CN115168644A - Music influence factor analysis method, device and equipment based on complex network - Google Patents

Music influence factor analysis method, device and equipment based on complex network Download PDF

Info

Publication number
CN115168644A
CN115168644A CN202210907941.8A CN202210907941A CN115168644A CN 115168644 A CN115168644 A CN 115168644A CN 202210907941 A CN202210907941 A CN 202210907941A CN 115168644 A CN115168644 A CN 115168644A
Authority
CN
China
Prior art keywords
musicians
influencer
music
network
follower
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
CN202210907941.8A
Other languages
Chinese (zh)
Inventor
翟文硕
朱睿
俞棋睿
白亮
于天元
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.)
National University of Defense Technology
Original Assignee
National University of Defense Technology
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 National University of Defense Technology filed Critical National University of Defense Technology
Priority to CN202210907941.8A priority Critical patent/CN115168644A/en
Publication of CN115168644A publication Critical patent/CN115168644A/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
    • G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • 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
    • G06F16/65—Clustering; Classification

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Library & Information Science (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The application relates to a music influence factor analysis method, device and equipment based on a complex network. The method comprises the following steps: preprocessing music data of an influencer and a follower of a musician to obtain a feature vector of the music data; calculating cosine distance according to the characteristic vector of the music data to obtain the similarity between the influencer and the follower; respectively setting the in-degree and out-degree of the nodes in the directional network model as the number of influencers of the musicians and the number of followers of the musicians; fusing nodes in the directional network according to the genre and the age of the influencer to obtain a fused network; optimizing the fused network according to the similarity between the influencer and the follower, analyzing music influence factors of the musicians by using a complex network, and pushing music to the users according to the times and genres influencing the musicians. By adopting the method, the accuracy of music pushing can be improved.

