CN107592339B - Music recommendation method and music recommendation system based on intelligent terminal - Google Patents
Music recommendation method and music recommendation system based on intelligent terminal Download PDFInfo
- Publication number
- CN107592339B CN107592339B CN201710696436.2A CN201710696436A CN107592339B CN 107592339 B CN107592339 B CN 107592339B CN 201710696436 A CN201710696436 A CN 201710696436A CN 107592339 B CN107592339 B CN 107592339B
- Authority
- CN
- China
- Prior art keywords
- sound information
- environmental sound
- standard
- music
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a music recommendation method and a music recommendation system based on an intelligent terminal, wherein the music recommendation method comprises the following steps: establishing an environmental sound database containing standard environmental sound information corresponding to various scenes at the intelligent terminal; establishing a music recommendation list library at the intelligent terminal, wherein the music list library comprises a music recommendation list formed by music associated with any scene in the plurality of scenes; acquiring current environmental sound information of an environment where the intelligent terminal is located; and comparing the current environmental sound information with the standard environmental sound information, and pushing a music list associated with a scene corresponding to the standard environmental sound information in the music recommendation list library when the current environmental sound information is matched with the standard environmental sound information. The environment where the user is located can be identified by collecting environmental sounds, and a music list suitable for the current environment is pushed for the user in combination with the recommended music list intelligence under different scenes.
Description
Technical Field
The invention relates to the field of intelligent equipment, in particular to a music recommendation method and a music recommendation system based on an intelligent terminal.
Background
With the development of intelligent terminals, music listening has become an indispensable part of people's life gradually, and on the subway, on the public transport, in the car and at home, music listening has become a habit, and meanwhile, going to KTV singing also becomes a common entertainment mode. When listening to music or singing in a KTV, the user is prevented from selecting music and selecting different music in different scenes, and at present, many music playing software have recommended music lists in different scenes, but the user is required to enter the software input scene for searching, so that the operation is very complicated.
According to the method and the device, the environmental scene where the user is located at present is identified by collecting the environmental sound, the music list suitable for the current environment is pushed for the user in combination with the recommended music list intelligence under different scenes, active searching by the user is not needed, time is saved, simplicity and convenience are realized, and user experience is improved. Meanwhile, in order to improve the accuracy of scene recognition, the invention also verifies the current environment of the user through the position information and the Wi-Fi name information carried by the GPS and Wi-Fi signals of the intelligent terminal.
Disclosure of Invention
In order to overcome the technical defects, the invention aims to provide a music recommendation method and a music recommendation system based on an intelligent terminal, which can identify the current environment scene of a user by collecting environmental sounds, and push a music list suitable for the current environment for the user by combining the recommended music list intelligence under different scenes, thereby saving time, being simple and convenient, and improving user experience. Meanwhile, the current environment of the user is verified through the position information and the Wi-Fi name information carried by the GPS and Wi-Fi signals of the intelligent terminal, and the accuracy is improved.
The invention discloses a music recommendation method based on an intelligent terminal, which comprises the following steps:
establishing an environmental sound database containing standard environmental sound information corresponding to various scenes at the intelligent terminal;
establishing a music recommendation list library at the intelligent terminal, wherein the music list library comprises a music recommendation list formed by music associated with any scene in the plurality of scenes;
acquiring current environmental sound information of an environment where the intelligent terminal is located;
and comparing the current environmental sound information with the standard environmental sound information, and pushing a music list associated with a scene corresponding to the standard environmental sound information in the music recommendation list library when the current environmental sound information is matched with the standard environmental sound information.
Preferably, the step of establishing an ambient sound database containing standard ambient sound information corresponding to a plurality of scenes at the intelligent terminal includes:
collecting environmental sound information corresponding to a plurality of scenes;
extracting the same information in a plurality of pieces of environmental sound information corresponding to the same scene to form standard sound information;
acquiring a storage space in the intelligent terminal, and storing the standard sound information into the storage space to form an environmental sound database
Preferably, the step of collecting the current environmental sound information of the environment where the intelligent terminal is located includes:
calling a sound collection system of the intelligent terminal, and capturing a sound wave signal of the current environment where the intelligent terminal is located;
and storing the sound wave signal in the intelligent terminal to form current environment sound information.
Preferably, the step of comparing the current environmental sound information with the standard environmental sound information, and when the current environmental sound information matches the standard environmental sound information, pushing a music list associated with a scene corresponding to the standard environmental sound information in the music recommendation list library includes:
carrying out audio analysis on the environmental sound information, and extracting current audio features in the environmental sound information;
comparing the current audio features with standard audio features in the standard environmental sound information;
and when the current audio features comprise the standard audio features, the current audio features are matched with the standard audio features, and a music list associated with a scene corresponding to the standard environmental sound information in the music recommendation list library is pushed.
Preferably, the music recommendation method further comprises:
and acquiring the position information and/or the wireless network information in the intelligent terminal, and checking the current environment of the intelligent terminal according to the position information in the intelligent terminal and/or the wireless network name contained in the wireless network information.
The invention also discloses a music recommendation system based on the intelligent terminal, which comprises the following components:
the environment sound database establishing module is used for establishing an environment sound database containing standard environment sound information corresponding to various scenes on the intelligent terminal;
the music list library establishing module is used for establishing a music recommendation list library at the intelligent terminal, wherein the music list library comprises a music recommendation list formed by music associated with any scene in the plurality of scenes;
the sound acquisition module is used for acquiring current environment sound information of the environment where the intelligent terminal is located;
and the music list recommendation module is connected with the environmental sound database establishment module, the sound acquisition module and the music list establishment module, compares the current environmental sound information with the standard environmental sound information, and pushes a music list associated with a scene corresponding to the standard environmental sound information in the music recommendation list database when the current environmental sound information is matched with the standard environmental sound information.
