CN106844660B - Music recommendation method and device - Google Patents
Music recommendation method and device Download PDFInfo
- Publication number
- CN106844660B CN106844660B CN201710050582.8A CN201710050582A CN106844660B CN 106844660 B CN106844660 B CN 106844660B CN 201710050582 A CN201710050582 A CN 201710050582A CN 106844660 B CN106844660 B CN 106844660B
- Authority
- CN
- China
- Prior art keywords
- music
- user
- step frequency
- bpm
- target
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/63—Querying
- G06F16/635—Filtering based on additional data, e.g. user or group profiles
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)
- Auxiliary Devices For Music (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Reverberation, Karaoke And Other Acoustics (AREA)
- Electrophonic Musical Instruments (AREA)
Abstract
The embodiment of the invention discloses a music recommendation method and device. The music recommendation method comprises the following steps: acquiring a target music list corresponding to an interest model of a target user; determining stride frequency data and the selected running mode of the target user; the running mode comprises any one of an excitation mode, a training mode and a matching mode; and determining music to be played from the target music list according to the running mode and the step frequency data. The embodiment of the invention can determine the music to be played by combining the step frequency data of the target user and the selected running mode, so that the accuracy of music recommendation can be improved by implementing the embodiment.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a music recommendation method and device.
Background
With the development of mobile network technology, people can enjoy music anytime and anywhere through terminals such as mobile phones, tablets and wearable devices, and in order to improve the user's experience of listening to songs, besides playing local music in the terminals, music lists in various scenes can be generated, for example, a music list corresponding to a work scene and a music list corresponding to a sport scene.
However, the inventor finds in practice that the above music recommendation method cannot embody the personalized features of the users in the corresponding scenes, that is, the selectable music lists of all the users in the sports scenes are substantially the same, so that the accuracy rate of the recommended music is not high.
Disclosure of Invention
The embodiment of the invention provides a music recommendation method, which can improve the accuracy of recommended music.
The embodiment of the invention provides a music recommendation method, which comprises the following steps:
acquiring a target music list corresponding to an interest model of a target user;
determining stride frequency data of the target user and the selected running mode; the running mode comprises any one of an excitation mode, a training mode and a matching mode;
and determining music to be played from the target music list according to the running mode and the step frequency data.
Correspondingly, an embodiment of the present invention further provides a music recommendation apparatus, including:
the acquisition unit is used for acquiring a target music list corresponding to the interest model of the target user;
a determining unit for determining the step frequency data of the target user and the selected running mode; the running mode comprises any one of an excitation mode, a training mode and a matching mode;
the determining unit is further configured to determine music to be played from the target music list according to the running mode and the stride frequency data.
The embodiment of the invention can obtain a target music list corresponding to the interest model of the target user; and determining stride frequency data and the selected running mode of the target user; the running mode comprises any one of an excitation mode, a training mode and a matching mode; and determining music to be played from the target music list according to the running mode and the step frequency data. Therefore, by implementing the embodiment of the invention, more matched running music can be provided for the user according to the step frequency data of the user and the selected running mode, and the accuracy of music recommendation is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a flowchart illustrating a music recommendation method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a mode selection interface provided by an embodiment of the invention;
FIG. 3 is a schematic diagram of a step frequency data display interface according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of another step frequency data display interface provided by an embodiment of the invention;
FIG. 5 is a flowchart illustrating another music recommendation method according to an embodiment of the present invention;
fig. 6 is a schematic diagram of a frequency-stepped similarity user list according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of a prompt box of a focused user according to an embodiment of the present invention;
FIG. 8 is a flowchart illustrating a music recommendation method according to another embodiment of the present invention;
fig. 9 is a schematic diagram of another step frequency similar user list provided by the embodiment of the present invention;
fig. 10 is a schematic structural diagram of a music recommendation apparatus according to an embodiment of the present invention;
fig. 11 is a schematic structural diagram of a music recommendation system according to an embodiment of the present invention;
fig. 12 is a schematic structural diagram of a terminal according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to facilitate understanding of the embodiments of the present invention, concepts and terms related to the embodiments of the present invention will be described.
The music recommendation method provided by the embodiment of the invention can be applied to various terminal devices, such as mobile phones, tablet computers, wearable devices and the like.
It should be understood that the interest model may also be referred to as a user profile to represent the user's preferences so that the music recommended for the user is music of interest to the user. The interest model may include various interest tags, with music matching the interest tags in the interest model as a target music list for the target user. The creation of the interest model may be determined according to the historical behavior data of the user, for example, analyzing operations of downloading, collecting, evaluating, or hobby music of the user, and the like, acquiring tags of music corresponding to the operations, and using the acquired tags or tags with a higher percentage in the acquired tags as the interest tags of the interest model. Optionally, the rhythm, the temperament and the like of the music corresponding to the operations may also be obtained, and the rhythm characteristics and the temperament characteristics of the music are used as interest tags of the interest model.
Optionally, the interest model of the friend concerned by the user may also be obtained as a part of the interest model of the user. Optionally, the target music list corresponding to the interest model of the concerned friend may also be used as a part of the target music list of the user. For example, if the user a and the user B are friends of each other, the target music list recommended to the user a may be recommended to the user B, and the target music list recommended to the user B may be recommended to the user a.
Optionally, the interest model may also include an interest model of a user with similar stride frequency, or a target music list of a user with similar stride frequency may be used as a part of the target music list of the user. For example, if the absolute difference between the step frequency values of the user a and the user B is smaller than the preset threshold value within the preset range, the target music list recommended to the user a may be recommended to the user B, and the target music list recommended to the user B may be recommended to the user a.
Optionally, the interest model may also include interest models of users with similar tastes, or a target music list of users with similar tastes is used as a part of the target music list of the users. For example, an interest model of the user a is obtained according to historical behavior data (such as operations of song listening duration, song cutting action, collection labels, and the like) of the user a, an interest model of the user B is obtained according to historical behavior data (such as operations of song listening duration, song cutting action, collection labels, and the like) of the user B, and if each interest tag in the interest model of the user a is smaller than each interest tag in the interest model of the user B or most interest tags are the same, the user a and the user B can be called users with similar tastes, a target music list recommended to the user a can be recommended to the user B, and a target music list recommended to the user B can be recommended to the user a.
As an optional implementation manner, it is determined that the scoring vectors of the user i and the user j for the same song are respectively S according to a preset scoring scheme i ＝[x 1 ，…，x n ]，S j ＝[y 1 ，…，y n ]Then the similarity w between user i and user j ij :
Thus, w ij And when the value is smaller than the preset threshold value, determining that the user i and the user j are users with similar tastes. Further, the target music list of the user can be determined.
