Information recommendation method and apparatus and related product

Abstract

Embodiments of the present disclosure provide an information recommendation method and apparatus and a related product. The method comprises: acquiring a first text of a user, and on the basis of the first text, determining music playback intent information of the user; and when the music playback intent information is used for playing back music data with ambiguous intent, acquiring music playback information of the user, wherein the music playback information of the user is determined on the basis of music use data of the user in a plurality of music platforms; and on the basis of music playback intent information and the music playback information of the user, determining first music data, and recommending the first music data to the user.

Description

Information recommendation method, device and related products

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese Patent Application No. 202410396553.7, filed on April 2, 2024, entitled “Information Recommendation Methods, Devices and Related Products,” the disclosure of which is incorporated herein by reference in its entirety. Technical Field

[0003] The present disclosure relates to the field of computer technology, and in particular to an information recommendation method, device, and related products. Background Art

[0004] With the development of mobile devices, users can install a variety of applications to meet different functions. For example, users can install music applications on their mobile terminals and play music data through them. To improve the user's music data playback experience, how to provide users with more accurate music data recommendations has become one of the most pressing issues to be solved. Summary of the Invention

[0005] In a first aspect, an embodiment of the present disclosure provides an information recommendation method, comprising:

[0006] Obtaining a first text of a user, and determining music playback intention information of the user based on the first text;

[0007] When the music playing intention information is used to play music data with ambiguous intention, obtaining the music playing information of the user; wherein the music playing information of the user is determined based on the music usage data of the user on multiple music platforms;

[0008] Based on the music playing intention information and the music playing information of the user, first music data is determined and the first music data is recommended to the user.

[0009] In a second aspect, an embodiment of the present disclosure provides an information recommendation device, including:

[0010] an intention determination unit, configured to obtain a first text of a user and determine music playing intention information of the user based on the first text;

[0011] an information acquisition unit, configured to acquire the user's music playback information when the music playback intention information is used to play music data with ambiguous intention; wherein the user's music playback information is determined based on the user's music usage data on multiple music platforms;

[0012] The music recommendation unit is used to determine first music data based on the music playback intention information and the music playback information of the user, and recommend the first music data to the user.

[0013] In a third aspect, an embodiment of the present disclosure provides an electronic device, comprising: a processor; and a memory configured to store computer-executable instructions, wherein the computer-executable instructions, when executed, enable the processor to implement the method described in the first aspect above.

[0014] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, which is used to store computer-executable instructions. When the computer-executable instructions are executed by a processor, they implement the method described in the first aspect above.

[0015] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the method described in the first aspect above.

[0016] In a sixth aspect, an embodiment of the present disclosure provides a computer program, which, when executed by a processor, implements the method described in the first aspect above. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in one or more embodiments of the present disclosure or related technologies, the following briefly introduces the drawings required for use in the description of the embodiments or related technologies. It is clear that the drawings described below are only some embodiments described in the present disclosure. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0018] FIG1 is a flow chart of an information recommendation method according to an embodiment of the present disclosure;

[0019] FIG2 is a schematic diagram showing the principle of generating a second feature vector set corresponding to music data according to an embodiment of the present disclosure;

[0020] FIG3 is a flow chart of an information recommendation method according to another embodiment of the present disclosure;

[0021] FIG4 is a schematic structural diagram of an information recommendation device provided by an embodiment of the present disclosure;

[0022] FIG5 is a schematic structural diagram of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of the present disclosure, the technical solutions in one or more embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in one or more embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on one or more embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present disclosure.

[0024] It is understandable that before using the technical solutions disclosed in the various embodiments of this disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved in this disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0025] For example, in response to a user's active request, a prompt message is sent to the user to clearly inform the user that the operation requested will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the electronic device, application, server, storage medium, or other software or hardware that performs the operations of the disclosed technical solution based on the prompt message.

[0026] As an optional but non-limiting implementation, in response to receiving a user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. Furthermore, the pop-up window may also contain a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0027] It is understandable that the above notification and user authorization process are merely illustrative and do not limit the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0028] The embodiments of the present disclosure provide an information recommendation method, device, and related products, which can recommend music data to users based on the users' music usage data on multiple music platforms, thereby improving the accuracy of the recommended music data.

[0029] In one or more embodiments of the present disclosure, first, a user's first text is obtained, and based on the first text, the user's music playback intention information is determined. When the music playback intention information is used to play music data with ambiguous intentions, the user's music playback information is obtained, and the user's music playback information is determined based on the user's music usage data on multiple music platforms. Based on the music playback intention information and the user's music playback information, first music data is determined and recommended to the user. It can be seen that through this embodiment, when the user's music playback intention information is used to play music data with ambiguous intentions, music data can be recommended to the user based on the user's music playback intention information and the user's music playback information, and the user's music playback information is determined based on the user's music usage data on multiple music platforms, thereby achieving the effect of recommending music data to the user based on the user's music usage data on multiple music platforms, thereby improving the accuracy of the recommended music data.

