Playlist recommendation method

Abstract

The present invention discloses a playlist recommendation method, comprising: obtaining a user interaction tag based on a recommendation request sent by a terminal; obtaining a to-be-recommended playlist corresponding to the user interaction tag, the to-be-recommended playlist including multiple songs to be recommended; obtaining target display text corresponding to the user interaction tag from the display text of the to-be-recommended songs; generating recommendation information based on the target display text; and transmitting the recommendation information to the terminal, causing the terminal to display the recommendation information. This solution not only simulates, extends, and expands the interaction between the user and the terminal by setting the user interaction tag, thereby improving the interactivity between the user and the terminal, but also obtains the target display text based on the user interaction tag, making the recommendation information generated based on the target display text more accurate, further improving the accuracy of the interaction between the terminal and the user.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to a playlist recommendation method. Background Art

[0002] With the development of Internet applications, many applications can recommend content based on user needs, such as audio music or video applications.

[0003] Existing audio applications recommend multiple audio tracks to users based on their historical playback history for them to choose from. Specifically, when a user selects the playlist "More Sad Than Sadness: I Can't Play With You," the audio application will play all the songs in that playlist in sequence.

[0004] In the above recommendation process, the interactivity between the audio application and the user is relatively poor. Therefore, it is necessary to provide an audio and video recommendation method that improves the interactive performance. Summary of the Invention

[0005] An embodiment of the present invention provides a playlist recommendation method, which can improve the interactivity between users and terminals.

[0006] An embodiment of the present invention provides a playlist recommendation method, which includes:

[0007] Obtain user interaction tags based on the recommendation request sent by the terminal;

[0008] Obtain a song list to be recommended corresponding to the user interaction tag, wherein the song list to be recommended includes multiple songs to be recommended;

[0009] Obtaining a target display text corresponding to the user interaction tag from the display text of the song to be recommended;

[0010] generating recommendation information according to the target display text;

[0011] The recommendation information is sent to the terminal, so that the terminal displays the recommendation information.

[0012] An embodiment of the present invention provides a server, which includes a processor and a memory, wherein the memory stores a plurality of instructions, and the instructions are suitable for the processor to load to execute the steps in the above-mentioned playlist recommendation method.

[0013] The embodiment of the present invention also provides a playlist recommendation method, which includes:

[0014] Sending a recommendation request to a server, so that the server obtains a user interaction tag through the recommendation request; the user interaction tag is used by the server to obtain a to-be-recommended song list corresponding to the user interaction tag, the to-be-recommended song list including a plurality of to-be-recommended songs; the display text of the to-be-recommended song is used by the server to obtain a target display text corresponding to the user interaction tag; the target display text is used by the server to generate recommendation information;

[0015] receiving the recommendation information;

[0016] Configuring the recommendation information into a conversation-formatted recommendation information;

[0017] The recommended information in the conversation format is displayed in a scrolling manner.

[0018] An embodiment of the present invention provides a terminal comprising a processor and a memory, wherein the memory stores a plurality of instructions suitable for loading by the processor to execute the steps in the above-mentioned playlist recommendation method.

[0019] The embodiment of the present invention further provides a playlist recommendation device, which includes:

[0020] The tag acquisition module is used to obtain user interaction tags based on the recommendation request sent by the terminal;

[0021] A song list acquisition module is used to acquire a song list to be recommended corresponding to the user interaction tag, wherein the song list to be recommended includes multiple songs to be recommended;

[0022] A text acquisition module, configured to acquire a target display text corresponding to the user interaction tag from the display text of the song to be recommended;

[0023] A generating module, configured to generate recommendation information according to the target display text;

[0024] The sending module is used to send the recommendation information to the terminal so that the terminal displays the recommendation information.

[0025] In one embodiment, the apparatus further comprises:

[0026] A first setting module is configured to set a plurality of user interaction tags according to an interaction mode between the user and the terminal, wherein each user interaction tag corresponds to an interaction mode;

[0027] The second setting module is used to set multiple song lists to be recommended, and make each song list to be recommended correspond to a user interaction tag.

[0028] In one embodiment, the apparatus further comprises:

[0029] A trigger acquisition module is used to obtain the trigger text from the display text of the song;

[0030] A tag module, configured to determine a user interaction tag corresponding to the trigger text;

[0031] The first classification module is used to classify the song into the song list to be recommended corresponding to the user interaction tag.

[0032] In one embodiment, the apparatus further comprises:

[0033] A content acquisition module, configured to acquire lyrics containing the trigger text from the display text of the song;

[0034] The third setting module is used to set the lyrics content as the target display text of the song under the user interaction tag.

[0035] In one embodiment, the generating module includes:

[0036] The singer acquisition submodule is used to obtain the singer information of the song to be recommended;

[0037] The generation submodule is used to generate recommendation information in a dialogue format based on the singer information and the target display text.

[0038] In one embodiment, the user interaction tag includes a preference tag, and the apparatus further includes:

[0039] A storage module is used to store the preference tag and the playlist to be recommended corresponding to the preference tag in the blockchain.

[0040] In one embodiment, a plurality of playlists to be recommended are included, and the apparatus further comprises:

[0041] A first frequency module is used to obtain the acquisition frequency of each to-be-recommended playlist and determine at least two to-be-recommended playlists whose acquisition frequencies meet a preset condition;

[0042] The second classification module is used to obtain repeated songs to be recommended from the at least two songs to be recommended lists, and classify the repeated songs to be recommended into the songs to be recommended lists corresponding to the preference tags.

[0043] In one embodiment, the apparatus further comprises:

[0044] A second frequency module is configured to obtain, when the repeated songs to be recommended correspond to multiple target display texts with different contents, the acquisition frequencies of the multiple target display texts with different contents;

[0045] A text determination module is used to determine a target display text from the multiple target display texts with different contents according to the acquisition frequency of the multiple target display texts with different contents, and to serve as the target display text corresponding to the repeated preset song under the preference tag.

[0046] In one embodiment, when the user interaction tag is a preference tag, the playlist acquisition module further includes:

[0047] The account acquisition submodule is used to obtain the user's account information;

[0048] The playlist acquisition submodule is used to obtain the playlist to be recommended corresponding to the preference tag based on the user's account information.

[0049] The embodiment of the present invention further provides a playlist recommendation device, which includes:

[0050] A request module is configured to send a recommendation request to a server, so that the server obtains a user interaction tag through the recommendation request; the user interaction tag is used by the server to obtain a to-be-recommended song list corresponding to the user interaction tag, the to-be-recommended song list including a plurality of to-be-recommended songs; the display text of the to-be-recommended song is used by the server to obtain a target display text corresponding to the user interaction tag; the target display text is used by the server to generate recommendation information;

[0051] A receiving module, configured to receive the recommendation information;

[0052] A recommendation setting module, configured to set the recommendation information into a conversation format recommendation information;

[0053] The scrolling module is used to scroll and display the recommended information in the dialog format.

