Recommended song determination method, apparatus and device, and computer readable storage medium

Abstract

The invention discloses a recommended song determination method and device, equipment and a computer readable storage medium, and belongs to the technical field of multimedia. The method comprises: obtaining song information of a plurality of songs and time corresponding to each song, the plurality of songs being songs of a target object executing a content interaction behavior, and the time corresponding to any song being time of the target object executing the content interaction behavior on any song; according to the time corresponding to each song, classifying the plurality of songs to obtain at least two categories; according to song information of songs included in each category, category labels of each category are determined, and the category label of any category is used for representing the preference of the target object in the time period corresponding to any category; and according to the category label of each category and the song information of the plurality of songs, determining a recommended song corresponding to each category. According to the method, songs recommended to the target object are richer, and the song listening requirement of the target object can be better met.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of multimedia, and in particular, relate to a method and device for determining recommended songs, an apparatus, and a computer readable storage medium. BACKGROUND

[0002] With the continuous development of multimedia technology, more and more users listen to songs online or download songs through music application programs. In addition, music application programs can also recommend songs to users, making it more convenient for users to listen to songs.

[0003] However, the user's interest in listening to songs will change to varying degrees over time, which also requires a higher precision of the personalized recommendation system to capture the different interests of the user at different time periods; therefore, how to more efficiently and accurately recommend more abundant songs to users during the use of the music application program is a current problem to be solved. SUMMARY

[0004] Embodiments of the present application provide a method and device for determining recommended songs, an apparatus, and a computer readable storage medium, which can be used to determine songs recommended to a target object. The technical solution is as follows:

[0005] In one aspect, the present application provides a method for determining recommended songs, the method comprising:

[0006] obtaining song information of a plurality of songs and corresponding times of the respective songs, the plurality of songs being songs on which a target object performs content interaction behavior, and the corresponding time of any song being the time at which the target object performs content interaction behavior on the any song;

[0007] classifying the plurality of songs according to the corresponding times of the respective songs to obtain at least two categories, different categories including songs corresponding to different time periods;

[0008] determining a category label of each category according to the song information of the songs included in the respective categories, the category label of any category being used to represent the preference of the target object in the time period corresponding to the any category;

[0009] determining recommended songs corresponding to the respective categories according to the category labels of the respective categories and the song information of the plurality of songs.

[0010] The method divides songs in which the target object performs content interaction behaviors according to time of the content interaction behaviors, obtains at least two categories, and determines recommended songs corresponding to each category, so that the songs recommended to the target object are more abundant and can meet listening needs of the target object, and thus a probability that the target object clicks the recommended songs is high, thereby improving a click rate of the recommended songs, improving a listening time of the target object in the song application, and improving a user retention rate of the song application.

[0011] In a possible implementation, the at least two categories include at least two of a first category, a second category, or a third category, the songs included in the first category correspond to a time located in a first time period later than a second time period in which the songs included in the second category correspond to a time located in, and the second time period is later than a third time period in which the songs included in the third category correspond to a time located in, and the song information includes at least one of a singer name or a song style;

[0012] The determining, according to the song information of the songs included in each category, of a category label of the each category includes:

[0013] For any one of the first category and the second category, the determining of a category label of the any one category includes at least one of a singer name of the songs included in the any one category and a song style of the songs included in the any one category and the song information of the plurality of songs.

[0014] For the third category, the determining of a category label of the third category includes at least one of a singer name of the songs included in the third category and a song style of the songs included in the third category and a weight of the songs included in the third category, and the weight corresponding to the songs included in the third category is proportional to the time corresponding to the songs included in the third category.

[0015] In a possible implementation, the determining, according to the singer name of the songs included in the any one category and the song style of the songs included in the any one category and the song information of the plurality of songs, of the category label of the any one category includes:

[0016] The determining of the singer name corresponding to the any one category according to the singer name of the songs included in the any one category.

[0017] The determining of a first song quantity of the plurality of songs in which a singer name is the singer name corresponding to the any one category.

[0018] The determining of the song style corresponding to the any one category according to the song style of the songs included in the any one category.

[0019] determine a second song quantity of songs in the plurality of songs whose song styles are the song style corresponding to the any category;

[0020] determine at least one of a first singer name or a first song style as the category label of the any category, the first singer name being a singer name corresponding to the any category and corresponding to a first song quantity greater than a first quantity threshold, the first song style being a song style corresponding to the any category and corresponding to a second song quantity greater than a second quantity threshold.

[0021] In a possible implementation, the determining the category label of the third category according to at least one of the singer names of the songs included in the third category and the song styles of the songs included in the third category and the weights of the songs included in the third category, comprises:

[0022] determining the weight of each singer name corresponding to the third category according to the singer names of the songs included in the third category and the weights of the songs included in the third category;

[0023] determining the weight of each song style corresponding to the third category according to the song styles of the songs included in the third category and the weights of the songs included in the third category;

[0024] determine at least one of a second singer name or a second song style as the category label of the third category, the second singer name being a singer name corresponding to the third category and having a weight greater than a first weight threshold, the second song style being a song style corresponding to the third category and having a weight greater than a second weight threshold.

[0025] In a possible implementation, the determining the recommended songs corresponding to the categories according to the category labels of the categories and the song information of the plurality of songs, comprises:

[0026] for any category in the categories, obtaining a plurality of first candidate songs according to the category label of the any category, the song information of each first candidate song including at least one category label of the any category;

[0027] determining second candidate songs from the plurality of first candidate songs according to the song information of the plurality of songs and the song information of each first candidate song;

[0028] determining the recommended songs corresponding to the any category from the second candidate songs according to the category label of the any category and the song features of each second candidate song.

[0029] In a possible implementation, the determining, according to the song information of the plurality of songs and the song information of each first candidate song, a second candidate song from the plurality of first candidate songs, includes:

[0030] determining, according to the song information of the plurality of songs, a first object feature, the first object feature being used to represent the preference information of the target object;

[0031] determining, according to the song information of each first candidate song, a song feature of each first candidate song, the song feature of any first candidate song being used to represent the any first candidate song;

[0032] determining, according to the first object feature and the song feature of each first candidate song, a first matching degree of each first candidate song, the first matching degree of any first candidate song being used to indicate a probability that the target object performs a content interaction behavior on the any first candidate song;

[0033] taking a first number of first candidate songs with the highest corresponding first matching degrees from the first candidate songs as the second candidate songs.

[0034] In a possible implementation, the determining, according to the category label of any category and the song feature of each second candidate song, a recommended song corresponding to the any category from the second candidate songs, includes:

[0035] determining, according to the category label of any category, a first song from the plurality of songs, the song information of the first song including at least one category label of the any category;

[0036] determining, according to the song information of the first song, a second object feature, the second object feature being used to represent the preference information of the target object;

[0037] determining, according to the second object feature and the song feature of each second candidate song, a second matching degree of each second candidate song, the second matching degree of any second candidate song being used to indicate a probability that the target object performs a content interaction behavior on the any second candidate song;

[0038] taking a second number of second candidate songs with the highest corresponding second matching degrees from the second candidate songs as the recommended songs corresponding to the any category, the second number being less than the first number.

[0039] In a possible implementation, after the determining, according to the category label of any category and the song feature of each second candidate song, a recommended song corresponding to the any category from the second candidate songs, the method further includes:

[0040] adjust the second matching degree of the recommended song corresponding to any category according to the category label of the any category, to obtain a third matching degree of the recommended song corresponding to the any category;

[0041] sort the recommended song corresponding to the any category according to the third matching degree, to obtain a sorting result;

[0042] recommend the recommended song corresponding to the any category to the target object according to the sorting result.

[0043] In a possible implementation, the adjusting the second matching degree of the recommended song corresponding to any category according to the category label of the any category, to obtain a third matching degree of the recommended song corresponding to the any category, includes:

[0044] for any recommended song in the recommended song corresponding to any category, multiplying the second matching degree of the any recommended song by a first weight parameter to obtain the third matching degree of the any recommended song, in a case that the song information of the any recommended song includes the category label of the any category;

[0045] multiplying the second matching degree of the any recommended song by a second weight parameter to obtain the third matching degree of the any recommended song, in a case that the song information of the any recommended song does not include the category label of the any category, the second weight parameter being less than the first weight parameter.

