Music recommendation method, device, equipment and computer-readable storage medium

Abstract

The present disclosure relates to a music recommendation method, apparatus, device and computer-readable storage medium, which obtains first record information of music played by a first terminal of a first target user and second record information of music played by a second terminal of each reference user among one or more reference users, and determines one or more second target users whose first similarity with the first target user is greater than or equal to a preset value from the one or more reference users according to the first record information and the second record information. According to the first similarity, the trustworthiness of each second target user, and the one or more first music played by the first terminal and the second terminal corresponding to each second target user, the target music pushed to the first terminal is determined. In this way, more suitable music can be recommended to the target user in combination with the similarity between different users and the trustworthiness of the reference users, thereby improving the user experience.

Description

Technical Field

[0001] The present disclosure relates to the field of information technology, and in particular to a music recommendation method, device, equipment and computer-readable storage medium. Background Art

[0002] With the increasing popularity of smart home devices, people can enjoy many conveniences brought by smart technology. For example, smart speakers are a kind of smart device that is very popular among users.

[0003] Generally, users can control smart speakers through voice interaction. For example, they can control the smart speaker to turn on or off, or control the smart speaker to play music. In other words, the smart speaker can obtain the user's control instructions through voice interaction and play music according to the control instructions. If the user does not specify specific songs or music, the smart speaker can enable the recommendation system to automatically recommend music or songs to the user.

[0004] However, most recommendation systems recommend music or songs to users based on popular songs or music charts, which may result in the music or songs recommended by the recommendation system not being in line with the user's taste, resulting in a poor user experience. Summary of the invention

[0005] In order to solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides a music recommendation method, device, equipment and computer-readable storage medium to avoid the problem that the recommendation results do not meet the taste of the target user due to the unreliability of the reference user, thereby improving the user experience.

[0006] In a first aspect, an embodiment of the present disclosure provides a music recommendation method, comprising:

[0007] Acquire first record information of music played by a first terminal of a first target user and second record information of music played by a second terminal of each reference user among one or more reference users;

[0008] Determine one or more second target users from the one or more reference users according to the first record information and the second record information, wherein a first similarity between each of the one or more second target users and the first target user is greater than or equal to a preset value;

[0009] The target music to be pushed to the first terminal is determined based on the first similarity between each second target user and the first target user, the trustworthiness of each second target user, and one or more first music played together by the first terminal and the second terminal corresponding to each second target user.

[0010] Optionally, the method further includes:

[0011] Calculating, according to the first record information, the trust degree of the first target user in each of the plurality of applications;

[0012] Determining a target application from the multiple applications according to the trust of the first target user in each of the applications, the target application having the highest trust by the first target user;

[0013] The trustworthiness of each second target user is calculated according to the target application and the second record information.

[0014] Optionally, the first record information includes a total duration during which the first terminal uses any of the multiple applications within a historical period, and a total number of times the first terminal starts any of the multiple applications within the historical period.

[0015] Optionally, calculating, according to the first record information, the trust of the first target user in each of the multiple applications includes:

[0016] The trust of the first target user in any of the multiple applications is calculated according to the total duration of use of any of the multiple applications by the first terminal in a historical period and the total number of times the first terminal starts the any of the applications in the historical period.

[0017] Optionally, the second record information includes the total number of times the second terminal plays music through the target application within the historical time, and the number of times each of the one or more second music played by the second terminal through the target application within the historical time is played.

[0018] Optionally, calculating the trustworthiness of each second target user according to the target application and the second record information includes:

[0019] Determining, according to the number of times each second music is played in the one or more second music, the second music whose number of times of playing meets a preset condition in the one or more second music;

[0020] The trustworthiness of each second target user is calculated according to the total number of times the second terminal plays music through the target application within the historical time and the number of times the second music that meets the preset condition is played.

[0021] Optionally, the trustworthiness of each second target user is the trustworthiness of each second target user on the target application.

[0022] Optionally, determining the target music to be pushed to the first terminal according to the first similarity between each second target user and the first target user, the trustworthiness of each second target user, and one or more first music played together by the first terminal and the second terminal corresponding to each second target user, includes:

[0023] Calculate, according to the first similarity between each second target user and the first target user, and the trustworthiness of each second target user, a predicted value of each of the one or more first music played together by the first terminal and the second terminal corresponding to each second target user;

[0024] According to the predicted value of each first music, the target music to be pushed to the first terminal is determined.

[0025] Optionally, determining the target music to be pushed to the first terminal according to the first similarity between each second target user and the first target user, the trustworthiness of each second target user, and one or more first music played together by the first terminal and the second terminal corresponding to each second target user, includes:

[0026] Determine the target music to be pushed to the first terminal according to the first similarity between each second target user and the first target user, the trustworthiness of each second target user, the second similarity between each second target user and the first target user, and one or more first music played together by the first terminal and the second terminal corresponding to each second target user;

[0027] The first similarity is used to indicate the similarity between the first terminal and the second terminal in playing music, and the second similarity is used to indicate the similarity between the attributes of the second target user and the first target user.

[0028] Optionally, the method further includes:

[0029] According to the first attribute of the first target user and the second attribute corresponding to each of the second target users, a second similarity between each of the second target users and the first target user is calculated.