[0054] In one embodiment, the device includes multiple recommendation information in a dialog format, and further includes:

[0055] a play acquisition module, configured to acquire a play request, wherein the play request is triggered when target recommendation information is selected, wherein the target recommendation information is one of the plurality of conversation-formatted recommendation information;

[0056] The stop module is used to stop scrolling the target recommendation information and play the song to be recommended corresponding to the target recommendation information.

[0057] Furthermore, an embodiment of the present invention also provides a computer-readable storage medium, which stores processor-executable instructions, and the processor provides any of the above playlist recommendation methods by executing the instructions.

[0058] The playlist recommendation method, device, computer-readable storage medium, terminal and server of the embodiments of the present invention not only simulate, extend and expand the interaction status between the user and the terminal by setting user interaction tags, thereby improving the interactivity between the user and the terminal, but also obtain the target display text according to the user interaction tags, thereby making the recommendation information generated according to the target display text more accurate, thereby further improving the accuracy of the interaction between the terminal and the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The technical solutions and other beneficial effects of the present invention will be made apparent by describing in detail the specific embodiments of the present invention in conjunction with the accompanying drawings.

[0060] Figure 1 A schematic diagram of a scenario of a playlist recommendation system provided in an embodiment of the present invention.

[0061] Figure 2 A timing diagram of the playlist recommendation system provided in an embodiment of the present invention.

[0062] Figure 3 A schematic diagram of the structure of a blockchain system provided by an embodiment of the present invention.

[0063] Figure 4 A first flow chart of the playlist recommendation method provided in an embodiment of the present invention.

[0064] Figure 5 A schematic diagram of the first scenario of the playlist recommendation method provided in an embodiment of the present invention.

[0065] Figure 6 A schematic diagram of a second scenario of the playlist recommendation method provided in an embodiment of the present invention.

[0066] Figure 7 A second flow chart of the playlist recommendation method provided in an embodiment of the present invention.

[0067] Figure 8 A third flow chart of the playlist recommendation method provided in an embodiment of the present invention.

[0068] Figure 9 A schematic diagram of a third scenario of the playlist recommendation method provided in an embodiment of the present invention.

[0069] Figure 10 This is a first structural diagram of the playlist recommendation device provided in an embodiment of the present invention.

[0070] Figure 11 A structural diagram of the song list acquisition module provided in an embodiment of the present invention.

[0071] Figure 12 A schematic diagram of the structure of a generation module provided in an embodiment of the present invention.

[0072] Figure 13 A second structural diagram of the playlist recommendation device provided in an embodiment of the present invention.

[0073] Figure 14 A schematic diagram of the structure of a server provided in an embodiment of the present invention.

[0074] Figure 15 A schematic diagram of the structure of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0075] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0076] Embodiments of the present invention relate to the field of artificial intelligence (AI). AI refers to the theories, methods, techniques, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results. In other words, AI is a comprehensive technology within computer science that attempts to understand the essence of intelligence and produce new intelligent machines that can respond in a manner similar to human intelligence. AI is the study of the design principles and implementation methods of various intelligent machines, enabling them to possess the capabilities of perception, reasoning, and decision-making.

[0077] Artificial intelligence (AI) technology is a comprehensive discipline encompassing a wide range of fields, encompassing both hardware and software technologies. Foundational AI technologies generally include sensors, specialized AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, speech processing, natural language processing, and machine learning / deep learning.

[0078] Embodiments of the present invention also relate to machine learning (ML). Machine learning is a multi-disciplinary interdisciplinary subject that involves probability theory, statistics, approximation theory, convex analysis, algorithmic complexity theory, and other disciplines. It specializes in studying how computers simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their own performance. Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent. Its applications are spread across all areas of artificial intelligence. Machine learning and deep learning generally include technologies such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and self-learning.

[0079] Embodiments of the present invention provide a playlist recommendation system, method, device, and computer-readable storage medium, which are described in detail below.

[0080] See Figure 1 , Figure 1 This is a schematic diagram of a playlist recommendation system according to an embodiment of the present invention. The system may include user-side devices and service-side devices, which are connected via the Internet, a variety of gateways, and other methods. The user-side devices include a terminal 11, and the service-side devices include a server 12 and a storage server 13.

[0081] The terminal 11 includes but is not limited to portable terminals such as mobile phones and tablets, fixed terminals such as computers, query machines, advertising machines, and various virtual terminals, etc. The server 12 and the storage server 13 include local servers and / or remote servers, etc.

[0082] Next, combine Figure 2 Explain how the playlist recommendation system recommends playlists. Figure 2 A timing diagram of the playlist recommendation system provided in an embodiment of the present invention.

[0083] In advance, the server 12 sets a plurality of user interaction tags according to the interaction mode between the user and the terminal, wherein each user interaction tag corresponds to an interaction mode. Then, a plurality of song lists to be recommended are set, and each song list to be recommended corresponds to a user interaction tag. Furthermore, the server 12 also sends a first acquisition request to the storage server 13, for obtaining the display text of the song from the storage server 13. After receiving the first acquisition request, the storage server 13 sends the display text of the song to the server 12. The server 12 then obtains the trigger text from the display text, determines the user interaction tag corresponding to the trigger text, and finally classifies the song into the song list to be recommended corresponding to the user interaction tag. The server 12 also obtains the lyrics content containing the trigger text from the display text of the song; and sets the lyrics content as the target display text of the song under the user interaction tag.

[0084] In the actual playlist recommendation process, the user first initiates a playlist recommendation request to the server 12 through the operation terminal 11. After receiving the playlist recommendation request, the server 12 first obtains the user interaction tag. Then it obtains the song list to be recommended corresponding to the user interaction tag, and the song list to be recommended includes multiple songs to be recommended. Then the server 12 sends a second acquisition request to the storage server 13, requesting to obtain the target display text corresponding to the song to be recommended under the user interaction tag. After receiving the second acquisition request, the storage server 13 sends the target display text to the server 12. The server 12 then generates recommendation information based on the target display text, and finally sends the recommendation information to the terminal 11. After receiving the recommendation information, the terminal 11 displays the recommendation information.

[0085] like Figure 3 As shown, the above-mentioned server and terminal can be a node in a distributed system, wherein the distributed system can be a blockchain system, and the blockchain system can be a distributed system formed by connecting multiple nodes through network communication. The nodes can form a peer-to-peer (P2P) network. Any form of computer equipment, such as servers, terminals and other electronic devices, can become a node in the blockchain system by joining the peer-to-peer network. The blockchain includes a series of blocks that are connected to each other in the order of their generation. Once a new block is added to the blockchain, it will not be removed. The block records the record data submitted by the nodes in the blockchain system.

[0086] In one embodiment, the user interaction tag includes a preference tag. After obtaining the playlist to be recommended corresponding to the preference tag, the server may also store the preference tag and the playlist to be recommended corresponding to the preference tag in the blockchain. Other nodes in the blockchain can obtain the playlist to be recommended based on the preference tag, thus enabling playlist sharing.

[0087] In an embodiment of the present invention, the invention will be described from the perspective of a playlist recommendation device, and the playlist recommendation method device can be specifically integrated into a server.