[0046] On the other hand, the embodiment of the present application provides a kind of determining device of recommended song, the device includes:

[0047] acquiring module, for obtaining the song information of multiple songs and the time corresponding to each song, the multiple songs are the songs of target object executing content interaction behavior, the time corresponding to any song is the time of the target object executing content interaction behavior on the any song;

[0048] classification module, for classifying the multiple songs according to the time corresponding to each song, to obtain at least two categories, different categories include the song corresponding to the time in different time periods;

[0049] determining module, for determining the category label of each category according to the song information of the song included in each category, the category label of any category is used to represent the preference of the target object in the time period corresponding to the any category;

[0050] the determining module is also used to determine the recommended song corresponding to the any category according to the category label of each category and the song information of the multiple songs.

[0051] In a possible implementation, the at least two categories include at least two of a first category, a second category, or a third category, the songs corresponding to the time located in a first time period of the first category are later than the songs corresponding to the time located in a second time period of the second category, the second time period is later than a third time period in which the songs corresponding to the time of the third category are located, and the song information includes at least one of a singer name or a song style;

[0052] The determination module is configured to, for any one of the first category and the second category, determine a category label of the any one category according to at least one of the singer name of the songs included in the any one category and the song style of the songs included in the any one category and the song information of the plurality of songs.

[0053] For the third category, a category label of the third category is determined according to at least one of the singer name of the songs included in the third category and the song style of the songs included in the third category and the weight of the songs included in the third category, and the weight corresponding to the songs included in the third category is proportional to the time corresponding to the songs included in the third category.

[0054] In a possible implementation, the determination module is configured to determine a singer name corresponding to the any one category according to the singer name of the songs included in the any one category.

[0055] A first number of songs in the plurality of songs whose singer name is the singer name corresponding to the any one category is determined.

[0056] A song style corresponding to the any one category is determined according to the song style of the songs included in the any one category.

[0057] A second number of songs in the plurality of songs whose song style is the song style corresponding to the any one category is determined.

[0058] At least one of a first singer name or a first song style is determined as the category label of the any one category, the first singer name is a singer name corresponding to the first number of songs in the any one category greater than a first number threshold, and the first song style is a song style corresponding to the second number of songs in the any one category greater than a second number threshold.

[0059] In a possible implementation, the determination module is configured to determine the weight of each singer name corresponding to the third category according to the singer name of the songs included in the third category and the weight of the songs included in the third category.

[0060] determine a weight of each song genre corresponding to the third category according to a song genre of a song included in the third category and a weight of the song included in the third category;

[0061] determine at least one of a second singer name or a second song genre as a category label of the third category, the second singer name being a singer name with a weight greater than a first weight threshold among each singer name corresponding to the third category, and the second song genre being a song genre with a weight greater than a second weight threshold among each song genre corresponding to the third category.

[0062] In a possible implementation, the determining module is configured to, for any category of the categories, acquire a plurality of first candidate songs according to a category label of the any category, song information of each first candidate song including at least one category label of the any category;

[0063] determine a second candidate song from the plurality of first candidate songs according to the song information of the plurality of songs and the song information of each first candidate song;

[0064] determine a recommended song corresponding to the any category from the second candidate songs according to the category label of the any category and a song feature of each second candidate song.

[0065] In a possible implementation, the determining module is configured to determine a first object feature according to the song information of the plurality of songs, the first object feature being used to represent preference information of the target object;

[0066] determine a song feature of each first candidate song according to the song information of the any first candidate song, the song feature of any first candidate song being used to represent the any first candidate song;

[0067] determine a first matching degree of each first candidate song according to the first object feature and the song feature of each first candidate song, the first matching degree of any first candidate song being used to indicate a probability that the target object performs a content interaction behavior on the any first candidate song;

[0068] take a first number of first candidate songs with the highest corresponding first matching degrees from the first candidate songs as the second candidate songs.

[0069] In a possible implementation, the determining module is configured to determine a first song from the plurality of songs according to a category label of the any category, the song information of the first song including at least one category label of the any category;

[0070] determine a second object feature according to the song information of the first song, the second object feature being used to represent preference information of the target object;

[0071] determine a second matching degree of each of the second candidate songs according to the second object feature and the song feature of each of the second candidate songs, the second matching degree of any of the second candidate songs being used to indicate a probability of the target object performing a content interaction behavior on the any of the second candidate songs;

[0072] select a second number of second candidate songs with the highest corresponding second matching degrees from the second candidate songs as the recommended songs corresponding to the any of the categories, the second number being less than the first number.

[0073] In a possible implementation, the apparatus further includes:

[0074] an adjusting module configured to adjust the second matching degree of the recommended songs corresponding to the any of the categories according to the category label of the any of the categories, to obtain a third matching degree of the recommended songs corresponding to the any of the categories;

[0075] a sorting module configured to sort the recommended songs corresponding to the any of the categories according to the third matching degree, to obtain a sorting result;

[0076] a recommending module configured to recommend the recommended songs corresponding to the any of the categories to the target object according to the sorting result.

[0077] In a possible implementation, the adjusting module is configured to, for any of the recommended songs corresponding to the any of the categories, multiply the second matching degree of the any of the recommended songs by a first weight parameter to obtain the third matching degree of the any of the recommended songs, in a case where the song information of the any of the recommended songs includes the category label of the any of the categories.

[0078] In a case where the song information of the any of the recommended songs does not include the category label of the any of the categories, multiply the second matching degree of the any of the recommended songs by a second weight parameter to obtain the third matching degree of the any of the recommended songs, the second weight parameter being less than the first weight parameter.

[0079] In another aspect, an embodiment of the present application provides a computer device including a processor and a memory, the memory storing at least one program code, the at least one program code being loaded and executed by the processor to enable the computer device to implement the above-described method for determining recommended songs.

[0080] In another aspect, a computer readable storage medium is provided, wherein at least one program code is stored in the computer readable storage medium, and the at least one program code is loaded and executed by a processor to enable a computer device to implement the method for determining recommended songs.

[0081] In another aspect, a computer program or computer program product is provided, wherein at least one computer instruction is stored in the computer program or computer program product, and the at least one computer instruction is loaded and executed by a processor to enable a computer device to implement any of the methods for determining recommended songs. BRIEF DESCRIPTION OF DRAWINGS

[0082] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort based on these drawings.

[0083] Figure 1 is a schematic diagram of an implementation environment of a method for determining recommended songs provided by an embodiment of the present application;

[0084] Figure 2 is a flowchart of a method for determining recommended songs provided by an embodiment of the present application;

[0085] Figure 3 is a display schematic diagram of song information of recommended songs corresponding to each category provided by an embodiment of the present application;

[0086] Figure 4 is a schematic diagram of displaying song information of recommended songs corresponding to a first category in a song playing interface provided by an embodiment of the present application;

[0087] Figure 5 is a flowchart of a method for determining recommended songs provided by an embodiment of the present application;

[0088] Figure 6 is a structural schematic diagram of a device for determining recommended songs provided by an embodiment of the present application;

[0089] Figure 7 is a structural schematic diagram of a terminal device provided by an embodiment of the present application;

[0090] Figure 8 is a structural schematic diagram of a server provided by an embodiment of the present application. DETAILED DESCRIPTION

[0091] For the purposes of the present application, the technical solutions and advantages, the embodiments of the present application will be further described in detail below with reference to the drawings.

[0092] It should be noted that the terms "first", "second" and the like in the present application are used to distinguish similar objects, and do not necessarily have to describe a specific order or sequence. It should be understood that the terms thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of devices and methods consistent with some aspects of the present application, as detailed in the appended claims.

[0093] Figure 1 is a schematic diagram of an implementation environment of a method for determining a recommended song provided by an embodiment of the present application, as shown in Figure 1 The computer device 101 can be a terminal device or a server, and embodiments of the present application do not limit the same. The computer device 101 is configured to execute the method for determining a recommended song provided by an embodiment of the present application.

[0094] Optionally, the computer device 101 is a terminal device, which can be any electronic device product capable of human-computer interaction with a user through one or more of a keyboard, a touchpad, a remote control, voice interaction, or a handwriting device, etc. For example, a PC (Personal Computer), a mobile phone, a smart phone, a PDA (Personal Digital Assistant), a wearable device, a PPC (Pocket PC), a tablet computer, a smart car machine, a smart television, a smart speaker, a smart watch, etc.

[0095] The terminal device can generally refer to one of a plurality of terminal devices, and the embodiments are only exemplified by the terminal device. Those skilled in the art can know that the number of the above-mentioned terminal devices can be more or less. For example, the above-mentioned terminal device can be only one, or the above-mentioned terminal device can be dozens or hundreds, or more, and the number and type of the terminal device are not limited by the embodiments of the present application.