Such a manner of recommending music to a User according to the relevance between users may also be referred to as a User-based Collaborative Filtering (User-based CF).
It should be understood that the target user may refer to a user login identifier such as an account of a music playing application or an application including a music recommendation function, or may refer to a terminal that uses the music recommendation method, which is not limited in the embodiment of the present invention. In addition, the target user is only one identification for distinguishing other users, any user may be referred to as a target user relative to other users, and the embodiment of the present invention adopts "target" to more clearly illustrate the scheme of the present application.
In the embodiment of the invention, the step frequency data may include the acceleration of the movement of the target user, the starting speed of the movement, the step length, the movement distance, the movement duration and the like, and the current step frequency value, the predicted step frequency value of a future duration, the speed change trend, the acceleration change trend and the like of the user are determined according to the step frequency data. The step frequency value may also be referred to as a step frequency, i.e., a frequency at which the legs alternate in a unit time.
For example, the pace of the user's motion is v t Within the time period t, v can be calculated by the following formula t ：
Let the step size of the user be L, L v t The step frequency value is the current step frequency value of the user, wherein the smaller the duration t is, the more accurate the step frequency value calculated by the above formula is. The acceleration can be measured in real time by an acceleration sensor or the like provided in the terminal.
In the embodiment of the invention, the music BPM of beats per minute can be obtained by performing fast Fourier transform to obtain the music sound spectrum, and then obtaining the music BPM through the statistics of wave crests and wave troughs. Since the music BPM calculation involves more algorithms, a third party music database, such as a Soundtouch audio processor, may be selected to calculate the music BPM. The BPM for calculating music may be a non-real-time operation, that is, as long as newly added music in the target music list is detected, a corresponding algorithm may be called to calculate the BPM and record the BPM into the database.
In the embodiment of the application, after the number of beats per minute of each piece of music in the target music list is determined, the target music list can be further sorted according to the sequence of the BPMs of each piece of music from small to large or from large to small; and dividing the ordered target music list into a plurality of sub-music lists by taking each preset plurality of different BPMs as intervals, wherein the BPM intervals corresponding to each sub-music list are different. The preceding BPM interval of each BPM interval is a BPM interval of which the BPM is smaller than the BPM in the BPM interval and the difference value is minimum, and the succeeding BPM interval of each BPM interval is a BPM interval of which the BPM is larger than the BPM in the BPM interval and the difference value is minimum.
In the embodiment of the present application, the running mode may also be referred to as an exercise mode, and may be used in exercises such as running and fast walking. The running mode includes any one of an excitation mode, a training mode, and a matching mode.
The matching mode refers to a sub-music list corresponding to a previous BPM interval and a next BPM interval of the BPM interval where the current pace frequency value of the user is located of the music recommended to the user in the mode, and can help the user to keep in a preset range of the current pace frequency value. The motivation mode refers to that the music recommended to the user in the motivation mode comes from a sub-music list corresponding to a BPM interval where the predicted pace frequency value of the user is located or comes from a sub-music list corresponding to a BPM interval after the BPM interval where the predicted pace frequency value of the user is located.
The training mode is that when the user enters the sprint stage, the user can immediately enter the motivation mode and play the song in the motivation mode, so as to motivate the user to sprint. Wherein, the music to be played before the user enters the sprint stage is determined according to the training example corresponding to the training mode and the current step frequency value. For example, if the training distance is 800 meters, and the sprint stage is started after 400 meters run out, 3 minutes are required for the 400 meters run out according to the current step frequency value of the user, and music with the duration of 3 minutes can be recommended by combining the matching mode; when the music is played, switching to an excitation mode, and determining the music to be played according to the excitation mode and the step frequency data (the step frequency data can be measured in a preset period to determine the current step frequency value and the predicted step frequency value of the user), so that sprint is finished under the excitation of the music in the excitation mode. The predicted step frequency value is determined according to the current speed and the acceleration change trend of the user in the step frequency data, so that the running mode can be automatically switched for the user.
Optionally, in the training mode, it may also be determined whether the user enters the sprint phase according to the step frequency data of the user. For example, when it is determined that the target user is in an accelerated motion state according to the stride frequency data, the selected running mode is switched to the motivation mode, and thus, music to be played by the target user is determined from the target music list according to the motivation mode and the stride frequency data.
According to the method and the device, the music to be played can be determined from the target music list according to the step frequency data of the target user and the selected running mode, and the running mode can be switched in real time according to the step frequency data of the user. For example, if the user is determined to be accelerating exercise at present according to the step frequency data, the user is automatically switched to an excitation mode to drive the exercise rhythm of the user; and if the user is determined to be approximately in uniform motion at present according to the step frequency data, switching to a matching mode to help the user stabilize the current motion rhythm.
Optionally, based on a certain degree of sociality of the movement, the embodiment of the application may further provide a ranking list of users with similar stride frequency, that is, a list of users with similar stride frequency, when the user moves. Determining the current step frequency value of the target user according to the step frequency data; acquiring a user set of which the absolute step frequency difference value between the step frequency value and the current step frequency value in a preset range is smaller than a preset threshold value; determining the ranking of each user in the user set according to the absolute step frequency difference value between the step frequency value of each user in the user set and the current step frequency value, and obtaining a step frequency similar user list corresponding to the user set; the larger the absolute step frequency difference is, the later the ranking of the user is. The step frequency similar user list can display the user name, the exercise duration, the exercise step number and other information of the user similar to the user step frequency (namely, the absolute step frequency difference value between the step frequency value and the current step frequency value in the preset range is smaller than the preset threshold), optionally, the user similar to the step frequency can be concerned through a 'concerned' button, and the purpose of social contact is achieved.
Optionally, in the embodiment of the application, the rank of a user who keeps similar to the step frequency value of the user for a longer time in the step frequency similar user list can be adjusted to the front, so that when the user wants to summon users with similar step frequencies in a preset range, the user only needs to keep similar step frequencies to the users as long as possible, and thus the user can make a summit in the step frequency similar user list of the other side and provide a summit opportunity, and the social contact of the music recommendation method is improved. Specifically, the adjusting process of the step frequency similar user list includes: and adjusting the ranking of each user in the step frequency similar user list according to the time length when the absolute step frequency difference value between the step frequency value of each user in the step frequency similar user list and the current step frequency value of the target user is continuously smaller than a preset threshold value, wherein the ranking of the user is more advanced the longer the kept time length is.
Based on the above, the following describes details related to the music recommendation method according to the embodiment of the present invention.