[0030] In a second aspect, an embodiment of the present disclosure provides a music recommendation device, including:

[0031] An acquisition module, used to acquire first record information of a first terminal of a first target user playing music, and second record information of a second terminal of each reference user of one or more reference users playing music;

[0032] A determination module is used to determine one or more second target users from the one or more reference users based on the first record information and the second record information, wherein the first similarity between each of the one or more second target users and the first target user is greater than or equal to a preset value; and determine the target music to be pushed to the first terminal based on the first similarity between each second target user and the first target user, the trustworthiness of each second target user, and one or more first music played together by the first terminal and the second terminal corresponding to each second target user.

[0033] Optionally, the device further comprises:

[0034] a calculation module, configured to calculate the trust of the first target user in each of the plurality of applications according to the first record information;

[0035] The determination module is further used to: determine a target application from the multiple applications according to the first target user's trust in each application, the target application having the highest trust in the first target user;

[0036] The calculation module is further used to calculate the trustworthiness of each second target user according to the target application and the second record information.

[0037] Optionally, the first record information includes a total duration during which the first terminal uses any of the multiple applications within a historical period, and a total number of times the first terminal starts any of the multiple applications within the historical period.

[0038] Optionally, the calculation module is specifically used for:

[0039] The trust of the first target user in any of the multiple applications is calculated according to the total duration of use of any of the multiple applications by the first terminal in a historical period and the total number of times the first terminal starts the any of the applications in the historical period.

[0040] Optionally, the second record information includes the total number of times the second terminal plays music through the target application within the historical time, and the number of times each of the one or more second music played by the second terminal through the target application within the historical time is played.

[0041] Optionally, the determination module is specifically used to: determine the second music whose number of plays meets a preset condition among the one or more second music according to the number of plays of each second music among the one or more second music;

[0042] The calculation module is specifically used to calculate the trustworthiness of each second target user according to the total number of times the second terminal plays music through the target application within the historical time and the number of times the second music that meets the preset conditions is played.

[0043] Optionally, the trustworthiness of each second target user is the trustworthiness of each second target user on the target application.

[0044] Optionally, the device further comprises:

[0045] a calculation module, configured to calculate, based on the first similarity between each second target user and the first target user and the trustworthiness of each second target user, a predicted value of each of the one or more first music played together by the first terminal and the second terminal corresponding to each second target user;

[0046] The determination module is specifically used to determine the target music to be pushed to the first terminal according to the predicted value of each first music.

[0047] Optionally, the determining module is specifically used to:

[0048] Determine the target music to be pushed to the first terminal according to the first similarity between each second target user and the first target user, the trustworthiness of each second target user, the second similarity between each second target user and the first target user, and one or more first music played together by the first terminal and the second terminal corresponding to each second target user;

[0049] The first similarity is used to indicate the similarity between the first terminal and the second terminal in playing music, and the second similarity is used to indicate the similarity between the attributes of the second target user and the first target user.

[0050] Optionally, the device further comprises:

[0051] The calculation module is used to calculate the second similarity between each second target user and the first target user according to the first attribute of the first target user and the second attribute corresponding to each second target user.

[0052] In a third aspect, an embodiment of the present disclosure provides a music recommendation device, including:

[0053] Memory;

[0054] Processor; and

[0055] Computer programs;

[0056] The computer program is stored in the memory and is configured to be executed by the processor to implement the method as described in the first aspect.

[0057] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the method described in the first aspect.

[0058] The music recommendation method, apparatus, device and computer-readable storage medium provided by the embodiments of the present disclosure obtain the first record information of the first terminal of the first target user playing the music, and the second record information of the second terminal of each reference user among one or more reference users playing the music, and determine one or more second target users whose first similarity with the first target user is greater than or equal to a preset value from the one or more reference users according to the first record information and the second record information. Further, according to the first similarity, the trustworthiness of each second target user, and the one or more first music played by the first terminal and the second terminal corresponding to each second target user, the target music pushed to the first terminal is determined. In this way, more suitable music can be recommended to the target user by combining the similarity between different users and the trustworthiness of the reference users, and at the same time, the problem that the recommendation results do not meet the taste of the target user due to the unreliability of the reference users can be avoided, thereby improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0060] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0061] Figure 1 A flowchart of a music recommendation method provided by an embodiment of the present disclosure;

[0062] Figure 2 A schematic diagram of an application scenario provided by an embodiment of the present disclosure;

[0063] Figure 3A schematic diagram of an application scenario provided by another embodiment of the present disclosure;

[0064] Figure 4 A schematic diagram of an application scenario provided by another embodiment of the present disclosure;

[0065] Figure 5 A flowchart of a music recommendation method provided by another embodiment of the present disclosure;

[0066] Figure 6 A flowchart of a music recommendation method provided by another embodiment of the present disclosure;

[0067] Figure 7 A schematic diagram of the structure of a music recommendation device provided by an embodiment of the present disclosure;

[0068] Figure 8 A schematic diagram of the structure of a music recommendation device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0069] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0070] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0071] Normally, users can control smart speakers through voice interaction. For example, control the smart speaker to turn on or off, or control the smart speaker to play music. In other words, the smart speaker can obtain the user's control instructions through voice interaction and play music according to the control instructions. If the user does not specify specific songs or music, the smart speaker can enable the recommendation system to automatically recommend music or songs to the user. However, most recommendation systems recommend music or songs to users based on popular songs or music charts, which may result in the music or songs recommended by the recommendation system not being in line with the user's taste, resulting in a low user experience. To address this issue, the embodiments of the present disclosure provide a music recommendation method, which is described below in conjunction with specific embodiments.