[0030] The disclosed embodiments provide an information recommendation method that can recommend music data to users based on their music usage data across multiple music platforms, thereby improving the accuracy of the recommended music data. This information recommendation method can be applied and executed by a server, which can be a single server or a server cluster.

[0031] FIG1 is a flow chart of an information recommendation method provided by an embodiment of the present disclosure. As shown in FIG1 , the method includes:

[0032] Step S102: obtaining a first text of the user, and determining the user's music playing intention information based on the first text;

[0033] Step S104: When the music playing intention information is used to play music data with ambiguous intention, obtaining the user's music playing information; wherein the user's music playing information is determined based on the user's music usage data on multiple music platforms;

[0034] Step S106: Determine first music data based on the music playing intention information and the user's music playing information, and recommend the first music data to the user.

[0035] In the disclosed embodiment, first, a user's first text is obtained, and based on the first text, the user's music playback intention information is determined. When the music playback intention information is used to play music data with ambiguous intentions, the user's music playback information is obtained, and the user's music playback information is determined based on the user's music usage data on multiple music platforms. Based on the music playback intention information and the user's music playback information, first music data is determined and recommended to the user. It can be seen that through this embodiment, when the user's music playback intention information is used to play music data with ambiguous intentions, music data can be recommended to the user based on the user's music playback intention information and the user's music playback information, and the user's music playback information is determined based on the user's music usage data on multiple music platforms, thereby achieving the effect of recommending music data to the user based on the user's music usage data on multiple music platforms, thereby improving the accuracy of the recommended music data.

[0036] The following is a detailed introduction to the method flow in Figure 1.

[0037] In step S102, the user's first text is obtained. The user's first text can be text sent by the user to the terminal device, or audio data input by the user to the terminal device. The terminal device converts the audio data to obtain the first text and sends the first text to the backend server. The terminal device can be an electronic product such as a mobile phone, computer, laptop computer, desktop computer, car computer, wearable device, etc. When the user inputs audio data to the terminal device, the user can use a sound receiving and playback device such as a microphone or headphones to input the audio data to the terminal device.

[0038] In one example, a music application is running on a terminal device. A user connects to the terminal device via headphones and inputs audio data into the terminal device through the headphones. The music application on the terminal device converts the audio data into a first text and sends the first text to the background server of the music application. The background server also executes the method flow in FIG1 above to recommend music data to the user based on the first text. In this example, the music data recommended to the user can be songs.

[0039] In the above step S102, the user's music playing intention information is determined based on the user's first text. In one embodiment, the user's music playing intention information is determined based on the first text, including:

[0040] Determining, using a generative model, music description information that matches the user based on the first text;

[0041] Through the generative model, the user's music playback intention information is determined based on the music description information.

[0042] In this embodiment, the generative model can be an LLM (Large Language Model), which determines the user's music playback intention information based on the user's first text through the generative model. First, the music description information that matches the user is determined based on the first text through the generative model. The music description information is used to describe the music characteristics of the music data that matches the user. The music description information includes but is not limited to at least one of music singer-songwriter information, music name information, music album information, music style information, music scene information, music language information, music lyrics information, playlist information of the music, and music arrangement information. In each embodiment of this specification, the music singer-songwriter includes at least one of a music composer, a music arranger, and a music singer.

[0043] Then, using a generative model, the user's music playback intent is determined based on the music description. The generative model prompt can be set as: "You are a music appreciation expert who can determine the user's music playback intent." For example, if the music description includes music scene information and music genre information, and the music scene information includes "library" and the music genre information includes "soothing" and "healing," the generative model can determine the user's music playback intent based on the music description: "The user is in a library and may need soothing or healing music."

[0044] For another example, it is determined that the music description information includes the music title information and the music singer-songwriter information, and the music title information includes: "XXX", and the music singer-songwriter information includes: "AAA". Then, through the generative model, based on the music description information, the user's music playback intention information is determined to be: the user wants to play the song XXX by AAA.

[0045] It can be seen that through this embodiment, the generative model can be used to determine the music description information that matches the user based on the first text, and the user's music playback intention information can be determined based on the music description information, so that the user's music playback intention can be accurately identified through the generative model, thereby achieving the effect of accurately recommending music data to the user.

[0046] In one embodiment, determining music description information matching the user based on the first text using a generative model includes:

[0047] By using a generative model, when a second text related to the music data is included in the first text, determining music description information matching the user based on the second text;

[0048] By using the generative model, when the first text does not include the second text but includes the third text related to the user status of the user, music description information matching the user is determined based on the third text.

[0049] In this embodiment, first, through the generative model, a second text related to the music data is retrieved from the first text. The second text related to the music data can be used to represent at least one of the following information: music singer-songwriter information, music name information, music album information, music genre information, music scene information, music language information, music lyrics information, playlist information of the music, music arrangement information, etc.