Referring to fig. 1, fig. 1 is a flowchart illustrating a music recommendation method according to an embodiment of the present invention, as shown in fig. 1, the music recommendation method may include the following steps:
s101, a terminal acquires a target music list corresponding to an interest model of a target user;
in the embodiment of the present invention, the interest model may be determined according to historical behavior data of the user, may also be determined according to a collaborative filtering algorithm based on the user, such as a friend concerned by the user, and may also be determined according to an interest model of the user whose stride frequency is similar to that of the target user, which is not limited in the embodiment of the present invention.
The operation of determining the target music list according to the interest model of the target user can be executed by the background server, and the terminal only needs to acquire the target music list from the background server. Because the target music list is determined by a large amount of calculation, excessive CPU occupation and the like are occupied, the terminal can send the historical behavior data and social data of the target user to the background server, and the background server determines the target music list based on a relevant algorithm, for example, a collaborative filtering algorithm of the user, so that the running load of the terminal can be reduced, and the generation efficiency of the target music list is improved.
S102, the terminal determines the step frequency data of the target user and the selected running mode; the running mode comprises any one of an excitation mode, a training mode and a matching mode;
in the embodiment of the present invention, the selection of the running mode may be determined by a mode selection option on a terminal adopting the music recommendation method, for example, fig. 2 is a schematic diagram of a mode selection interface provided in the embodiment of the present invention, as shown in fig. 2, a matching mode may automatically select a song according to a pace; the mode is excited, and the user is motivated at a faster pace; the training mode is effective training with different meters, 800m or 1000m can be selected, and optionally, other training distances can be set.
Optionally, the target user may also manually switch the running mode during the exercise. For example, fig. 3 is a schematic diagram of a stride frequency data display interface provided by an embodiment of the present invention, which may include a current stride frequency value of 55 steps/second, a distance traveled (distance traveled) of 10m, and a length traveled of 00:03 seconds, and may prompt a user that music is being recommended according to the current stride frequency (value). The target user can intuitively switch the running mode according to the information, for example, the target user can switch to the excitation mode to improve the current step frequency value and improve the exercise intensity.
Optionally, after the exercise is finished, the step frequency display interface may further include a distance of the whole exercise, an average step frequency value, and a total exercise duration. Fig. 4 is a schematic diagram of another step frequency data display interface according to an embodiment of the present invention, and as shown in fig. 4, after the exercise is finished, the step frequency display interface may further include a distance of the whole exercise of 5km, an average step frequency value of 105 steps/minute, and a total exercise duration of 27 minutes, and may further display a music list played in the exercise, which is not limited in the embodiment of the present invention.
Optionally, the terminal may also automatically switch the running mode according to the exercise condition of the target user. Determining music to be played for the target user from the target music list according to the running mode and the step frequency data, wherein the music comprises: when the target user is determined to be in an accelerated motion state according to the step frequency data, switching the selected running mode to an excitation mode, and determining music to be played by the target user from the target music list according to the excitation mode and the step frequency data; and when the target user is determined to be in a uniform motion state according to the step frequency data, switching the selected running mode to a matching mode, and determining music to be played by the target user from the target music list according to the matching mode and the step frequency data. According to the embodiment, the running mode can be automatically switched according to the motion condition in the motion process of the target user, and the complexity of manual operation of the user is avoided.
S103, determining music to be played from the target music list according to the running mode and the step frequency data.
Optionally, when the running mode is the matching mode, the determining music to be played from the target music list according to the matching mode and the stride frequency data includes: determining the current step frequency value of the target user according to the step frequency data; determining music to be played from a sub-music list corresponding to a previous BPM interval of the BPM interval in which the current step frequency value is located and a sub-music list corresponding to a next BPM interval; the former BPM intervals are the BPM intervals with the smallest difference and the BPM intervals are the BPM intervals with the smallest difference, and the later BPM intervals are the BPM intervals with the smallest difference and all the BPM intervals are larger than the BPM intervals with the current step frequency. By implementing the embodiment, the BPM of the music recommended for the target user is larger than the current step frequency value or smaller than the current step frequency value, so that the target user can be kept in a certain range before and after the current step frequency value, and the aim of body building or weight losing is fulfilled.
In this embodiment of the present invention, the determining, by the terminal, music to be played from the target music list according to the excitation pattern and the stride frequency data may include: determining a predicted step frequency value which can be reached by the target user within a preset time length according to the step frequency data; determining music to be played from a sub-music list corresponding to the BPM interval where the predicted step frequency value is located and a sub-music list corresponding to the next BPM interval; the last BPM interval is a BPM interval with the BPM being all larger than the BPM in the BPM interval in which the prediction step frequency value is located and the difference value being minimum. By implementing the embodiment, the music recommended for the target user is the music in the BPM interval in which the current step frequency value is greater than or the music in the BPM interval in which the current step frequency value is greater than, so that the target user can be gradually greater than the current step frequency value, the user is encouraged to accelerate along with the rhythm of the music, and the purpose of body building or weight losing is achieved.
Optionally, the running mode is a training mode, and the terminal determines, from the target music list, music to be played by the target user according to the running mode and the stride frequency data, including: determining the current step frequency value of the target user according to the step frequency data; determining music to be played before the target user enters a sprint stage according to the training distance corresponding to the training mode and the current step frequency value; and when the determined music to be played before the target user enters the sprint stage is played, switching to an excitation mode, and determining the music to be played by the target user from the target music list according to the excitation mode and the stride frequency data. By implementing the implementation mode, the music to be played determined before the target user enters the sprint stage is determined according to the current step frequency value and the training distance, so that the music playing time length before the sprint stage can be matched with the time length before the sprint stage, when the sprint stage is entered, the music playing right before the sprint stage is finished or is about to be played, the music to be played determined in the excitation mode can be played after the music playing before the sprint stage is finished, and the sprint of the user can be finished under the excitation of the fast-rhythm music.
Therefore, the embodiment of the invention can obtain the target music list corresponding to the interest model of the target user; determining stride frequency data and the selected running mode of the target user; the running mode comprises any one of an excitation mode, a training mode and a matching mode; and determining music to be played from the target music list according to the running mode and the step frequency data. Since music to be played is determined in combination with the stride frequency data of the target user and the selected running mode, the accuracy of music recommendation can be improved.
Referring to fig. 5, fig. 5 is a flowchart illustrating another music recommendation method according to an embodiment of the present invention, and compared with the music recommendation method shown in fig. 1, the music recommendation method shown in fig. 5 may update, in real time, user information similar to the stride frequency of a target user within a preset range, and specifically, in addition to the steps S101 to S103, the music recommendation method shown in fig. 5 may further include the following steps:
s104, the terminal determines the current step frequency value of the target user according to the step frequency data;
s105, the terminal acquires a user set of which the absolute step frequency difference value between the step frequency value in a preset range and the current step frequency value is smaller than a preset threshold value;
s106, the terminal determines the ranking of each user in the user set according to the absolute step frequency difference value between the step frequency value of each user in the user set and the current step frequency value, and obtains a step frequency similar user list corresponding to the user set.