[0072] Figure 1 The flowchart of the music recommendation method provided by the embodiment of the present disclosure is as follows. Figure 2The application scenario shown, for example, includes a server 20 and a terminal, and the terminal includes a smart speaker 21, a smart phone 22, and a smart phone 23. It is understandable that the terminal is not limited to a smart speaker and a smart phone, for example, it can also include a PDA, a tablet computer, a wearable device with a display screen, a desktop computer, a laptop computer, an all-in-one machine, a smart home device, etc. In addition, the smart speaker 21, the smart phone 22, and the smart phone 23 can be terminals of different users. Among them, the server 20 can be a cloud server or a server cluster. Specifically, the server 20 can execute the music recommendation method described in the embodiment of the present disclosure. Alternatively, the terminal can execute the music recommendation method described in the embodiment of the present disclosure. The following is a schematic illustration taking the server 20 executing the music recommendation method as an example.

[0073] like Figure 1 As shown, the specific steps of this method are as follows:

[0074] S101, obtaining first record information of a first terminal of a first target user playing music, and second record information of a second terminal of each reference user among one or more reference users playing music.

[0075] For example Figure 2 Each of the smart speakers 21, smart phones 22 and smart phones 23 shown in the figure may be installed with one or more music applications (Application, APP). Figure 3 As shown, the smart speaker 21 and the smart phone 24 can be connected in communication, and one or more music apps are installed in the smart phone 24. The smart phone 24 can control the smart speaker 21 to play music through the music apps.

[0076] For example, smart speaker 21 and smart phone 24 are terminals of user A, smart phone 22 is a terminal of user B, and smart phone 23 is a terminal of user C. It is understandable that server 20 is not limited to communicating with terminals of user A, user B, and user C. For example, server 20 can also communicate with terminals of other users. Here, user A, user B, and user C are used as examples for schematic illustration. In addition, the embodiments of the present disclosure do not limit the number of terminals that server 20 can communicate with.

[0077] In the case where user A does not specify the smart speaker 21 to play specific music, the server 20 can use the method described in this embodiment to recommend music or songs to user A. In this case, user A can be recorded as the first target user. User B and user C are recorded as reference users. It can be understood that the number of reference users may not be specifically limited, for example, it can be one or more, and two reference users are used as an example for schematic illustration. Accordingly, the smart speaker 21 and the smart phone 24 can be recorded as the first terminal. Smartphone 22 and smart phone 23 can be recorded as the second terminal.

[0078] In a possible implementation, the server 20 may be a server corresponding to the music APP installed in the smart speaker 21, the smart phone 22, the smart phone 23, and the smart phone 24. In this case, the server 20 may record the record information of the music played by each terminal in the smart speaker 21, the smart phone 22, the smart phone 23, and the smart phone 24. The record information may specifically be the number of times the music APP is used, the identification information of the music played in the past, the number of times the music is played in the past, and the like. Here, the record information of the music played by the first terminal, such as the smart speaker 21 and the smart phone 24, may be recorded as the first record information, and the record information of the music played by the second terminal, such as the smart phone 22 and the smart phone 23, may be recorded as the second record information.

[0079] In another possible implementation, the music apps installed in the smart speaker 21, the smart phone 22, the smart phone 23, and the smart phone 24 may be different, and different music apps may correspond to different servers. Figure 4 As shown, the music APP installed in the smart speaker 21 corresponds to the server 41, the music APP installed in the smart phone 22 corresponds to the server 42, and the music APP installed in the smart phone 23 corresponds to the server 43. In this case, the server 41 can record the first record information as described above, and the server 42 and the server 43 can respectively record the second record information as described above. Further, the server 20 can obtain the first record information from the server 41, and obtain the second record information from the server 42 and the server 43.

[0080] S102: Determine one or more second target users from the one or more reference users according to the first record information and the second record information, wherein a first similarity between each of the one or more second target users and the first target user is greater than or equal to a preset value.

[0081] For example, when the server 20 obtains the first record information and the second record information, it can determine one or more second target users from reference users such as user B and user C according to the first record information and the second record information. The similarity between each second target user and the first target user such as user A is greater than or equal to a preset value. The similarity can be the similarity between the reference user and user A in listening to music, and the similarity can be recorded as the first similarity.

[0082] S103, determining target music to be pushed to the first terminal based on the first similarity between each second target user and the first target user, the trustworthiness of each second target user, and one or more first music played together by the first terminal and the second terminal corresponding to each second target user.

[0083] For example, when a second target user, such as user B, is determined from user B and user C, the target music to be pushed to the smart speaker 21 can be determined from one or more first music played jointly by the smart speaker 21 and the smart phone 22 based on the first similarity between user B and user A and the trustworthiness of user B.

[0084] For another example, when multiple second target users such as user B and user C are determined from user B and user C, one or more first music played together by the smart speaker 21 and the smart phone 22 can be scored and sorted according to the first similarity between user B and user A and the trustworthiness of user B to obtain a first sorting result. In addition, one or more first music played together by the smart speaker 21 and the smart phone 23 can be scored and sorted according to the first similarity between user C and user A and the trustworthiness of user C to obtain a second sorting result. Further, according to the first sorting result and the second sorting result, the target music pushed to the smart speaker 21 is determined.