Preferably, the ambient sound database building module includes:
the environment sound acquisition unit is used for acquiring environment sound information corresponding to various scenes;
the standard environmental sound information extraction unit is connected with the environmental sound acquisition unit and is used for extracting the same information in a plurality of pieces of environmental sound information corresponding to the same scene to form standard environmental sound information;
and the database establishing unit is connected with the standard sound information extracting unit, acquires a storage space in the intelligent terminal, and stores the standard environmental sound information into the storage space to form an environmental sound database.
Preferably, the sound collection module includes:
the sound wave signal acquisition unit is used for calling a sound acquisition system of the intelligent terminal and capturing a sound wave signal of the current environment where the intelligent terminal is located;
and the sound information storage unit is connected with the sound wave signal acquisition unit, and the intelligent terminal stores the sound wave signals to form current environment sound information.
Preferably, the music list recommendation module includes:
the audio characteristic extraction unit is used for carrying out audio analysis on the environmental sound information and extracting the current audio characteristic in the environmental sound information;
the sound information comparison unit is connected with the audio characteristic extraction unit and compares the current audio characteristic with a standard audio characteristic in the standard environment sound information;
and the music list recommendation unit is connected with the sound information comparison unit, and when the current audio features comprise the standard audio features, the current audio features are matched with the standard audio features, and a music list associated with a scene corresponding to the standard environmental sound information in the music recommendation list library is pushed.
Preferably, the music recommendation system further comprises:
and the verification module is connected with the music list recommendation module, acquires the position information and/or the wireless network information in the intelligent terminal, and verifies the current environment of the intelligent terminal through the position information in the intelligent terminal and/or the wireless network name contained in the wireless network information.
After the technical scheme is adopted, compared with the prior art, the method has the following beneficial effects:
1. the environment scene where the user is currently located can be identified by collecting the environment sound, and the music suitable for the current environment is intelligently recommended;
2. the time is saved, the method is simple and convenient, and the user experience is improved.
Drawings
FIG. 1 is a flow chart illustrating a music recommendation method according to a preferred embodiment of the present invention;
FIG. 2 is a flowchart illustrating a method for creating an ambient sound database according to a preferred embodiment of the present invention;
fig. 3 is a schematic flowchart of a method for acquiring current environmental sound information of an environment where the intelligent terminal is located according to a preferred embodiment of the present invention;
fig. 4 is a flowchart illustrating a method for pushing a music list associated with a scene corresponding to the standard environmental sound information in the music recommendation list library according to a preferred embodiment of the present invention;
FIG. 5 is a flow chart illustrating a music recommendation method according to another preferred embodiment of the present invention;
fig. 6 is a system diagram of a music recommendation system according to a preferred embodiment of the present invention.
Fig. 7 is a schematic structural diagram of an ambient sound database building module of the music recommendation system according to a preferred embodiment of the present invention.
Fig. 8 is a schematic structural diagram of a sound collection module of a music recommendation system according to a preferred embodiment of the present invention.
Fig. 9 is a schematic diagram of a connection structure of a setup module of the music recommendation system according to a preferred embodiment of the present invention.
Fig. 10 is a system configuration diagram of a music recommendation system according to another preferred embodiment of the present invention.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
The terminology used in the present disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. As used in this disclosure and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
In the description of the present invention, unless otherwise specified and defined, specific meanings of the above terms may be understood as specific circumstances by one of ordinary skill in the art.
In the following description, suffixes such as "module", "component", or "unit" used to denote elements are used only for facilitating the explanation of the present invention, and have no specific meaning in themselves. Thus, "module" and "component" may be used in a mixture.
The smart terminal may be implemented in various forms. For example, the terminal described in the present invention may include a mobile terminal such as a mobile phone, a smart phone, a notebook computer, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a navigation device, and the like, and a fixed terminal such as a digital TV, a desktop computer, and the like.
Fig. 1 is a schematic flow chart of a music recommendation method based on an intelligent terminal according to a preferred embodiment of the present invention. In this embodiment, the music recommendation method specifically includes the following steps:
s100: establishing an environmental sound database containing standard environmental sound information corresponding to various scenes on the intelligent terminal
The method includes the steps that environment sounds are collected to identify the current environment scene of a user so as to recommend proper music to the user, firstly, an environment sound database needs to be established, the database needs to contain environment sounds of various scenes, if the environment sounds are on a subway, standard environment sounds formed by subway sounds are contained, and if the environment sounds are KTV, standard environment sounds formed by KTV sound sounds are contained. The environment sound database can be established in various ways, and standard sounds with various scene characteristics, such as booming sound of a subway train and loud noise of KTV, can be directly downloaded from a network or introduced from other equipment, or can be acquired by acquiring sounds in a scene for many times and then learning through a sample. The standard environmental sound may be a unique characteristic sound of a scene, such as a booming sound of a subway in a subway environment, or may be a sound including a noise, such as a standard environmental sound including a human voice and a booming sound of a subway in a subway environment, where the standard environmental sound may be obtained by obtaining a common sound of a plurality of subway sounds. The specific method for using the standard environmental sound depends on the method for comparing the current environmental sound information with the standard environmental sound information.
S200: establishing a music recommendation list library at the intelligent terminal, wherein the music list library comprises music recommendation list composition formed by music associated with any scene in the plurality of scenes
The environment sound is collected to identify the current environment scene of the user so as to recommend proper music to the user, and besides an environment sound database needs to be established, a music recommendation list library also needs to be established. The music recommendation list library should include a plurality of scenes and a music recommendation list formed by music associated with any of the plurality of scenes. Particularly, three scenes of a subway, a house and a KTV are taken as examples, the music suitable for the three scenes is not very same, the subway is suitable for relatively noisy music due to large noise, the family is generally quite quiet and suitable for rest, so that the subway is suitable for quiet light music, and the KTV is generally mainly used for requesting songs and singing songs, so that the KTV is suitable for recommending popular song requesting songs, such as most dazzling folk winds, apples and the like. Therefore, the music recommendation list library should include three scenes, namely subway, home and KTV, each scene corresponds to one music recommendation list one by one, and when the system identifies that the current environment is in the subway or a certain scene, the music recommendation list library recommends the associated music list according to the music recommendation list library. The music recommendation list can be preset by a system, can be set by a user, is not fixed, and can be adjusted according to music selection of the user in the current scene and the like.