Wherein, the larger the absolute step frequency difference value is, the later the corresponding user rank is.
In the embodiment of the present invention, the execution sequence of steps S101 to S106 is not limited, that is, the step S104 may be executed simultaneously with the step S103, or the current step value may be determined according to the step data of the latest cycle when determining the step similar user list.
In the embodiment of the present invention, the preset threshold value in determining the user set may be determined according to the scale of the user set, and the larger the preset threshold value is, the more the number of users that can be included in the user set is.
Fig. 6 is a schematic diagram of a stride frequency similarity user list provided in an embodiment of the present invention, as shown in fig. 6, the stride frequency similarity user list may display a current stride frequency value of each user in a user set, a user account, and may also focus on the users through a "focus" option, for example, Mike 105 steps/minute, Jak 103 steps/minute, Lucy 101 steps/minute, and Lily 98 steps/minute. Correspondingly, a prompt box of "the user has been concerned about" may also pop up, as shown in fig. 7, fig. 7 is a schematic diagram of a prompt box of a user having been concerned about according to an embodiment of the present invention, and a prompt box of "the user has been concerned about" may pop up when a certain user is concerned about. The step frequency similar user list may be displayed during the movement of the target user or after the movement, which is not limited in the embodiment of the present invention.
It can be seen that the music recommendation method shown in fig. 5 provides a music social logic, and the music recommendation method introduces a running social logic, so that users with similar step frequency can run together, on one hand, the music recommendation method of this embodiment is popularized, and on the other hand, the users can be encouraged to keep on exercising.
Referring to fig. 8, fig. 8 is a flowchart illustrating another music recommendation method according to an embodiment of the present invention, where, compared with the music recommendation method shown in fig. 5, the music recommendation method shown in fig. 8 may further adjust the rank of each user in the stride frequency similar user list according to a continuous duration that the other users keep the stride frequency similar to the target user, and specifically, the music recommendation method shown in fig. 8 may further include the following steps in addition to steps S101 to S106:
s107, the terminal adjusts the ranking of each user in the step frequency similar user list according to the duration that the absolute step frequency difference value between the step frequency value of each user in the step frequency similar user list and the current step frequency value of the target user is continuously smaller than a preset threshold value.
Wherein, the longer the duration of the holding, the higher the ranking of the user.
It can be seen that the music recommendation method shown in fig. 8 can also add social logic.
Fig. 9 is a schematic diagram of another similar stride frequency user list provided in an embodiment of the present invention, as shown in fig. 9, the similar stride frequency duration of the target user in the user set is displayed in the similar stride frequency user list, and the greater the duration of the stride frequency duration, the more advanced the rank is, as shown in fig. 9, the "similar stride frequency and TA as long as me" list shows that the similar stride frequency of me as Mike is 10 minutes, the similar stride frequency as Jak is 6 minutes, the similar stride frequency as Lucy is 3 minutes, and the similar stride frequency is 2 minutes; and may also focus on the corresponding user through the "focus" button, it can be seen that this embodiment provides the user or target user with the opportunity to accost. For example, when the target user wants to recognize other users with similar nearby stride frequency, the user account and other information of the target user can be displayed in the similar user list of the stride frequency of the other party by being similar to the stride frequency of the other party which is kept as long as possible.
Referring to fig. 10, fig. 10 is a schematic structural diagram of a music recommendation device according to an embodiment of the present invention, as shown in fig. 10, the music recommendation device may include the following units:
an obtaining unit 210, configured to obtain a target music list corresponding to an interest model of a target user;
a determining unit 220 for determining the step frequency data of the target user and the selected running mode; the running mode comprises any one of an excitation mode, a training mode and a matching mode;
the determining unit 220 is further configured to determine music to be played from the target music list according to the running mode and the stride frequency data.
The obtaining unit 210 may determine the operation of the target music list according to the interest model of the target user, or may be executed by a background server, and the obtaining unit 210 only needs to obtain the target music list from the background server. Because the target music list is determined by a large amount of calculation, the CPU is excessively occupied, and the like, the terminal can send the historical behavior data and the social data of the target user to the background server, and the background server determines the target music list based on a relevant algorithm, for example, a collaborative filtering algorithm of the user, so that the running load of the music recommendation device can be reduced, and the generation efficiency of the target music list is improved.
The interest models include the interest models of the users in the step frequency similarity list, or the interest models of the friends concerned by the target user, and the like, as described above, this embodiment is not described in detail.
Optionally, the determining unit 220 determines, from the target music list according to the running mode and the step frequency data, music to be played by the target user, specifically: when the target user is determined to be in an accelerated motion state according to the step frequency data, switching the selected running mode to an excitation mode, and determining music to be played by the target user from the target music list according to the excitation mode and the step frequency data; and when the target user is determined to be in a uniform motion state according to the step frequency data, switching the selected running mode to a matching mode, and determining music to be played by the target user from the target music list according to the matching mode and the step frequency data. In this embodiment, the determining unit 220 may automatically switch the motion mode according to the motion state of the target user, so as to avoid the user manually switching the motion mode, and reduce the complexity of the operation.
Optionally, when the running mode is the training mode, the determining unit 220 may determine, from the target music list, music to be played by the target user according to the running mode and the step frequency data, specifically: determining the current step frequency value of the target user according to the step frequency data; determining music to be played before the target user enters a sprint stage according to the training distance corresponding to the training mode and the current step frequency value; and when the determined music to be played before the target user enters the sprint stage is played, switching to an excitation mode, and determining the music to be played by the target user from the target music list according to the excitation mode and the stride frequency data. In this embodiment, the determining unit 220 may select the corresponding music according to whether the target user enters the sprint phase in the training mode, so as to help the target user complete the training and stimulate the target user to perform sprint in the sprint phase.
Optionally, the determining unit 220 is further configured to determine a current step frequency value of the target user according to the step frequency data; correspondingly, the obtaining unit 210 is further configured to obtain a user set in which an absolute step frequency difference value between a step frequency value in a preset range and the current step frequency value is smaller than a preset threshold; the determining unit 220 is further configured to determine ranks of users in the user set according to an absolute step frequency difference between the step frequency value of each user in the user set and the current step frequency value, and obtain a step frequency similar user list corresponding to the user set; the larger the absolute step frequency difference is, the later the ranking of the user is. By implementing the embodiment, the information of the users similar to the pace frequency of the target user can be displayed, so that the social contact of the music recommendation device is increased, and the user group is expanded.