[0085] It is understandable that the first record information and the second record information may be stored in a matrix form, for example, the matrix may include identification information of each played music, the number of times each played music is played by each of one or more different users, the total number of times each played music is played by all users, etc. The greater the number of times it is played, the more popular the music is.

[0086] The disclosed embodiment obtains the first record information of the first terminal of the first target user playing music, and the second record information of the second terminal of each reference user among one or more reference users playing music, and determines one or more second target users whose first similarity with the first target user is greater than or equal to a preset value from the one or more reference users according to the first record information and the second record information. Further, according to the first similarity, the trustworthiness of each second target user, and the one or more first music played by the first terminal and the second terminal corresponding to each second target user, the target music pushed to the first terminal is determined. In this way, more suitable music can be recommended to the target user by combining the similarity between different users and the trustworthiness of the reference users, and at the same time, the problem that the recommendation results do not meet the taste of the target user due to the unreliability of the reference users can be avoided, thereby improving the user experience.

[0087] Based on the above embodiment, the method further includes: Figure 5 The following steps are shown:

[0088] S501. Calculate the first target user's trust in each of a plurality of applications according to the first record information.

[0089] For example, multiple music apps may be installed in the first terminal of user A, such as the smart speaker 21 and the smart phone 24, or user A may evaluate the apps he has installed in the application installation mall. Further, the server 20 may calculate the trust of user A in each of the multiple music apps installed in the smart speaker 21 and the smart phone 24 based on the first record information as described above. Alternatively, the server 20 may calculate the trust of user A in each of all the apps he has evaluated based on the first record information as described above.

[0090] Optionally, the first record information includes a total duration during which the first terminal uses any of the multiple applications within a historical period, and a total number of times the first terminal starts any of the multiple applications within the historical period.

[0091] For example, the first record information may include the total duration of use of each music APP by the smart phone 24 or the smart speaker 21 in the historical time, and the total number of times each music APP is started in the historical time. Since some users may prefer a certain music APP, in view of this phenomenon, this embodiment can calculate the trust of user A in each music APP based on the frequency of use of each music APP by user A, that is, the total duration of use of each music APP in the historical time, and the total number of times each music APP is started in the historical time.

[0092] Optionally, based on the first recorded information, the trust of the first target user in each of the multiple applications is calculated, including: calculating the trust of the first target user in any of the multiple applications based on the total time that the first terminal uses any of the multiple applications within a historical period, and the total number of times the first terminal starts any of the applications within the historical period.

[0093] For example, the total time that a smartphone 24 or smart speaker 21 uses a music app in the past six months is recorded as T a , which is the total time that user A has used a music app in the past six months. The total number of times a music app is started by the smartphone 24 or smart speaker 21 in the past six months is recorded as F a , which is the total number of times user A has used a music app in the past six months. User A's trust in the music app can be recorded as AppTrust(a), which can be calculated using the following formula (1):

[0094]

[0095] It is understandable that user A's trust in other music apps can also be calculated using the above formula (1), which will not be described in detail here. For a certain music app, T a and F a The larger the ratio is, the higher the trust of user A in the music APP is, and the higher the acceptance of user A is. a and F a The smaller the ratio, the lower the trust of user A in the music APP, and the lower the acceptance of user A to the music APP. In addition, it can be explained that when user A uses the music APP, he may not use it for listening to songs, but for other purposes, such as searching for songs, and it is not a frequently used APP.

[0096] S502: Determine a target application from the multiple applications according to the trust of the first target user in each of the applications, the first target user having the highest trust in the target application.

[0097] For example, according to formula (1), the trust of each music app among all the music apps evaluated by user A can be calculated. Furthermore, the trust of each music app can be ranked to obtain the music app with the highest trust. The music app with the highest trust can be recorded as the target application.

[0098] S503: Calculate the trustworthiness of each second target user according to the target application and the second record information.

[0099] For example, the server 20 may calculate the trustworthiness of each second target user according to the target application and the second record information.

[0100] Optionally, the second record information includes the total number of times the second terminal plays music through the target application within the historical time, and the number of times each of the one or more second music played by the second terminal through the target application within the historical time is played.

[0101] For example, the second target user includes user B, and the second record information corresponding to user B may include the total number of times the smartphone 22 plays music through the target application within the historical time, and the number of times each of the one or more second music played by the smartphone 22 through the target application within the historical time is played.

[0102] Optionally, the trustworthiness of each second target user is calculated based on the target application and the second recorded information, including: determining the second music whose number of plays meets a preset condition among the one or more second music based on the number of plays of each second music among the one or more second music; and calculating the trustworthiness of each second target user based on the total number of times the second terminal plays music through the target application within the historical time and the number of plays of the second music that meets the preset condition.

[0103] For example, the total number of times the smartphone 22 plays music through the target application in the past six months is recorded as C b , that is, the total number of times user B has used the target application to listen to songs in the past six months. Smartphone 22 has played multiple second music through the target application in the past six months. Further, according to the number of times each second music played by the smart phone 22 through the target application in the past six months, the second music that meets the preset conditions in the multiple second music is determined. Among them, the second music that meets the preset conditions in the multiple second music can be the two second music with the highest number of plays in the multiple second music. The number of plays of these two second music may be the same or different. Further, the sum of the number of plays of these two second music can be recorded as C b (1-2), that is, the total number of times user B listened to the two songs with the highest number of times through the target application in the past six months. b and C b(1-2) can calculate the trustworthiness of user B, which can be recorded as CTrust(b). CTrust(b) can be calculated by the following formula (2):

[0104]

[0105] The larger the value of CTrust(b), the more evenly user B listens to multiple second music, the less likely user B is to engage in malicious order-swiping, and the more trustworthy user B is. On the contrary, the greater the value of CTrust(b), the more likely user B is to engage in malicious order-swiping, and the less trustworthy user B is.