[0088] A playlist recommendation method includes: obtaining a user interaction tag based on a recommendation request sent by a terminal; obtaining a to-be-recommended playlist corresponding to the user interaction tag, the to-be-recommended playlist including a plurality of to-be-recommended songs; obtaining a target display text corresponding to the user interaction tag from the display text of the to-be-recommended songs; generating recommendation information based on the target display text; and sending the recommendation information to the terminal so that the terminal displays the recommendation information.

[0089] Please refer to Figure 4 , Figure 4 A flowchart of a playlist recommendation method provided by an embodiment of the present invention, which may include:

[0090] Step S101: Obtain a user interaction tag according to a recommendation request sent by a terminal.

[0091] Among them, user interaction tags can be set from multiple dimensions. For example, from the dimension of the time when the user operates the terminal, user interaction tags such as "morning", "morning", "afternoon" and "evening" can be set. From the dimension of the user's mood when operating the terminal, user interaction tags such as "happy", "frustrated" and "calm" can be set. For example, from the dimension of the user's preference for operating the terminal, user interaction tags such as "light music", "Cantonese golden songs" and "drama" can be set. The settings of the above user interaction tags can simulate, extend and expand the interaction status between the user and the terminal, thereby improving the interactivity between the user and the terminal.

[0092] Specifically, such as Figure 5 As shown, a "Recommend" selection button is provided on the terminal interface. When the user clicks the "Recommend" selection button, a recommendation request is generated. At this time, the user interaction time with the terminal can be obtained as 6:00 according to the recommendation request, and the user interaction tag "morning" corresponding to 6:00 can be obtained.

[0093] Step S102: Obtain a song list to be recommended corresponding to the user interaction tag, where the song list to be recommended includes multiple songs to be recommended.

[0094] In advance, a playlist to be recommended can be set for each user interaction tag, that is, songs can be categorized according to the user interaction tag. For example, a first playlist to be recommended can be set for the user interaction tag "sadness", and a second playlist to be recommended can be set for the user interaction tag "morning". Each playlist to be recommended can include multiple songs to be recommended.

[0095] After the user interaction tag is obtained according to the recommendation request, the song list to be recommended corresponding to the user interaction tag can be obtained. For example, when the obtained user interaction tag is "morning", the second song list to be recommended is obtained.

[0096] Step S103: Obtain the target display text corresponding to the user interaction tag from the display text of the song to be recommended.

[0097] In advance, the song's audio, video, and display text information can be stored in a storage server. The display text can include the artist's name, artist's profile picture, and lyrics. This way, after obtaining a playlist to be recommended, the corresponding display text can be quickly searched from the storage server for each song in the playlist, and the target display text corresponding to the user's interaction tag can be obtained from the display text.

[0098] In advance, multiple trigger texts can be set for each user interaction tag. For example, the trigger text of the user interaction tag "sadness" can include "sad", "hug", "don't cry", "lonely" and "comfort", etc. The trigger text of the user interaction tag "morning" can include "sunrise", "wake up" and "wake up", etc. If the display text of the song contains a trigger text, the user interaction tag corresponding to the trigger text can be found, and the song can be classified into the recommended playlist corresponding to the user interaction tag.

[0099] Assume that the song to be recommended is "Tomorrow is Good" and the user interaction tag is "Sadness". The display text of the song to be recommended "Tomorrow is Good" stored in the storage server includes the first lyrics: Gently wake up the sleeping heart, slowly open your eyes, and see if the world is still spinning alone. After obtaining the first lyrics, you can search whether the first lyrics include trigger texts such as "sad", "hold", "don't cry", "lonely" and "comfort". Since the first lyrics contain the trigger text "loneliness", and therefore the lyrics content where the trigger text "loneliness" is located is "see if the world is still spinning alone". Therefore, the lyrics content of "see if the world is still spinning alone" can be set as the target display text of the song "Tomorrow is Good" in the user interaction tag "Sadness".

[0100] In summary, when the song to be recommended is "Tomorrow is Good", its target display text in the user interaction tag "Sadness" can be obtained: See if the world is still turning alone.

[0101] Step S104: Generate recommendation information based on the target display text.

[0102] In one embodiment, the target display text can be directly set as the recommendation information. In one embodiment, the singer information of the song to be recommended can be obtained first. Then, based on the singer information and the target display text, the recommendation information in a conversational format is generated.

[0103] The singer information may include the singer's name, and the specific dialog-formatted recommendation information may be "singer's name + target display text" or "target display text + singer's name." In one embodiment, the singer information may also include the singer's portrait. The specific dialog-formatted recommendation information may be "singer's portrait + singer's name + target display text" or "target display text + singer's name + singer's portrait."

[0104] Step S105: Send the recommendation information to the terminal so that the terminal displays the recommendation information.

[0105] After the recommended information in the conversation format is sent to the terminal, the terminal will display the recommended information in the conversation format. Figure 6As shown, when the singer information includes the singer's name, the terminal displays "Singer A: Remember to keep smiling when you welcome the first ray of sunshine." This simulates a conversation between the singer and the user, improving the interactivity between the user and the terminal.

[0106] The playlist recommendation method provided by an embodiment of the present invention first obtains a user interaction tag and a playlist to be recommended corresponding to the user interaction tag. Then, based on the display text of the song to be recommended in the playlist, it obtains the target display text for the song under the user interaction tag. Recommendation information is then generated based on the target display text. Finally, the recommendation information is sent to the terminal for display. This solution not only simulates, extends, and expands the interaction between the user and the terminal by setting the user interaction tag, thereby improving the interactivity between the user and the terminal, but also obtains the target display text based on the user interaction tag, making the recommendation information generated based on the target display text more accurate, further improving the accuracy of the interaction between the terminal and the user.

[0107] The playlist recommendation method described in the above embodiment will be further described below with examples. In the embodiment of the present invention, the playlist recommendation device will be described from the perspective of the playlist recommendation device, which can be integrated into a server.

[0108] Please refer to Figure 7 , Figure 7 Another flow chart of a playlist recommendation method provided by an embodiment of the present invention, the method may include:

[0109] Step S201 : setting a plurality of user interaction tags according to the interaction mode between the user and the terminal, wherein each user interaction tag corresponds to an interaction mode.

[0110] The user interaction tag may be a time tag, a mood tag, a preference tag, etc. Specifically, a plurality of user interaction tags may be set according to the interaction mode between the terminal and the user.

[0111] In one embodiment, user interaction labels can be set based on the time the user interacts with the terminal. The interaction time within a day can be set to three user interaction labels: "Morning," "Morning," "Afternoon," and "Evening." The interaction time within a week can also be set to "Workday" and "Holiday."

[0112] In one embodiment, user interaction labels may be set according to the interaction mood of the user with the terminal, such as "happy", "frustrated", and "calm".

[0113] In one embodiment, a user interaction tag may be set according to the interaction preference between the user and the terminal, such as a "preference" user interaction tag.

[0114] The settings of the above user interaction tags can simulate, extend and expand the interaction state between the user and the terminal, thereby improving the interactivity between the user and the terminal.

[0115] Step S202: Set multiple song lists to be recommended, and make each song list to be recommended correspond to a user interaction tag.

