatus.
Background technology
Music commending system can when user listens to music, according to the history of user partially come for user carry out music
Recommend.Existing music commending system listens to record generally according to user's history, is realized to user using the strategy such as collaborative filtering
Recommend music.
However, existing music commending system system only simple going through with reference to user when carrying out music recommendation
History listens to record, and the factor of consideration is relatively simple；And for that there is no the new user that history listens to record, cannot provide effectively
Music recommend.Therefore, user experience is poor.
Invention content
The application provides a kind of song recommendations method and apparatus, can be flexibly that user recommends song, to improve user
Experience.
To achieve the above object, the application provides a kind of song recommendations method, including the following contents：
Obtain at least one of text message, audio-frequency information and the image information of user information；
According at least one information and mood analysis model, the current emotional of the user, the mood point are determined
Analysis model is used to indicate the mapping relations of at least one information and the current emotional；
According to the current emotional, it is determined as the target song type that the user recommends；
According to the target song type, recommend at least one described song, at least one described song for the user
Types of songs belong to the target song type.
Song recommendations method provided by the embodiments of the present application can combine during carrying out song recommendations for user
The current emotional of user flexibly recommends song, to improve user experience for user.
To achieve the above object, the application also provides a kind of song recommendations device, which specifically includes：
Acquiring unit, at least one of text message, audio-frequency information and image information for obtaining user information；
Determination unit, at least one information for being obtained according to the acquiring unit and mood analysis model, really
The current emotional of the fixed user, the mood analysis model are used to indicate at least one information and the current emotional
Mapping relations；According to the current emotional, it is determined as the target song type that the user recommends；
Recommendation unit, the target song type for being determined according to the determination unit recommend institute for the user
At least one song is stated, the types of songs of at least one song belongs to the target song type.
To achieve the above object, the application also provides a kind of computer equipment, including memory, processor, communication interface
And it is stored in the computer program that can be run on the memory and on the processor, wherein the memory, described
It is communicated by internal connecting path between processor and the communication interface, the processor executes the computer journey
The step of above method is realized when sequence.
To achieve the above object, the application also provides computer readable storage medium, is stored thereon with computer program, institute
State the step of above method is realized when computer program is executed by processor.
Description of the drawings
Fig. 1 is the schematic flow chart of song recommendations method provided by the embodiments of the present application；
Fig. 2 is the schematic flow chart of another song recommendations method provided by the embodiments of the present application；
Fig. 3 is the schematic block diagram of song recommendations device provided by the embodiments of the present application；
Fig. 4 is the schematic block diagram of another song recommendations device provided by the embodiments of the present application.
Specific implementation mode
Below in conjunction with attached drawing, the technical solution in the application is described.
Existing music commending system listens to record according to the history of user, is recommended for user by the method for collaborative filtering
Music.
However, since existing music commending system is listened to during carrying out music recommendation to user only with reference to history
Record, the angle changing rate of consideration is single, and if the user is new user, listens to record without relevant, thus can not
Recommend music for the user.Therefore, existing music commending system recommends the flexibility of music poor, to user experience compared with
Difference.
This application provides a kind of song recommendations method, song recommendations device is by obtaining text message, the audio of user
At least one of information and image information information；According to above-mentioned at least one information and mood analysis model, determine user's
Current emotional, the mood analysis model are used to indicate the mapping relations of above-mentioned at least one information and above-mentioned current emotional；Root
According to current emotional, it is determined as the target song type of user's recommendation；According to above-mentioned target song type, for user recommend described in extremely
A few song, the types of songs of at least one above-mentioned song belong to above-mentioned target song type.It is carried using the embodiment of the present application
The song recommendations method of confession can be flexibly that user recommends song, to improve user experience.
Fig. 1 shows the schematic flow chart of song recommendations method 100 provided by the embodiments of the present application.
S110 obtains at least one of the text message, audio-frequency information and image information of user information.
S120 determines the current emotional of the user, the feelings according at least one information and mood analysis model
Thread analysis model is used to indicate the mapping relations of at least one information and the current emotional.
S130 is determined as the target song type that the user recommends according to the current emotional.
S140 recommends at least one described song according to the target song type for the user, it is described at least one
The types of songs of song belongs to the target song type.
Optionally, this method 100 can be executed by song recommendations device, it should be appreciated that the song recommendations device can be tool
There is the device of computing function.