Optionally, the music recommendation apparatus shown in fig. 10 may further include an adjusting unit 230, configured to adjust the ranks of the users in the stride frequency similar user list according to a duration that an absolute stride frequency difference between the stride frequency value of each user in the stride frequency similar user list and the current stride frequency value of the target user is continuously smaller than a preset threshold, where the greater the duration that the absolute stride frequency difference is continuously smaller than the preset threshold, the higher the rank of the user is. The embodiment may also display a similar duration of time to the target user's pace frequency in the user set in the pace frequency similar user list, with the greater duration of time kept ranked higher, thereby providing the user or target user with the opportunity to burden. For example, when the target user wants to recognize other users with similar nearby stride frequency, the user account and other information of the target user can be displayed in the similar user list of the stride frequency of the other party by being similar to the stride frequency of the other party which is kept as long as possible.
The determining unit 220 is further configured to determine the number of beats per minute BPM of each piece of music in the target music list; accordingly, the music recommendation apparatus shown in fig. 10 may further include the following units:
a sorting unit 240, configured to sort the target music list according to a sequence from a small BPM to a large BPM of each music;
the dividing unit 250 is configured to divide the sorted target music list into a plurality of sub-music lists by using each preset number of different BPMs as an interval, where the BPM interval corresponding to each sub-music list is different.
The determining unit 220 may further determine, from the target music list, music to be played by the target user according to the excitation pattern and the stride frequency data, specifically: determining a predicted step frequency value which can be reached by the target user within a preset time length according to the step frequency data; determining music to be played from a sub-music list corresponding to the BPM interval where the predicted step frequency value is located and a sub-music list corresponding to the next BPM interval; the last BPM interval is a BPM interval with the BPM being all larger than the BPM in the BPM interval in which the prediction step frequency value is located and the difference value being minimum. By implementing the embodiment, the music recommended for the target user is the music in the BPM interval in which the current step frequency value is greater than or the music in the BPM interval in which the current step frequency value is greater than, so that the target user can be gradually greater than the current step frequency value, the user is encouraged to accelerate along with the rhythm of the music, and the purpose of body building or weight losing is achieved.
The determining unit 220 determines the music to be played from the target music list according to the matching pattern and the stride frequency data, specifically: determining the current step frequency value of the target user according to the step frequency data; determining music to be played from a sub-music list corresponding to a previous BPM interval of the BPM interval in which the current step frequency value is located and a sub-music list corresponding to a next BPM interval; the former BPM intervals are the BPM intervals with the BPM smaller than the BPM in the BPM intervals with the current step frequency value and the difference value is the smallest, and the later BPM intervals are the BPM intervals with the BPM larger than the BPM in the BPM intervals with the current step frequency value and the difference value is the smallest. By implementing the implementation mode, the music to be played determined before the target user enters the sprint stage is determined according to the current step frequency value and the training distance, so that the music playing time length before the sprint stage can be matched with the time length before the sprint stage, when the sprint stage is entered, the music playing right before the sprint stage is finished or is about to be played, the music to be played determined in the excitation mode can be played after the music playing before the sprint stage is finished, and the sprint of the user can be finished under the excitation of the fast-rhythm music.
As can be seen, in the embodiment of the present invention, the obtaining unit 210 may obtain a target music list corresponding to the interest model of the target user; the determining unit 220 may determine the step frequency data of the target user and the selected running mode; the running mode comprises any one of an excitation mode, a training mode and a matching mode; further, the determination unit 220 may determine music to be played from the target music list according to the running mode and the stride frequency data. Since the music to be played is determined in combination with the step frequency data of the target user and the selected running mode, the accuracy of music recommendation can be improved.
Optionally, referring to fig. 11, fig. 11 is a schematic structural diagram of a music recommendation system according to an embodiment of the present invention, as shown in fig. 11, the music recommendation system may include a front-end service module 310, a back-end service module 320, a song BPM calculation module 330, and a recommendation module 340, where:
the front-end service module 310 is configured to directly process data related to user interaction, communicate with the background service module, obtain step frequency data of the user, and display the processed data (e.g., a current step frequency value, a length of exercise time, a distance, etc.) to the user. The step frequency data of the user can acquire the acceleration in each motion direction through an accelerometer, so that the current step frequency value of the user is calculated or the predicted step frequency value of the user in a preset time period in the future is predicted. The step frequency value is predicted by establishing the change situation of the step frequency value of the user according to the step frequency values of the user at a plurality of moments. On the other hand, the front-end service module can also interact with the background service module, and the determined information of the music to be played is obtained through an API (application program interface) provided by the background service module so as to play the music.
Optionally, the front-end service module 310 may also send information such as a user account and a password of the target user to the background service module 320 to complete processing such as verification and authentication.
The background service module 320 is configured to determine a target music list based on a collaborative filtering algorithm of the user, and may also construct a target music list recommended to the user according to step frequency similarity, taste similarity, and the like; and on the other hand, the method is also used for determining music to be played for the user according to the running mode currently in and the step frequency data of the user.
The back-office module 320 may also be used to provide a complete authentication framework and protection mechanisms for possible song theft-chaining. Since the user can use the software without logging in, a token mechanism can be adopted to check and authenticate the validity of the user. A complete token acquisition and interaction mechanism includes: the user firstly requests a token from the background service module 320 through the front-end service module 310, and the background service module 320 returns a token, so that the token can be carried by the user when the user requests a service from the background service module 320 to implement an authentication mechanism.
For the problem of stealing the songs, the effectiveness and the validity period of the song link are controlled by the song link generated in real time by the background service module 320, so that the problem of stealing the songs caused by excessive exposure of the actual storage address and the permanently effective path of the background to the songs is prevented.
In addition, the background service module 320 is also responsible for recording and implementing socialization functions, temporarily records user information similar to the user step frequency through Redis, and outputs the user information to the front-end service module for display during or after the user exercise. The background service module 320 may perform related functions of the obtaining unit 210, the determining unit 220, and the adjusting unit 230, which is not described in detail in the embodiments of the present invention.
The song BPM calculation module 330 may perform the relevant functions of the determination unit, the sorting unit, and the dividing unit, that is, determine the BPMs of the pieces of music in the target music list, and sort the target music list according to the order of the BPMs of the pieces of music from small to large; and dividing the ordered target music list into a plurality of sub-music lists by taking each preset plurality of different BPMs as intervals, wherein the BPM intervals corresponding to each sub-music list are different. For example, 5 BPMs are taken as a BPM interval, and the BPMs of music are categorized as a sub-music list of the 5 BPMs.