[0096] The computer device 101 is a server, or a server cluster composed of multiple servers, or any one of a cloud computing platform and a virtualization center, and embodiments of the present application do not limit the same. The server is in communication connection with the terminal device through a wired network or a wireless network. The server has a data receiving function, a data processing function and a data sending function. Of course, the server can also have other functions, and embodiments of the present application do not limit the same.

[0097] In the exemplary embodiments of the present application, the computer device 101 obtains song information of a plurality of songs and a time corresponding to each song, the plurality of songs being songs for which a target object performs a content interaction behavior, and the time corresponding to any song being a time at which the target object performs a content interaction behavior on any song; the computer device 101 classifies the plurality of songs according to the time corresponding to each song, to obtain at least two categories, different categories including songs corresponding to different time periods; the computer device 101 determines a category label of each category according to the song information of the songs included in each category, the category label of any category being used to represent a preference of the target object in a time period corresponding to any category; and the computer device 101 determines a recommended song corresponding to each category according to the category label of each category and the song information of the plurality of songs.

[0098] Those skilled in the art should understand that the terminal device and the server described above are only examples, and other existing or future terminal devices or servers, such as those applicable to the present application, should also be included in the protection scope of the present application and are hereby incorporated by reference.

[0099] Embodiments of the present application provide a method for determining a recommended song, which can be applied to the implementation environment shown in Figure 1 Embodiments of the present application provide a method for determining a recommended song, which can be applied to the implementation environment shown in Figure 2 The flowchart of the method for determining a recommended song provided by the embodiments of the present application is taken as an example, which can be executed by the computer device 101 in Figure 1 As shown in Figure 2 The method includes the following steps 201 to 204.

[0100] In step 201, the song information of a plurality of songs and the time corresponding to each song are obtained, the plurality of songs being songs for which a target object performs a content interaction behavior, and the time corresponding to any song being a time at which the target object performs a content interaction behavior on any song.

[0101] In the exemplary embodiments of the present application, the content interaction behavior includes but is not limited to collecting, playing, replaying, liking, commenting, etc.

[0102] In a possible implementation, in the case that the computer device is a terminal device, the terminal device sends a request for acquisition to a server, and the request for acquisition includes an object identifier of a target object; the server receives the request for acquisition, and parses the request for acquisition to obtain the object identifier of the target object. The server stores historical behavior data of each object and a correspondence between the object identifier of each object and the historical behavior data of each object. The server acquires the historical behavior data of the target object according to the object identifier of the target object, and returns the historical behavior data of the target object to the terminal device, wherein the historical behavior data of the target object includes song information of a plurality of songs and a time corresponding to each song, so that the terminal device acquires the song information of the plurality of songs and the time corresponding to each song.

[0103] In another possible implementation, in the case that the computer device is a server, since the server stores historical behavior data of each object and a correspondence between the object identifier of each object and the historical behavior data of each object, the server acquires the historical behavior data of the target object from a storage space of the server, wherein the historical behavior data of the target object includes song information of a plurality of songs and a time corresponding to each song, so that the server acquires the song information of the plurality of songs and the time corresponding to each song.

[0104] The object identifier of the target object can be an account name of the target object in a song application, or can be an account number of the target object in the song application, which is not limited in the embodiments of the present application.

[0105] In a possible implementation, the song information includes but is not limited to a song name, a singer name, a song style, and the like.

[0106] In step 202, the plurality of songs are classified according to the time corresponding to each song to obtain at least two categories, and the songs included in different categories correspond to time located in different time periods.

[0107] The at least two categories include at least two of a first category, a second category, or a third category. The first time period of the time corresponding to the songs included in the first category is later than the second time period of the time corresponding to the songs included in the second category, and the second time period is later than the third time period of the time corresponding to the songs included in the third category. The duration of the first time period is less than the duration of the second time period, and the duration of the second time period is less than the duration of the third time period.

[0108] In a possible implementation, the determination process of the first time period is as follows: the first time period is determined according to the current time and the duration of the first time period. The duration of the first time period is set based on experience, or is flexibly adjusted according to the implementation environment, which is not limited in the embodiments of the present application. For example, the duration of the first time period is 1 hour.

[0109] Optionally, the current time is used as the end time of the first time period, and the first time period is determined according to the end time of the first time period and the duration of the first time period.

[0110] For example, if the current time is 10:00 on June 20, 2025, the end time of the first time period is 10:00 on June 20, 2025, and the duration of the first time period is 1 hour, then the first time period is from 9:00 on June 20, 2025 to 10:00 on June 20, 2025.

[0111] In one possible implementation, determining the second time period includes determining the second time period based on the start time of the first time period and the duration of the second time period. The duration of the second time period is set based on experience or flexibly adjusted based on the implementation environment, and is not limited in this embodiment of the present application. For example, the duration of the second time period is 71 hours.

[0112] Optionally, the start time of the first time period is used as the end time of the second time period, and the second time period is determined according to the end time of the second time period and the duration of the second time period.

[0113] For example, the start time of the first time period is 9:00 on June 20, 2025, and the end time of the second time period is 9:00 on June 20, 2025. The duration of the second time period is 71 hours, so the second time period is from 10:00 on June 17, 2025 to 9:00 on June 20, 2025.

[0114] In one possible implementation, the process of determining the third time period includes: determining the third time period according to the start time of the second time period. Optionally, using the start time of the second time period as the end time of the third time period.

[0115] For example, the start time of the second time period is 10:00 on June 17, 2025, and the end time of the third time period is 10:00 on June 17, 2025, that is, the time period before 10:00 on June 17, 2025 is the third time period.

[0116] In one possible implementation, multiple songs are classified according to the time corresponding to each song to obtain at least two categories, including: songs whose corresponding time among the multiple songs is in the first time period are included in the first category, songs whose corresponding time among the multiple songs is in the second time period are included in the second category, and songs whose corresponding time among the multiple songs is in the third time period are included in the third category.

[0117] In step 203, according to the song information of the songs included in each category, a category label of each category is determined, and the category label of any category is used to represent the preference of the target object in the time period corresponding to the category.

[0118] In a possible implementation, the process of determining the category label of the first category according to the song information of the songs included in the first category is similar to the process of determining the category label of the second category according to the song information of the songs included in the second category, and the process of determining the category label of the first category according to the song information of the songs included in the first category is different from the process of determining the category label of the third category according to the song information of the songs included in the third category.

[0119] In a possible implementation, the song information includes at least one of a singer name and a song style. For any of the first category and the second category, the category label of any of the first category and the second category is determined according to at least one of the singer name of the songs included in any of the first category and the second category and the song style of the songs included in any of the first category and the second category and the song information of the plurality of songs. For the third category, the category label of the third category is determined according to at least one of the singer name of the songs included in the third category and the song style of the songs included in the third category and the weight of the songs included in the third category, and the weight corresponding to the songs included in the third category is proportional to the time corresponding to the songs included in the third category.

[0120] In the implementation, the earlier the time corresponding to the songs included in the third category, the lower the weight corresponding to the songs included in the third category. Conversely, the later the time corresponding to the songs included in the third category, the higher the weight corresponding to the songs included in the third category.

[0121] Optionally, the weight corresponding to the songs included in the third category is also related to the number of repetitions of the content interaction behavior. For example, the third category includes a song a and a song b, the song a is played multiple times after being collected by the user, and the song b has no play behavior after being collected by the user, and the weight corresponding to the song a is greater than the weight corresponding to the song b.

[0122] In the implementation, different categories are determined in different ways. For the first category and the second category, the category label is generated according to at least one of the singer name and the song style of the included songs and the song information of the plurality of songs, and for the third category, the corresponding category label is generated according to at least one of the singer name and the song style of the included songs and the weight of the songs. Not only the information of the songs is considered, but also the weight change caused by the time factor, so that the category label can dynamically reflect the change trend of the song popularity or importance, thereby improving the accuracy and comprehensiveness of the category label.

[0123] In a possible implementation, the process of determining the category label of any category according to at least one of the singer names of the songs included in any category and the song moods of the songs included in any category and the song information of the plurality of songs includes: determining the singer names corresponding to any category according to the singer names of the songs included in any category, determining the first song quantity of the plurality of songs whose singer names are the singer names corresponding to any category; determining the song moods corresponding to any category according to the song moods of the songs included in any category, determining the second song quantity of the plurality of songs whose song moods are the song moods corresponding to any category; and determining at least one of the first singer names or the first song moods as the category label of any category, the first singer names being the singer names corresponding to any category and corresponding to the first song quantity greater than the first quantity threshold, and the first song moods being the song moods corresponding to any category and corresponding to the second song quantity greater than the second quantity threshold.