Description

Music influence factor analysis method, device and equipment based on complex network
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a method and an apparatus for analyzing music influencing factors based on a complex network, a computer device, and a storage medium.
Background
Music is a part of human society from the beginning, is an important component of cultural heritage, and plays an important role in expressing the thought of people and reflecting social life.
The existing music pushing software, such as internet cloud and QQ music, has the problems of low accuracy rate of pushing related music, no accordance with the preference of a client and the like when recommending the same type of songs and musicians according to the music liked by the client and the downloaded music.
Disclosure of Invention
In view of the above, it is necessary to provide a complicated network-based music influence factor analysis method, apparatus, computer device and storage medium capable of improving music pushing accuracy of music software.
A music influence factor analysis method based on a complex network, the method comprising:
acquiring a musician data set in music software; the musician data set contains music data of a plurality of musicians influencers and followers;
preprocessing music data of an influencer and a follower of a musician to obtain a feature vector of the music data;
calculating cosine distance according to the characteristic vector of the music data to obtain the similarity between the influencer and the follower;
constructing a directional network model; respectively setting the in-degree and out-degree of the nodes in the directional network model as the number of influencers of the musicians and the number of followers of the musicians; fusing nodes in the directional network according to the genre and the age of the influencer to obtain a fused network;
optimizing the fused network according to the similarity between the influencer and the follower to obtain a complex network; nodes in the complex network represent musicians; a musician year-on-year attribute and a genre attribute;
analyzing music influence factors of the musicians by using a complex network to obtain the times and genres influencing the musicians;
and pushing music to the user according to the times and the genres of the affected musicians.
In one embodiment, the music influence factor analysis is performed on the musicians by using a complex network to obtain the ages and genres of the musicians, and the analysis comprises the following steps:
and according to the weight comparison result of all the edges of the musicians, selecting the year and the genre of the node corresponding to the edge with the highest weight as the year and the genre of the influenced musicians respectively.
In one embodiment, the calculating the cosine distance according to the feature vector of the music data to obtain the similarity between the influencer and the follower includes:
classifying the feature vectors of the music data according to the types of the musicians, putting the musicians of the same type into a set, calculating the cosine distance between every two seven-dimensional feature vectors in the set and the cosine distance between every two seven-dimensional feature vectors in different sets, and obtaining the similarity between an influencer and a follower of the musicians of the same type and the similarity between the influencer and the follower of different types of musicians.
In one embodiment, the similarity between the influencer and follower of the same type of musician is
Figure BDA0003773199510000021
Wherein, a ij Represents the cosine distance between the ith musician and the jth musician of the same type, n represents the number of feature vectors in the set of musicians of the same type,
Figure BDA0003773199510000022
representing the number of possible combinations of two-by-two combinations between musicians of the same type, i.e. a pair of an influencer and a follower between musicians of the same typeAll possible numbers of (a).
In one embodiment, the similarity between the influencer and follower for different types of musicians is
Figure BDA0003773199510000023
m and n represent the number of feature vectors in the current set of two different types of musicians, b ij Indicating the cosine distances of different types of the ith and jth musicians.
In one embodiment, fusing nodes in the directional network according to the genre and the age of the influencer to obtain a fused network, including:
and according to the genre and the year fusion nodes where the influencers are located, simultaneously accumulating the in-degree and the out-degree of each fusion node to form new in-degree and out-degree of the fused points, so as to obtain the fused network.
In one embodiment, optimizing the fused network according to the similarity between the influencer and the follower to obtain a complex network, including:
and determining the connection weight of the nodes in the fused network according to the similarity between the influencer and the follower, and optimizing the fused network according to the connection weight of the nodes to obtain the complex network.
A complex network based music impact factor analysis device, the device comprising:
the data preprocessing module is used for acquiring a musician data set in the music software; the musician data set contains music data of a plurality of musicians influencers and followers; preprocessing music data of an influencer and a follower of a musician to obtain a feature vector of the music data;
the similarity calculation module is used for calculating cosine distance according to the characteristic vector of the music data to obtain the similarity between the influencer and the follower;
the node fusion module is used for constructing a directional network model; respectively setting the in-degree and out-degree of the nodes in the directional network model as the number of influencers of the musicians and the number of followers of the musicians; fusing nodes in the directional network according to the genre and the age of the influencer to obtain a fused network;
the network optimization module is used for optimizing the fused network according to the similarity between the influencer and the follower to obtain a complex network; nodes in the complex network represent musicians; a musician year-on-year attribute and a genre attribute;
the music pushing module is used for analyzing music influence factors of the musicians by using a complex network to obtain the times and genres influencing the musicians; and pushing music to the user according to the times and the genres of the affected musicians.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
acquiring a musician data set in music software; the musician data set contains music data of a plurality of musicians influencers and followers;
preprocessing music data of an influencer and a follower of a musician to obtain a feature vector of the music data;
calculating cosine distance according to the characteristic vector of the music data to obtain the similarity between the influencer and the follower;
constructing a directional network model; respectively setting the in degree and the out degree of the nodes in the directional network model as the number of influencers of the musicians and the number of followers of the musicians; fusing nodes in the directional network according to the genre and the age of the influencer to obtain a fused network;
optimizing the fused network according to the similarity between the influencer and the follower to obtain a complex network; nodes in the complex network represent musicians; a musician year-on-year attribute and a genre attribute;
analyzing music influence factors of the musicians by using a complex network to obtain the times and genres influencing the musicians;