S300: acquiring current environment sound information of environment where intelligent terminal is located
After the environment sound database and the music recommendation list library are established, sound information of the current environment where the intelligent terminal is located needs to be collected, and current environment sound information is formed. Since various information, especially noise, generally exists in different scenes, various sound information also exists in the current environmental sound information. For example, when a subway starts, the sound collected on the subway not only includes the booming sound of the subway, but also includes a large amount of human voice, and when the sound information of the current environment is collected, the noise does not need to be removed, and the real and complete current environment sound is extracted. The method for collecting the current environmental sound is generally achieved by collecting sound wave signals through sound collection equipment or a sound collection system in the intelligent terminal.
S400: comparing the current environmental sound information with the standard environmental sound information, and pushing a music list associated with a scene corresponding to the standard environmental sound information in the music recommendation list library when the current environmental sound information is matched with the standard environmental sound information
After current environment sound information is acquired through sound acquisition equipment in the intelligent terminal, in order to identify the current environment, the current environment sound information needs to be compared with standard environment sound information, and when the current environment sound information is matched with the standard environment sound information, a music list associated with a scene corresponding to the standard environment sound information in the music recommendation list library is pushed to a user. Here, instead of playing music directly to the user, a list of music suitable for the current environment is pushed to the user, and the user selects whether to listen to the music or which music to listen to the music. The method for comparing the current environmental sound information with the standard environmental sound information can be through integral comparison, because the integral environmental sound under different environments is very different, such as subway, KTV, home, supermarket, and the integral is very different, therefore, the current environmental sound information can be separated into a plurality of groups of different sounds through integral comparison method, or through characteristic comparison, taking the environmental sound in subway as an example, it can be divided into booming sound and human voice when subway starts, at this time, the sound information in the environmental sound database should also be separated, the booming sound of subway is extracted as the standard environmental sound information of subway, when the comparison result after comparing the current environmental sound information with the standard environmental sound information of subway is that the current environmental sound information includes the standard environmental sound information of subway, the current environmental sound information should be considered to be matched with the standard environmental sound information, and at the moment, a music list associated with the subway scene corresponding to the standard environmental sound information is pushed according to the music recommendation list library, and music suitable for listening in the subway is pushed.
After the configuration is adopted, the current environment scene of the user can be identified by collecting the environment sound, and the music list suitable for the current environment is pushed for the user by combining the recommended music list intelligence under different scenes, so that the user experience is improved.
Referring to fig. 2, in a preferred embodiment, the step of establishing an ambient sound database containing standard ambient sound information corresponding to a plurality of scenes in the intelligent terminal specifically includes:
s101: collecting environmental sound information corresponding to multiple scenes
The method for extracting the standard environmental sound information by collecting the environmental sound information and learning through samples can be used for establishing the environmental sound database containing the standard environmental sound information corresponding to various scenes. Therefore, enough environmental sound information needs to be collected firstly, and in order to ensure the accuracy of the standard environmental sound information extraction result, the environmental sound needs to be collected for multiple times in the same scene, so that the sample size is increased, and the accuracy is improved. Meanwhile, because environmental sound information of different scenes is required, different scenes also need to be collected, and each scene collects a plurality of environmental sound samples. The scenes captured here should correspond to the scenes of the music recommendation list. The method for collecting the environmental sound is to call the sound collecting equipment or the sound collecting system of the intelligent terminal, capture the sound wave of the environment where the intelligent terminal is located, collect the environmental sound information of the environment where the intelligent terminal is located, avoid the intelligent terminal holder to send the sound of great loudness during collection, so as not to interfere collection, because the sound signal intensity of the nearest position of the sound collecting equipment can be far higher than the surrounding environment sound, and the weakening of the environmental sound is caused.
S102: extracting the same information in a plurality of environment sound information corresponding to the same scene to form standard environment sound information
After the environmental sound information is collected, a plurality of environmental sound information collected in the same scene need to be processed, and an audio information having the most characteristic of the scene is obtained as standard environmental sound information. The method for obtaining the audio information with the most scene characteristics can be to perform mean analysis on a plurality of environment sound information corresponding to the same scene to obtain the whole sound information of the scene, and can also extract a plurality of same information corresponding to the same scene in the environment sound information, the same information is the most audio information with the most scene characteristics, taking a subway as an example, the environment sound information collected on the subway has necessarily noisy human voice and booming voice of subway running, and human voice is different, but the booming voice of subway running is basically consistent, therefore, the basically same booming voice and different human voice of subway running can be separated from the environment sound information collected many times on the subway, the same information in the subway environment sound information collected many times is extracted here, namely the booming voice of subway running, and the audio information with the most scene characteristics on the subway is the sound of subway running, when a booming sound containing nearly uniform subway travel is detected in a certain sound, it can be considered to be on the subway. Therefore, the same information in the plurality of pieces of environmental sound information corresponding to the same scene is the audio information having the most characteristic of the scene, and the same information in the plurality of pieces of environmental sound information corresponding to the same scene may be extracted as the standard environmental sound information of the scene. When extracting, the environmental sound information needs to be converted from the analog signal into the digital signal, then the characteristic extraction and the filtering are carried out, so that the sound is separated, and the same audio information is obtained through a plurality of comparisons.
S103: acquiring a storage space in the intelligent terminal, and storing the standard environmental sound information into the storage space to form an environmental sound database
The method comprises the steps of extracting the same information in a plurality of environment sound information corresponding to the same scene, obtaining a storage space in an intelligent terminal after forming standard environment sound information, storing the standard environment sound information of each scene in the storage space to form an environment sound database, and storing the standard environment sound information and the scene names represented by the standard environment sound information in a one-to-one correspondence mode.