[0050] If a second text related to music data is retrieved from the first text using a generative model, music description information matching the user is determined based on the second text. For example, the information represented by the second text is determined as the music description information matching the user, or the information represented by the second text and information associated with the information represented by the second text are collectively determined as the music description information matching the user. For example, if the second text represents music artist information such as AAA and music title information such as XXX, then the music artist information "AAA" and the music title information "XXX" are determined as the music description information matching the user. In this example, the user's first text may be: "Please play XXX by AAA." For another example, if the second text represents music scene information such as a library, then the music scene information "library" and the information associated with "library" "quiet" are determined as the music description information matching the user. In this example, the user's first text may be: "Please play a song suitable for a library." For another example, if the second text represents music lyrics information such as "Little Sun," then the music lyrics information "Little Sun" are determined as the music description information matching the user. In this example, the user's first text may be: "Please play a song containing the lyrics "Little Sun."

[0051] In this embodiment, if the generative model does not retrieve the second text related to the music data from the first text, the generative model then retrieves the third text related to the user's user status from the first text. The user status includes, but is not limited to, the user's environment and what the user is doing. For example, if the first text is "I am at work," the user status is "at work." For another example, if the first text is "I am at the library," the user status is "user is at the library."

[0052] If a third text related to the user's user status is retrieved from the first text through the generative model, the music description information matching the user is determined based on the third text. The information represented by the third text can be determined as the music description information matching the user, or the information represented by the third text and the information associated with the information represented by the third text can be jointly determined as the music description information matching the user. For example, if the third text is "going to work", which is used to indicate that the user status is that the user is at work, then the music description information matching the user includes music style information and music scene information. The music style information can be "soothing", and the music scene information can be "going to work". For another example, if the third text is "library", which is used to indicate that the user status is that the user is at the library, then the music description information matching the user includes music style information and music scene information. The music style information can be "quiet", and the music scene information can be "library".

[0053] It should be noted here that when scene description words such as "park," "bookstore," "library," and "outdoors" appear in the first text, in one case, if these scene description words are associated with music-related words, then the generative model determines these scene description words as a second text related to music data used to represent music scene information. The association of scene description words with music-related words can be exemplified by the presence of music-related words such as "song," "play," and "music" before or after the scene description words in the first text. In another case, if these scene description words are associated with user-related words, then the generative model determines these scene description words as a third text related to the user's user status. The association of scene description words with user-related words can be exemplified by the presence of user-related words such as "I," "myself," "I am," and "I am" before or after the scene description words in the first text.

[0054] It can be seen that through this embodiment, when the first text includes a second text related to the music data, the generative model can be used to determine the music description information matching the user based on the second text; and when the first text does not include the second text but includes a third text related to the user status of the user, the music description information matching the user can be determined based on the third text. In this way, the music description information can be determined based on the first text from multiple perspectives, thereby improving the accuracy of recommending music data to users.

[0055] In one embodiment, if the generative model does not retrieve the second text related to the music data nor the third text related to the user's user status in the first text, then the music description information matching the user cannot be determined, that is, the music description information determination fails, and it is determined that the user does not have music playback intention information, that is, the user does not have the intention to play music, and the user's first text is a text unrelated to music playback, such as "What day is it today?", "What's the weather like today?" and other chat texts unrelated to music playback.

[0056] After determining that the user's music playback intention information is obtained, in the above step S104, it is determined whether the user's music playback intention information is used to play music data with ambiguous intentions or to play music data with clear intentions. The user's music playback intention information being used to play music data with ambiguous intentions means that the user's music playback intention information points to ambiguous music data, for example, the music playback intention information does not include a music title. The user's music playback intention information being used to play music data with clear intentions means that the user's music playback intention information points to clear music data, for example, the music playback intention information includes a music title.

[0057] Based on this, in one embodiment, the above method flow further includes:

[0058] When the music playing intention information does not include preset information, determining that the music playing intention information is used to play music data with ambiguous intention;

[0059] When the music playing intention information includes preset information, it is determined that the music playing intention information is used to play music data with a clear intention.

[0060] In this embodiment, it is determined whether the music playback intention information includes preset information. The preset information may include music name information, and may also include music name information and music singer-songwriter information. First, it is determined whether the music playback intention information includes preset information, such as whether it includes music name information and music singer-songwriter information. If the music playback intention information includes preset information, it is determined that the music playback intention information is used to play music data with clear intentions, and the music data with clear intentions is the music data corresponding to the preset information. If the music playback intention information does not include preset information, it is determined that the music playback intention information is used to play music data with ambiguous intentions, that is, the music playback intention information does not point to one or more clear music data.

[0061] It can be seen that through this embodiment, it is possible to accurately determine whether the music playback intention information is used to play music data with ambiguous intentions or to play music data with clear intentions based on whether the music playback intention information includes preset information.

[0062] In one embodiment, the above method further includes:

[0063] When the music playing intention information is used to play music data with a clear intention, determining the second music data according to the music playing intention information;

[0064] The second music data is recommended to the user.

[0065] In this embodiment, when the music playback intention information is used to play music data with a clear intention, the second music data is determined based on the preset information in the music playback intention information. For example, the music data corresponding to the preset information is determined as the second music data, and the second music data is recommended to the user.