[0106] Optionally, the trustworthiness of each second target user is the trustworthiness of each second target user on the target application.

[0107] For example, the trustworthiness of user B calculated by formula (2) may be the trustworthiness of user B on the target application. In addition, when the second target user includes user C, the trustworthiness of user C, i.e., the trustworthiness of user C on the target application, may also be calculated according to the principle of formula (2).

[0108] The disclosed embodiment calculates the trust of the first target user in each of the multiple applications through the first record information, and determines the target application with the highest trust from the multiple applications based on the trust of the first target user in each application. Further, the target music pushed to the first terminal is determined based on the first similarity between each second target user and the first target user, the trust of each second target user on the target application, and one or more first music played by the first terminal and the second terminal corresponding to each second target user. The target music can be the music played by the second target user with the highest trust through the target application that the first target user trusts the most. Therefore, when the first target user tends to use the target application, the trust of the second target user on the target application can be considered, avoiding the problem of inaccurate recommendation results caused by not referring to the trust of the second target user on the target application when calculating the first similarity between the first target user and the second target user.

[0109] On the basis of the above embodiment, according to the first similarity between each second target user and the first target user, the trustworthiness of each second target user, and one or more first music played together by the first terminal and the second terminal corresponding to each second target user, the target music pushed to the first terminal is determined, including: Figure 6 The following steps are shown:

[0110] S601. Calculate, based on the first similarity between each second target user and the first target user, and the trustworthiness of each second target user, a predicted value of each of the one or more first music played together by the first terminal and the second terminal corresponding to each second target user.

[0111] For example, based on the first similarity between user B and user A and the trustworthiness of user B, the trustworthiness of the combined user can be calculated. The trustworthiness of the combined user can be recorded as ZTrust(a,b). ZTrust(a,b) can be calculated by the following formula (3):

[0112] ZTrust(a,b)=sim(a,b)CTrust(b)(3)

[0113] Wherein, sim(a,b) represents the first similarity between user B and user A. sim(a,b) can be calculated by the Pearson correlation system method described in the following formula (4):

[0114]

[0115] Among them, I a,b represents one or more first music played by the first terminal and the second terminal, that is, music listened to by user A and user B, i represents I a,b The i-th music in R. a,i represents the number of times the smart phone 24 or smart speaker 21 plays music i, that is, the number of times user A listens to music i, R b,i It indicates the number of times the smartphone 22 plays the music i, that is, the number of times the user B listens to the music i. It represents the total number of times all music played by the smart phone 24 or smart speaker 21 through a music app within a historical period, for example, within a week, that is, the total number of times all music listened to by user A within a week is played. It represents the total number of times all music played by the smart phone 22 through the music APP in the historical time, for example, within a week, that is, the total number of times all music listened to by user B within a week.

[0116] It can be understood that the first similarity sim(a,c) between user C and user A can also be calculated according to formula (4). Similarly, the trustworthiness CTrust(c) of user C can also be calculated according to formula (2). The trustworthiness of the combined user ZTrust(a,c)=sim(a,c)CTrust(c) can also be calculated according to formula (3).

[0117] When sim(a, b) and sim(a, c) are both greater than or equal to a preset value, user B and user C may be regarded as the nearest neighbors of user A, that is, the neighbor set most similar to user A.

[0118] According to ZTrust(a,b)=sim(a,b)CTrust(b), the prediction value of each of the one or more first music played by the smart speaker 21 and the smart phone 22 can be calculated. For example, b∈UNN(a) means that the song played by user B is a song played by user A and user B. j means the jth song played by user A and user B. The prediction value of the jth song can be recorded as P a,j , P a,j It is calculated by the following formula (5):

[0119]

[0120] in, The meaning of is as described above and will not be repeated here. b,j It indicates the number of times the smart phone 22 plays the j-th song, that is, the number of times user B listens to the j-th song. a,j represents the number of times the smart phone 24 or smart speaker 21 plays the j-th song, that is, the number of times user A listens to the j-th song. a,j In some embodiments, it can be expressed as the predicted value of the j-th song corresponding to user A. a,j It can represent the degree of liking of user A for the j-th song predicted by the recommendation system.

[0121] Similarly, according to ZTrust(a,c)=sim(a,c)CTrust(c), the predicted value of each of the one or more first music played together by the smart speaker 21 and the smart phone 23 can be calculated.

[0122] S602: Determine the target music to be pushed to the first terminal according to the predicted value of each first music.

[0123] For example, one or more first music played together by the smart speaker 21 and the smart phone 22 can be sorted according to the predicted value of each of the one or more first music played together by the smart speaker 21 and the smart phone 22, for example, sorted in descending order of the predicted value. In addition, one or more first music played together by the smart speaker 21 and the smart phone 23 can also be sorted according to the predicted value of each of the one or more first music played together by the smart speaker 21 and the smart phone 23. Furthermore, the first music with the highest predicted value in the previous two sortings can be used as the target music pushed to the smart speaker 21.