It should be noted that the song recommendations device can be independently of computer equipment, or can be to be integrated in calculating
In machine equipment, makees and as the function module in the computer equipment, the embodiment of the present application is not construed as limiting this.
It should be understood that the text message of user includes the information for indicating state vocabulary in text data, wherein descriptive word
Converging can be there are many type, which includes but not limited to：People claims class, money class, healthy class etc..
For example, the information of state vocabulary may include the existing word frequency of descriptive word remittance abroad.
For example, people claims the information of class to may include the word frequency of the first person, word frequency of the second person etc..
Optionally, which can be empirical according to or machine learning can be obtained according to, this
Application embodiment is not construed as limiting this.
Optionally, the text data of user for example may include the microblogging text data, QQ text datas, wechat of the user
The socially relevant text data with user such as text data, short message text data.
Specifically, which can obtain the text data of user, and determine this article according to this article notebook data
This information.
Optionally, which can obtain this article notebook data in several ways, and the embodiment of the present application is to this
It is not construed as limiting.
In one possible implementation, which may be used web crawlers technology and captures user mutual
The method that big data analysis may be used in text data or the song recommendations device in networking, for example, spark technologies, distribution
Formula calculates the text data on the acquisition network data platform such as (Hadoop) technology (cloud storage platform).
For example, the song recommendations device collects user's chat record with friend on QQ within some period.
In alternatively possible realization method, which can obtain the text data of user's importing.
For example, the song recommendations device obtains the chat record with friend in wechat that user imports.
In another possible realization method, which can obtain the voice data of user, and should
Voice is converted to text data.
For example, the song recommendations device can obtain the calling record of user, turned by carrying out word to the calling record
It changes, obtains lteral data corresponding with the calling record.
It should be understood that the audio-frequency information of user includes the information for indicating sound characteristic in voice data, wherein the sound
Feature can be there are many type, which includes but not limited to audio class, tempo class, decibel class, frequency spectrum class, tone color class
Deng.
Specifically, which can obtain the voice data of user, and determine the sound according to the voice data
Frequency information.
Optionally, which can obtain the voice data in several ways, and the embodiment of the present application is to this
It is not construed as limiting.
In one possible implementation, which can acquire the voice of user by audio collection device
Data.
For example, the song recommendations device acquires the calling record of user by audio collection device.
In another example the song recommendations device acquires one section of word that user expresses mood or mood by audio collection device.
In alternatively possible realization method, which can obtain the voice data of user's importing.
For example, the song recommendations device obtains one section of voice that user imports.
It should be understood that the image information of user includes the information for indicating face characteristic in image data, wherein the face
Feature can be there are many type, which includes but not limited to：Eyes class, nose class, face class, eyebrow class etc..
For example, the information of eyes class may include the position of eyes, the angle etc. that canthus raises up.
Specifically, which can obtain the image data of user, and determine the figure according to the image data
As information.
Optionally, which can obtain the image data in several ways, and the embodiment of the present application is to this
It is not construed as limiting.
In one possible implementation, which can obtain the picture number by video collector
According to.
For example, the song recommendations device can acquire the self-timer image of user by video collector.
In alternatively possible realization method, which can obtain the image data of user's importing.
For example, the song recommendations device can obtain the picture that can reflect mood or mood of user's importing.
In another possible realization method, which can obtain the video data of user, according to this
Video data obtains image data.
For example, the song recommendations device acquires user by video collector shoots the small video of oneself, and it is small to intercept this
Picture in video.
Optionally, the image information of the user can also include for the information of limbs feature in image data or other
It can reflect that the information of the current emotional of user, the embodiment of the present application are not construed as limiting this.
It should be understood that above example enumerate the song recommendations device and obtain text information, audio-frequency information or image
The possible realization method of information, the song recommendations device can also obtain text information, audio-frequency information by other means
Or image information, for example, the text message of user, audio-frequency information or image information are directly inputted the song recommendations by staff
Device etc., the embodiment of the present application should not be so limited to this.
Optionally, the mood analysis model in S120 may include the first mood analysis model and the second mood analysis mould
Type, the first mood analysis model are used to indicate that each information of each information and this at least one information to be corresponding current
The mapping relations of mood, the second mood analysis model are used to indicate working as the corresponding current emotional of each information and the user
The mapping relations of preceding mood.
Correspondingly, in S120, according to each information and the first mood analysis model at least one information, determining should
The corresponding current emotional of each information；And according to the corresponding current emotional of each information and the second status information analysis model,
Determine the current emotional of the user.