[0124] The first quantity threshold and the second quantity threshold are both set based on experience or are flexibly adjusted according to the implementation environment, and the embodiments of the present application do not limit this. For example, the first quantity threshold is 30, and the second quantity threshold is 30.

[0125] For example, any category includes 30 songs, of which 11 songs are by singer A, 13 songs are by singer B, and 6 songs are by singer C. The singer names corresponding to any category are singer A, singer B, and singer C. The first song quantity of the plurality of songs whose singer names are singer A is 40, the first song quantity of the plurality of songs whose singer names are singer B is 50, and the first song quantity of the plurality of songs whose singer names are singer C is 10. The first quantity threshold is 30. Since the first song quantity of the plurality of songs whose singer names are singer A and the first song quantity of the plurality of songs whose singer names are singer B are both greater than the first quantity threshold, singer A and singer B are determined as the first singer names.

[0126] For another example, any category includes 30 songs, of which 11 songs are of mood one, 13 songs are of mood two, and 6 songs are of mood three. The song moods corresponding to any category are mood one, mood two, and mood three. The second song quantity of the plurality of songs whose song moods are mood one is 40, the second song quantity of the plurality of songs whose song moods are mood two is 50, and the second song quantity of the plurality of songs whose song moods are mood three is 10. The second quantity threshold is 30. Since the second song quantity of the plurality of songs whose song moods are mood one and the second song quantity of the plurality of songs whose song moods are mood two are both greater than the second quantity threshold, mood one and mood two are determined as the first song moods.

[0127] After the first singer name and the first song style are determined, at least one of the first singer name or the first song style is taken as a category label of any category.

[0128] In this implementation, by respectively counting the occurrence frequencies of the singer names and the song styles corresponding to any category in multiple songs, the first singer name and the first song style higher than the corresponding quantity threshold are screened out, and the category label of any category is determined based on at least one of the first singer name and the first song style. The data is supported, the low-frequency interference information is excluded, the accuracy of the determined category label of any category is higher, and the songs can be more accurately recommended for the target object.

[0129] In a possible implementation, according to at least one of the singer names of the songs included in the third category and the song styles of the songs included in the third category and the weights of the songs included in the third category, the process of determining the category label of the third category includes: determining the weights of each singer name corresponding to the third category according to the singer names of the songs included in the third category and the weights of the songs included in the third category; determining the weights of each song style corresponding to the third category according to the song styles of the songs included in the third category and the weights of the songs included in the third category; and determining at least one of the second singer name or the second song style as the category label of the third category, the second singer name being a singer name whose weight is greater than a first weight threshold in each singer name corresponding to the third category, and the second song style being a song style whose weight is greater than a second weight threshold in each song style corresponding to the third category.

[0130] The first weight threshold and the second weight threshold are both set based on experience, or are flexibly adjusted according to an implementation environment, and embodiments of the present application do not limit this. Exemplarily, the first weight threshold is 2, and the second weight threshold is 2.

[0131] Optionally, the process of determining the weight of each singer name corresponding to the third category according to the singer names of the songs included in the third category and the weights of the songs included in the third category includes: determining the singer name corresponding to the third category according to the singer names of the songs included in the third category; and for any singer name corresponding to the third category, adding the weights of the songs whose singer names are the any singer name in the songs included in the third category to obtain the weight of the any singer name corresponding to the third category.

[0132] Exemplarily, the singer name corresponding to the third category includes singer D, and the songs included in the third category include four songs whose singer names are singer D, and the weights of the four songs are 0.2, 0.3, 0.5 and 0.7 respectively, so the weight of singer D is 1.7.

[0133] Optionally, the process of determining the weight of each song style corresponding to the third category according to the song styles of the songs included in the third category and the weights of the songs included in the third category comprises: determining the song styles corresponding to the third category according to the song styles of the songs included in the third category; and for any song style corresponding to the third category, adding the weights of the songs included in the third category and having the any song style to obtain the weight of the any song style corresponding to the third category.

[0134] Exemplarily, the song styles corresponding to the third category include a song style four, the songs included in the third category and having the song style four are three, and the weights of the three songs are 0.3, 0.6 and 0.4 respectively, and the weight of the song style four is 1.3.

[0135] In this implementation, the weights of each singer name and each song style corresponding to the third category are determined by the weights of the songs included in the third category, and then the second singer name and the second song style are determined according to the corresponding weight threshold, and the category label of the third category is determined according to at least one of the second singer name and the second song style, which makes the determined category label of the third category more accurate, and further enables more accurate recommendation of songs for the target object.

[0136] In step 204, the recommended songs corresponding to each category are determined according to the category labels of each category and the song information of the plurality of songs.

[0137] In a possible implementation, the process of determining the recommended songs corresponding to each category according to the category labels of each category and the song information of the plurality of songs comprises: for any category in each category, obtaining a plurality of first candidate songs according to the category label of the any category, the song information of each first candidate song including at least one category label of the any category; determining second candidate songs from the plurality of first candidate songs according to the song information of the plurality of songs and the song information of each first candidate song; and determining the recommended songs corresponding to the any category from the second candidate songs according to the category label of the any category and the song features of each second candidate song.

[0138] The number of the obtained first candidate songs is not limited in the embodiments of the present application. Exemplarily, 3600 first candidate songs are obtained.

[0139] In the implementation manner, the first candidate songs satisfying the category label of any category are screened out, the second candidate songs are screened out from the first candidate songs according to the song information of the multiple songs on which the target object historically performs content interaction behaviors, the third candidate songs are screened out from the second candidate songs according to the category label of any category, and then the recommended songs corresponding to any category are screened out from the third candidate songs. The method not only considers the category label of any category, but also considers the multiple songs on which the target object historically performs content interaction behaviors and the category label of any category, so that the accuracy of the recommended songs corresponding to any category determined is higher.

[0140] In a possible implementation manner, the process of determining the second candidate songs from the multiple first candidate songs according to the song information of the multiple songs and the song information of each first candidate song includes: determining a first object feature according to the song information of the multiple songs, the first object feature being used to represent the preference information of the target object; determining a song feature of each first candidate song according to the song information of each first candidate song, the song feature of any first candidate song being used to represent any first candidate song; and determining the second candidate songs from the multiple first candidate songs according to the first object feature and the song feature of each first candidate song.

[0141] Optionally, the process of determining the first object feature according to the song information of the multiple songs is similar to the process of determining the song feature of each first candidate song according to the song information of each first candidate song, and the embodiments of the present application only take the process of determining the first object feature according to the song information of the multiple songs as an example for description. Exemplarily, the process of determining the first object feature according to the song information of the multiple songs includes: processing the song information of the multiple songs by a feature acquisition model to obtain the first object feature.

[0142] In the implementation manner, the first candidate songs satisfying the category label of any category are screened out, the second candidate songs are screened out from the first candidate songs according to the song information of the multiple songs on which the target object historically performs content interaction behaviors, the third candidate songs are screened out from the second candidate songs according to the category label of any category, and then the recommended songs corresponding to any category are screened out from the third candidate songs. The method not only considers the category label of any category, but also considers the multiple songs on which the target object historically performs content interaction behaviors and the category label of any category, so that the accuracy of the recommended songs corresponding to any category determined is higher.

[0143] In a possible implementation manner, the process of determining the second candidate songs from the multiple first candidate songs according to the first object feature and the song feature of each first candidate song includes: determining a first matching degree of each first candidate song according to the first object feature and the song feature of each first candidate song, the first matching degree of any first candidate song being used to indicate a probability that the target object performs content interaction behaviors on any first candidate song; and taking the first candidate songs corresponding to the highest first matching degrees in the first candidate songs as the second candidate songs.

[0144] The first quantity is set based on experience or is flexibly adjusted according to an implementation environment, and embodiments of the present application do not limit this. Exemplarily, the first quantity is 300. That is, 300 first candidate songs with the highest first matching degrees in the first candidate songs are taken as the second candidate songs.

[0145] In a possible implementation, the process of determining the first matching degree of each first candidate song according to the first object feature and the song feature of each first candidate song includes: for any first candidate song in each first candidate song, multiplying the first object feature and the song feature of the any first candidate song to obtain the first matching degree of the any first candidate song.

[0146] In this implementation, the first matching degree of each first candidate song is determined through the song feature of each first candidate song and the first object feature, and the first candidate songs with the highest first matching degrees are screened out from the first candidate songs as the second candidate songs. This way, the second candidate songs are screened out through the matching degrees, so that the matching degrees of the screened-out second candidate songs with the target object are higher, and thus the songs recommended to the target object in the subsequent determination can be more in line with the requirements of the target object.