Referring to fig. 3, in a preferred embodiment, the step of collecting the current environmental sound information of the environment where the intelligent terminal is located specifically includes:
s301: calling a sound collection system of the intelligent terminal, and capturing a sound wave signal of the current environment where the intelligent terminal is located
After the environment sound database and the music recommendation list library are established, sound information of the current environment where the intelligent terminal is located needs to be collected, and current environment sound information is formed. The method comprises the steps of collecting sound information of the current environment of the intelligent terminal, calling a sound collection system of the intelligent terminal, and capturing sound wave signals of the current environment of the intelligent terminal through the sound collection system, wherein the collected recording system is a sound collection system and can be used for capturing the sound wave signals of the current environment of the intelligent terminal and collecting the sound information of the current environment.
S302: storing the sound wave signal in the intelligent terminal to form current environmental sound information
After the sound wave signal of the current environment where the intelligent terminal is located is captured and acquired, the sound wave signal needs to be stored in the intelligent terminal to form current environment sound information so as to carry out audio processing on the current environment sound information.
Referring to fig. 4, in a preferred embodiment, comparing the current environmental sound information with the standard environmental sound information, and when the current environmental sound information matches the standard environmental sound information, the step of pushing the music list associated with the scene corresponding to the standard environmental sound information in the music recommendation list library specifically includes:
s401: performing audio analysis on the environmental sound information, and extracting current audio features in the environmental sound information
After an environment sound database formed by standard environment sound information is established and current environment sound information of the intelligent terminal is collected, the current environment needs to be identified through comparison. Because the standard environmental sound information in the environmental sound database is processed audio information, in order to complete audio comparison, the current environmental sound information needs to be processed, the processing method is suitable for the processing method when the standard environmental sound information is obtained, if the standard environmental sound information is obtained, mean analysis is carried out on the current environmental sound information, multiple times of environmental sounds are collected in the current scene for mean analysis, if the standard environmental sound information is obtained, the same information in the standard environmental sound information is extracted as the audio information with the most characteristics of the scene, the processing method of the current environmental sound information suitable for the standard environmental sound information is to separate the current environmental sound information and separate the sounds emitted by different sound sources, no matter which audio analysis method, the tone color of each sound needs to be extracted finally, And audio features such as tone and loudness form the current audio feature.
S402: comparing the current audio features with standard audio features in the standard environmental sound information
After the current audio features of the current environmental sound information are obtained, audio features such as timbre, tone, loudness and the like in the standard environmental sound information also need to be extracted to form standard audio features, the current audio features are compared with the standard audio features in the standard environmental sound information, a comparison method is adapted to a processing method when the standard environmental sound information is obtained and a processing method of the current environmental sound information, a comparison method is integrated comparison when mean value analysis is carried out, when the standard environmental sound information is obtained, the same information in the standard environmental sound information is extracted to serve as the audio information with the most characteristics of the scene, the processing of the current environmental sound information adapted to the current environmental sound information is to separate the current environmental sound information to separate the sounds emitted by different sound sources, the matching method is a single comparison, which compares the sound emitted by different separated sound sources with the standard environmental sound. No matter what kind of comparison method is used for comparison, the audio characteristics such as tone, tone and loudness are compared.
S403: when the current audio features comprise the standard audio features, the current audio features are matched with the standard audio features, and a music list associated with a scene corresponding to the standard environmental sound information in the music recommendation list library is pushed
And after comparing the current audio features with the standard audio features in the standard environmental sound information, when the current audio features contain the standard audio features, considering that the current audio features are matched with the standard audio features. The standard of the current audio features including the standard audio features is that the current audio features identical to the standard audio features exist, the identical standard is mainly based on tone and tone, and the loudness is auxiliary. And if the current audio features are matched with the standard audio features, the current environment sound information is matched with the standard environment sound information, the scene where the intelligent terminal is located is a scene corresponding to the standard environment sound information, and a music list associated with the scene corresponding to the standard environment sound information is pushed according to the music recommendation list.
Fig. 5 is a schematic flowchart of a music recommendation method based on an intelligent terminal according to another preferred embodiment of the present invention. In this embodiment, the music recommendation method further includes the following steps:
s500: acquiring the position information and/or the wireless network information in the intelligent terminal, and checking the current environment of the intelligent terminal according to the position information in the intelligent terminal and/or the wireless network name contained in the wireless network information
The environment can be identified through comparison of environmental sound information, errors exist, therefore, GPS positioning information in the intelligent terminal and Wi-Fi information connected with the intelligent terminal can be assisted in identifying the environment, the current environment judged through comparison of the environmental sound information is verified through the two information or one of the two information, if the current environment is identified to be KTV through comparison of the environmental sound information, a KTV exists in the position where the GPS is located or the position within the GPS error range through GPS positioning, the judgment result is accurate, the verification can also be verified through the Wi-Fi information, and if the name of Wi-Fi connected with the intelligent terminal is a certain KTV or the IP number of the Wi-Fi belongs to a certain KTV, the judgment can be considered to be accurate. If the GPS positioning information and the Wi-Fi information connected with the intelligent terminal are verified, if one verification result is that the judgment is accurate, the judgment is accurate. If the verification result is that the judgment is wrong, the current environmental sound information is collected again for recognition, and the music list can be pushed to the user and then confirmed by the user.
Referring to fig. 6, a music recommendation system based on an intelligent terminal according to a preferred embodiment of the present invention specifically includes the following components:
the environment sound database establishing module is used for identifying the current environment scene of the user by collecting environment sounds so as to recommend proper music to the user, firstly, an environment sound database needs to be established, the database comprises environment sounds of various scenes, if the environment sounds are on a subway, standard environment sounds formed by subway sounds are included, and if the environment sounds are KTV, standard environment sounds formed by KTV sound sounds are included. The environment sound database can be established in various ways, and standard sounds with various scene characteristics, such as booming sound of a subway train and loud noise of KTV, can be directly downloaded from a network or introduced from other equipment, or can be acquired by acquiring sounds in a scene for many times and then learning through a sample. The standard environmental sound may be a unique characteristic sound of a scene, such as a booming sound of a subway in a subway environment, or may be a sound including a noise, such as a standard environmental sound including a human voice and a booming sound of a subway in a subway environment, where the standard environmental sound may be obtained by obtaining a common sound of a plurality of subway sounds. The specific method for using the standard environmental sound depends on the method for comparing the current environmental sound information with the standard environmental sound information.