[0116] A playlist of recommended songs can be set for each user interaction tag, that is, songs can be categorized according to the user interaction tag. For example, a first playlist of recommended songs can be set for the user interaction tag "sadness," and a second playlist of recommended songs can be set for the user interaction tag "morning." Each playlist of recommended songs can include multiple songs.

[0117] Step S203, obtaining a trigger text from the display text of the song; determining a user interaction tag corresponding to the trigger text; and classifying the song into a to-be-recommended playlist corresponding to the user interaction tag.

[0118] For example, each user interaction tag can be set with multiple trigger texts. For example, the trigger texts for the user interaction tag "sadness" can include "sad", "hug", "don't cry", "lonely" and "comfort", etc. The trigger texts for the user interaction tag "morning" can include "sunrise", "wake up" and "wake up", etc. If the display text of a song contains a trigger text, the user interaction tag corresponding to the trigger text can be found, and the song can be classified into the playlist to be recommended corresponding to the user interaction tag.

[0119] In advance, the song's audio, video, and display text information can be stored in a storage server. The display text can include the artist's name, artist's profile picture, and lyrics. In this way, after obtaining a playlist to be recommended, the corresponding display text can be quickly searched from the storage server based on the songs in the playlist.

[0120] like Figure 6 As shown, for example, the song "Tomorrow is Good" has the following display text: "Gently awaken the sleeping heart, slowly open your eyes, and see if the world continues to spin around in loneliness." These lyrics contain the trigger text "loneliness," which corresponds to the user interaction tag "sadness." Therefore, the song "Tomorrow is Good" can be categorized into the first recommended playlist corresponding to the user interaction tag "sadness."

[0121] It should be noted that a song's display text usually includes multiple trigger texts, and different trigger texts correspond to different user interaction tags. Therefore, the same song may be classified into different playlists to be recommended. Figure 6As shown, the song "Tomorrow Will Be Good" also includes the trigger text "Wake Up", and the trigger text "Wake Up" corresponds to the user interaction label "Morning", so the song "Tomorrow Will Be Good" can also be classified into the second recommended playlist corresponding to the user interaction label "Morning".

[0122] Step S204: Obtain the lyrics content including the trigger text from the display text of the song; and set the lyrics content as the target display text of the song under the user interaction tag.

[0123] like Figure 6 As shown, in the song "Tomorrow is Good", the lyrics containing the trigger text "wake up" are "gently wake up the sleeping heart", and the trigger text "wake up" corresponds to the user interaction label "morning". Therefore, "gently wake up the sleeping heart" can be set as the target display text under the user interaction label "morning" for the song "Tomorrow is Good".

[0124] Furthermore, in the song "Tomorrow Will Be Fine," the lyrics containing the trigger text "loneliness" are "See if the world is still spinning around lonely," and the trigger text "loneliness" corresponds to the user interaction tag "sadness." Therefore, "See if the world is still spinning around lonely" can be set as the target display text for the song "Tomorrow Will Be Fine" under the user interaction tag "sadness."

[0125] In summary, since a song's display text typically includes multiple trigger texts, and different trigger texts correspond to different user interaction tags, the same song may be categorized into different playlists to be recommended. Accordingly, songs to be recommended under different user interaction tags will have different target display texts.

[0126] Step S205: Obtain a user interaction tag according to the recommendation request sent by the terminal.

[0127] Specifically, such as Figure 5 As shown, a "Recommend" selection button is provided on the terminal interface. When the user clicks the "Recommend" selection button, a recommendation request is generated. At this time, the user interaction time with the terminal can be obtained as 6:00 according to the recommendation request, and the user interaction tag "morning" corresponding to 6:00 can be obtained.

[0128] In one embodiment, the recommendation request may include a first recommendation request and a second recommendation request. Figure 5As shown, a "Recommend" selection button is provided on the terminal interface. When the user clicks this button, a first recommendation request is generated. Based on this first recommendation request, the user's interaction time with the terminal is obtained as 6:00 AM, and the user interaction tag "Morning" corresponding to 6:00 AM is obtained. Furthermore, based on this first recommendation request, a "Mood" selection button and a "Preference" button can be displayed on the terminal interface. When the user clicks the "Preference" selection button, a second recommendation request is generated. Based on this second recommendation request, the server obtains the user interaction tag "Preference".

[0129] Step S206: Obtain a song list to be recommended corresponding to the user interaction tag, where the song list to be recommended includes multiple songs to be recommended.

[0130] Specifically, when the song to be recommended is "Tomorrow is Good", the target display text corresponding to it under the user interaction tag "Sadness" can be obtained as: See if the world is still spinning alone.

[0131] In summary, after obtaining the user interaction tag according to the recommendation request, the song list to be recommended corresponding to the user interaction tag can be obtained. For example, when the obtained user interaction tag is "morning", the second song list to be recommended is obtained.

[0132] In one embodiment, when the user interaction tag includes a preference tag, after obtaining the song list to be recommended corresponding to the user interaction tag, the song list to be recommended corresponding to the preference tag can also be updated. The following describes the detailed steps of the update:

[0133] (A1) Obtaining the acquisition frequency of each song list to be recommended, and determining at least two song lists to be recommended whose acquisition frequencies meet a preset condition.

[0134] (B1) Obtaining duplicate songs to be recommended from at least two to-be-recommended playlists, and classifying the duplicate songs to be recommended into the to-be-recommended playlist corresponding to the preference tag.

[0135] Each time a playlist to be recommended is obtained, its frequency of acquisition is increased by 1. In this way, the preference of each playlist to be recommended can be determined based on its frequency of acquisition. The higher the acquisition frequency, the more preferred the playlist to be recommended is by the user. Specifically, at least two playlists to be recommended with an acquisition frequency higher than a preset frequency can be selected, and then duplicate songs to be recommended can be searched from the at least two playlists to be recommended. Finally, the duplicate songs to be recommended are classified into the playlist to be recommended corresponding to the preference tag, so as to update the tracks in the playlist to be recommended corresponding to the preference tag, thereby improving the accuracy of playlist recommendations when making recommendations based on user preferences.

[0136] In one embodiment, the user preference tag and the playlist to be recommended corresponding to the user preference tag can be stored in the blockchain. Other nodes in the blockchain can obtain the playlist to be recommended based on the preference tag, thus enabling playlist sharing.

[0137] In one embodiment, since the target display texts corresponding to the songs to be recommended in different playlists may be different, the following methods may be adopted to improve the accuracy of the target display texts:

[0138] (A2) When repeated songs to be recommended correspond to multiple target display texts with different contents, obtain the acquisition frequencies of the multiple target display texts with different contents.

[0139] (B2) Determining a target display text from the plurality of target display texts with different contents according to the acquisition frequency of the plurality of target display texts with different contents, and using it as the target display text corresponding to the repeated preset song under the preference tag.

[0140] Similarly, based on the acquisition frequencies of multiple target display texts with different contents, the target display text with the highest acquisition frequency can be selected as the target display text corresponding to the repeated preset song under the preference tag. If the acquisition frequencies are the same, a target display text can be randomly selected as the target display text corresponding to the repeated preset song under the preference tag.