Optionally, the current emotional in S120 can there are many type mood, a plurality of types of moods include but
It is not limited to：Happiness, sadness, pain, excitement, anxiety etc..
Optionally, which can be divided into multiple strength grades, which can also include each
The strength grade of the mood of type.
For example, it is 0.7 that the current emotional, which may include sad strength grade, glad strength grade is 0, and painful is strong
It is 0.2 to spend grade, and nervous strength grade is 0.1.
Optionally, the mood analysis model can be pre-configured, or the song recommendations device according to this at least one
Kind of information and mood analysis model, before the current emotional for determining the user, what the song recommendations device oneself was established, the application
Embodiment is not construed as limiting this.
Optionally, in S130, which can be determined as the use in several ways according to the current emotional
The target song type that family is recommended, the embodiment of the present application are not construed as limiting this.
In one possible implementation, which can be according to the current emotional and song recommendations mould
Type determines the target song type, and the song recommendations model is for indicating the current emotional and the target song class
Mapping relations between type.
In alternatively possible realization method, which can be according to the current emotional and described current
The strength grade of mood determines the target song type.
For example, when the strength grade of the current emotional is less than or equal to preset first strength grade, by meeting
The types of songs for stating current emotional is determined as the target song type, enables a user to reach mood and the heart by song
Sympathetic response in feelings.
In another example when the current emotional is negative feeling, and the strength grade of the negative feeling is greater than or equal in advance
If the second strength grade when, the types of songs for meeting the mood opposite with the current emotional is determined as the target song
Type, wherein second strength grade be more than first strength grade, enable a user to by song reach to
The intervention and adjusting of family mood.
Optionally, in S140, which can be the use according to the target song type and library
Recommend at least one the described song for belonging to the target song type in the library in family, wherein wrapped in the library
Number of songs are included, the number of songs belong to a variety of types of songs, and a variety of types of songs include the target song type.
Optionally, institute is recommended for the user according to the target song type and library in the song recommendations device
Before stating at least one song, which can obtain the library in advance.
Optionally, which can establish for the be pre-configured or song recommendations device, and the embodiment of the present application is to this
It is not construed as limiting.
In one possible implementation, for the song of the not lyrics, which can obtain described
The audio data of first song in library；Fourier transformation is carried out to the audio data, obtains the plum of first song
That spectrogram；According to the Meier spectrogram and the first categorizing songs model, the types of songs of first song is determined, it is described
First categorizing songs model is used to indicate the mapping relations between the Meier spectrogram and the types of songs；This first is sung
Bent and first song types of songs is stored in the library.
In alternatively possible realization method, for there is the song of the lyrics, which can obtain described
The lyrics text of second song in library；According to the lyrics text and the second categorizing songs model, second song is determined
Bent types of songs, the second categorizing songs model are used to indicate the mapping between the lyrics text and the types of songs
Relationship；The types of songs of second song and second song is preserved into the library.
Fig. 2 shows the schematic flow chart of another song recommendations method 200 provided by the embodiments of the present application, this method
200 can for example be executed by song recommendations device.
S210 obtains at least one of the text message, audio-frequency information and image information of user information.
S220 determines the current emotional of the user, the feelings according at least one information and mood analysis model
Thread analysis model is used to indicate the mapping relations of at least one information and the current emotional.
S230 determines the target song type, the song recommendations according to the current emotional and song recommendations model
Model is used to indicate the mapping relations between the current emotional and the target song type.
S240 recommends to belong to described in the library for the user according to the target song type and library
At least one described song of target song type, wherein the library includes number of songs, and the number of songs belong to
A variety of types of songs, a variety of types of songs include the target song type.
Describe song recommendations method provided by the embodiments of the present application above in conjunction with Fig. 1 and Fig. 2, below in conjunction with Fig. 3 and
Fig. 4 introduces song recommendations device provided by the embodiments of the present application.
Fig. 3 shows the schematic block diagram of song recommendations device 300 provided by the embodiments of the present application.The device 300 includes：
Acquiring unit 310, at least one of text message, audio-frequency information and image information for obtaining user letter
Breath；
Determination unit 320, at least one information for being obtained according to the acquiring unit and mood analysis model,
Determine the current emotional of the user, the mood analysis model is for indicating at least one information and the current emotional
Mapping relations；According to the current emotional, it is determined as the target song type that the user recommends；
Recommendation unit 330, the target song type for being determined according to the determination unit are recommended for the user
The types of songs of at least one described song, at least one song belongs to the target song type.