[0066] It can be seen that through this embodiment, when the music playback intention information is used to play music data with clear intention, the second music data can be determined and recommended to the user based on the music playback intention information, thereby achieving the effect of accurately recommending music data to the user according to the user's intention.

[0067] In one embodiment, recommending second music data to the user includes:

[0068] acquiring the second music data from a music platform storing the second music data;

[0069] The second music data is recommended to the user.

[0070] In this embodiment, the second music data is obtained from a music platform storing the second music data. In one case, if the second music data is stored in the background server of the music platform corresponding to the music application executing this embodiment, the second music data is obtained from the background server and recommended to the user. In another case, if the second music data is not stored in the background server of the music platform corresponding to the music application executing this embodiment, the music platform storing the second music data is determined, the second music data is obtained from the background server of the determined music platform, and the second music data is recommended to the user. In this case, after determining the music platform storing the second music data, the communication interface and communication protocol corresponding to the background server of the music platform can be used to communicate with the background server, obtain the second music data from the background server, and send it to the user.

[0071] It can be seen that through this embodiment, multiple music platforms can be connected and interacted with, the second music data can be obtained from the music platform storing the second music data, and the second music data can be recommended to the user, thereby achieving the effect of accurately recommending music data to the user according to the user's intention.

[0072] In Figure 1, in step S104, when it is determined that the music playing intention information is used to play music data with ambiguous intention, the user's music playing information is obtained. The user's music playing information is determined based on the user's music usage data on multiple music platforms.

[0073] In one embodiment, the music usage data comes from one or more music platforms authorized by the user, and the user's music playback information can be determined through a generative model based on the user's music usage data on multiple music platforms.

[0074] In this embodiment, based on the user's authorization, the user's music usage data across multiple music platforms can be obtained. This music usage data includes at least the user's created playlists, favorited music, and played music. Then, using a generative model, the user's music playback information is determined based on the user's music usage data across multiple music platforms. For example, user A's music playback information might include: User A likes Chinese music, occasionally listens to English music, dislikes Korean music, often listens to rock music, also enjoys pop music, dislikes folk music, has a favorite song called XXX, and a favorite artist called AAA.

[0075] 1 , after obtaining the user's music playing information, in step S106 , first music data is determined based on the music playing intention information and the user's music playing information, and the first music data is recommended to the user.

[0076] In one embodiment, determining the first music data according to the music playing intention information and the user's music playing information includes:

[0077] generating a first sub-feature vector for representing text content features of music playback intention information and a second sub-feature vector for representing text content features of the user's music playback information, and obtaining a first feature vector set based on a combination of the first sub-feature vector and the second sub-feature vector;

[0078] The first music data is determined from each music data according to the first feature vector set and the second feature vector set corresponding to each music data; wherein the second feature vector set is used to represent the music features of the music data.

[0079] In this embodiment, according to the previous description, the music playback intention information can be in text form, and the user's music playback information can also be in text form. Therefore, with the help of an embedding model such as the OPENAI model, one or more feature vectors for representing the text content features of the music playback intention information can be generated, and the one or more feature vectors can be used as the first sub-feature vector. In addition, with the help of an embedding model such as the OPENAI model, one or more feature vectors for representing the text content features of the user's music playback information can be generated, and the one or more feature vectors can be used as the second sub-feature vector. All the first sub-feature vectors and all the second sub-feature vectors are combined to obtain a first feature vector set.

[0080] Next, in this embodiment, a second feature vector set corresponding to each music data is generated in advance through an embedding model such as the OPENAI model. These music data are a plurality of predetermined music data, and one music data corresponds to a second feature vector set. The second feature vector set includes multiple second feature vectors. The second feature vector set can represent the music characteristics of the corresponding music data by abstracting the music data into text.

[0081] Then, in this embodiment, the first music data is determined in each piece of music data based on the first feature vector set and the second feature vector set corresponding to each piece of music data.

[0082] It can be seen that through this embodiment, the first music data can be determined among various music data based on the first feature vector set corresponding to the music playback intention information and the user's music playback information and the second feature vector set corresponding to each music data, and the first music data can be accurately determined among multiple music data based on the feature vector comparison method.

[0083] In one embodiment, determining the first music data from each music data according to the first feature vector set and the second feature vector set corresponding to each music data includes:

[0084] Calculating vector distances between the first set of eigenvectors and each set of second eigenvectors;

[0085] Based on the vector distance, the first music data is determined among the respective music data.

[0086] In this embodiment, the vector distance between the first feature vector set and each second feature vector set is calculated to obtain multiple vector distances, each vector distance corresponds to a second feature vector set, that is, corresponds to a piece of music data. The vector distance between the first feature vector set and each second feature vector set can be calculated through an embedding model such as the OPENAI model.

[0087] Next, the first music data is determined from each piece of music data based on the vector distance. For example, the music data corresponding to the smallest vector distance among each piece of music data is determined as the first music data.