[0124] The disclosed embodiment calculates the predicted value of each of the one or more first music played by the first terminal and the second terminal corresponding to each second target user through the first similarity between each second target user and the first target user, and the trustworthiness of each second target user, and determines the target music pushed to the first terminal according to the predicted value of each first music. Thus, the trust of the user in different APPs can be calculated according to the frequency of listening to songs in different APPs, so that songs that are more in line with the user's taste can be recommended to the first target user.

[0125] On the basis of the above embodiment, the target music to be pushed to the first terminal is determined according to the first similarity between each second target user and the first target user, the trustworthiness of each second target user, and one or more first music that the first terminal has played together with the second terminal corresponding to each second target user, including: determining the target music to be pushed to the first terminal according to the first similarity between each second target user and the first target user, the trustworthiness of each second target user, the second similarity between each second target user and the first target user, and one or more first music that the first terminal has played together with the second terminal corresponding to each second target user; wherein the first similarity is used to represent the similarity between the music played by the first terminal and the second terminal, and the second similarity is used to represent the attribute similarity between the second target user and the first target user.

[0126] In some scenarios, the attributes of different users have certain similarities. Therefore, the second similarity between the second target user and the first target user can be calculated based on the attributes of the second target user and the attributes of the first target user. The second similarity is used to indicate the attribute similarity between the second target user and the first target user. The first similarity is used to indicate the similarity between the first terminal of the first target user and the second terminal of the second target user in playing music.

[0127] Optionally, the method further includes: calculating a second similarity between each second target user and the first target user according to the first attribute of the first target user and a second attribute corresponding to each second target user.

[0128] For example, the first attribute of user A includes the gender, age, and duration of each listening to music of user A. The second attribute of user B includes the gender, age, and duration of each listening to music of user B. It is understandable that the first attribute of user A and the second attribute of user B are not limited to gender, age, and duration of each listening to music, and may also include other information.

[0129] Specifically, the second similarity between user A and user B may be calculated according to the first attribute of user A and the second attribute of user B.

[0130] For example, user A's gender is denoted by S a , user B’s gender is denoted as S b , the gender similarity between user A and user B can be recorded as S(a,b), which can be calculated by the following formula (6):

[0131]

[0132] For example, user A's age is recorded as A a , user B’s age is recorded as A b , the age similarity between user A and user B can be recorded as A(a,b), which can be calculated by the following formula (7):

[0133]

[0134] For example, the duration of each song listened by user A is recorded as M a , the duration of user B listening to the song each time is recorded as M b , the similarity of the listening time of user A and user B can be recorded as M(a,b), which can be calculated by the following formula (8):

[0135]

[0136] Furthermore, according to formulas (6), (7) and (8), the second similarity between user A and user B can be calculated. The second similarity can be recorded as STrust(a, b). STrust(a, b) can be calculated by the following formula (9):

[0137] STrust(a,b)=0.3×S(a,b)+0.3×A(a,b)+0.4×M(a,b)(9)

[0138] Furthermore, based on the first similarity sim(a,b) between user A and user B, the trustworthiness CTrust(b) of user B, and the second similarity STrust(a,b) between user A and user B, the predicted value of each of the one or more first music played together by the smart speaker 21 and the smart phone 22 is calculated.

[0139] Specifically, the final trust can be calculated based on sim(a,b), CTrust(b), and STrust(a,b). The final trust can be recorded as OutputTrust(a,b). OutputTrust(a,b) can be calculated by the following formula (10):

[0140] OutputTrust(a,b)=μ×ZTrust(a,b)+(1-μ)×STrust(a,b)(10)

[0141] Among them, ZTrust(a,b)=sim(a,b)CTrust(b). μ represents the weighting factor, which is used to measure the weight between ZTrust(a,b) and STrust(a,b). μ can be adjusted according to the actual situation. For example, the initial value of μ can be 0.5.

[0142] In this embodiment, when calculating the predicted value of each of the one or more first music played by the smart speaker 21 and the smart phone 22, ZTrust(a, b) in formula (5) can be replaced by OutputTrust(a, b) to obtain the following formula (11):

[0143]

[0144] Specifically, according to formula (11), the predicted value of each of the one or more first music played together by the smart speaker 21 and the smart phone 22 can be calculated, and the predicted value of each of the one or more first music played together by the smart speaker 21 and the smart phone 22 can be sorted in descending order to obtain a first sorting result.

[0145] It can be understood that according to the principle of formula (11), the predicted value of each of the one or more first music played together by the smart speaker 21 and the smart phone 23 can also be calculated, and the predicted value of each of the one or more first music played together by the smart speaker 21 and the smart phone 23 can be sorted in order from large to small to obtain a second sorting result.

[0146] Furthermore, the first music with the highest prediction value in the first sorting result and the second sorting result can be used as the target music to be pushed to the smart speaker 21.

[0147] By calculating the trustworthiness of the second target user, the disclosed embodiment can make the predicted value of the music or songs that the second target user and the first target user have listened to together lower when the trustworthiness of the second target user is low, and the possibility of the music or song being recommended as the target music to the first target user is lower. Thereby, the problem that the target music recommended to the first target user by the second target user is inaccurate or does not conform to the taste of the first target user due to malicious order brushing by the second target user can be avoided. In addition, by calculating the attribute similarity between the second target user and the first target user, and determining the target music to be pushed to the first target user based on the similarity between the second target user and the first target user in listening to songs, the trustworthiness of the second target user, and the attribute similarity between the second target user and the first target user, the accuracy of the target music can be further improved to meet the taste requirements of the first target user, and the user experience can be further improved.