The music list library establishing module is used for identifying the current environment scene of the user by collecting the environment sound so as to recommend proper music to the user, and needs to establish a music recommendation list library besides an environment sound database. The music recommendation list library should include a plurality of scenes and a music recommendation list formed by music associated with any of the plurality of scenes. Particularly, three scenes of a subway, a house and a KTV are taken as examples, the music suitable for the three scenes is not very same, the subway is suitable for relatively noisy music due to large noise, the family is generally quite quiet and suitable for rest, so that the subway is suitable for quiet light music, and the KTV is generally mainly used for requesting songs and singing songs, so that the KTV is suitable for recommending popular song requesting songs, such as most dazzling folk winds, apples and the like. Therefore, the music recommendation list library should include three scenes, namely subway, home and KTV, each scene corresponds to one music recommendation list one by one, and when the system identifies that the current environment is in the subway or a certain scene, the music recommendation list library recommends the associated music list according to the music recommendation list library. The music recommendation list can be preset by a system, can be set by a user, is not fixed, and can be adjusted according to music selection of the user in the current scene and the like.
And the sound acquisition module is used for acquiring sound information of the current environment where the intelligent terminal is located after the environment sound database and the music recommendation list library are established, so as to form the sound information of the current environment. Since various information, especially noise, generally exists in different scenes, various sound information also exists in the current environmental sound information. For example, when a subway starts, the sound collected on the subway not only includes the booming sound of the subway, but also includes a large amount of human voice, and when the sound information of the current environment is collected, the noise does not need to be removed, and the real and complete current environment sound is extracted. The method for collecting the current environmental sound is generally achieved by collecting sound wave signals through sound collection equipment or a sound collection system in the intelligent terminal.
And the music list recommendation module is connected with the environmental sound database establishment module, the sound collection module and the music list establishment module, after current environmental sound information is acquired through sound collection equipment in the intelligent terminal, in order to identify the current environment, the current environmental sound information needs to be compared with standard environmental sound information, and when the current environmental sound information is matched with the standard environmental sound information, a music list associated with a scene corresponding to the standard environmental sound information in the music recommendation list database is pushed to a user. Here, instead of playing music directly to the user, a list of music suitable for the current environment is pushed to the user, and the user selects whether to listen to the music or which music to listen to the music. The method for comparing the current environmental sound information with the standard environmental sound information can be through integral comparison, because the integral environmental sound under different environments is very different, such as subway, KTV, home, supermarket, and the integral is very different, therefore, the current environmental sound information can be separated into a plurality of groups of different sounds through integral comparison method, or through characteristic comparison, taking the environmental sound in subway as an example, it can be divided into booming sound and human voice when subway starts, at this time, the sound information in the environmental sound database should also be separated, the booming sound of subway is extracted as the standard environmental sound information of subway, when the comparison result after comparing the current environmental sound information with the standard environmental sound information of subway is that the current environmental sound information includes the standard environmental sound information of subway, the current environmental sound information should be considered to be matched with the standard environmental sound information, and at the moment, a music list associated with the subway scene corresponding to the standard environmental sound information is pushed according to the music recommendation list library, and music suitable for listening in the subway is pushed.
Referring to fig. 7, in a preferred embodiment, the ambient sound database creating module specifically includes:
the environmental sound acquisition unit is used for establishing an environmental sound database containing standard environmental sound information corresponding to various scenes, and can be used for extracting the standard environmental sound information by acquiring the environmental sound information and learning through samples. Therefore, enough environmental sound information needs to be collected firstly, and in order to ensure the accuracy of the standard environmental sound information extraction result, the environmental sound needs to be collected for multiple times in the same scene, so that the sample size is increased, and the accuracy is improved. Meanwhile, because environmental sound information of different scenes is required, different scenes also need to be collected, and each scene collects a plurality of environmental sound samples. The scenes captured here should correspond to the scenes of the music recommendation list. The method for collecting the environmental sound is to call the sound collecting equipment or the sound collecting system of the intelligent terminal, capture the sound wave of the environment where the intelligent terminal is located, collect the environmental sound information of the environment where the intelligent terminal is located, avoid the intelligent terminal holder to send the sound of great loudness during collection, so as not to interfere collection, because the sound signal intensity of the nearest position of the sound collecting equipment can be far higher than the surrounding environment sound, and the weakening of the environmental sound is caused.
And the standard environmental sound information extraction unit is connected with the environmental sound acquisition unit, and is used for processing a plurality of pieces of environmental sound information acquired in the same scene after acquiring the environmental sound information to obtain audio information with the most scene characteristics as the standard environmental sound information. The method for obtaining the audio information with the most scene characteristics can be to perform mean analysis on a plurality of environment sound information corresponding to the same scene to obtain the whole sound information of the scene, and can also extract a plurality of same information corresponding to the same scene in the environment sound information, the same information is the most audio information with the most scene characteristics, taking a subway as an example, the environment sound information collected on the subway has necessarily noisy human voice and booming voice of subway running, and human voice is different, but the booming voice of subway running is basically consistent, therefore, the basically same booming voice and different human voice of subway running can be separated from the environment sound information collected many times on the subway, the same information in the subway environment sound information collected many times is extracted here, namely the booming voice of subway running, and the audio information with the most scene characteristics on the subway is the sound of subway running, when a booming sound containing nearly uniform subway travel is detected in a certain sound, it can be considered to be on the subway. Therefore, the same information in the plurality of pieces of environmental sound information corresponding to the same scene is the audio information having the most characteristic of the scene, and the same information in the plurality of pieces of environmental sound information corresponding to the same scene may be extracted as the standard environmental sound information of the scene. When extracting, the environmental sound information needs to be converted from the analog signal into the digital signal, then the characteristic extraction and the filtering are carried out, so that the sound is separated, and the same audio information is obtained through a plurality of comparisons.