and pushing music to the user according to the times and the genres of the affected musicians.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring a musician data set in music software; the musician data set contains music data of a plurality of musicians influencers and followers;
preprocessing music data of an influencer and a follower of a musician to obtain a feature vector of the music data;
calculating cosine distance according to the characteristic vector of the music data to obtain the similarity between the influencer and the follower;
constructing a directional network model; respectively setting the in-degree and out-degree of the nodes in the directional network model as the number of influencers of the musicians and the number of followers of the musicians; fusing nodes in the directional network according to the genre and the age of the influencer to obtain a fused network;
optimizing the fused network according to the similarity between the influencer and the follower to obtain a complex network; nodes in the complex network represent musicians; a musician year-on-year attribute and a genre attribute;
analyzing music influence factors of the musicians by using a complex network to obtain the times and genres influencing the musicians;
and pushing music to the user according to the times and the genres of the affected musicians.
According to the music influence factor analysis method, the music influence factor analysis device, the computer equipment and the storage medium based on the complex network, the number of influencers of a musician and the number of followers of the musician are respectively set as the degree of entry and the degree of exit of nodes in the directional network model; the method comprises the steps of fusing nodes in a directional network according to genres and ages of influencers to obtain a fused network, then giving weights to the nodes in the fused network by utilizing the similarity between the influencers and followers of the same type and different types to perform network optimization, and using the similarity between the influencers and the followers as the weights of the nodes in the complex network, so that the influence of the influencers and the followers on music pushing can be better reflected.
Drawings
FIG. 1 is a schematic flow chart illustrating a method for analyzing influence factors of music over a complex network according to an embodiment;
FIG. 2 is a schematic diagram of a directed network of musical influence in one embodiment;
FIG. 3 is a block diagram of an apparatus for analyzing music influencing factors based on a complex network according to an embodiment;
FIG. 4 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application.
In one embodiment, as shown in fig. 1, there is provided a music influence factor analysis method based on a complex network, including the steps of:
102, acquiring a musician data set in music software; the musician data set contains music data of a plurality of musicians influencers and followers; music data of an influencer and a follower of a musician are preprocessed to obtain a feature vector of the music data.
The music data is data containing different music characteristics, including pop, rock, R \ and RAP, the influencer refers to the same type of musician or different types of musicians having influence on the musicians to compose music, the follower refers to the musicians who are influenced by the musicians to create the same type of music, the directional network model is shown in fig. 2 and comprises nodes and edges, and the nodes represent the musicians. Music data of an influencer and a follower of the musician are preprocessed to generate a multi-dimensional feature vector, each dimension corresponds to a feature index, and the feature vector can be used for calculating the similarity of the influencer and the follower of the musician.
And step 104, calculating cosine distance according to the feature vector of the music data to obtain the similarity between the influencer and the follower.
Classifying the feature vectors of the music data according to the types of the musicians to be analyzed, putting the musicians of the same type into a set, calculating the cosine distance between every two seven-dimensional feature vectors in the set and the cosine distance between every two seven-dimensional feature vectors in different sets, and obtaining the similarity between an influencer and a follower of the musicians of the same type and the similarity between an influencer and a follower of different types of musicians.
106, constructing a directional network model; respectively setting the in-degree and out-degree of the nodes in the directional network model as the number of influencers of the musicians and the number of followers of the musicians; and fusing the nodes in the directional network according to the genre and the age of the influencer to obtain a fused network.
The process of constructing the directed network model is prior art and is not described in great detail in this application. The degree of in-degree and the degree of out-degree of the nodes in the directional network model are respectively set as the number of influencers of the musicians and the number of followers of the musicians, and the influence degrees of the influencers and the followers on the musicians, namely the influence degrees of the influencers and the followers on the musicians, can be used as weights of edges in the network to preliminarily reflect the closeness degree of the relationship between the nodes.
Step 108, optimizing the fused network according to the similarity between the influencer and the follower to obtain a complex network; nodes in the complex network represent musicians; the musicians carry a year attribute and a genre attribute.
The similarity between the influencers and followers of the same type and different types is used for giving weights to the nodes in the fused network for network optimization, the similarity between the influencers and the followers is used as the weight of the edges in the complex network, and the influence of the influencers and the followers on music creation can be better reflected.
Step 110, analyzing music influence factors of the musicians by using a complex network to obtain the times and genres influencing the musicians; and pushing music to the user according to the times and the genres of the affected musicians.
The nodes in the complex network represent different musicians, the musicians can be divided into the same type of musicians and different types of musicians, the similarity between an influencer and a follower of the musicians is used as the weight of edges in the complex network, the influence of the influencer and the follower on music creation can be better reflected, whether the influencer of the same type of musicians or different types of musicians really influences the music created by the follower or not can be known, the influence of the same influencer on different followers or different influences of different influencers on specific followers can be known, the year and the genre of the node corresponding to the edge with the highest weight are respectively selected as the year and the genre of the influencer according to the comparison result of the weights of all the edges of the musicians, and the same year and genre of the user are pushed according to the year and genre of the influencer.