Optionally, described that the target song type that the user recommends is determined as according to the current emotional, including：Root
According to the current emotional and song recommendations model, the target song type is determined, the song recommendations model is for indicating institute
State the mapping relations between current emotional and the target song type.
Optionally, the current emotional is divided into different strength grades, described according to the current emotional, is determined as described
The target song type that user recommends, including：According to the strength grade of the current emotional and the current emotional, determine described in
Target song type.
Optionally, the strength grade according to the current emotional is determined as the target song class that the user recommends
Type, including：When the strength grade of the current emotional is less than or equal to preset first strength grade, will meet described current
The types of songs of mood is determined as the target song type；Or work as the current emotional for negative feeling, and the negative feeling
Strength grade be greater than or equal to preset second strength grade when, the song of the mood opposite with the negative feeling will be met
Type is determined as the target song type, wherein second strength grade is more than first strength grade.
Optionally, described according to the target song type, recommend at least one described song for the user, including：
According to the target song type and library, recommend to belong to the target song type in the library for the user
At least one described song, wherein the library includes number of songs, and the number of songs belong to a variety of types of songs,
A variety of types of songs include the target song type.
Optionally, recommended in the library for the user according to the target song type and library described
Belong to before at least one described song of the target song type, the method includes：It obtains first in the library
The audio data of song；Fourier transformation is carried out to the audio data, obtains the Meier spectrogram of first song；According to
The Meier spectrogram and the first categorizing songs model determine the types of songs of first song, first categorizing songs
Model is used to indicate the mapping relations between the Meier spectrogram and the types of songs.
Optionally, recommended in the library for the user according to the target song type and library described
Belong to before at least one described song of the target song type, the method includes：It obtains second in the library
The lyrics text of song；According to the lyrics text and the second categorizing songs model, the types of songs of second song is determined,
The second categorizing songs model is used to indicate the mapping relations between the lyrics text and the types of songs.
Fig. 4 shows the schematic block diagram of song recommendations device 400 provided by the embodiments of the present application.The song recommendations device
400 can be the song recommendations device described in Fig. 4, which may be used hardware structure as shown in Figure 4.It should
Song recommendations device may include processor 410, communication interface 420 and memory 430, the processor 410, communication interface 420
It is communicated by internal connecting path with memory 430.The phase that determination unit 320 and recommendation unit 330 in Fig. 3 are realized
Closing function can be realized by processor 410, and the correlation function that acquiring unit 310 is realized can be controlled logical by processor 410
Interface 420 is believed to realize.
The processor 410 may include be one or more processors, such as including one or more central processing unit
(central processing unit, CPU), in the case where processor is a CPU, which can be monokaryon CPU,
It can be multi-core CPU.
The communication interface 420 is for input and/or output data.The communication interface may include that transmission interface and reception connect
Mouthful, transmission interface is used for output data, and receiving interface is used for input data.
The memory 430 include but not limited to be random access memory (random access memory, RAM), only
Read memory (read-only memory, ROM), erasable and programable memory (erasable programmable read
Only memory, EPROM), CD-ROM (compact disc read-only memory, CD-ROM), the memory 430
For storing dependent instruction and data.
Memory 430 is used to store the program code and data of song recommendations device, can be individual device or integrated
In processor 410.
Specifically, the processor 410 is for controlling communication interface and other devices, for example, with the device of establishing library
Or library carries out data transmission.For details, reference can be made to the descriptions in embodiment of the method, and details are not described herein.
It is designed it is understood that Fig. 4 illustrate only simplifying for song recommendations device.In practical applications, image is examined
Rope device can also separately include necessary other elements, including but not limited to any number of communication interface, processor, control
Device, memory etc., and all song recommendations devices that the application may be implemented are all within the protection domain of the application.
In a kind of possible design, song recommendations device 400 may alternatively be chip apparatus, such as can be available
Chip in song recommendations device, for realizing the correlation function of processor 410 in song recommendations device.The chip apparatus can
Think the field programmable gate array for realizing correlation function, special integrated chip, System on Chip/SoC, central processing unit, network processes
Device, digital signal processing circuit, microcontroller can also use programmable controller or other integrated chips.It, can in the chip
Choosing may include one or more memories, for storing program code, when the code is performed so that processor is real
Now corresponding function.