[0141] Furthermore, when the user interaction tag is a preference tag, obtaining a song list to be recommended corresponding to the user interaction tag, where the song list to be recommended includes multiple songs to be recommended, further includes:

[0142] (A3) Obtain the user's account information.

[0143] (B3) Obtain the playlist to be recommended corresponding to the preference tag based on the user's account information.

[0144] If the user interaction tag is a time tag, the specific time tag can be determined by calling the system time. If the user interaction tag is a mood tag, the specific mood tag can be determined by selecting the current user's mood. When the user interaction tag is a preference tag, targeted updates are required based on changes in user preferences across different accounts. Therefore, when recommending playlists based on preference tags, the user's account information is first obtained, and then the playlists to be recommended corresponding to the preference tags are obtained based on the user's account information.

[0145] Step S207: Obtain the target display text corresponding to the user interaction tag from the display text of the song to be recommended.

[0146] Assume that the song to be recommended is "Tomorrow is Good" and the user interaction tag is "Sadness". The display text of the song to be recommended "Tomorrow is Good" stored in the storage server includes the first lyrics: Gently wake up the sleeping heart, slowly open your eyes, and see if the world is still spinning alone. After obtaining the first lyrics, you can search whether the first lyrics include trigger texts such as "sad", "hold", "don't cry", "lonely" and "comfort". Since the first lyrics contain the trigger text "loneliness", and therefore the lyrics content where the trigger text "loneliness" is located is "see if the world is still spinning alone". Therefore, the lyrics content of "see if the world is still spinning alone" can be set as the target display text of the song "Tomorrow is Good" in the user interaction tag "Sadness".

[0147] Step S208: Generate recommendation information based on the target display text;

[0148] In one embodiment, the target display text can be directly set as the recommendation information. In one embodiment, the singer information of the song to be recommended can be obtained first. Then, based on the singer information and the target display text, the recommendation information in a conversational format is generated.

[0149] The singer information may include the singer's name, and the specific dialog-formatted recommendation information may be "singer's name + target display text" or "target display text + singer's name." In one embodiment, the singer information may also include the singer's portrait. The specific dialog-formatted recommendation information may be "singer's portrait + singer's name + target display text" or "target display text + singer's name + singer's portrait."

[0150] Step S209: Send the recommendation information to the terminal so that the terminal displays the recommendation information.

[0151] After the recommended information in the conversation format is sent to the terminal, the terminal will display the recommended information in the conversation format. Figure 6 As shown, when the singer information includes the singer's name, the terminal displays "Singer A: Remember to keep smiling when you welcome the first ray of sunshine." This simulates a conversation between the singer and the user, improving the interactivity between the user and the terminal.

[0152] The playlist recommendation method provided by an embodiment of the present invention first obtains user interaction tags and the playlist to be recommended corresponding to the user interaction tags. Then, based on the display text of the songs to be recommended in the playlist, it obtains the target display text corresponding to the user interaction tags. Recommendation information is then generated based on the target display text. Finally, the recommendation information is sent to the terminal for display. This solution not only simulates, extends, and expands the interaction between the user and the terminal by setting user interaction tags, thereby improving the interactivity between the user and the terminal, but also obtains the target display text based on the user interaction tags, making the recommendation information generated based on the target display text more accurate, further improving the accuracy of the interaction between the terminal and the user.

[0153] The playlist recommendation method described in the above embodiment will be further described below with examples. In the embodiment of the present invention, the playlist recommendation device will be described from the perspective of the playlist recommendation device, which can be integrated in a terminal.

[0154] Please refer to Figure 8 , Figure 8 Another flow chart of a playlist recommendation method provided by an embodiment of the present invention, the method may include:

[0155] Step S301, sending a recommendation request to the server, so that the server obtains the user interaction tag through the recommendation request; the user interaction tag is used by the server to obtain the song list to be recommended corresponding to the user interaction tag, and the song list to be recommended includes multiple songs to be recommended; the display text of the song to be recommended is used for the server to obtain the target display text corresponding to the user interaction tag; the target display text is used for the server to generate recommendation information.

[0156] In advance, the server can set a song list to be recommended for each user interaction tag, that is, it can classify songs according to the user interaction tag. For example, a second song list to be recommended is set for the user interaction tag "morning". Each song list to be recommended can include multiple songs to be recommended.

[0157] After obtaining the user interaction tag according to the recommendation request, the server can obtain the song list to be recommended corresponding to the user interaction tag. For example, when the obtained user interaction tag is "morning", the second song list to be recommended is obtained.

[0158] In advance, the song's audio, video, and display text information can be stored in a storage server. The display text can include the artist's name, artist's profile picture, and lyrics. This way, after the server obtains a list of songs to be recommended, it can quickly search the storage server for the corresponding display text based on the songs in the list, and then retrieve the target display text corresponding to the user's interaction tag from the display text.

[0159] The server can pre-set multiple trigger texts for each user interaction tag. For example, the trigger texts for the user interaction tag "morning" can include "sunrise," "wake up," and "wake up." If the song's display text contains trigger text, the server can find the user interaction tag corresponding to the trigger text and classify the song into the recommended playlist corresponding to the user interaction tag.

[0160] Assume that the song to be recommended is "Tomorrow is Good" and the user interaction tag is "Morning". The display text of the song to be recommended "Tomorrow is Good" stored in the storage server includes the lyrics: Gently wake up the sleeping atrium, slowly open your eyes, and see if the world is still spinning alone. After obtaining the first lyrics, you can search whether the lyrics include trigger texts such as "sunrise", "wake up" and "wake up". Since the lyrics contain the trigger text "wake up", and the lyrics content of the trigger text "wake up" is "gently wake up the sleeping atrium". Therefore, the lyrics content of "gently wake up the sleeping atrium" can be set as the target display text of the song "Tomorrow is Good" under the user interaction tag "Morning".

[0161] In summary, when the song to be recommended is "Tomorrow is Good", the server can obtain its target display text in the user interaction tag "Sadness": See if the world is still turning lonely. And send the target display text to the terminal.

[0162] Furthermore, the server may also obtain information about the singer of the song to be recommended, and combine the information with the target display text to form recommendation information and send it to the terminal. Specifically, the singer information may include the singer's name and / or head portrait.

[0163] Step S302: Receive recommendation information.

[0164] In one embodiment, after receiving the recommendation information, the terminal may display the recommendation information in the following manner:

[0165] S303: Setting the recommendation information into a conversation format recommendation information.

[0166] S304: Scroll and display the recommended information in a dialog format.

[0167] Specifically, the terminal can set the recommendation information to the dialog format of "singer name + target display text" or "target display text + singer name". The terminal can also set the recommendation information to the dialog format of "singer portrait + singer name + target display text" or "target display text + singer name + singer portrait". Finally, if Figure 9 As shown, the recommended information in a dialog format is scrolled and displayed on the terminal interface.

[0168] Furthermore, the terminal can also obtain a play request, which is triggered when the target recommendation information is selected, wherein the target recommendation information is one of multiple dialog-format recommendation information; stop scrolling the target recommendation information, and play the song to be recommended corresponding to the target recommendation information.