In the music influence factor analysis method based on the complex network, the number of the influencers of the musicians and the number of the followers of the musicians are respectively set as the degree of entry and the degree of exit of the nodes in the directional network model; the method comprises the steps of fusing nodes in a directional network according to genres and years in which influencers are located to obtain a fused network, then giving weights to the nodes in the fused network by utilizing the similarity between the influencers and followers of the same type and different types to perform network optimization, and using the similarity between the influencers and the followers as the weights of edges in a complex network, so that the influence of the influencers and the followers on music creation can be better reflected.
In one embodiment, the music influence factor analysis is performed on the musicians by using a complex network to obtain the ages and genres of the musicians, and the analysis comprises the following steps:
and according to the weight comparison result of all the edges of the musicians, selecting the year and the genre of the node corresponding to the edge with the highest weight as the year and the genre of the influenced musicians respectively.
In one embodiment, the calculating the cosine distance according to the feature vector of the music data to obtain the similarity between the influencer and the follower includes:
classifying the feature vectors of the music data according to the types of the musicians, putting the musicians of the same type into a set, calculating the cosine distance between every two seven-dimensional feature vectors in the set and the cosine distance between every two seven-dimensional feature vectors in different sets, and obtaining the similarity between an influencer and a follower of the musicians of the same type and the similarity between the influencer and the follower of different types of musicians.
In particular embodiments, the degree of influence of an influencer on a follower may be measured by calculating the similarity between influencers and followers for the same type of musician and the similarity between influencers and followers for different types of musicians.
In one embodiment, the similarity between the influencer and follower of the same type of musician is
Figure BDA0003773199510000081
Wherein, a ij Represents the cosine distance between the ith musician and the jth musician of the same type, n represents the number of feature vectors in the set of musicians of the same type,
Figure BDA0003773199510000082
representing the number of possible combinations of two-by-two combinations between musicians of the same type, i.e., all possible numbers of pairs of an influencer and a follower between musicians of the same type.
In one embodiment, the similarity between the influencer and follower for different types of musicians is
Figure BDA0003773199510000083
m and n represent the number of feature vectors in the current set of two different types of musicians, b ij Indicating the cosine distances of different types of the ith and jth musicians.
In one embodiment, fusing nodes in the directional network according to the genre and the age of the influencer to obtain a fused network, including:
and according to the genre and the year fusion nodes where the influencers are located, simultaneously accumulating the in-degree and the out-degree of each fusion node to form new in-degree and out-degree of the fused points, so as to obtain the fused network.
The network after node fusion can reasonably and skillfully reflect the influence of a certain music genre in each period, because the influence of music in different genres is greatly different in different ages, and the influence of a specific genre on music in different age groups in a specific year is also different, the fused network is more targeted, clearer and quantifiable in time.
In one embodiment, optimizing the fused network according to the similarity between the influencer and the follower to obtain a complex network, including:
and determining the connection weight of the nodes in the fused network according to the similarity between the influencer and the follower, and optimizing the fused network according to the connection weight of the nodes to obtain the complex network.
The nodes in the complex network represent different musicians, the musicians can be divided into the same type of musicians and different types of musicians, the similarity between an influencer and a follower of the musicians is used as the weight of the edges in the complex network, so that the influence of the influencer and the follower on music creation can be better reflected, whether the influencer of the same type of musicians or the different types of musicians really influences the music created by the followers or not can be known, and the influence of the same influencer on different followers or the different influence of different influencers on specific followers can be known.
It should be understood that, although the steps in the flowchart of fig. 1 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 1 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 3, there is provided a music influence factor analyzing apparatus based on a complex network, including: a data preprocessing module 302, a similarity calculation module 304, a node fusion module 306, a network optimization module 308, and a music push module 310, wherein:
a data preprocessing module 302, configured to obtain a musician data set in the music software; the musician data set contains music data of a plurality of musicians influencers and followers; preprocessing music data of an influencer and a follower of a musician to obtain a feature vector of the music data;
a similarity calculation module 304, configured to perform cosine distance calculation according to the feature vector of the music data to obtain a similarity between the influencer and the follower;
a node fusion module 306, configured to construct a directional network model; respectively setting the in-degree and out-degree of the nodes in the directional network model as the number of influencers of the musicians and the number of followers of the musicians; fusing nodes in the directional network according to the genre and the age of the influencer to obtain a fused network;
the network optimization module 308 is configured to optimize the fused network according to the similarity between the influencer and the follower, so as to obtain a complex network; nodes in the complex network represent musicians; a musician year-on-year attribute and a genre attribute;
the music pushing module 310 is configured to perform music influence factor analysis on the musicians by using a complex network to obtain the times and genres influencing the musicians; and pushing music to the user according to the times and the genres of the affected musicians.
For the specific limitation of the music influence factor analyzing apparatus based on the complex network, refer to the above limitation of the music influence factor analyzing method based on the complex network, and are not described herein again. The modules in the above-mentioned complicated network-based music influence factor analyzing apparatus may be wholly or partially implemented by software, hardware, or a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 4. The computer device comprises a processor, a memory, a network interface, a display screen and an input device which are connected through a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a complex network based music impact factor analysis method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 4 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In an embodiment, a computer device is provided, comprising a memory storing a computer program and a processor implementing the steps of the method in the above embodiments when the processor executes the computer program.
In an embodiment, a computer storage medium is provided, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method in the above-mentioned embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, and these are all within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (9)