Those of ordinary skill in the art may realize that lists described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, depends on the specific application and design constraint of technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
Scope of the present application.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In several embodiments provided herein, it should be understood that disclosed systems, devices and methods, it can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only a kind of division of logic function, formula that in actual implementation, there may be another division manner, such as multiple units or component
It can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, it is shown or
The mutual coupling, direct-coupling or communication connection discussed can be the indirect coupling by some interfaces, device or unit
It closes or communicates to connect, can be electrical, machinery or other forms.
The unit illustrated as separating component may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, you can be located at a place, or may be distributed over multiple
In network element.Some or all of unit therein can be selected according to the actual needs to realize the mesh of this embodiment scheme
's.
In addition, each functional unit in each embodiment of the application can be integrated in a processing unit, it can also
It is that each unit physically exists alone, it can also be during two or more units be integrated in one unit.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer read/write memory medium.Based on this understanding, the technical solution of the application is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be expressed in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be
People's computer, server or network equipment etc.) execute each embodiment the method for the application all or part of step.
And storage medium above-mentioned includes：USB flash disk, mobile hard disk, ROM, RAM, magnetic disc or CD etc. are various can to store program code
Medium.
The above, the only specific implementation mode of the application, but the protection domain of the application is not limited thereto, it is any
Those familiar with the art can easily think of the change or the replacement in the technical scope that the application discloses, and should all contain
It covers within the protection domain of the application.Therefore, the protection domain of the application should be based on the protection scope of the described claims.
Claims (10)
1. a kind of song recommendations method, which is characterized in that including：
Obtain at least one of text message, audio-frequency information and the image information of user information；
According at least one information and mood analysis model, determine that the current emotional of the user, the mood analyze mould
Type is used to indicate the mapping relations of at least one information and the current emotional；
According to the current emotional, it is determined as the target song type that the user recommends；
According to the target song type, recommend at least one described song, the song of at least one song for the user
Bent type belongs to the target song type.
2. according to the method described in claim 1, it is characterized in that, described according to the current emotional, it is determined as the user
The target song type of recommendation, including：
According to the current emotional and song recommendations model, determine that the target song type, the song recommendations model are used for
Indicate the mapping relations between the current emotional and the target song type.
3. described according to the method described in claim 1, it is characterized in that, the current emotional is divided into different strength grades
According to the current emotional, it is determined as the target song type that the user recommends, including：
According to the strength grade of the current emotional and the current emotional, the target song type is determined.
4. according to the method described in claim 3, it is characterized in that, the strength grade according to the current emotional, determines
For the user recommend target song type, including：
When the strength grade of the current emotional is less than or equal to preset first strength grade, the current emotional will be met
Types of songs be determined as the target song type；Or
When the current emotional is negative feeling, and the strength grade of the negative feeling is greater than or equal to preset second intensity etc.
When grade, the types of songs for meeting the mood opposite with the negative feeling is determined as the target song type, wherein described
Second strength grade is more than first strength grade.
5. method according to claim 1 to 4, which is characterized in that it is described according to the target song type,
Recommend at least one described song for the user, including：
According to the target song type and library, recommend to belong to the target song class in the library for the user
At least one described song of type, wherein the library includes number of songs, and the number of songs belong to a variety of song classes
Type, a variety of types of songs include the target song type.
6. according to the method described in claim 5, it is characterized in that, described according to the target song type and library,
Before recommending to belong at least one song described in the target song type in the library for the user, the method
Including：
Obtain the audio data of the first song in the library；
Fourier transformation is carried out to the audio data, obtains the Meier spectrogram of first song；
According to the Meier spectrogram and the first categorizing songs model, the types of songs of first song is determined, described first
Categorizing songs model is used to indicate the mapping relations between the Meier spectrogram and the types of songs.
7. according to the method described in claim 5, it is characterized in that, described according to the target song type and library,
Before recommending to belong at least one song described in the target song type in the library for the user, the method
Including：
Obtain the lyrics text of the second song in the library；
According to the lyrics text and the second categorizing songs model, the types of songs of second song, second song are determined
Bent disaggregated model is used to indicate the mapping relations between the lyrics text and the types of songs.
8. a kind of song recommendations device, which is characterized in that including：
Acquiring unit, at least one of text message, audio-frequency information and image information for obtaining user information；
Determination unit, at least one information for being obtained according to the acquiring unit and mood analysis model, determine institute
The current emotional of user is stated, the mood analysis model is used to indicate the mapping of at least one information and the current emotional
Relationship；According to the current emotional, it is determined as the target song type that the user recommends；
Recommendation unit, for the target song type that is determined according to the determination unit, be described in user recommendation extremely
A few song, the types of songs of at least one song belong to the target song type.