[0088] In one example, a second feature vector set corresponding to each piece of music data can be generated through an embedding model, and the second feature vector set is stored in the embedding model. Then, when executing the method in Figure 1, the user's music playback intention information and the user's music playback information are input into the embedding model. The embedding model is used to generate the above-mentioned first feature vector set, and the vector distance between the first feature vector set and each second feature vector set is calculated. Based on the vector distance, the first music data is determined in each piece of music data, and the embedding model outputs the identification information of the first music data.

[0089] It can be seen that through this embodiment, the vector distance between the first feature vector set and each second feature vector set can be calculated, and based on the vector distance, the first music data can be accurately determined in each music data.

[0090] In one embodiment, the second feature vector set corresponding to each music data is generated in the following manner:

[0091] For each piece of music data, at least one of the following information of the music data is obtained: music singer-songwriter information, music title information, music album information, music genre information, music scene information, music language information, music lyrics information, playlist information of the music, music arrangement information, and music structure information;

[0092] For each piece of music data, a sub-feature vector corresponding to each piece of acquired information is generated, and based on the sub-feature vectors corresponding to each piece of acquired information, a second feature vector set corresponding to the music data is generated.

[0093] In this embodiment, for each music data among a plurality of predetermined music data, at least one of the above information of the music data is obtained, wherein the music singer-songwriter information includes but is not limited to music singer information, music arranger information, etc., the music album information includes the name of the album where the music data is located, the music language information can be exemplified by Chinese, English, etc., the music lyrics information includes but is not limited to the lyrics of the music data and keywords in the lyrics, the playlist information where the music is located includes the name of the playlist where the music data is located, the music arrangement information includes but is not limited to the accompaniment, instrument and other information of the music data, and the music structure information refers to the duration range of each stage in the music data, and each stage includes the music starting stage, music gradual stage, music climax stage, music ending stage, etc.

[0094] Then, for each piece of music data, a sub-feature vector corresponding to each acquired information is generated through the embedding model. One piece of information corresponds to one or more sub-feature vectors, and based on each sub-feature vector, a second feature vector set corresponding to the music data is obtained by combining them.

[0095] FIG2 is a schematic diagram of the principle of generating a second feature vector set corresponding to music data provided by an embodiment of the present disclosure. As shown in FIG2, in this embodiment, for a piece of music data, the music singer-songwriter information, music title information, music album information, music style information, music scene information, music language information, music lyrics information, music playlist information, music arrangement information, and music structure information of the music data are obtained, and a sub-feature vector library corresponding to each acquired information is generated, and each sub-feature vector library includes at least one sub-feature vector. In FIG2, the music singer-songwriter information, music title information, music album information, music style information, music scene information, and music language information correspond to the metadata sub-feature vector library, which includes at least one sub-feature vector, the music lyrics information and music structure information correspond to the lyrics structure sub-feature vector library, which includes at least one sub-feature vector, the music playlist information corresponds to the playlist data sub-feature vector library, which includes at least one sub-feature vector, and the music arrangement information corresponds to the music description sub-feature vector library, which includes at least one sub-feature vector. Finally, each sub-feature vector library is fused to obtain the second feature vector set corresponding to the music data.

[0096] It can be seen that through this embodiment, at least one of the above information of the music data can be obtained for each music data, and a sub-feature vector corresponding to each acquired information can be generated for each music data. According to the sub-feature vectors corresponding to each acquired information, a second feature vector set corresponding to the music data is generated, thereby accurately and efficiently obtaining the second feature vector set corresponding to each music data.

[0097] After determining that the first music data is obtained, recommending the first music data to the user. In one embodiment, recommending the first music data to the user includes:

[0098] Acquire the first music data from a music platform storing the first music data;

[0099] The first music data is recommended to the user.

[0100] In this embodiment, the first music data is obtained from a music platform storing the first music data. In one case, if the backend server of the music platform corresponding to the music application executing this embodiment stores the first music data, the first music data is obtained from the backend server and recommended to the user. In another case, if the backend server of the music platform corresponding to the music application executing this embodiment does not store the first music data, a music platform storing the first music data is determined, the first music data is obtained from the backend server of the determined music platform, and the first music data is recommended to the user.

[0101] It can be seen that through this embodiment, the first music data can be obtained from the music platform storing the first music data, and the first music data can be recommended to the user, thereby achieving the effect of accurately recommending music data to the user according to the user's intention.

[0102] In one embodiment, obtaining the first music data from a music platform storing the first music data includes:

[0103] determining a music platform storing the first music data among a plurality of music platforms;

[0104] The first music data is obtained from the music platform through the communication interface of the music platform and the communication protocol of the music platform.

[0105] In this embodiment, when the first music data is not stored in the background server of the music platform corresponding to the music application executing this embodiment, a music platform storing the first music data is determined among multiple music platforms, and the first music data is obtained from the music platform through the communication interface and communication protocol of the music platform. For example, communication is performed with the background server through the communication interface and communication protocol corresponding to the background server of the music platform, and the first music data is obtained from the background server and sent to the user.

[0106] It can be seen that through this embodiment, multiple music platforms can be connected and interacted with, thereby obtaining the first music data, and achieving the effect of accurately recommending music data to the user according to the user's intention.