1. A music influence factor analysis method based on a complex network is characterized by comprising the following steps:
acquiring a musician data set in music software; the musician data set contains music data of a plurality of musicians influencers and followers;
preprocessing the music data of the influencers and followers of the musicians to obtain the characteristic vectors of the music data;
calculating cosine distance according to the feature vector of the music data to obtain the similarity between the influencer and the follower;
constructing a directional network model; respectively setting the in-degree and out-degree of the nodes in the directional network model as the number of influencers of the musicians and the number of followers of the musicians; fusing nodes in the directional network according to the genre and the age of the influencer to obtain a fused network;
optimizing the fused network according to the similarity between the influencer and the follower to obtain a complex network; nodes in the complex network represent musicians; the musician carrying age attribute and genre attribute;
analyzing music influence factors of the musicians by using the complex network to obtain the times and genres influencing the musicians;
and carrying out music pushing on the user according to the age and the genre of the affected musicians.
2. The method of claim 1, wherein performing a music impact factor analysis on the musicians using the complex network to obtain the age and genre of the musicians comprises:
and taking the similarity between the influencers and the followers of the musicians as the weights of the edges in the complex network, and selecting the year and the genre of the node corresponding to the edge with the highest weight as the year and the genre of the influencers respectively according to the weight comparison results of all the edges of the musicians.
3. The method of claim 1, wherein the calculating the cosine distance according to the feature vector of the music data to obtain the similarity between the influencer and the follower comprises:
classifying the feature vectors of the music data according to the types of the musicians, putting the musicians of the same type into a set, calculating the cosine distance between every two seven-dimensional feature vectors in the set and the cosine distance between every two seven-dimensional feature vectors in different sets, and obtaining the similarity between an influencer and a follower of the musicians of the same type and the similarity between the influencer and the follower of different types of musicians.
4. The method of claim 3, wherein the similarity between the influencer and follower of the same type of artist is
Figure FDA0003773199500000021
Wherein, a ij Represents the cosine distance of the ith artist and the jth artist of the same type, n represents the number of feature vectors in the collection of artists of the same type,
Figure FDA0003773199500000022
representing the number of possible combinations of pairwise combinations between musicians of the same type, i.e., all possible numbers of a pair of an influencer and a follower between musicians of the same type.
5. The method of claim 4, wherein the similarity between the influencer and follower of different types of artists is
Figure FDA0003773199500000023
m and n represent the number of feature vectors in the current set of two artists of different types, b ij Indicating the cosine distance of the ith artist and the jth artist of different types.
6. The method according to claim 1, wherein fusing nodes in the directional network according to the influencer and the genre in which the influencer is located to obtain a fused network comprises:
and simultaneously accumulating the in-degree and out-degree of each fusion node according to the activity of the influencer and the genre fusion node where the influencer is located to form new in-degree and out-degree of the fused point, so as to obtain the fused network.
7. The method according to any one of claims 1 to 6, wherein optimizing the fused network according to the similarity between the influencer and the follower to obtain a complex network comprises: determining the connection weight of the nodes in the fused network according to the similarity between the influencer and the follower, and optimizing the fused network according to the connection weight of the nodes to obtain the complex network.
8. An apparatus for analyzing music influence factors based on a complex network, the apparatus comprising:
the data preprocessing module is used for acquiring a musician data set in the music software; the musician data set contains music data of a plurality of musicians influencers and followers; preprocessing the music data of the influencers and followers of the musicians to obtain the characteristic vectors of the music data;
the similarity calculation module is used for calculating cosine distance according to the characteristic vector of the music data to obtain the similarity between the influencer and the follower;
the node fusion module is used for constructing a directional network model; respectively setting the in-degree and out-degree of the nodes in the directional network model as the number of influencers of the musicians and the number of followers of the musicians; fusing nodes in the directional network according to the genre and the age of the influencer to obtain a fused network;
the network optimization module is used for optimizing the fused network according to the similarity between the influencer and the follower to obtain a complex network; nodes in the complex network represent musicians; the musician carrying year attribute and genre attribute;
the music pushing module is used for analyzing music influence factors of the musicians by utilizing the complex network to obtain the times and genres influencing the musicians; and carrying out music pushing on the user according to the age and the genre of the affected musicians.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.
CN202210907941.8A 2022-07-29 2022-07-29 Music influence factor analysis method, device and equipment based on complex network Pending CN115168644A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210907941.8A CN115168644A (en) 2022-07-29 2022-07-29 Music influence factor analysis method, device and equipment based on complex network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210907941.8A CN115168644A (en) 2022-07-29 2022-07-29 Music influence factor analysis method, device and equipment based on complex network