9. a kind of computer equipment, including memory, processor, communication interface and it is stored on the memory and can be in institute
State the computer program run on processor, wherein pass through between the memory, the processor and the communication interface
Internal connecting path communicates, which is characterized in that realizes that aforesaid right is wanted when the processor executes the computer program
The step of seeking the method described in any one of 1 to 7.
10. a kind of computer readable storage medium, for storing computer program, which is characterized in that the computer program quilt
The step of method described in any one of the claims 1 to 7 is realized when processor executes.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810537968.6A CN108804609A (en) | 2018-05-30 | 2018-05-30 | Song recommendation method and device |
| PCT/CN2018/096331 WO2019227630A1 (en) | 2018-05-30 | 2018-07-19 | Song recommending method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810537968.6A CN108804609A (en) | 2018-05-30 | 2018-05-30 | Song recommendation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108804609A true CN108804609A (en) | 2018-11-13 |
Family
ID=64089368
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810537968.6A Withdrawn CN108804609A (en) | 2018-05-30 | 2018-05-30 | Song recommendation method and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN108804609A (en) |
| WO (1) | WO2019227630A1 (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109684501A (en) * | 2018-11-26 | 2019-04-26 | 平安科技（深圳）有限公司 | Lyrics information generation method and its device |
| CN111128103A (en) * | 2019-12-19 | 2020-05-08 | 北京凯来科技有限公司 | Immersive KTV intelligent song-requesting system |
| CN111583890A (en) * | 2019-02-15 | 2020-08-25 | 阿里巴巴集团控股有限公司 | Audio classification method and device |
| CN111737414A (en) * | 2020-06-04 | 2020-10-02 | 腾讯音乐娱乐科技（深圳）有限公司 | Song recommendation method and device, server and storage medium |
| CN111753049A (en) * | 2020-06-15 | 2020-10-09 | 广东美的厨房电器制造有限公司 | Menu recommendation method and device, household appliance and storage medium |
| WO2021004481A1 (en) * | 2019-07-08 | 2021-01-14 | 华为技术有限公司 | Media files recommending method and device |
| CN112905835A (en) * | 2021-02-26 | 2021-06-04 | 成都潜在人工智能科技有限公司 | Multi-mode music title generation method and device and storage medium |
| CN113010728A (en) * | 2021-04-06 | 2021-06-22 | 金宝贝网络科技(苏州)有限公司 | Song recommendation method, system, intelligent device and storage medium |
| CN113518263A (en) * | 2021-07-23 | 2021-10-19 | 南京炫佳网络科技有限公司 | Video recommendation method and device for interactive network television, television and storage medium |
| CN113572893A (en) * | 2021-07-13 | 2021-10-29 | 青岛海信移动通信技术股份有限公司 | Terminal device, emotion feedback method and storage medium |
| CN113744445A (en) * | 2021-09-06 | 2021-12-03 | 北京雷石天地电子技术有限公司 | Match voting method, device, computer equipment and storage medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103412646B (en) * | 2013-08-07 | 2016-03-30 | 南京师范大学 | Based on the music mood recommend method of brain-machine interaction |
| CN106202103A (en) * | 2015-05-06 | 2016-12-07 | 阿里巴巴集团控股有限公司 | Music recommends method and apparatus |
| CN105426381B (en) * | 2015-08-27 | 2018-10-26 | 浙江大学 | A kind of music recommendation method based on microblogging mood context |
| CN107562850A (en) * | 2017-08-28 | 2018-01-09 | 百度在线网络技术（北京）有限公司 | Music recommends method, apparatus, equipment and storage medium |
-
2018
- 2018-05-30 CN CN201810537968.6A patent/CN108804609A/en not_active Withdrawn
- 2018-07-19 WO PCT/CN2018/096331 patent/WO2019227630A1/en active Application Filing
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109684501B (en) * | 2018-11-26 | 2023-08-22 | 平安科技（深圳）有限公司 | Lyric information generation method and device |
| CN109684501A (en) * | 2018-11-26 | 2019-04-26 | 平安科技（深圳）有限公司 | Lyrics information generation method and its device |
| CN111583890A (en) * | 2019-02-15 | 2020-08-25 | 阿里巴巴集团控股有限公司 | Audio classification method and device |
| WO2021004481A1 (en) * | 2019-07-08 | 2021-01-14 | 华为技术有限公司 | Media files recommending method and device |
| CN111128103A (en) * | 2019-12-19 | 2020-05-08 | 北京凯来科技有限公司 | Immersive KTV intelligent song-requesting system |