And the database establishing unit is connected with the standard sound information extracting unit, extracts the same information in a plurality of environment sound information corresponding to the same scene, forms standard environment sound information, needs to acquire a storage space in the intelligent terminal, stores the standard environment sound information of each scene in the storage space, forms an environment sound database, and not only needs to store the standard environment sound information but also needs to store the scene names represented by the standard environment sound information during storage to perform one-to-one correspondence.
Referring to fig. 8, in a preferred embodiment, the sound collection module specifically includes:
and the sound wave signal acquisition unit is used for acquiring the sound information of the current environment where the intelligent terminal is located after the environment sound database and the music recommendation list library are established, so as to form the sound information of the current environment. The method comprises the steps of collecting sound information of the current environment of the intelligent terminal, calling a sound collection system of the intelligent terminal, and capturing sound wave signals of the current environment of the intelligent terminal through the sound collection system, wherein the collected recording system is a sound collection system and can be used for capturing the sound wave signals of the current environment of the intelligent terminal and collecting the sound information of the current environment.
And the sound information storage unit is connected with the sound wave signal acquisition unit, captures and acquires the sound wave signal of the current environment where the intelligent terminal is located, and then stores the sound wave signal in the intelligent terminal to form the sound information of the current environment so as to carry out audio processing on the sound information.
Referring to fig. 9, in a preferred embodiment, the music list recommendation module specifically includes:
and the audio characteristic extraction unit is used for establishing an environment sound database formed by standard environment sound information, acquiring current environment sound information of the intelligent terminal, and identifying the current environment by comparison. Because the standard environmental sound information in the environmental sound database is processed audio information, in order to complete audio comparison, the current environmental sound information needs to be processed, the processing method is suitable for the processing method when the standard environmental sound information is obtained, if the standard environmental sound information is obtained, mean analysis is carried out on the current environmental sound information, multiple times of environmental sounds are collected in the current scene for mean analysis, if the standard environmental sound information is obtained, the same information in the standard environmental sound information is extracted as the audio information with the most characteristics of the scene, the processing method of the current environmental sound information suitable for the standard environmental sound information is to separate the current environmental sound information and separate the sounds emitted by different sound sources, no matter which audio analysis method, the tone color of each sound needs to be extracted finally, And audio features such as tone and loudness form the current audio feature.
A sound information comparison unit connected to the audio feature extraction unit, for extracting the audio features such as timbre, tone and loudness in the standard environmental sound information after acquiring the current audio feature of the current environmental sound information to form a standard audio feature, comparing the current audio feature with the standard audio feature in the standard environmental sound information, wherein the comparison method is adapted to the processing method for acquiring the standard environmental sound information and the processing method for the current environmental sound information, the comparison method is an integral comparison in mean analysis, when the same information in the standard environmental sound information is extracted as the audio information with the most characteristic of the scene in acquiring the standard environmental sound information, the processing of the current environmental sound information adapted to the standard environmental sound information is to separate the current environmental sound information to separate the sounds emitted by different sound sources, and the comparison method adapted to the current environmental sound information is a single comparison, and comparing the separated sounds emitted by different sound sources with the standard environmental sound. No matter what kind of comparison method is used for comparison, the audio characteristics such as tone, tone and loudness are compared.
And the music list recommendation unit is connected with the sound information comparison unit, compares the current audio features with the standard audio features in the standard environment sound information, and considers that the current audio features are matched with the standard audio features when the current audio features contain the standard audio features. The standard of the current audio features including the standard audio features is that the current audio features identical to the standard audio features exist, the identical standard is mainly based on tone and tone, and the loudness is auxiliary. And if the current audio features are matched with the standard audio features, the current environment sound information is matched with the standard environment sound information, the scene where the intelligent terminal is located is a scene corresponding to the standard environment sound information, and a music list associated with the scene corresponding to the standard environment sound information is pushed according to the music recommendation list.
Referring to fig. 10, in order to provide a music recommendation system based on an intelligent terminal according to another preferred embodiment of the present invention, the application control system further includes the following components:
the verification module is connected with the music list recommendation module, and can identify the environment through comparison of environmental sound information, but has errors, so that GPS positioning information in the intelligent terminal and Wi-Fi information connected with the intelligent terminal can be assisted when the environment is identified, the current environment judged through comparison of the environmental sound information is verified through the two information or one of the two information, if the current environment is identified to be KTV through comparison of the environmental sound information, through GPS positioning, a KTV is found to exist in the position where the GPS is located or the position within the GPS error range, the verification result is accurate judgment, and can also be verified through the Wi-Fi information, and if the name of the Wi-Fi connected with the intelligent terminal is a certain KTV or the IP number of the Wi-Fi belongs to a certain KTV, the judgment can be considered to be accurate. If the GPS positioning information and the Wi-Fi information connected with the intelligent terminal are verified, if one verification result is that the judgment is accurate, the judgment is accurate. If the verification result is that the judgment is wrong, the current environmental sound information is collected again for recognition, and the music list can be pushed to the user and then confirmed by the user.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It should be noted that the embodiments of the present invention have been described in terms of preferred embodiments, and not by way of limitation, and that those skilled in the art can make modifications and variations of the embodiments described above without departing from the spirit of the invention.