Publications (1)

Publication Number Publication Date
CN115168644A true CN115168644A (en) 2022-10-11

Family

ID=83476631

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210907941.8A Pending CN115168644A (en) 2022-07-29 2022-07-29 Music influence factor analysis method, device and equipment based on complex network

Country Status (1)

Country Link
CN (1) CN115168644A (en)

Similar Documents

Publication Publication Date Title
US20210287048A1 (en) System and method for efficient generation of machine-learning models
CN106251174A (en) Information recommendation method and device
CN111242310B (en) Feature validity evaluation method and device, electronic equipment and storage medium
Andrés et al. Linkages between Formal Institutions, ICT Adoption, and inclusive human development in sub-Saharan Africa
CN109918653B (en) Training method, device and equipment for determining related topics and model of text data
CN104679743A (en) Method and device for determining preference model of user
CN107818491A (en) Electronic installation, Products Show method and storage medium based on user's Internet data
Luque Ruiz et al. Robust QSAR prediction models for volume of distribution at steady state in humans using relative distance measurements
Linton et al. An extension to a DEA support system used for assessing R&D projects
CN113343091A (en) Industrial and enterprise oriented science and technology service recommendation calculation method, medium and program
CN111259167B (en) User request risk identification method and device
CN112989179B (en) Model training and multimedia content recommendation method and device
CN115630221A (en) Terminal application interface display data processing method and device and computer equipment
Murugesan et al. Benchmarking in cluster analysis: a study on spectral clustering, DBSCAN, and K-Means
CN110909975B (en) Scientific research platform benefit evaluation method and device
CN116503031B (en) Personnel similarity calculation method, device, equipment and medium based on resume analysis
CN111859238A (en) Method and device for predicting data change frequency based on model and computer equipment
CN117093477A (en) Software quality assessment method and device, computer equipment and storage medium
CN115796548A (en) Resource allocation method, device, computer equipment, storage medium and product
CN115168644A (en) Music influence factor analysis method, device and equipment based on complex network
CN113961811B (en) Event map-based conversation recommendation method, device, equipment and medium
CN114491296A (en) Proposal affiliate recommendation method, system, computer device and readable storage medium
US20140324523A1 (en) Missing String Compensation In Capped Customer Linkage Model
CN111125541B (en) Method for acquiring sustainable multi-cloud service combination for multiple users
Al-Zanbouri et al. Data-aware web service recommender system for energy-efficient data mining services

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