[0107] In this embodiment, recommending the first music data and the second music data to the user may be sending the first music data and the second music data to a terminal device of the user.

[0108] FIG3 is a flow chart of an information recommendation method according to another embodiment of the present disclosure. As shown in FIG3 , the flow includes:

[0109] Step S302: The backend server obtains the user's music usage data on multiple music platforms;

[0110] The backend server is a backend server for the music platform corresponding to the music application, and the plurality of music platforms includes the music platform corresponding to the music application; the backend server obtains the user's music usage data on each music platform through the communication interface and communication protocol of each music platform;

[0111] Step S304: The background server determines the user's music playing information, which may be determined based on the user's music usage data on various music platforms.

[0112] Step S306: the music application in the user's terminal device obtains the user's first text and sends the first text to the background server;

[0113] Step S308: The background server determines that the user's music playing intention information is used to play music data with ambiguous intentions, and may determine, based on the first text, that the user's music playing intention information is used to play music data with ambiguous intentions;

[0114] Step S310: The background server determines the first music data, and the first music data may be determined based on the music playing intention information and the user's music playing information;

[0115] In step S312, the background server sends the first music data to the user's terminal device.

[0116] In summary, through the various embodiments of the above-described information recommendation method, on the one hand, a user's music playback information can be determined based on the user's music usage data on various music platforms, achieving the effect of comprehensively determining the user's music playback information by combining data from the entire network. On the other hand, the method can obtain first music data from the music platform storing the first music data and recommend it to the user, and obtain second music data from the music platform storing the second music data and recommend it to the user, breaking down the barriers between various music platforms. This allows users to obtain the required music data from the entire network by operating a single music application, thereby improving the user's music data playback experience.

[0117] FIG4 is a schematic diagram of the structure of an information recommendation device provided by an embodiment of the present disclosure. As shown in FIG4 , the device includes:

[0118] The intention determination unit 41 is configured to obtain a first text of a user and determine the user's music playing intention information based on the first text;

[0119] an information acquisition unit 42, configured to acquire the user's music playback information when the music playback intention information is used to play music data with ambiguous intention; wherein the user's music playback information is determined based on the user's music usage data on multiple music platforms;

[0120] The music recommendation unit 43 is configured to determine first music data based on the music playing intention information and the music playing information of the user, and recommend the first music data to the user.

[0121] Optionally, the intention determination unit 41 is specifically configured to:

[0122] Determining, using a generative model, music description information matching the user based on the first text;

[0123] The generative model is used to determine the user's music playing intention information based on the music description information.

[0124] Optionally, the intention determination unit 41 is further specifically configured to:

[0125] When the first text includes a second text related to music data, determining music description information matching the user based on the second text by using the generative model;

[0126] By using the generative model, when the first text does not include the second text but includes a third text related to the user status of the user, music description information matching the user is determined based on the third text.

[0127] Optionally, the system further includes an intention judgment unit, configured to:

[0128] When the music playing intention information does not include preset information, determining that the music playing intention information is used to play music data with ambiguous intention;

[0129] When the music playing intention information includes the preset information, it is determined that the music playing intention information is used to play music data with a clear intention.

[0130] Optionally, the system further includes a music determination unit configured to:

[0131] When the music playing intention information is used to play music data with a clear intention, determining second music data according to the music playing intention information;

[0132] The second music data is recommended to the user.

[0133] Optionally, the music determination unit is specifically configured to:

[0134] acquiring the second music data from a music platform storing the second music data;

[0135] The second music data is recommended to the user.

[0136] Optionally, the music recommendation unit 43 is specifically configured to:

[0137] generating a first sub-feature vector for representing text content features of the music playback intention information and a second sub-feature vector for representing text content features of the user's music playback information, and obtaining a first feature vector set based on a combination of the first sub-feature vector and the second sub-feature vector;

[0138] The first music data is determined from the various music data based on the first feature vector set and the second feature vector set corresponding to the various music data; wherein the second feature vector set is used to represent the music features of the music data.

[0139] Optionally, the music recommendation unit 43 is further configured to:

[0140] Calculating vector distances between the first set of feature vectors and each set of the second feature vectors;

[0141] The first music data is determined from among the respective music data based on the vector distance.

[0142] Optionally, the method further includes a vector set generating unit, configured to:

[0143] For each piece of music data, obtaining at least one of the following information of the music data: music singer-songwriter information, music title information, music album information, music genre information, music scene information, music language information, music lyrics information, playlist information of the music, music arrangement information, and music structure information;

[0144] For each piece of music data, a sub-feature vector corresponding to each piece of acquired information is generated, and based on the sub-feature vectors corresponding to each piece of acquired information, a second feature vector set corresponding to the music data is generated.

[0145] Optionally, the music recommendation unit 43 is specifically configured to:

[0146] Acquire the first music data from a music platform storing the first music data;

[0147] The first music data is recommended to the user.

[0148] Optionally, the music recommendation unit 43 is further configured to:

[0149] determining a music platform storing the first music data among the plurality of music platforms;

[0150] The first music data is obtained from the music platform through the communication interface of the music platform and the communication protocol of the music platform.