[0148] Figure 7 Schematic diagram of the structure of the music recommendation device provided in the embodiment of the present disclosure. The music recommendation device may be the server 20 or the terminal as described above, or the music recommendation device may be a component in the server 20 or the terminal as described above. The music recommendation device provided in the embodiment of the present disclosure may execute the processing flow provided in the music recommendation method embodiment, such as Figure 7 As shown, the music recommendation device 70 includes:

[0149] An acquisition module 71 is used to acquire first record information of a first terminal of a first target user playing music, and second record information of a second terminal of each reference user of one or more reference users playing music;

[0150] The determination module 72 is used to determine one or more second target users from the one or more reference users based on the first record information and the second record information, and each of the one or more second target users has a first similarity greater than or equal to a preset value with the first target user; and determine the target music to be pushed to the first terminal based on the first similarity between each second target user and the first target user, the trustworthiness of each second target user, and one or more first music played together by the first terminal and the second terminal corresponding to each second target user.

[0151] Optionally, the device 70 further includes: a calculation module 73, configured to calculate the trust of the first target user in each of the multiple applications according to the first record information;

[0152] The determination module 72 is further used to: determine a target application from the multiple applications according to the first target user's trust in each application, the target application having the highest trust in the first target user;

[0153] The calculation module 73 is further used to calculate the trustworthiness of each second target user according to the target application and the second record information.

[0154] Optionally, the first record information includes a total duration during which the first terminal uses any of the multiple applications within a historical period, and a total number of times the first terminal starts any of the multiple applications within the historical period.

[0155] Optionally, the calculation module 73 is specifically used to calculate the trust of the first target user in any of the multiple applications based on the total time that the first terminal uses any of the multiple applications within the historical time, and the total number of times the first terminal starts any of the applications within the historical time.

[0156] Optionally, the second record information includes the total number of times the second terminal plays music through the target application within the historical time, and the number of times each of the one or more second music played by the second terminal through the target application within the historical time is played.

[0157] Optionally, the determining module 72 is specifically used to: determine the second music whose number of plays meets a preset condition among the one or more second music according to the number of plays of each second music among the one or more second music;

[0158] The calculation module 73 is specifically used to calculate the trustworthiness of each second target user according to the total number of times the second terminal plays music through the target application within the historical time and the number of times the second music that meets the preset conditions is played.

[0159] Optionally, the trustworthiness of each second target user is the trustworthiness of each second target user on the target application.

[0160] Optionally, the device 70 further includes: a calculation module 73, configured to calculate, based on the first similarity between each second target user and the first target user, and the trustworthiness of each second target user, a predicted value of each of the one or more first music played together by the first terminal and the second terminal corresponding to each second target user;

[0161] The determination module 72 is specifically used to determine the target music to be pushed to the first terminal according to the predicted value of each first music.

[0162] Optionally, the determining module 72 is specifically configured to:

[0163] Determine the target music to be pushed to the first terminal according to the first similarity between each second target user and the first target user, the trustworthiness of each second target user, the second similarity between each second target user and the first target user, and one or more first music played together by the first terminal and the second terminal corresponding to each second target user;

[0164] The first similarity is used to indicate the similarity between the first terminal and the second terminal in playing music, and the second similarity is used to indicate the similarity between the attributes of the second target user and the first target user.

[0165] Optionally, the device 70 further includes: a calculation module 73, configured to calculate a second similarity between each second target user and the first target user according to the first attribute of the first target user and the second attribute corresponding to each second target user.

[0166] Figure 7 The music recommendation device of the illustrated embodiment can be used to implement the technical solution of the above method embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.

[0167] Figure 8 Schematic diagram of the structure of the music recommendation device provided in the embodiment of the present disclosure. The music recommendation device may be the server 20 or the terminal as described above. The music recommendation device provided in the embodiment of the present disclosure may execute the processing flow provided in the music recommendation method embodiment, such as Figure 8 As shown, the music recommendation device 80 includes: a memory 81, a processor 82, a computer program and a communication interface 83; wherein the computer program is stored in the memory 81 and is configured so that the processor 82 executes the music recommendation method as described above.

[0168] In addition, an embodiment of the present disclosure further provides a computer-readable storage medium on which a computer program is stored. The computer program is executed by a processor to implement the music recommendation method described in the above embodiment.

[0169] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0170] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A music recommendation method, characterized in that: The method comprises: Acquire first record information of music played by a first terminal of a first target user and second record information of music played by a second terminal of each reference user among one or more reference users; Determine one or more second target users from the one or more reference users according to the first record information and the second record information, wherein a first similarity between each of the one or more second target users and the first target user is greater than or equal to a preset value; Determine the target music to be pushed to the first terminal according to the first similarity between each second target user and the first target user, the trustworthiness of each second target user, and one or more first music played together by the first terminal and the second terminal corresponding to each second target user; The method further comprises: Calculating, according to the first record information, the trust degree of the first target user in each of the plurality of applications; Determining a target application from the multiple applications according to the trust of the first target user in each of the applications, the target application having the highest trust by the first target user; The trustworthiness of each second target user is calculated according to the target application and the second record information.