[0147] In a possible implementation, the process of determining the recommended song corresponding to any category in the second candidate songs according to the category label of any category and the song feature of each second candidate song includes: determining a first song in the plurality of songs according to the category label of any category, the song information of the first song including at least one category label of any category; determining a second object feature according to the song information of the first song, the second object feature being used to represent the preference information of the target object; and determining the recommended song corresponding to any category in the second candidate songs according to the second object feature and the song feature of each second candidate song.

[0148] In this implementation, the process of determining the first song in the plurality of songs according to the category label of any category includes: taking a song in the plurality of songs whose song information includes at least one category label of any category as the first song.

[0149] Exemplarily, the category label of any category is a singer A and a style one, and a song in the plurality of songs whose singer name is the singer A is taken as the first song, a song in the plurality of songs whose song style is the style one is taken as the first song, and a song in the plurality of songs whose singer name is the singer A and whose song style is the style one is taken as the first song.

[0150] In a possible implementation, the process of determining the second object feature according to the song information of the first song is similar to the process of determining the first object feature according to the song information of the plurality of songs, and embodiments of the present application do not repeat the description here.

[0151] In a possible implementation, the process of determining the recommended songs corresponding to any category in the second candidate songs according to the second object feature and the song features of the second candidate songs includes: determining a second matching degree of each second candidate song according to the second object feature and the song features of the second candidate songs, where the second matching degree of any second candidate song indicates a probability that the target object performs a content interaction behavior on the second candidate song; and taking the second candidate songs with the highest second matching degrees in the second candidate songs as the recommended songs corresponding to any category, where the second quantity is less than the first quantity.

[0152] The second quantity is set based on experience or is flexibly adjusted according to an implementation environment, which is not limited in the embodiments of the present application. For example, the second quantity is 30. That is, the 30 second candidate songs with the highest second matching degrees in the second candidate songs are taken as the recommended songs corresponding to any category.

[0153] The process of determining the second matching degree of each second candidate song according to the second object feature and the song features of the second candidate songs is similar to the process of determining the first matching degree of each first candidate song according to the first object feature and the song features of the first candidate songs, which is not repeated here.

[0154] In this implementation, the second matching degree of each second candidate song is determined according to the song features of the second candidate songs and the second object feature, and the second candidate songs with the highest second matching degrees are selected from the second candidate songs as the recommended songs corresponding to any category. This way of selecting the recommended songs corresponding to any category through the matching degree makes the selected recommended songs corresponding to any category have a higher matching degree with the target object and better meet the listening requirements of the target object.

[0155] In a possible implementation, after determining the recommended songs corresponding to any category in the second candidate songs according to the category label of any category and the song features of the second candidate songs, the second matching degree of the recommended songs corresponding to any category can be adjusted according to the category label of any category to obtain a third matching degree of the recommended songs corresponding to any category; the recommended songs corresponding to any category are sorted according to the third matching degree to obtain a sorting result; and the recommended songs corresponding to any category are recommended to the target object according to the sorting result.

[0156] In the process of sorting the recommended songs corresponding to any category according to the third matching degree, the recommended songs corresponding to any category can be sorted in descending order of the third matching degree, or can be sorted in ascending order of the third matching degree, and the application embodiments do not limit this.

[0157] In a possible implementation, the process of adjusting the second matching degree of the recommended songs corresponding to any category according to the category labels of any category to obtain the third matching degree of the recommended songs corresponding to any category includes: for any recommended song in the recommended songs corresponding to any category, if the song information of the any recommended song includes the category labels of any category, multiplying the second matching degree of the any recommended song by the first weight parameter to obtain the third matching degree of the any recommended song; if the song information of the any recommended song does not include the category labels of any category, multiplying the second matching degree of the any recommended song by the second weight parameter to obtain the third matching degree of the any recommended song, and the second weight parameter is less than the first weight parameter.

[0158] The first weight parameter and the second weight parameter are both set based on experience or are flexibly adjusted according to an implementation environment, and the application embodiments do not limit this. For example, the first weight parameter is 2, and the second weight parameter is 1.

[0159] In this implementation, if the song information of any recommended song includes all the category labels of any category, the matching degree of the any recommended song is improved to improve the position of the any recommended song in the recommended songs corresponding to any category, and if the song information of the any recommended song does not include all the category labels of any category, the matching degree of the any recommended song is reduced or maintained to reduce the position of the any recommended song in the recommended songs corresponding to any category.

[0160] In a possible implementation, after the recommended songs corresponding to each category are determined, the recommended songs corresponding to each category are recommended to the target object.

[0161] Optionally, based on the computer device being a server, the process of recommending the recommended songs corresponding to any category to the target object according to the sorting result includes: sending the sorting result of any category to a terminal device, and displaying the song information of the recommended songs corresponding to any category according to the sorting result by the terminal device. Based on the computer device being a terminal device, the song information of the recommended songs corresponding to any category is directly displayed according to the sorting result.

[0162] In a possible implementation, the process in which the terminal device displays the song information of the recommended songs corresponding to each category includes: the terminal device displays the song information of the recommended songs corresponding to each category according to different categories on a song recommendation interface.

[0163] The song recommendation interface can be a home page of a song application, a search interface of the song application, or a ranking interface of the song application, and the embodiments of the present application do not limit this.

[0164] For example, the categories include a first category, a second category, and a third category, and the terminal device displays the song information of the recommended songs corresponding to the first category, the song information of the recommended songs corresponding to the second category, and the song information of the recommended songs corresponding to the third category.

[0165] Further, the terminal device displays the song information of the recommended songs corresponding to the first category according to the sorting result of the first category, displays the song information of the recommended songs corresponding to the second category according to the sorting result of the second category, and displays the song information of the recommended songs corresponding to the third category according to the sorting result of the third category.

[0166] For example, Figure 3 FIG. 1 is a display diagram of the song information of the recommended songs corresponding to each category provided by an embodiment of the present application. In Figure 3 301 in FIG. 1 is the song information of the recommended songs corresponding to the first category, 302 is the song information of the recommended songs corresponding to the second category, and 303 is the song information of the recommended songs corresponding to the third category.

[0167] In a possible implementation, after the recommended songs corresponding to each category are determined, in the case where the categories include the first category and a song playing operation is received, the song information of the recommended songs corresponding to the first category is displayed on a song playing interface.

[0168] For example, Figure 4 FIG. 2 is a display diagram of the song information of the recommended songs corresponding to the first category on a song playing interface provided by an embodiment of the present application. As shown in FIG. 2, Figure 4 401 in FIG. 2 is the song information of the recommended songs corresponding to the first category.

[0169] The above method divides the songs on which the target object has performed content interaction behaviors according to the time of the content interaction behaviors, obtains at least two categories, determines the recommended songs corresponding to each category, so that the songs recommended to the target object are more abundant and can better meet the song listening needs of the target object, and thus the probability that the target object clicks the recommended songs is higher, thereby the click rate of the recommended songs can be improved, the song listening time of the target object in the song application can be improved, and the user retention rate of the song application can be improved.

[0170] Figure 5 is a flowchart of a method for determining recommended songs provided by an embodiment of the present application. As shown in the figure, the method comprises the following. Figure 5

[0171] Step 501: Obtain song information of a plurality of songs and corresponding time of each song.

[0172] The plurality of songs are songs for which the target object performs content interaction behavior, and the corresponding time of any song is the time at which the target object performs content interaction behavior on the any song.

[0173] In a possible implementation, the process of obtaining the song information of the plurality of songs and the corresponding time of each song has been described in step 201 above, and the embodiments of the present application will not be repeated here.

[0174] Step 502: Classify the plurality of songs according to the corresponding time of each song to obtain a first category, a second category and a third category.

[0175] The different categories include songs corresponding to different time periods.

[0176] In a possible implementation, the process of classifying the plurality of songs according to the corresponding time of each song to obtain the first category, the second category and the third category has been described in step 202 above, and the embodiments of the present application will not be repeated here.

[0177] Step 503: Determine a category label of each category according to the song information of the songs included in each category.

[0178] The category label of any category is used to represent the preference of the target object in the time period corresponding to any category.

[0179] In a possible implementation, the process of determining the category label of each category according to the song information of the songs included in each category has been described in step 203 above, and the embodiments of the present application will not be repeated here.

[0180] Step 504: For any category in each category, obtain a first candidate song according to the category label of any category.