Also, the song BPM calculation module 330 may calculate a BPM of the newly added music and assign the music to a sub-music list including a BPM section of the BPM when it is detected that music is added to the target music list. Optionally, the song BPM calculation module 330 may also use a timing mechanism to periodically detect whether there is newly added music, and periodically update each sub-music list divided by the target music list.
And a recommending module 340 for determining the target music list based on the interest model of the user. Reference may be made in particular to the related algorithms or embodiments described above in relation to the creation of the target music list. That is, the background service module 320 may perform an operation of "building a target music list recommended to the user together according to similar pace frequency, similar taste, etc.", by the recommendation module 340. The recommendation module 340 may update the interest model of the user every preset time, and further update the target music list.
Referring to fig. 12, fig. 12 is a schematic structural diagram of a terminal according to an embodiment of the present invention, and as shown in fig. 12, the terminal may include: a processor 401, a communication interface 402, a memory 403 and a communication bus 404, wherein the communication bus 404 is used for realizing the communication connection among the components, and the communication interface 402 is used for realizing the communication connection among the machines. The memory 403 may be a high-speed RAM memory or a non-volatile memory (e.g., at least one disk memory). The memory 403 may optionally be at least one storage device located remotely from the processor 401. Wherein, the processor 401 may be combined with the music recommendation apparatus shown in fig. 10 or the music recommendation system shown in fig. 11, the memory 403 stores a set of program codes, and the processor 401 calls the program codes stored in the memory 403 to perform the following operations:
acquiring a target music list corresponding to an interest model of a target user;
determining stride frequency data of the target user and the selected running mode; the running mode comprises any one of an excitation mode, a training mode and a matching mode;
and determining music to be played from the target music list according to the running mode and the step frequency data.
In this embodiment of the present invention, the processor 401 invokes the program code stored in the memory 403, and determines the music to be played by the target user from the target music list according to the running mode and the stride frequency data, which may include the following operations:
when the target user is determined to be in an accelerated motion state according to the step frequency data, switching the selected running mode to an excitation mode, and determining music to be played by the target user from the target music list according to the excitation mode and the step frequency data;
and when the target user is determined to be in a uniform motion state according to the step frequency data, switching the selected running mode to a matching mode, and determining music to be played by the target user from the target music list according to the matching mode and the step frequency data.
In this embodiment of the present invention, the invoking, by the processor 401, the program code stored in the memory 403, the running mode being a training mode, and determining, from the target music list, music to be played by the target user according to the running mode and the stride frequency data, may include the following operations:
determining the current step frequency value of the target user according to the step frequency data;
determining music to be played before the target user enters a sprint stage according to the training distance corresponding to the training mode and the current step frequency value;
and when the determined music to be played before the target user enters the sprint stage is played, switching to an excitation mode, and determining the music to be played by the target user from the target music list according to the excitation mode and the stride frequency data.
In this embodiment of the present invention, the processor 401 calls the program code stored in the memory 403, and may further perform the following operations:
determining the current step frequency value of the target user according to the step frequency data;
acquiring a user set of which the absolute step frequency difference value between the step frequency value and the current step frequency value in a preset range is smaller than a preset threshold value;
determining the rank of each user in the user set according to the absolute step frequency difference value between the step frequency value of each user in the user set and the current step frequency value, and obtaining a step frequency similar user list corresponding to the user set; the larger the absolute step frequency difference is, the later the ranking of the user is.
In this embodiment of the present invention, the processor 401 calls the program code stored in the memory 403, and may further perform the following operations:
and adjusting the ranking of each user in the step frequency similar user list according to the time length when the absolute step frequency difference value between the step frequency value of each user in the step frequency similar user list and the current step frequency value of the target user is continuously smaller than a preset threshold value, wherein the ranking of the user is more advanced the longer the kept time length is.
The interest model comprises an interest model of each user in the step frequency similarity list, or the target music list further comprises a favorite target music list of the users in the step frequency similarity list.
In this embodiment of the present invention, the processor 401 calls the program code stored in the memory 403, and may further perform the following operations:
determining the BPM of the beats per minute of each piece of music in the target music list;
sequencing the target music list according to the sequence of the BPMs of the music from small to large or from large to small;
and dividing the ordered target music list into a plurality of sub-music lists by taking each preset plurality of different BPMs as intervals, wherein the BPM intervals corresponding to each sub-music list are different.
In this embodiment of the present invention, the processor 401 calls the program code stored in the memory 403, determines the music to be played from the target music list according to the excitation pattern and the stride frequency data, and may perform the following operations:
determining a predicted step frequency value which can be reached by the target user within a preset time length according to the step frequency data;
determining music to be played from a sub-music list corresponding to the BPM interval where the predicted step frequency value is located and a sub-music list corresponding to the next BPM interval; the last BPM interval is a BPM interval with the BPM being all larger than the BPM in the BPM interval in which the prediction step frequency value is located and the difference value being minimum.
In this embodiment of the present invention, the processor 401 calls the program code stored in the memory 403, determines the music to be played from the target music list according to the matching pattern and the stride frequency data, and may perform the following operations:
determining the current step frequency value of the target user according to the step frequency data;
determining music to be played from a sub-music list corresponding to a previous BPM interval of the BPM interval in which the current step frequency value is located and a sub-music list corresponding to a next BPM interval; the former BPM intervals are the BPM intervals with the BPM smaller than the BPM in the BPM intervals with the current step frequency value and the difference value is the smallest, and the later BPM intervals are the BPM intervals with the BPM larger than the BPM in the BPM intervals with the current step frequency value and the difference value is the smallest.
The music recommendation method and apparatus provided by the embodiment of the present invention are described in detail above, and the principle and the embodiment of the present invention are explained in detail herein by applying specific examples, and the description of the above embodiments is only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (16)
1. A music recommendation method, comprising:
acquiring a target music list corresponding to an interest model of a target user;
determining stride frequency data and the selected running mode of the target user; the running mode comprises any one of an excitation mode, a training mode and a matching mode, wherein the running mode is automatically switched according to the step frequency data of the target user;
determining music to be played from the target music list according to the running mode and the stride frequency data, and determining music to be played from the target music list according to the motivation mode and the stride frequency data when the running mode is the motivation mode, wherein the music comprises: determining a predicted step frequency value which can be reached by the target user within a preset time length according to the step frequency data; determining music to be played from a sub-music list corresponding to the BPM interval of the beat number per minute where the predicted step frequency value is located and a sub-music list corresponding to the next BPM interval; the last BPM interval is a BPM interval with the BPM being all larger than the BPM in the BPM interval in which the prediction step frequency value is located and the difference value being minimum.