2. The method according to claim 1, characterized in that Calculating the trust of the first target user in each of the plurality of applications according to the first record information includes: The trust of the first target user in any of the multiple applications is calculated according to the total duration of use of any of the multiple applications by the first terminal in a historical period and the total number of times the first terminal starts the any of the applications in the historical period.

3. The method according to claim 1, characterized in that The second record information includes the total number of times the second terminal plays music through the target application within the historical time, and the number of times each of the one or more second music played by the second terminal through the target application within the historical time is played.

4. The method according to claim 3, characterized in that Calculating the trustworthiness of each second target user according to the target application and the second record information includes: Determining, according to the number of times each second music is played in the one or more second music, the second music whose number of times of playing meets a preset condition in the one or more second music; The trustworthiness of each second target user is calculated according to the total number of times the second terminal plays music through the target application within the historical time and the number of times the second music that meets the preset condition is played.

5. The method according to claim 4, characterized in that The trustworthiness of each second target user is the trustworthiness of each second target user on the target application.

6. The method according to claim 1, characterized in that Determining target music to be pushed to the first terminal according to the first similarity between each second target user and the first target user, the trustworthiness of each second target user, and one or more first music played together by the first terminal and the second terminal corresponding to each second target user, includes: Calculate, according to the first similarity between each second target user and the first target user, and the trustworthiness of each second target user, a predicted value of each of the one or more first music played together by the first terminal and the second terminal corresponding to each second target user; According to the predicted value of each first music, the target music to be pushed to the first terminal is determined.

7. The method according to claim 1, characterized in that Determining target music to be pushed to the first terminal according to the first similarity between each second target user and the first target user, the trustworthiness of each second target user, and one or more first music played together by the first terminal and the second terminal corresponding to each second target user, includes: Determine the target music to be pushed to the first terminal according to the first similarity between each second target user and the first target user, the trustworthiness of each second target user, the second similarity between each second target user and the first target user, and one or more first music played together by the first terminal and the second terminal corresponding to each second target user; The first similarity is used to indicate the similarity between the first terminal and the second terminal in playing music, and the second similarity is used to indicate the similarity between the attributes of the second target user and the first target user.

8. The method according to claim 7, characterized in that The method further comprises: According to the first attribute of the first target user and the second attribute corresponding to each of the second target users, a second similarity between each of the second target users and the first target user is calculated.

9. A music recommendation device, characterized in that: include: An acquisition module, used to acquire first record information of a first terminal of a first target user playing music, and second record information of a second terminal of each reference user of one or more reference users playing music; a determination module, configured to determine one or more second target users from the one or more reference users according to the first record information and the second record information, wherein a first similarity between each of the one or more second target users and the first target user is greater than or equal to a preset value; Determine the target music to be pushed to the first terminal according to the first similarity between each second target user and the first target user, the trustworthiness of each second target user, and one or more first music played together by the first terminal and the second terminal corresponding to each second target user; The device also includes: a calculation module, configured to calculate the trust of the first target user in each of the plurality of applications according to the first record information; The determination module is further used to: determine a target application from the multiple applications according to the first target user's trust in each application, the target application having the highest trust in the first target user; The calculation module is further used to calculate the trustworthiness of each second target user according to the target application and the second record information.

10. The device according to claim 9, characterized in that The calculation module is specifically used for: The trust of the first target user in any of the multiple applications is calculated according to the total duration of use of any of the multiple applications by the first terminal in a historical period and the total number of times the first terminal starts the any of the applications in the historical period.

11. The device according to claim 9, characterized in that The second record information includes the total number of times the second terminal plays music through the target application within the historical time, and the number of times each of the one or more second music played by the second terminal through the target application within the historical time is played.

12. The device according to claim 11, characterized in that The determining module is specifically used to: determine the second music whose playing times meet the preset condition among the one or more second music according to the playing times of each second music among the one or more second music; The calculation module is specifically used to calculate the trustworthiness of each second target user according to the total number of times the second terminal plays music through the target application within the historical time and the number of times the second music that meets the preset conditions is played.

13. The device according to claim 12, characterized in that The trustworthiness of each second target user is the trustworthiness of each second target user on the target application.

14. The device according to claim 9, characterized in that The device also includes: a calculation module, configured to calculate, based on the first similarity between each second target user and the first target user and the trustworthiness of each second target user, a predicted value of each of the one or more first music played together by the first terminal and the second terminal corresponding to each second target user; The determination module is specifically used to determine the target music to be pushed to the first terminal according to the predicted value of each first music.

15. The device according to claim 9, characterized in that The determination module is specifically used for: Determine the target music to be pushed to the first terminal according to the first similarity between each second target user and the first target user, the trustworthiness of each second target user, the second similarity between each second target user and the first target user, and one or more first music played together by the first terminal and the second terminal corresponding to each second target user; The first similarity is used to indicate the similarity between the first terminal and the second terminal in playing music, and the second similarity is used to indicate the similarity between the attributes of the second target user and the first target user.

16. The device according to claim 15, characterized in that The device also includes: The calculation module is used to calculate the second similarity between each second target user and the first target user according to the first attribute of the first target user and the second attribute corresponding to each second target user.

17. A music recommendation device, characterized in that: include: Memory; processor; as well as Computer programs; The computer program is stored in the memory and is configured to be executed by the processor to implement the method according to any one of claims 1 to 8.

18. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images