Claims (6)
1. A music recommendation method based on an intelligent terminal is characterized by comprising the following steps:
establishing an environmental sound database containing standard environmental sound information corresponding to various scenes at the intelligent terminal;
establishing a music recommendation list library at the intelligent terminal, wherein the music recommendation list library comprises a music recommendation list formed by music associated with any scene in the plurality of scenes;
acquiring current environmental sound information of an environment where the intelligent terminal is located;
comparing the current environmental sound information with the standard environmental sound information, and pushing a music list associated with a scene corresponding to the standard environmental sound information in the music recommendation list library when the current environmental sound information is matched with the standard environmental sound information;
the step of establishing an environmental sound database containing standard environmental sound information corresponding to a plurality of scenes at the intelligent terminal comprises the following steps:
collecting environmental sound information corresponding to a plurality of scenes;
performing mean value analysis on a plurality of pieces of environmental sound information corresponding to the same scene to obtain the whole sound information of the scene to form first standard environmental sound information, or extracting the same information in the plurality of pieces of environmental sound information corresponding to the same scene to form second standard environmental sound information;
acquiring a storage space in the intelligent terminal, and storing the first standard environmental sound information or the second standard environmental sound information into the storage space to form an environmental sound database;
the step of comparing the current environmental sound information with the standard environmental sound information includes:
when the standard environmental sound information is first standard environmental sound information, acquiring multiple times of current environmental sound information to perform mean value analysis, and performing integral comparison on the current environmental sound information subjected to the mean value analysis and the first standard environmental sound information; when the standard environmental sound information is first standard environmental sound information, separating the collected current environmental sound information, separating the sounds emitted by different sound sources, and comparing the separated sounds emitted by different sound sources with the standard environmental sound; wherein, when comparing, the tone and the loudness are compared;
the music recommendation method further comprises the steps of,
and acquiring the position information and/or the wireless network information in the intelligent terminal, and checking the current environment of the intelligent terminal according to the position information in the intelligent terminal and/or the wireless network name contained in the wireless network information.
2. The music recommendation method of claim 1,
the step of collecting the current environmental sound information of the environment where the intelligent terminal is located comprises the following steps:
calling a sound collection system of the intelligent terminal, and capturing a sound wave signal of the current environment where the intelligent terminal is located;
and storing the sound wave signal in the intelligent terminal to form current environment sound information.
3. The music recommendation method of claim 1,
comparing the current environmental sound information with the standard environmental sound information, and when the current environmental sound information is matched with the standard environmental sound information, pushing a music list associated with a scene corresponding to the standard environmental sound information in the music recommendation list library, wherein the step of pushing the music list comprises the following steps:
carrying out audio analysis on the environmental sound information, and extracting current audio features in the environmental sound information;
comparing the current audio features with standard audio features in the standard environmental sound information;
and when the current audio features comprise the standard audio features, the current audio features are matched with the standard audio features, and a music list associated with a scene corresponding to the standard environmental sound information in the music recommendation list library is pushed.
4. The utility model provides a music recommendation system based on intelligent terminal which characterized in that includes:
the environment sound database establishing module is used for establishing an environment sound database containing standard environment sound information corresponding to various scenes on the intelligent terminal;
the music recommendation system comprises a music list library establishing module, a music recommendation module and a music recommendation module, wherein the music list library establishing module establishes a music recommendation list library at the intelligent terminal, and the music recommendation list library comprises a music recommendation list formed by music associated with any scene in the plurality of scenes;
the sound acquisition module is used for acquiring current environment sound information of the environment where the intelligent terminal is located;
the music list recommendation module is connected with the ambient sound database establishment module, the sound acquisition module and the music list library establishment module, compares the current ambient sound information with the standard ambient sound information, and pushes a music list associated with a scene corresponding to the standard ambient sound information in the music recommendation list library when the current ambient sound information is matched with the standard ambient sound information;
the environment sound database building module comprises:
the environment sound acquisition unit is used for acquiring environment sound information corresponding to various scenes;
the standard environmental sound information extraction unit is connected with the environmental sound acquisition unit and is used for carrying out mean value analysis on a plurality of pieces of environmental sound information corresponding to the same scene to obtain the whole sound information of the scene to form first standard environmental sound information, or extracting the same information in a plurality of pieces of environmental sound information corresponding to the same scene to form second standard environmental sound information;
the database establishing unit is connected with the standard environmental sound information extracting unit, acquires a storage space in the intelligent terminal, and stores the first standard environmental sound information or the second standard environmental sound information into the storage space to form an environmental sound database;
the music list recommendation module comprises a sound information comparison unit, wherein the sound information comparison unit is used for collecting current environment sound information for multiple times to perform mean value analysis when the standard environment sound information is first standard environment sound information, and performing integral comparison on the current environment sound information subjected to the mean value analysis and the first standard environment sound information;
when the standard environmental sound information is first standard environmental sound information, separating the collected current environmental sound information, separating the sounds emitted by different sound sources, and comparing the separated sounds emitted by different sound sources with the standard environmental sound; wherein, when comparing, the tone and the loudness are compared;
the music recommendation system further comprises:
and the verification module is connected with the music list recommendation module, acquires the position information and/or the wireless network information in the intelligent terminal, and verifies the current environment of the intelligent terminal through the position information in the intelligent terminal and/or the wireless network name contained in the wireless network information.
5. The music recommendation system of claim 4,
the sound collection module includes:
the sound wave signal acquisition unit is used for calling a sound acquisition system of the intelligent terminal and capturing a sound wave signal of the current environment where the intelligent terminal is located;
and the sound information storage unit is connected with the sound wave signal acquisition unit, and the intelligent terminal stores the sound wave signals to form current environment sound information.