[0181] The song information of the first candidate song includes at least one category label of any category.

[0182] In a possible implementation, the process of obtaining the first candidate song according to the category label of any category has been described in step 204 above, and the embodiments of the present application will not be repeated here.

[0183] ​Step 505. Determine a second candidate song from the first candidate songs according to the song information of the multiple songs and the song information of each first candidate song.

[0184] In a possible implementation, the process of determining the second candidate song from the first candidate songs according to the song information of the multiple songs and the song information of each first candidate song has been described in step 204, and the embodiments of the present application will not be repeated here.

[0185] Step 506. Determine a recommended song corresponding to any category from the second candidate songs according to the category label of any category and the song feature of each second candidate song.

[0186] In a possible implementation, the process of determining a recommended song corresponding to any category from the second candidate songs according to the category label of any category and the song feature of each second candidate song has been described in step 204, and the embodiments of the present application will not be repeated here.

[0187] Figure 6 Fig. 6 shows a structural schematic diagram of a device for determining a recommended song according to an embodiment of the present application, which comprises: Figure 6

[0188] The obtaining module 601 is configured to obtain song information of multiple songs and time corresponding to each song, the multiple songs being songs for which a target object performs a content interaction behavior, and the time corresponding to any song being a time at which the target object performs a content interaction behavior on the any song.

[0189] The classification module 602 is configured to classify the multiple songs according to the time corresponding to each song to obtain at least two categories, different categories including songs corresponding to different time periods.

[0190] The determining module 603 is configured to determine a category label of each category according to the song information of the songs included in each category, the category label of any category being used to represent a preference of the target object in a time period corresponding to the any category.

[0191] The determining module 603 is further configured to determine a recommended song corresponding to each category according to the category label of each category and the song information of the multiple songs.

[0192] In a possible implementation, the at least two categories include at least two of a first category, a second category, or a third category, the time corresponding to the songs included in the first category is located in a first time period later than the time corresponding to the songs included in the second category is located in a second time period, the second time period is later than the time corresponding to the songs included in the third category is located in a third time period, and the song information includes at least one of a singer name or a song style.​

[0193] The determining module 603 is configured to determine, for any one of the first category and the second category, a category label of the any one of the categories according to at least one of the singer names of the songs included in the any one of the categories and the song moods of the songs included in the any one of the categories and the song information of the plurality of songs.

[0194] For the third category, a category label of the third category is determined according to at least one of the singer names of the songs included in the third category and the song moods of the songs included in the third category and the weights of the songs included in the third category, and the weight corresponding to the song included in the third category is proportional to the time corresponding to the song included in the third category.

[0195] In a possible implementation, the determining module 603 is configured to determine the singer names corresponding to any one of the categories according to the singer names of the songs included in the any one of the categories.

[0196] The determining module 603 is configured to determine the first number of songs in the plurality of songs whose singer names are the singer names corresponding to any one of the categories.

[0197] The determining module 603 is configured to determine the song moods corresponding to any one of the categories according to the song moods of the songs included in the any one of the categories.

[0198] The determining module 603 is configured to determine the second number of songs in the plurality of songs whose song moods are the song moods corresponding to any one of the categories.

[0199] The determining module 603 is configured to determine at least one of the first singer names or the first song moods as the category label of any one of the categories, the first singer names being the singer names corresponding to any one of the categories and corresponding to the first number of songs greater than the first number threshold, and the first song moods being the song moods corresponding to any one of the categories and corresponding to the second number of songs greater than the second number threshold.

[0200] In a possible implementation, the determining module 603 is configured to determine the weights of the respective singer names corresponding to the third category according to the singer names of the songs included in the third category and the weights of the songs included in the third category.

[0201] The determining module 603 is configured to determine the weights of the respective song moods corresponding to the third category according to the song moods of the songs included in the third category and the weights of the songs included in the third category.

[0202] The determining module 603 is configured to determine at least one of the second singer names or the second song moods as the category label of the third category, the second singer names being the respective singer names corresponding to the third category and having weights greater than the first weight threshold, and the second song moods being the respective song moods corresponding to the third category and having weights greater than the second weight threshold.

[0203] In a possible implementation, the determining module 603 is configured to: for any one of the categories, obtain a plurality of first candidate songs according to the category label of the any one of the categories, and the song information of each of the first candidate songs comprises at least one category label of the any one of the categories.

[0204] determine the second candidate songs from the plurality of first candidate songs according to the song information of the plurality of songs and the song information of each of the first candidate songs.

[0205] determine the recommended songs corresponding to the any one of the categories from the second candidate songs according to the category label of the any one of the categories and the song feature of each of the second candidate songs.

[0206] In a possible implementation, the determining module 603 is configured to: determine a first object feature according to the song information of the plurality of songs, and the first object feature is used to represent the preference information of the target object.

[0207] determine the song feature of each of the first candidate songs according to the song information of each of the first candidate songs, and the song feature of any one of the first candidate songs is used to represent the any one of the first candidate songs.

[0208] determine the first matching degree of each of the first candidate songs according to the first object feature and the song feature of each of the first candidate songs, and the first matching degree of any one of the first candidate songs is used to indicate the probability that the target object performs the content interaction behavior on the any one of the first candidate songs.

[0209] select the first candidate songs corresponding to the first matching degrees that are highest from the first candidate songs as the second candidate songs.

[0210] In a possible implementation, the determining module 603 is configured to: determine a first song from the plurality of songs according to the category label of the any one of the categories, and the song information of the first song comprises at least one category label of the any one of the categories.

[0211] determine a second object feature according to the song information of the first song, and the second object feature is used to represent the preference information of the target object.

[0212] determine the second matching degree of each of the second candidate songs according to the second object feature and the song feature of each of the second candidate songs, and the second matching degree of any one of the second candidate songs is used to indicate the probability that the target object performs the content interaction behavior on the any one of the second candidate songs.

[0213] select the second candidate songs corresponding to the second matching degrees that are highest from the second candidate songs as the recommended songs corresponding to the any one of the categories, and the second quantity is less than the first quantity.

[0214] In a possible implementation, the apparatus further includes:

[0215] The adjusting module is configured to adjust the second matching degree of the recommended song corresponding to any category according to the category label of the category, to obtain a third matching degree of the recommended song corresponding to any category.

[0216] The sorting module is configured to sort the recommended song corresponding to any category according to the third matching degree, to obtain a sorting result.

[0217] The recommending module is configured to recommend the recommended song corresponding to any category to the target object according to the sorting result.

[0218] In a possible implementation, the adjusting module is configured to, for any recommended song in the recommended songs corresponding to any category, multiply the second matching degree of the any recommended song by a first weight parameter to obtain the third matching degree of the any recommended song, if the song information of the any recommended song includes the category labels of any category; and multiply the second matching degree of the any recommended song by a second weight parameter to obtain the third matching degree of the any recommended song, if the song information of the any recommended song does not include the category labels of any category, the second weight parameter being less than the first weight parameter.

[0219] The above device divides the songs on which the target object has performed content interaction behaviors according to the time of the content interaction behaviors, to obtain at least two categories, and determines the recommended songs corresponding to each category, so that the songs recommended to the target object are more abundant and can better meet the listening needs of the target object, and thus the probability of the target object clicking the recommended songs is higher, thereby the click rate of the recommended songs can be improved, the listening time of the target object in the song application can be prolonged, and the user retention rate of the song application can be improved.

[0220] It should be understood that the above device provided in the embodiments only takes the above division of the functional modules as an example, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the above described functions. In addition, the device and method provided in the above embodiments belong to the same concept, and the specific implementation process is described in the method embodiments, which will not be repeated here.

[0221] Figure 7A structure block diagram of a terminal device 700 provided by an example embodiment of the present application is shown. The terminal device 700 can be any electronic device product that can interact with a user through one or more ways such as a keyboard, a touchpad, a remote controller, voice interaction, or a handwriting device. For example, a PC (Personal Computer), a mobile phone, a smart phone, a PDA (Personal Digital Assistant), a wearable device, a PPC (Pocket PC), a tablet computer, a smart car, a smart television, a smart speaker, a smart watch, etc.

[0222] Generally, the terminal device 700 includes a processor 701 and a memory 702.

[0223] The processor 701 can include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 701 can be implemented in at least one of a hardware form of a DSP (Digital Signal Processing), a FPGA (Field-Programmable Gate Array), a PLA (Programmable Logic Array). The processor 701 can also include a main processor and a coprocessor. The main processor is a processor for processing data in a wake-up state, also known as a CPU (Central Processing Unit). The coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 701 can be integrated with a GPU (Graphics Processing Unit) for rendering and drawing the content required to be displayed by the display screen. In some embodiments, the processor 701 can further include an AI (Artificial Intelligence) processor for processing machine learning related computing operations.