[0169] like Figure 5 As shown, after the target recommendation "Singer A: Remember to Keep Smiling When You Welcome the First Sunshine" is selected, a play request is generated. In response to this play request, the terminal stops scrolling the target recommendation and plays the corresponding song, "Good Morning! Come On!" During this process, other recommendations continue to scroll. It should be noted that the target recommendation can be changed to the format of song title + singer information.

[0170] The playlist recommendation method provided by an embodiment of the present invention first sends a recommendation request to a server, allowing the server to obtain a user interaction tag through the recommendation request. The user interaction tag is used by the server to obtain a playlist to be recommended corresponding to the user interaction tag, and the playlist to be recommended includes multiple songs to be recommended. The display text of the songs to be recommended is used by the server to obtain target display text corresponding to the user interaction tag. The target display text is used by the server to generate recommendation information. The server then receives the recommendation information and sets the recommendation information into a conversational format. Finally, the conversational format recommendation information is displayed in a scrolling manner. This solution not only simulates, extends, and expands the interaction between the user and the terminal by setting the user interaction tag, thereby improving the interactivity between the user and the terminal, but also obtains the target display text based on the user interaction tag, making the recommendation information generated based on the target display text more accurate, further improving the accuracy of the interaction between the terminal and the user.

[0171] According to the method described in the above embodiment, this embodiment will be further described from the perspective of a song list recommendation device, which can be integrated into a server.

[0172] Please refer to Figure 10 , Figure 10 This is a structural diagram of a playlist recommendation device provided in an embodiment of the present invention. The playlist recommendation device 40 includes a tag acquisition module 401, a playlist acquisition module 402, a text acquisition module 403, a generation module 404 and a sending module 405.

[0173] In one embodiment, the playlist recommendation device 40 further includes a first setting module 406 and a second setting module 407. The first setting module 406 is configured to set multiple user interaction tags based on the user's interaction method with the terminal, where each user interaction tag corresponds to an interaction method. The second setting module 407 is configured to set multiple playlists to be recommended, and each playlist to be recommended is associated with a user interaction tag.

[0174] The user interaction tag may be a time tag, a mood tag, a preference tag, etc. Specifically, the first setting module 406 may set a plurality of user interaction tags according to the interaction mode between the terminal and the user.

[0175] In one embodiment, the first setting module 406 can set user interaction labels based on the time the user interacts with the terminal. The interaction time within a day can be set as three user interaction labels: "Morning," "Forenoon," "Afternoon," and "Evening." The interaction time within a week can also be set as "Workday" and "Holiday."

[0176] In one embodiment, the first setting module 406 may set user interaction labels according to the interaction mood of the user with the terminal, such as user interaction labels such as “happy”, “frustrated”, and “calm”.

[0177] In one embodiment, the first setting module 406 may set a user interaction tag according to the interaction preference between the user and the terminal, such as a "preference" user interaction tag.

[0178] The settings of the above user interaction tags can simulate, extend and expand the interaction state between the user and the terminal, thereby improving the interactivity between the user and the terminal.

[0179] The second setting module 407 can set a song list to be recommended for each user interaction tag. In other words, the second setting module 407 can classify songs according to the user interaction tag. For example, a first song list to be recommended can be set for the user interaction tag "sadness," and a second song list to be recommended can be set for the user interaction tag "morning." Each song list to be recommended can include multiple songs to be recommended.

[0180] In one embodiment, the playlist recommendation device 40 further includes a trigger acquisition module 408, a tag module 409, and a first classification module 410. The trigger acquisition module 408 is configured to acquire trigger text from the song's display text. The tag module 409 is configured to determine the user interaction tag corresponding to the trigger text. The first classification module 410 is configured to classify the song into a playlist to be recommended corresponding to the user interaction tag.

[0181] For example, each user interaction tag can be set with multiple trigger texts. For example, the trigger texts for the user interaction tag "sadness" can include "sad", "hug", "don't cry", "lonely" and "comfort", etc. The trigger texts for the user interaction tag "morning" can include "sunrise", "wake up" and "wake up", etc. If the display text of a song contains a trigger text, the user interaction tag corresponding to the trigger text can be found, and the song can be classified into the playlist to be recommended corresponding to the user interaction tag.

[0182] In advance, the song's audio, video, and display text information can be stored in a storage server. The display text can include the artist's name, artist's profile picture, and lyrics. In this way, after obtaining a playlist to be recommended, the corresponding display text can be quickly searched from the storage server based on the songs in the playlist.

[0183] like Figure 6 As shown, taking the song "Tomorrow is Good" as an example, its displayed text includes the lyrics: "Gently awaken the sleeping heart, slowly open your eyes, and see if the world still spins lonely." First, the trigger acquisition module 408 can find the trigger text "loneliness" from the above lyrics. Then, the tag module 409 can match the trigger text "loneliness" with the user interaction tag "sadness." Therefore, the first classification module 410 can classify the song "Tomorrow is Good" into the first recommended song list corresponding to the user interaction tag "sadness."

[0184] It should be noted that a song's display text usually includes multiple trigger texts, and different trigger texts correspond to different user interaction tags. Therefore, the first classification module 410 may classify the same song into different to-be-recommended playlists. Figure 6 As shown, the trigger acquisition module 408 can also find the trigger text "wake up" from the song "Tomorrow is Good", and the label module 409 determines that the trigger text "wake up" corresponds to the user interaction label "morning", so the first classification module 410 can also classify the song "Tomorrow is Good" into the second to-be-recommended song list corresponding to the user interaction label "morning".

[0185] In one embodiment, the playlist recommendation device 40 further includes a content acquisition module 411 and a third setting module 412. The content acquisition module 411 is configured to acquire lyrics containing trigger text from the song's display text. The third setting module 412 is configured to set the lyrics as the target display text for the song under the user interaction tag.

[0186] like Figure 6 As shown, in the song "Tomorrow is Good", the content acquisition module 411 determines that the lyrics containing the trigger text "wake up" are "gently wake up the sleeping heart", and the trigger text "wake up" corresponds to the user interaction tag "morning". Therefore, the third setting module 412 can set "gently wake up the sleeping heart" as the target display text under the user interaction tag "morning" for the song "Tomorrow is Good".

[0187] Furthermore, in the song "Tomorrow Will Be Fine," the content acquisition module 411 determines that the lyrics containing the trigger text "loneliness" are "See if the world still keeps turning lonely," and the trigger text "loneliness" corresponds to the user interaction tag "sadness." Therefore, the third setting module 412 can set "See if the world still keeps turning lonely" as the target display text for the song "Tomorrow Will Be Fine" under the user interaction tag "sadness."

[0188] In summary, since a song's display text typically includes multiple trigger texts, and different trigger texts correspond to different user interaction tags, the same song may be categorized into different playlists to be recommended. Accordingly, songs to be recommended under different user interaction tags will have different target display texts.