[0151] The information recommendation device in the embodiment of the present disclosure can implement each process of the above-mentioned information recommendation method embodiment and achieve the same effects and functions, which will not be repeated here.

[0152] An embodiment of the present disclosure also provides an electronic device. FIG5 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. As shown in FIG5 , the electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors 501 and a memory 502. One or more applications or data may be stored in the memory 502. Among them, the memory 502 may be a temporary storage or a persistent storage. The application stored in the memory 502 may include one or more modules (not shown in the figure), each module may include a series of computer executable instructions in the electronic device. Furthermore, the processor 501 may be configured to communicate with the memory 502 and execute a series of computer executable instructions in the memory 502 on the electronic device. The electronic device may also include one or more power supplies 503, one or more wired or wireless network interfaces 504, one or more input or output interfaces 505, one or more keyboards 506, etc.

[0153] In a specific embodiment, the electronic device includes a processor; and a memory configured to store computer-executable instructions, wherein when the computer-executable instructions are executed, the processor implements the following process:

[0154] Obtaining a first text of a user, and determining music playback intention information of the user based on the first text;

[0155] When the music playing intention information is used to play music data with ambiguous intention, obtaining the music playing information of the user; wherein the music playing information of the user is determined based on the music usage data of the user on multiple music platforms;

[0156] Based on the music playing intention information and the music playing information of the user, first music data is determined and the first music data is recommended to the user.

[0157] The electronic device in the embodiment of the present disclosure can implement each process of the above-mentioned information recommendation method embodiment and achieve the same effects and functions, which will not be repeated here.

[0158] Another embodiment of the present disclosure further provides a computer-readable storage medium for storing computer-executable instructions. When the computer-executable instructions are executed by a processor, the following process is implemented:

[0159] Obtaining a first text of a user, and determining music playback intention information of the user based on the first text;

[0160] When the music playing intention information is used to play music data with ambiguous intention, obtaining the music playing information of the user; wherein the music playing information of the user is determined based on the music usage data of the user on multiple music platforms;

[0161] Based on the music playing intention information and the music playing information of the user, first music data is determined and the first music data is recommended to the user.

[0162] The storage medium in the embodiment of the present disclosure can implement each process of the above-mentioned information recommendation method embodiment and achieve the same effects and functions, which will not be repeated here.

[0163] Another embodiment of the present disclosure further provides a computer program product, the computer program product including a computer program, which implements the following process when executed by a processor:

[0164] Obtaining a first text of a user, and determining music playback intention information of the user based on the first text;

[0165] When the music playing intention information is used to play music data with ambiguous intention, obtaining the music playing information of the user; wherein the music playing information of the user is determined based on the music usage data of the user on multiple music platforms;

[0166] Based on the music playing intention information and the music playing information of the user, first music data is determined and the first music data is recommended to the user.

[0167] The computer program product in the embodiment of the present disclosure can implement each process of the above-mentioned information recommendation method embodiment and achieve the same effects and functions, which will not be repeated here.

[0168] Another embodiment of the present disclosure further provides a computer program, which implements the following process when executed by a processor:

[0169] Obtaining a first text of a user, and determining music playback intention information of the user based on the first text;

[0170] When the music playing intention information is used to play music data with ambiguous intention, obtaining the music playing information of the user; wherein the music playing information of the user is determined based on the music usage data of the user on multiple music platforms;

[0171] Based on the music playing intention information and the music playing information of the user, first music data is determined and the first music data is recommended to the user.

[0172] The computer program in the embodiment of the present disclosure can implement each process of the above-mentioned information recommendation method embodiment and achieve the same effects and functions, which will not be repeated here.

[0173] In various embodiments of the present disclosure, the computer-readable storage medium includes a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0174] In the 1990s, technological improvements could be clearly distinguished as either hardware improvements (for example, improvements to circuit structures such as diodes, transistors, and switches) or software improvements (improvements to process flows). However, with the advancement of technology, many process flow improvements today can now be considered direct improvements to hardware circuit structures. Designers almost always create the corresponding hardware circuit structure by programming the improved process flow into the hardware circuit. Therefore, it cannot be said that a process flow improvement cannot be implemented using hardware modules. For example, a programmable logic device (PLD), such as a field programmable gate array (FPGA), is an integrated circuit whose logical function is determined by user programming. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to hire a chip manufacturer to design and manufacture a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly done using "logic compiler" software. This is similar to the software compiler used when developing programs. Before compilation, the original code must also be written in a specific programming language, called a hardware description language (HDL). There is not just one HDL, but many, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art will also understand that by simply programming the method flow in one of these hardware description languages ​​and then programming it into an integrated circuit, a hardware circuit that implements the logic method flow can be easily obtained.

[0175] The controller can be implemented in any suitable manner. For example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also know that in addition to implementing the controller in a purely computer-readable program code format, the controller can be implemented in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be considered as structures within the hardware component. Or even, the devices for implementing various functions can be considered as both software modules that implement the method and structures within the hardware component.