[0224] The memory 702 can include one or more computer-readable storage media, which can be non-transitory. The memory 702 can also include a high-speed random access memory, and a non-volatile memory such as one or more disk storage devices, flash storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 702 is used to store at least one instruction for being executed by the processor 701 to implement the method for determining a recommended song provided by the method embodiments of the present application.

[0225] In some embodiments, the terminal device 700 can further optionally include a peripheral device interface 703 and at least one peripheral device. The processor 701, the memory 702 and the peripheral device interface 703 can be connected through a bus or a signal line. Each peripheral device can be connected to the peripheral device interface 703 through a bus, a signal line or a circuit board. Specifically, the peripheral device includes at least one of a radio frequency circuit 704, a display screen 705, a camera component 706, an audio circuit 707 and a power supply 708.

[0226] The peripheral device interface 703 can be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 701 and the memory 702. In some embodiments, the processor 701, the memory 702 and the peripheral device interface 703 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 701, the memory 702 and the peripheral device interface 703 can be implemented on a separate chip or circuit board, and the present embodiments are not limited in this regard.

[0227] The radio frequency circuit 704 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 704 communicates with a communication network and other communication devices through electromagnetic signals. The radio frequency circuit 704 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals into electrical signals. Optionally, the radio frequency circuit 704 includes an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a subscriber identity module card, and the like. The radio frequency circuit 704 can communicate with other terminal devices through at least one wireless communication protocol. The wireless communication protocol includes but is not limited to the World Wide Web, a metropolitan area network, an intranet, various generations of mobile communication networks (2G, 3G, 4G and 5G), a wireless local area network and / or a WiFi (Wireless Fidelity) network. In some embodiments, the radio frequency circuit 704 can also include NFC (Near Field Communication) related circuitry, which is not limited in the present application.

[0228] The display screen 705 is configured to display a UI (User Interface). The UI can include graphics, text, icons, video, and any combination thereof. When the display screen 705 is a touch display screen, the display screen 705 is further configured to capture touch signals on or above the surface of the display screen 705. The touch signals can be input to the processor 701 as control signals for processing. In this case, the display screen 705 can also be configured to provide virtual buttons and / or virtual keyboard, also known as soft buttons and / or soft keyboard. In some embodiments, the display screen 705 can be one, disposed on the front panel of the terminal device 700; in other embodiments, the display screen 705 can be at least two, respectively disposed on different surfaces of the terminal device 700 or in a folding design; in other embodiments, the display screen 705 can be a flexible display screen, disposed on a curved surface or a folding surface of the terminal device 700. Even, the display screen 705 can also be disposed in an irregular shape, i.e., a special-shaped screen. The display screen 705 can be made of LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), etc.

[0229] The camera assembly 706 is configured to capture images or videos. Optionally, the camera assembly 706 includes a front camera and a rear camera. Typically, the front camera is disposed on the front panel of the terminal device 700, and the rear camera is disposed on the back of the terminal device 700. In some embodiments, the rear camera is at least two, which are any one of a main camera, a depth-of-field camera, a wide-angle camera, and a telephoto camera, to realize the background blur function by fusing the main camera and the depth-of-field camera, the panoramic shooting and VR (Virtual Reality) shooting function by fusing the main camera and the wide-angle camera, or other fusion shooting functions. In some embodiments, the camera assembly 706 can further include a flash. The flash can be a single-color-temperature flash or a dual-color-temperature flash. The dual-color-temperature flash refers to the combination of a warm light flash and a cold light flash, which can be used for light compensation under different color temperatures.

[0230] The audio circuit 707 can include a microphone and a speaker. The microphone is used to collect sound waves of a user and an environment, and convert the sound waves into an electrical signal input to the processor 701 for processing or to the radio frequency circuit 704 to realize voice communication. The microphone can be multiple for stereo sound collection or noise reduction purposes, and can be arranged at different parts of the terminal device 700. The microphone can also be an array microphone or an omnidirectional collection microphone. The speaker is used to convert an electrical signal from the processor 701 or the radio frequency circuit 704 into sound waves. The speaker can be a conventional diaphragm speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can not only convert an electrical signal into a sound wave audible to humans, but also convert an electrical signal into an inaudible sound wave to humans for ranging purposes. In some embodiments, the audio circuit 707 can also include a headphone jack.

[0231] The power supply 708 is used to supply power to each component in the terminal device 700. The power supply 708 can be alternating current, direct current, disposable battery or rechargeable battery. When the power supply 708 includes a rechargeable battery, the rechargeable battery can be a wired charging battery or a wireless charging battery. The wired charging battery is a battery charged through a wired line, and the wireless charging battery is a battery charged through a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0232] In some embodiments, the terminal device 700 further includes one or more sensors 709. The one or more sensors 709 include, but are not limited to, an acceleration sensor 710, a gyroscope sensor 711, a pressure sensor 712, an optical sensor 713, and a proximity sensor 714.

[0233] The acceleration sensor 710 can detect the acceleration in three coordinate axes of the coordinate system established by the terminal device 700. For example, the acceleration sensor 710 can be used to detect the components of gravitational acceleration in three coordinate axes. The processor 701 can control the display screen 705 to display a user interface in a landscape view or a portrait view according to the gravitational acceleration signal collected by the acceleration sensor 710. The acceleration sensor 710 can also be used for game or user motion data collection.

[0234] The gyroscope sensor 711 can detect the body direction and rotation angle of the terminal device 700, and the gyroscope sensor 711 can collect 3D actions of the user on the terminal device 700 in cooperation with the acceleration sensor 710. The processor 701 can realize the following functions according to the data collected by the gyroscope sensor 711: motion sensing (such as changing the UI according to the user's tilt operation), image stabilization when shooting, game control, and inertial navigation.

[0235] The pressure sensor 712 can be arranged at the side frame of the terminal device 700 and / or the lower layer of the display screen 705. When the pressure sensor 712 is arranged at the side frame of the terminal device 700, the holding signal of the user to the terminal device 700 can be detected, and the left-hand or right-hand recognition or shortcut operation can be performed by the processor 701 according to the holding signal collected by the pressure sensor 712. When the pressure sensor 712 is arranged at the lower layer of the display screen 705, the operability control on the UI interface can be controlled by the processor 701 according to the pressure operation of the user to the display screen 705. The operability control includes at least one of a button control, a scroll bar control, an icon control, and a menu control.

[0236] The optical sensor 713 is used to collect the ambient light intensity. In an embodiment, the processor 701 can control the display brightness of the display screen 705 according to the ambient light intensity collected by the optical sensor 713. Specifically, when the ambient light intensity is high, the display brightness of the display screen 705 is increased; when the ambient light intensity is low, the display brightness of the display screen 705 is decreased. In another embodiment, the processor 701 can also dynamically adjust the shooting parameters of the camera assembly 706 according to the ambient light intensity collected by the optical sensor 713.

[0237] The proximity sensor 714, also referred to as a distance sensor, is usually arranged at the front panel of the terminal device 700. The proximity sensor 714 is used to collect the distance between the user and the front of the terminal device 700. In an embodiment, when the proximity sensor 714 detects that the distance between the user and the front of the terminal device 700 gradually decreases, the display screen 705 is switched from the bright screen state to the off-screen state by the processor 701; when the proximity sensor 714 detects that the distance between the user and the front of the terminal device 700 gradually increases, the display screen 705 is switched from the off-screen state to the bright screen state by the processor 701.

[0238] Those skilled in the art can understand that the structures shown in the above embodiments are not a limitation on the terminal device 700, and the terminal device 700 can include more or fewer components than those shown in the figures, or combine certain components, or adopt different component arrangements. Figure 7

[0239] Figure 8 ​A structural diagram of a server provided in the embodiments of the present application is shown in FIG. 8. The server 800 can have great differences due to different configurations or performances, and can include one or more processors (Central Processing Units, CPUs) 801 and one or more memories 802. The one or more memories 802 store at least one piece of program code, which is loaded and executed by the one or more processors 801 to implement the method for determining recommended songs provided in any of the above embodiments. Of course, the server 800 can also have a wired or wireless network interface, a keyboard, an input and output interface, and other components for implementing device functions, and the like, so as to perform input and output. The server 800 can also include other components for implementing device functions, which are not described herein.