[0189] (1) Tag acquisition module 401

[0190] The tag acquisition module 401 is used to acquire user interaction tags according to the recommendation request sent by the terminal. Figure 5 As shown, a "Recommend" selection button is provided on the terminal interface. When the user clicks the "Recommend" selection button, a recommendation request is generated. At this time, the tag acquisition module 401 can obtain the user interaction time between the user and the terminal as 6:00 according to the recommendation request, and then obtain the user interaction tag "Morning" corresponding to 6:00.

[0191] In one embodiment, the recommendation request may include a first recommendation request and a second recommendation request. Figure 5 As shown, a "Recommend" selection button is provided on the terminal interface. When the user clicks the "Recommend" selection button, it will trigger the generation of a first recommendation request. At this time, the label acquisition module 401 can obtain the user interaction time with the terminal as 6:00 according to the first recommendation request, and then obtain the user interaction label "Morning" corresponding to 6:00. Furthermore, the label acquisition module 401 can also display the "Mood" selection button and the "Preference" button on the terminal interface according to the first recommendation request. When the user clicks the "Preference" selection button, a second recommendation request is generated. Based on the second recommendation request, the server obtains the user interaction label of "Preference" through the label acquisition module 401.

[0192] (2) Song list acquisition module 402

[0193] The song list acquisition module 402 is used to obtain a song list to be recommended corresponding to the user interaction tag, and the song list to be recommended includes multiple songs to be recommended.

[0194] Specifically, when the song to be recommended is "Tomorrow Will Be Good", the playlist acquisition module 402 can obtain its target display text under the user interaction tag "Sadness" as: See if the world is still spinning alone.

[0195] In summary, when the user interaction tag is obtained according to the recommendation request, the song list acquisition module 402 can obtain the song list to be recommended corresponding to the user interaction tag. For example, when the obtained user interaction tag is "morning", the song list acquisition module 402 obtains the second song list to be recommended.

[0196] In one embodiment, when the user interaction tag includes a preference tag, the playlist recommendation device 40 further includes a storage module 417. Storage module 417 is configured to store the preference tag and the playlist to be recommended corresponding to the preference tag in the blockchain. Other nodes in the blockchain can obtain the playlist to be recommended based on the preference tag, thereby enabling playlist sharing.

[0197] In one embodiment, when the user interaction tag includes a preference tag, the playlist recommendation device 40 further includes: a first frequency module 413 and a second classification module 414. The first frequency module 413 is used to obtain the acquisition frequency of each playlist to be recommended, and to determine at least two playlists to be recommended whose acquisition frequencies meet preset conditions. The second classification module 414 is used to obtain repeated songs to be recommended from at least two playlists to be recommended, and to classify the repeated songs to be recommended into the playlist to be recommended corresponding to the preference tag. After obtaining the playlist to be recommended corresponding to the user interaction tag, the playlist to be recommended corresponding to the preference tag can also be updated through the first frequency module 413 and the second classification module 414.

[0198] Specifically, every time a song list to be recommended is obtained, its acquisition frequency is increased by 1. In this way, the preference of each song list to be recommended can be determined based on its acquisition frequency. Among them, the higher the acquisition frequency, the more preferred the song list to be recommended is by the user. Specifically, the first frequency module 413 can select at least two song lists to be recommended with an acquisition frequency higher than a preset frequency, and then search for duplicate songs to be recommended from the at least two song lists to be recommended. Finally, the second classification module 414 classifies the duplicate songs to be recommended into the song list to be recommended corresponding to the preference label, so as to update the tracks in the song list to be recommended corresponding to the preference label, thereby improving the accuracy of song list recommendations when making recommendations based on user preferences.

[0199] In one embodiment, the playlist recommendation device 40 further includes a second frequency module 415 and a text determination module 416. The second frequency module 415 is configured to obtain the acquisition frequencies of multiple target display texts with different contents when a repeated song to be recommended corresponds to multiple target display texts with different contents. The text determination module 416 is configured to determine a target display text from the multiple target display texts with different contents based on the acquisition frequencies of the multiple target display texts with different contents, to be used as the target display text corresponding to the repeated preset song under the preference tag.

[0200] Since the target display texts corresponding to the songs to be recommended in different to-be-recommended playlists may have different contents, the second frequency module 415 and the text determination module 416 may be provided to improve the accuracy of the target display text.

[0201] Similarly, the second frequency module 415 can also obtain the acquisition frequencies of multiple target display texts with different contents. The text determination module 416 can also select the target display text with the highest acquisition frequency from the multiple target display texts with different contents as the target display text corresponding to the repeated preset song under the preference tag. If the acquisition frequencies are the same, a target display text can be randomly selected as the target display text corresponding to the repeated preset song under the preference tag.

[0202] In one embodiment, if Figure 11 As shown, the playlist acquisition module 402 further includes: an account acquisition submodule 4021 and a playlist acquisition submodule 4022. The account acquisition submodule 4021 is used to obtain the user's account information. The playlist acquisition submodule 4022 is used to obtain a playlist to be recommended corresponding to the preference tag based on the user's account information.

[0203] If the user interaction tag is a time tag, the specific time tag can be determined by calling the system time. If the user interaction tag is a mood tag, the specific mood tag can be determined by selecting the current user's mood. When the user interaction tag is a preference tag, specific updates are required based on changes in user preferences across different accounts. Therefore, when recommending playlists based on preference tags, the account acquisition submodule 4021 first obtains the user's account information, and the playlist acquisition submodule 4022 then uses the user's account information to obtain the playlist to be recommended corresponding to the preference tag.

[0204] (3) Text Acquisition Module 403

[0205] The text acquisition module 403 is used to acquire the target display text of the song to be recommended under the user interaction tag from the display text of the song to be recommended.

[0206] Assume that the song to be recommended is "Tomorrow is Good" and the user interaction tag is "Sadness". The display text of the song to be recommended "Tomorrow is Good" stored in the storage server includes the first lyrics: Gently wake up the sleeping heart, slowly open your eyes, and see if the world is still spinning alone. After obtaining the first lyrics, the text acquisition module 403 can search whether the first lyrics include trigger texts such as "sad", "hold", "don't cry", "lonely" and "comfort". Since the first lyrics contain the trigger text "loneliness", and therefore the lyrics content where the trigger text "loneliness" is located is "see if the world is still spinning alone". Therefore, the text acquisition module 403 can set the lyrics content of "see if the world is still spinning alone" as the target display text of the song "Tomorrow is Good" in the user interaction tag "Sadness".

[0207] (4) Generate module 404

[0208] The generating module 404 is used to generate recommendation information according to the target display text.

[0209] In one embodiment, the generation module 404 may directly set the target display text as the recommendation information. In one embodiment, the generation module 404 may also first obtain the singer information of the song to be recommended, and then generate the recommendation information in a conversational format based on the singer information and the target display text.

[0210] The singer information may include the singer's name, and the specific dialog-formatted recommendation information may be "singer's name + target display text" or "target display text + singer's name." In one embodiment, the singer information may also include the singer's portrait. The specific dialog-formatted recommendation information may be "singer's portrait + singer's name + target display text" or "target display text + singer's name + singer's portrait."