2. The method of claim 1, wherein the determining music from the target music list to be played for the target user according to the running mode and the stride frequency data comprises:
when the target user is determined to be in an accelerated motion state according to the step frequency data, switching the selected running mode to an excitation mode, and determining music to be played by the target user from the target music list according to the excitation mode and the step frequency data;
and when the target user is determined to be in a uniform motion state according to the step frequency data, switching the selected running mode to a matching mode, and determining music to be played by the target user from the target music list according to the matching mode and the step frequency data.
3. The method of claim 1, wherein the running mode is a training mode, and wherein the determining music to be played for the target user from the target music list according to the running mode and the stride frequency data comprises:
determining the current step frequency value of the target user according to the step frequency data;
determining music to be played before the target user enters a sprint stage according to the training distance corresponding to the training mode and the current step frequency value;
and when the determined music to be played by the target user before entering the sprint stage is played, switching to an excitation mode, and determining the music to be played by the target user from the target music list according to the excitation mode and the step frequency data.
4. The method of claim 1, further comprising:
determining the current step frequency value of the target user according to the step frequency data;
acquiring a user set of which the absolute step frequency difference value between the step frequency value and the current step frequency value in a preset range is smaller than a preset threshold value;
determining the ranking of each user in the user set according to the absolute step frequency difference value between the step frequency value of each user in the user set and the current step frequency value, and obtaining a step frequency similar user list corresponding to the user set; the larger the absolute step frequency difference is, the later the ranking of the user is.
5. The method of claim 4, further comprising:
and adjusting the ranking of each user in the step frequency similar user list according to the time length when the absolute step frequency difference value between the step frequency value of each user in the step frequency similar user list and the current step frequency value of the target user is continuously smaller than a preset threshold value, wherein the ranking of the user is more advanced the longer the kept time length is.
6. The method of claim 4, wherein the interest model comprises an interest model for each user in the similar stride frequency list.
7. The method of any of claims 1 to 6, further comprising:
determining the Beats Per Minute (BPM) of each piece of music in the target music list;
sequencing the target music list according to the sequence of the BPMs of the music from small to large or from large to small;
and dividing the ordered target music list into a plurality of sub-music lists by taking each preset plurality of different BPMs as intervals, wherein the BPM intervals corresponding to each sub-music list are different.
8. The method of claim 7, wherein the determining music to be played from the target music list according to the matching pattern and the stride frequency data comprises:
determining the current step frequency value of the target user according to the step frequency data;
determining music to be played from a sub-music list corresponding to a previous BPM interval of the BPM interval in which the current step frequency value is located and a sub-music list corresponding to a next BPM interval; the former BPM intervals are the BPM intervals with the smallest difference and the BPM intervals are the BPM intervals with the smallest difference, and the later BPM intervals are the BPM intervals with the smallest difference and all the BPM intervals are larger than the BPM intervals with the current step frequency.
9. A music recommendation device, comprising:
the acquisition unit is used for acquiring a target music list corresponding to the interest model of the target user;
a determining unit for determining the step frequency data of the target user and the selected running mode; the running mode comprises any one of an excitation mode, a training mode and a matching mode, wherein the running mode is automatically switched according to the step frequency data of the target user;
the determining unit is further configured to determine music to be played from the target music list according to the running mode and the stride frequency data, and when the running mode is the motivation mode, determine music to be played from the target music list according to the motivation mode and the stride frequency data, and includes: determining a predicted step frequency value which can be reached by the target user within a preset time length according to the step frequency data; determining music to be played from a sub-music list corresponding to the Beat Per Minute (BPM) interval where the predicted step frequency value is located and a sub-music list corresponding to the next BPM interval; the last BPM interval is a BPM interval with the BPM being all larger than the BPM in the BPM interval in which the prediction step frequency value is located and the difference value being minimum.
10. The apparatus according to claim 9, wherein the determining unit determines the music to be played by the target user from the target music list according to the running mode and the stride frequency data, specifically:
when the target user is determined to be in an accelerated motion state according to the step frequency data, switching the selected running mode to an excitation mode, and determining music to be played by the target user from the target music list according to the excitation mode and the step frequency data;
and when the target user is determined to be in a uniform motion state according to the step frequency data, switching the selected running mode to a matching mode, and determining music to be played by the target user from the target music list according to the matching mode and the step frequency data.
11. The apparatus according to claim 9, wherein the running mode is a training mode, and the determining unit determines the music to be played by the target user from the target music list according to the running mode and the stride frequency data, specifically:
determining the current step frequency value of the target user according to the step frequency data;
determining music to be played before the target user enters a sprint stage according to the training distance corresponding to the training mode and the current step frequency value;
and when the determined music to be played before the target user enters the sprint stage is played, switching to an excitation mode, and determining the music to be played by the target user from the target music list according to the excitation mode and the stride frequency data.
12. The apparatus of claim 9,
the determining unit is further configured to determine a current step frequency value of the target user according to the step frequency data;
the acquiring unit is further configured to acquire a user set in which an absolute step frequency difference value between a step frequency value in a preset range and the current step frequency value is smaller than a preset threshold;
the determining unit is further configured to determine ranks of users in the user set according to an absolute step frequency difference value between a step frequency value of each user in the user set and the current step frequency value, and obtain a step frequency similar user list corresponding to the user set; the larger the absolute step frequency difference is, the later the ranking of the user is.
13. The apparatus of claim 12, further comprising:
and the adjusting unit is used for adjusting the ranking of each user in the step frequency similar user list according to the duration that the absolute step frequency difference value between the step frequency value of each user in the step frequency similar user list and the current step frequency value of the target user is continuously smaller than a preset threshold, wherein the greater the duration that the absolute step frequency difference value is continuously smaller than the preset threshold is, the higher the ranking of the user is.
14. The apparatus of claim 12, wherein the interest model comprises an interest model for each user in the similar stride frequency list.
15. The apparatus according to any one of claims 9 to 14,
the determining unit is further used for determining the Beats Per Minute (BPM) of each piece of music in the target music list;
the device further comprises:
the sequencing unit is used for sequencing the target music list according to the sequence of the BPM of each music from small to large;
and the dividing unit is used for dividing the ordered target music list into a plurality of sub-music lists by taking each preset plurality of different BPMs as intervals, wherein the BPM intervals corresponding to each sub-music list are different.