6. The music recommendation system of claim 4,
the music list recommendation module comprises:
the audio characteristic extraction unit is used for carrying out audio analysis on the environmental sound information and extracting the current audio characteristic in the environmental sound information;
the sound information comparison unit is connected with the audio characteristic extraction unit and compares the current audio characteristic with a standard audio characteristic in the standard environment sound information;
and the music list recommendation unit is connected with the sound information comparison unit, and when the current audio features comprise the standard audio features, the current audio features are matched with the standard audio features, and a music list associated with a scene corresponding to the standard environmental sound information in the music recommendation list library is pushed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710696436.2A CN107592339B (en) | 2017-08-15 | 2017-08-15 | Music recommendation method and music recommendation system based on intelligent terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710696436.2A CN107592339B (en) | 2017-08-15 | 2017-08-15 | Music recommendation method and music recommendation system based on intelligent terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107592339A CN107592339A (en) | 2018-01-16 |
| CN107592339B true CN107592339B (en) | 2021-05-18 |
Family
ID=61043152
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710696436.2A Active CN107592339B (en) | 2017-08-15 | 2017-08-15 | Music recommendation method and music recommendation system based on intelligent terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107592339B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111753127B (en) * | 2019-03-29 | 2024-05-07 | 阿里巴巴集团控股有限公司 | Music information processing and recommending method and device |
| CN110401769A (en) * | 2019-07-15 | 2019-11-01 | 上海听邸文化传媒工作室 | A kind of multizone sound scape rendering method, system and storage medium |
| CN111601000B (en) * | 2020-05-14 | 2022-03-08 | 支付宝(杭州)信息技术有限公司 | Communication network fraud identification method and device and electronic equipment |
| CN112181348A (en) * | 2020-08-28 | 2021-01-05 | 星络智能科技有限公司 | Sound style switching method, system, computer equipment and readable storage medium |
| CN113616898B (en) * | 2021-08-09 | 2023-08-04 | 深圳分贝声学科技有限公司 | Noise pollution control method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101080065A (en) * | 2006-05-24 | 2007-11-28 | 三星电子株式会社 | Method for providing idle screen layer endowed with visual effect and method for providing idle screen by using the same |
| CN104618446A (en) * | 2014-12-31 | 2015-05-13 | 百度在线网络技术（北京）有限公司 | Multimedia pushing implementing method and device |
| CN105335507A (en) * | 2015-10-29 | 2016-02-17 | 维沃移动通信有限公司 | Method and device for pushing music |
| CN106302591A (en) * | 2015-05-28 | 2017-01-04 | 苏宁云商集团股份有限公司 | A kind of data transmission method, intelligent terminal and data transmission system |
| CN106657300A (en) * | 2016-12-09 | 2017-05-10 | 捷开通讯(深圳)有限公司 | Application program pushing method and mobile terminal pushing application programs |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100775585B1 (en) * | 2006-12-13 | 2007-11-15 | 삼성전자주식회사 | Method for recommending music about character message and system thereof |
| CN104199876B (en) * | 2014-08-20 | 2018-03-02 | 广州三星通信技术研究有限公司 | The method and apparatus for associating melody and picture |
-
2017
- 2017-08-15 CN CN201710696436.2A patent/CN107592339B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101080065A (en) * | 2006-05-24 | 2007-11-28 | 三星电子株式会社 | Method for providing idle screen layer endowed with visual effect and method for providing idle screen by using the same |
| CN104618446A (en) * | 2014-12-31 | 2015-05-13 | 百度在线网络技术（北京）有限公司 | Multimedia pushing implementing method and device |
| CN106302591A (en) * | 2015-05-28 | 2017-01-04 | 苏宁云商集团股份有限公司 | A kind of data transmission method, intelligent terminal and data transmission system |
| CN105335507A (en) * | 2015-10-29 | 2016-02-17 | 维沃移动通信有限公司 | Method and device for pushing music |
| CN106657300A (en) * | 2016-12-09 | 2017-05-10 | 捷开通讯(深圳)有限公司 | Application program pushing method and mobile terminal pushing application programs |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107592339A (en) | 2018-01-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107592339B (en) | Music recommendation method and music recommendation system based on intelligent terminal | |
| KR102436168B1 (en) | Systems and methods for creating listening logs and music libraries | |
| CN106652996B (en) | Prompt tone generation method and device and mobile terminal | |
| JP6060155B2 (en) | Method and system for performing a comparison of received data and providing subsequent services based on the comparison | |
| RU2513772C2 (en) | System and method for automatic creation of atmosphere suitable for public environment and mood in ambient environment | |
| CN106469557B (en) | Method and device for providing accompaniment music | |
| US20050182627A1 (en) | Audio signal processing apparatus and audio signal processing method | |
| US20150082175A1 (en) | Information processing device, information processing method, information processing program, and terminal device | |
| JP2006504115A (en) | Music identification system and method | |
| KR20120038000A (en) | Method and system for determining the topic of a conversation and obtaining and presenting related content | |
| CN110335625A (en) | The prompt and recognition methods of background music, device, equipment and medium | |
| CN110970014A (en) | Voice conversion, file generation, broadcast, voice processing method, device and medium | |
| CN105187630A (en) | Mobile terminal music saving method and system based on emotion recognition | |
| CN104618446A (en) | Multimedia pushing implementing method and device | |
| CN110047497B (en) | Background audio signal filtering method and device and storage medium | |
| KR20160106075A (en) | Method and device for identifying a piece of music in an audio stream | |
| CN106055659B (en) | Lyric data matching method and equipment thereof | |
| CN104091596A (en) | Music identifying method, system and device | |
| CN113126951B (en) | Audio playing method and device, computer readable storage medium and electronic equipment | |
| CN117221781A (en) | Intelligent earphone volume automatic adjusting method based on data analysis | |
| CN110827849A (en) | Human voice separation method and device for database building, terminal and readable storage medium | |
| CN105119953B (en) | The method and device of APP binding audio-video processing terminal | |
| US20070110397A1 (en) | Playback apparatus and bookmark system | |
| CN109215688B (en) | Same-scene audio processing method, device, computer readable storage medium and system | |
| CN109754820B (en) | Target audio acquisition method and device, storage medium and terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20221214 Address after: 201203 1st floor, building 1, Lane 36, Xuelin Road, Pudong New Area Free Trade Zone, Shanghai Patentee after: SHANGHAI TRANSSION INFORMATION TECHNOLOGY Ltd. Address before: Room 922 / 926, block a, No.1 Lane 399, shengxia Road, Pudong New Area pilot Free Trade Zone, Shanghai 201203 Patentee before: SHANGHAI SPREADRISE COMMUNICATION TECHNOLOGY Ltd. |
|
| TR01 | Transfer of patent right |