| CN111737414A (en) * | 2020-06-04 | 2020-10-02 | 腾讯音乐娱乐科技（深圳）有限公司 | Song recommendation method and device, server and storage medium |
| CN111753049A (en) * | 2020-06-15 | 2020-10-09 | 广东美的厨房电器制造有限公司 | Menu recommendation method and device, household appliance and storage medium |
| CN111753049B (en) * | 2020-06-15 | 2024-04-16 | 广东美的厨房电器制造有限公司 | Menu recommendation method and device, household electrical appliance and storage medium |
| CN112905835B (en) * | 2021-02-26 | 2022-11-11 | 成都潜在人工智能科技有限公司 | Multi-mode music title generation method and device and storage medium |
| CN112905835A (en) * | 2021-02-26 | 2021-06-04 | 成都潜在人工智能科技有限公司 | Multi-mode music title generation method and device and storage medium |
| CN113010728A (en) * | 2021-04-06 | 2021-06-22 | 金宝贝网络科技(苏州)有限公司 | Song recommendation method, system, intelligent device and storage medium |
| CN113572893B (en) * | 2021-07-13 | 2023-03-14 | 青岛海信移动通信技术股份有限公司 | Terminal device, emotion feedback method and storage medium |
| CN113572893A (en) * | 2021-07-13 | 2021-10-29 | 青岛海信移动通信技术股份有限公司 | Terminal device, emotion feedback method and storage medium |
| CN113518263A (en) * | 2021-07-23 | 2021-10-19 | 南京炫佳网络科技有限公司 | Video recommendation method and device for interactive network television, television and storage medium |
| CN113744445A (en) * | 2021-09-06 | 2021-12-03 | 北京雷石天地电子技术有限公司 | Match voting method, device, computer equipment and storage medium |
| CN113744445B (en) * | 2021-09-06 | 2024-01-05 | 北京雷石天地电子技术有限公司 | Method, device, computer equipment and storage medium for voting game |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019227630A1 (en) | 2019-12-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108804609A (en) | Song recommendation method and device | |
| Malik et al. | Stacked convolutional and recurrent neural networks for music emotion recognition | |
| CN110491383A (en) | A kind of voice interactive method, device, system, storage medium and processor | |
| US20180276540A1 (en) | Modeling of the latent embedding of music using deep neural network | |
| CN108874895B (en) | Interactive information pushing method and device, computer equipment and storage medium | |
| CN109582822A (en) | A kind of music recommended method and device based on user speech | |
| CN110209869A (en) | A kind of audio file recommended method, device and storage medium | |
| CN109474845A (en) | Bullet screen control method, bullet screen processing server and computer readable storage medium | |
| CN107589828A (en) | The man-machine interaction method and system of knowledge based collection of illustrative plates | |
| Kabani et al. | Emotion based music player | |
| CN110444229A (en) | Communication service method, device, computer equipment and storage medium based on speech recognition | |
| Medina et al. | Emotional classification of music using neural networks with the MediaEval dataset | |
| CN108766451B (en) | Audio file processing method and device and storage medium | |
| CN110010125A (en) | Control method and device of intelligent robot, terminal equipment and medium | |
| CN110851650B (en) | Comment output method and device and computer storage medium | |
| CN108804525A (en) | A kind of intelligent Answering method and device | |
| CN108614987A (en) | The method, apparatus and robot of data processing | |
| CN110162606A (en) | For solving the session proxy learning model services selection of client-side service request | |
| CN108847222A (en) | Speech recognition modeling generation method, device, storage medium and electronic equipment | |
| CN113813609A (en) | Game music style classification method and device, readable medium and electronic equipment | |
| CN108765011A (en) | Method and apparatus for creating user portrayal and creating state information analysis model | |
| Patel et al. | A comparative study of music recommendation systems | |
| CN107331399A (en) | Learning effect detection method and system and terminal equipment | |
| CN110070891B (en) | Song identification method and device and storage medium | |
| CN115798513A (en) | Talent expression management method, system and computer readable storage medium |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20181113 |