16. The apparatus according to claim 15, wherein the determining unit determines the music to be played from the target music list according to the matching pattern and the stride frequency data, specifically:
determining the current step frequency value of the target user according to the step frequency data;
determining music to be played from a sub-music list corresponding to a previous BPM interval of the BPM interval in which the current step frequency value is located and a sub-music list corresponding to a next BPM interval; the former BPM intervals are the BPM intervals with the BPM smaller than the BPM in the BPM intervals with the current step frequency value and the difference value is the smallest, and the later BPM intervals are the BPM intervals with the BPM larger than the BPM in the BPM intervals with the current step frequency value and the difference value is the smallest.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710050582.8A CN106844660B (en) | 2017-01-23 | 2017-01-23 | Music recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710050582.8A CN106844660B (en) | 2017-01-23 | 2017-01-23 | Music recommendation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106844660A CN106844660A (en) | 2017-06-13 |
| CN106844660B true CN106844660B (en) | 2022-09-13 |
Family
ID=59119594
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710050582.8A Active CN106844660B (en) | 2017-01-23 | 2017-01-23 | Music recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106844660B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109189979B (en) * | 2018-08-13 | 2020-11-24 | 腾讯科技（深圳）有限公司 | Music recommendation method and device, computing equipment and storage medium |
| CN109376265A (en) * | 2018-12-12 | 2019-02-22 | 杭州网易云音乐科技有限公司 | Song recommendations list generation method, medium, device and calculating equipment |
| CN109829107A (en) * | 2019-01-23 | 2019-05-31 | 华为技术有限公司 | A kind of recommended method and electronic equipment based on user movement state |
| CN111026934A (en) * | 2019-12-20 | 2020-04-17 | 中科寒武纪科技股份有限公司 | Intelligent recommendation method and related equipment |
| CN113050848A (en) * | 2019-12-26 | 2021-06-29 | 佛山市云米电器科技有限公司 | Music playing method, system, equipment and computer readable storage medium |
| CN112131460A (en) * | 2020-08-21 | 2020-12-25 | 英睿健康科技有限公司 | Information pushing system, method and equipment |
| CN113312102B (en) * | 2021-05-27 | 2024-03-19 | 维沃移动通信有限公司 | Control method and electronic equipment |
| CN113641902A (en) * | 2021-08-10 | 2021-11-12 | 广州艾美网络科技有限公司 | Music information pushing method and device, computer equipment and storage medium thereof |
| CN114267381A (en) * | 2021-12-14 | 2022-04-01 | 咪咕音乐有限公司 | Intelligent music playing method and equipment during sports and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104468840A (en) * | 2014-12-30 | 2015-03-25 | 安徽华米信息科技有限公司 | Audio pushing method, device and system |
| CN105190626A (en) * | 2012-12-13 | 2015-12-23 | 耐克创新有限合伙公司 | Monitoring fitness using a mobile device |
| CN105892628A (en) * | 2015-08-11 | 2016-08-24 | 乐视体育文化产业发展（北京）有限公司 | Music recommendation method and device as well as bicycle |
| CN105930429A (en) * | 2016-04-19 | 2016-09-07 | 乐视控股（北京）有限公司 | Music recommendation method and apparatus |
| CN106066780A (en) * | 2016-06-06 | 2016-11-02 | 网易（杭州）网络有限公司 | A kind of running data processing method and device |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| BRPI1013330A2 (en) * | 2009-04-27 | 2016-03-29 | Nike International Ltd | training program and athletic training playlist |
| US20150142147A1 (en) * | 2013-11-15 | 2015-05-21 | Spring Moves | Audio system for rhythm-based activity |
-
2017
- 2017-01-23 CN CN201710050582.8A patent/CN106844660B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105190626A (en) * | 2012-12-13 | 2015-12-23 | 耐克创新有限合伙公司 | Monitoring fitness using a mobile device |
| CN104468840A (en) * | 2014-12-30 | 2015-03-25 | 安徽华米信息科技有限公司 | Audio pushing method, device and system |
| CN105892628A (en) * | 2015-08-11 | 2016-08-24 | 乐视体育文化产业发展（北京）有限公司 | Music recommendation method and device as well as bicycle |
| CN105930429A (en) * | 2016-04-19 | 2016-09-07 | 乐视控股（北京）有限公司 | Music recommendation method and apparatus |
| CN106066780A (en) * | 2016-06-06 | 2016-11-02 | 网易（杭州）网络有限公司 | A kind of running data processing method and device |
Non-Patent Citations (2)
| Title |
|---|
| 你与PB,仅一曲之遥;张香君等;《健康与营养》;20150415(第04期);全文 * |
| 脑电信号驱动的个性化情绪音乐播放***算法研究及初步实现;马勇等;《生物医学工程学杂志》;20160225(第01期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106844660A (en) | 2017-06-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106844660B (en) | Music recommendation method and device | |
| CN107077648B (en) | Virtual alliance platform for athletic activities and online training platform | |
| US7696427B2 (en) | Method and system for recommending music | |
| US8568277B2 (en) | Training program and music playlist generation for athletic training | |
| TWI396574B (en) | Mothod of providing continuous feedback, opponent service application for executing the method, and related mobile terminal and application server | |
| JP7033587B2 (en) | How and system to automatically create video highlights | |
| US20090006397A1 (en) | Systems, Methods, Devices and Computer Program Products for Providing Media Recommendation Trekking | |
| US20150142147A1 (en) | Audio system for rhythm-based activity | |
| WO2017024825A1 (en) | Music recommendation method, apparatus, and bicycle | |
| US10311462B2 (en) | Music streaming for athletic activities | |
| CN109947438B (en) | Game installation method based on machine learning, electronic equipment and readable storage medium | |
| CN104460981A (en) | Presenting audio based on biometrics parameters | |
| CN110176221B (en) | Singing competition method, singing competition device and storage medium | |
| CN108579060B (en) | Exercise system and application method thereof | |
| EP2729887A1 (en) | Identifying similar items based on interaction history | |
| US20120214644A1 (en) | Notification signal control apparatus and method | |
| US11717750B2 (en) | Method and apparatus for providing dance game based on recognition of user motion | |
| US20160192866A1 (en) | Determining performance indicators for periodic movements | |
| CN104166716B (en) | A kind of method and device for assessing media file | |
| CN106156270B (en) | Multimedia data pushing method and device | |
| EP2750057B1 (en) | Crowdsourced ranking of music for improving performance | |
| US20210283504A1 (en) | Computer system and game system | |
| JP7074800B2 (en) | Information provision system and information provision method | |
| CN105848737B (en) | Analysis device, recording medium, and analysis method | |
| CN108830636A (en) | A kind of inquiry amount method and apparatus of any active ues |
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 |