[0176] The systems, devices, modules, or units described in the above embodiments may be implemented by computer chips or entities, or by products having certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0177] For the convenience of description, the above devices are described as being divided into various units according to their functions. Of course, when implementing the embodiments of the present disclosure, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0178] Those skilled in the art will appreciate that one or more embodiments of the present disclosure may be provided as a method, system, or computer program product. Therefore, one or more embodiments of the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, one or more embodiments of the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0179] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0180] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0181] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0182] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0183] One or more embodiments of the present disclosure may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. One or more embodiments of the present disclosure may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communications network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0184] The various embodiments of this disclosure are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiments are generally similar to the method embodiments, so their description is relatively simple. For relevant portions, refer to the description of the method embodiments.

[0185] The foregoing is merely an embodiment of the present disclosure and is not intended to limit the present disclosure. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present disclosure are intended to be included within the scope of the claims of the present disclosure.

Claims

1. An information recommendation method, comprising: Obtaining a first text of a user, and determining music playback intention information of the user based on the first text; When the music playing intention information is used to play music data with ambiguous intention, obtaining the music playing information of the user; wherein the music playing information of the user is determined based on the music usage data of the user on multiple music platforms; According to the music playing intention information and the music playing information of the user, first music data is determined and the first music data is recommended to the user.

2. The method according to claim 1, wherein The determining, based on the first text, the user's music playback intention information includes: Determining, using a generative model, music description information matching the user based on the first text; The generative model is used to determine the user's music playing intention information based on the music description information.

3. The method according to claim 2, wherein: Determining music description information matching the user based on the first text using a generative model includes: When the first text includes a second text related to music data, determining music description information matching the user based on the second text by using the generative model; By using the generative model, when the first text does not include the second text but includes a third text related to the user status of the user, music description information matching the user is determined based on the third text.

4. The method according to any one of claims 1 to 3, wherein: The method further comprises: When the music playing intention information does not include preset information, determining that the music playing intention information is used to play music data with ambiguous intention; When the music playing intention information includes the preset information, it is determined that the music playing intention information is used to play music data with a clear intention.

5. The method according to claim 4, wherein The method further comprises: When the music playing intention information is used to play music data with a clear intention, determining second music data according to the music playing intention information; The second music data is recommended to the user.

6. The method according to claim 5, wherein: The recommending the second music data to the user includes: acquiring the second music data from a music platform storing the second music data; The second music data is recommended to the user.

7. The method according to any one of claims 1 to 6, wherein: The determining the first music data according to the music playing intention information and the music playing information of the user includes: generating a first sub-feature vector for representing text content features of the music playback intention information and a second sub-feature vector for representing text content features of the user's music playback information, and obtaining a first feature vector set based on a combination of the first sub-feature vector and the second sub-feature vector; The first music data is determined from the various music data based on the first feature vector set and the second feature vector set corresponding to the various music data; wherein the second feature vector set is used to represent the music features of the music data.

8. The method according to claim 7, wherein: The determining the first music data from the respective music data according to the first feature vector set and the second feature vector set corresponding to the respective music data includes: Calculating vector distances between the first set of feature vectors and each set of the second feature vectors; The first music data is determined from among the respective music data based on the vector distance.

9. The method according to claim 7, wherein: The method further comprises: For each piece of music data, obtaining at least one of the following information of the music data: music singer-songwriter information, music title information, music album information, music genre information, music scene information, music language information, music lyrics information, playlist information of the music, music arrangement information, and music structure information; For each piece of music data, a sub-feature vector corresponding to each piece of acquired information is generated, and based on the sub-feature vectors corresponding to each piece of acquired information, a second feature vector set corresponding to the music data is generated.

10. The method according to any one of claims 1 to 9, wherein The recommending the first music data to the user includes: Acquire the first music data from a music platform storing the first music data; The first music data is recommended to the user.

11. The method according to claim 10, wherein: The acquiring the first music data from a music platform storing the first music data includes: determining a music platform storing the first music data among the plurality of music platforms; The first music data is obtained from the music platform through the communication interface of the music platform and the communication protocol of the music platform.

12. An information recommendation device, comprising: an intention determination unit, configured to obtain a first text of a user and determine music playing intention information of the user based on the first text; an information acquisition unit, configured to acquire the user's music playback information when the music playback intention information is used to play music data with ambiguous intention; wherein the user's music playback information is determined based on the user's music usage data on multiple music platforms; The music recommendation unit is used to determine first music data based on the music playback intention information and the music playback information of the user, and recommend the first music data to the user.

13. An electronic device comprising: processor; as well as, A memory configured to store computer-executable instructions which, when executed, cause the processor to implement the method according to any one of claims 1 to 11.

14. A computer-readable storage medium for storing computer-executable instructions, wherein the computer-executable instructions implement the method according to any one of claims 1 to 11 when executed by a processor.

15. A computer program product, comprising a computer program, wherein the computer program, when executed by a processor, implements the method according to any one of claims 1 to 11.

16. A computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 11.

Images