[0240] In exemplary embodiments, a computer-readable storage medium is also provided, which stores at least one piece of program code, which is loaded and executed by a processor to enable a computer device to implement any of the above methods for determining recommended songs.

[0241] Optionally, the computer-readable storage medium can be a Read-Only Memory (ROM), a Random Access Memory (RAM), a Compact Disc Read-Only Memory (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, or the like.

[0242] In exemplary embodiments, a computer program or computer program product is also provided, which stores at least one computer instruction, which is loaded and executed by a processor to enable a computer device to implement any of the above methods for determining recommended songs.

[0243] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data for analysis, stored data, displayed data, etc.), and signals involved in the present application are all authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data need to comply with relevant laws, regulations, and standards of relevant countries and regions. For example, the song information of the plurality of songs and the time corresponding to each song involved in the present application are obtained under full authorization.

[0244] It should be understood that the "multiple" mentioned herein refers to two or more than two. The "and / or" describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent: A exists alone, A and B exist together, and B exists alone. The character " / " generally represents that the associated objects before and after it are in an "or" relationship.

[0245] The above only describes exemplary embodiments of the present application and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for determining a recommended song, characterized in that: The method comprises: Obtain song information of multiple songs and the time corresponding to each song, wherein the multiple songs are songs for which the target object performs content interaction behaviors, and the time corresponding to any song is the time when the target object performs the content interaction behavior on the any song; Classifying the plurality of songs according to the time corresponding to each song to obtain at least two categories, where the time corresponding to the songs included in different categories is in different time periods; Determining category labels for the respective categories based on song information of the songs included in the respective categories, wherein the category label for any category is used to characterize the preference of the target subject for the time period corresponding to the respective category; According to the category labels of the respective categories and the song information of the plurality of songs, the recommended songs corresponding to the respective categories are determined.

2. The method according to claim 1, characterized in that The at least two categories include at least two of a first category, a second category, or a third category, wherein the time corresponding to the songs included in the first category is located in a first time period later than the time corresponding to the songs included in the second category, and the second time period is later than the time corresponding to the songs included in the third category, and the song information includes at least one of a singer name or a song genre; The step of determining the category labels of the respective categories based on the song information of the songs included in the respective categories includes: For any one of the first category and the second category, determining a category label for the any one of the categories based on at least one of the singer names of the songs included in the any one of the categories and the genres of the songs included in the any one of the categories, and song information of the plurality of songs; For the third category, the category label of the third category is determined based on at least one of the singer names of the songs included in the third category and the song genres of the songs included in the third category, as well as the weights of the songs included in the third category, and the weights corresponding to the songs included in the third category are proportional to the time corresponding to the songs included in the third category.

3. The method according to claim 2, characterized in that Determining the category label of any category according to at least one of the singer name of the songs included in any category and the song genre of the songs included in any category and the song information of the plurality of songs includes: Determine the name of the singer corresponding to any one of the categories according to the singer names of the songs included in any one of the categories; Determine the number of first songs in the plurality of songs whose singers' names are singers' names corresponding to any of the categories; Determining the song genre corresponding to any one of the categories according to the song genres of the songs included in any one of the categories; Determine a second number of songs in the plurality of songs whose song genres are those corresponding to any one of the categories; Determine at least one of the first singer name or the first song style as the category label of any one of the categories, the first singer name is the singer name whose corresponding number of first songs among the singer names corresponding to any one of the categories is greater than a first quantity threshold, and the first song style is the song style whose corresponding number of second songs among the song styles corresponding to any one of the categories is greater than a second quantity threshold.

4. The method according to claim 2, characterized in that Determining the category label of the third category based on at least one of the singer names of the songs included in the third category and the genres of the songs included in the third category and the weights of the songs included in the third category includes: Determining the weight of each singer name corresponding to the third category according to the singer names of the songs included in the third category and the weights of the songs included in the third category; Determining the weight of each song genre corresponding to the third category according to the song genres of the songs included in the third category and the weights of the songs included in the third category; Determine at least one of a second singer name or a second song style as a category label of the third category, the second singer name is a singer name whose weight is greater than a first weight threshold among all singer names corresponding to the third category, and the second song style is a song style whose weight is greater than a second weight threshold among all song styles corresponding to the third category.

5. The method according to any one of claims 1 to 4, characterized in that: The determining, based on the category labels of the respective categories and the song information of the plurality of songs, the recommended songs corresponding to the respective categories includes: For any category in the various categories, obtaining a plurality of first candidate songs according to the category label of the any category, wherein the song information of each first candidate song includes at least one category label of the any category; determining a second candidate song from the plurality of first candidate songs based on the song information of the plurality of songs and the song information of each first candidate song; According to the category label of any category and the song features of each second candidate song, a recommended song corresponding to any category is determined in the second candidate songs.

6. The method according to claim 5, characterized in that The determining of a second candidate song from the plurality of first candidate songs according to the song information of the plurality of songs and the song information of each first candidate song comprises: determining a first object feature according to song information of the plurality of songs, where the first object feature is used to represent preference information of the target object; Determining song features of each first candidate song based on the song information of each first candidate song, wherein the song features of any first candidate song are used to characterize the any first candidate song; Determining a first matching degree of each first candidate song based on the first object feature and the song features of each first candidate song, wherein the first matching degree of any first candidate song is used to indicate a probability that the target object will perform a content interaction behavior on the first candidate song; A first number of first candidate songs with the highest first matching degrees among the first candidate songs are used as the second candidate songs.

7. The method according to claim 5, characterized in that The determining, based on the category label of the any category and the song features of each second candidate song, a recommended song corresponding to the any category from the second candidate songs includes: determining a first song from the plurality of songs according to the category label of any one of the categories, wherein song information of the first song includes at least one category label of any one of the categories; determining a second object feature according to the song information of the first song, where the second object feature is used to represent the preference information of the target object; Determining a second matching degree of each second candidate song based on the second object feature and the song features of each second candidate song, wherein the second matching degree of any second candidate song is used to indicate a probability that the target object performs a content interaction behavior on any second candidate song; A second number of second candidate songs with the highest second matching degrees among the second candidate songs are used as recommended songs corresponding to any one of the categories, and the second number is smaller than the first number.

8. The method according to claim 7, characterized in that After determining the recommended song corresponding to the any category among the second candidate songs based on the category label of the any category and the song features of each second candidate song, the method further includes: Adjusting the second matching degree of the recommended songs corresponding to the any category according to the category label of the any category to obtain a third matching degree of the recommended songs corresponding to the any category; Sorting the recommended songs corresponding to any one of the categories according to the third matching degree to obtain a sorting result; Recommend songs corresponding to any category to the target object according to the sorting result.

9. The method according to claim 8, characterized in that The adjusting the second matching degree of the recommended songs corresponding to the any category according to the category label of the any category to obtain the third matching degree of the recommended songs corresponding to the any category includes: For any recommended song among the recommended songs corresponding to any category, when the song information of the recommended song includes each category label of the category, multiplying the second matching degree of the recommended song by the first weight parameter to obtain a third matching degree of the recommended song; In the case that the song information of any recommended song does not include the category labels of any category, the second matching degree of any recommended song is multiplied by the second weight parameter to obtain the third matching degree of any recommended song, and the second weight parameter is less than the first weight parameter.

10. A device for determining recommended songs, characterized in that: The device comprises: an acquisition module, configured to acquire song information of a plurality of songs and a time corresponding to each song, wherein the plurality of songs are songs for which a target object performs a content interaction behavior, and the time corresponding to any song is the time when the target object performs the content interaction behavior on the any song; a classification module, configured to classify the plurality of songs according to the time corresponding to each song, to obtain at least two categories, wherein the time corresponding to the songs included in different categories is in different time periods; a determination module, configured to determine a category label for each category based on song information of the songs included in each category, wherein the category label of any category is used to represent the preference of the target subject in the time period corresponding to the category; The determination module is further configured to determine the recommended songs corresponding to the respective categories based on the category labels of the respective categories and the song information of the plurality of songs.

11. A computer device, characterized in that: The computer device includes a processor and a memory, wherein at least one program code is stored in the memory, and the at least one program code is loaded and executed by the processor so that the computer device implements the method for determining recommended songs as described in any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that The computer-readable storage medium stores at least one program code, which is loaded and executed by a processor to enable the computer to implement the method for determining recommended songs as described in any one of claims 1 to 9.

13. A computer program product, characterized in that The computer program product stores at least one computer instruction, which is loaded and executed by a processor to enable the computer to implement the method for determining recommended songs as described in any one of claims 1 to 9.

Images