[0211] In one embodiment, if Figure 12 As shown, the generation module 404 includes a singer acquisition submodule 4041 and a generation submodule 4042. The singer acquisition submodule 4041 is used to obtain singer information of the song to be recommended. The generation submodule 4042 is used to generate recommendation information in a conversational format based on the singer information and the target display text.

[0212] (5) Sending module 405

[0213] The sending module 405 is used to send the recommendation information to the terminal so that the terminal can display the recommendation information. After the recommendation information in the dialogue format is sent to the terminal, the terminal will display the recommendation information in the dialogue format. Figure 6 As shown, when the singer information includes the singer's name, the terminal displays "Singer A: Remember to keep smiling when you welcome the first ray of sunshine." This simulates a conversation between the singer and the user, improving the interactivity between the user and the terminal.

[0214] The playlist recommendation device provided in an embodiment of the present invention first obtains user interaction tags and the playlist to be recommended corresponding to the user interaction tags. It then obtains target display text corresponding to the user interaction tags based on the display text of the songs to be recommended in the playlist. It then generates recommendation information based on the target display text, and finally sends the recommendation information to the terminal for display. This solution not only simulates, extends, and expands the interaction between the user and the terminal by setting user interaction tags, thereby improving the interactivity between the user and the terminal, but also obtains target display text based on the user interaction tags, making the recommendation information generated based on the target display text more accurate, further improving the accuracy of the interaction between the terminal and the user.

[0215] Please refer to Figure 13 , Figure 13 This is a structural diagram of a song list recommendation device provided in an embodiment of the present invention. The song list recommendation device 50 includes: a request module 501, a receiving module 502, a recommendation setting module 503 and a scrolling module 504.

[0216] The request module 501 is used to send a recommendation request to the server, so that the server obtains the user interaction tag through the recommendation request; the user interaction tag is used by the server to obtain the song list to be recommended corresponding to the user interaction tag, and the song list to be recommended includes multiple songs to be recommended; the display text of the song to be recommended is used to enable the server to obtain the target display text corresponding to the user interaction tag; the target display text is used by the server to generate recommendation information.

[0217] In advance, the server can set a song list to be recommended for each user interaction tag, that is, it can classify songs according to the user interaction tag. For example, a second song list to be recommended is set for the user interaction tag "morning". Each song list to be recommended can include multiple songs to be recommended.

[0218] After obtaining the user interaction tag according to the recommendation request, the server can obtain the song list to be recommended corresponding to the user interaction tag. For example, when the obtained user interaction tag is "morning", the second song list to be recommended is obtained.

[0219] In advance, the song's audio, video, and display text information can be stored in a storage server. The display text can include the artist's name, artist's profile picture, and lyrics. This way, after the server obtains a list of songs to be recommended, it can quickly search the storage server for the corresponding display text based on the songs in the list, and then retrieve the target display text corresponding to the user's interaction tag from the display text.

[0220] The server can pre-set multiple trigger texts for each user interaction tag. For example, the trigger texts for the user interaction tag "morning" can include "sunrise," "wake up," and "wake up." If the song's display text contains trigger text, the server can find the user interaction tag corresponding to the trigger text and classify the song into the recommended playlist corresponding to the user interaction tag.

[0221] Assume that the song to be recommended is "Tomorrow is Good" and the user interaction tag is "Morning". The display text of the song to be recommended "Tomorrow is Good" stored in the storage server includes the lyrics: Gently wake up the sleeping atrium, slowly open your eyes, and see if the world is still spinning alone. After obtaining the first lyrics, you can search whether the lyrics include trigger texts such as "sunrise", "wake up" and "wake up". Since the lyrics contain the trigger text "wake up", and the lyrics content of the trigger text "wake up" is "gently wake up the sleeping atrium". Therefore, the lyrics content of "gently wake up the sleeping atrium" can be set as the target display text of the song "Tomorrow is Good" under the user interaction tag "Morning".

[0222] In summary, when the song to be recommended is "Tomorrow is Good", after the request module 501 sends the recommendation request, the server can obtain the target display text for the user interaction tag "Sadness": See if the world is still turning lonely. And send the target display text to the terminal.

[0223] Furthermore, the server may also obtain information about the singer of the song to be recommended, and combine the information with the target display text to form recommendation information and send it to the terminal. Specifically, the singer information may include the singer's name and / or head portrait.

[0224] Next, the receiving module 502 receives the recommendation information. The recommendation setting module 503 sets the recommendation information as the recommendation information in the conversation format. The scrolling module 504 scrolls and displays the recommendation information in the conversation format.

[0225] Specifically, the recommendation setting module 503 can set the recommendation information to the dialog format of "singer name + target display text" or "target display text + singer name". The recommendation setting module 503 can also set the recommendation information to the dialog format of "singer portrait + singer name + target display text" or "target display text + singer name + singer portrait". Finally, if Figure 9 As shown, the scrolling module 504 scrolls and displays the recommended information in the dialog format on the terminal interface.

[0226] In one embodiment, when multiple conversational recommendation information is included, the playlist recommendation device 50 further includes a play acquisition module 505 and a stop module 506. The play acquisition module 505 is configured to acquire a play request, which is triggered when a target recommendation information is selected, where the target recommendation information is one of the multiple conversational recommendation information. The stop module 506 is configured to stop scrolling the target recommendation information and play the song to be recommended corresponding to the target recommendation information.

[0227] like Figure 5 As shown, after the target recommendation information "Singer A: Remember to keep smiling when you welcome the first ray of sunshine" is selected, a play request is generated. After the play acquisition module 505 obtains the play request, the stop module 506 stops scrolling the target recommendation information according to the play request and plays the song to be recommended corresponding to the target recommendation information, "Good morning! Come on!" During this process, other recommended information continues to scroll. It should be noted that the target recommendation information can be changed to the format of song name + singer information.

[0228] The playlist recommendation device provided by an embodiment of the present invention first sends a recommendation request to a server, allowing the server to obtain a user interaction tag through the recommendation request. The user interaction tag is used by the server to obtain a playlist to be recommended corresponding to the user interaction tag, and the playlist to be recommended includes multiple songs to be recommended. The display text of the songs to be recommended is used by the server to obtain target display text corresponding to the user interaction tag. The target display text is used by the server to generate recommendation information. The server then receives the recommendation information and sets the recommendation information into a conversational format. Finally, the conversational format recommendation information is scrolled and displayed. This solution not only simulates, extends, and expands the interaction between the user and the terminal by setting the user interaction tag, thereby improving the interactivity between the user and the terminal, but also obtains the target display text based on the user interaction tag, making the recommendation information generated based on the target display text more accurate, further improving the accuracy of the interaction between the terminal and the user.

[0229] Accordingly, an embodiment of the present invention further provides a server, such as Figure 14 As shown, it shows a schematic diagram of the structure of the server involved in the embodiment of the present invention, specifically:

[0230] The server may include one or more processing core processors 501, one or more computer-readable storage media memories 502, a power supply 503, an input unit 504 and other components. Those skilled in the art will appreciate that Figure 14 The server structure shown in the figure does not constitute a limitation on the server, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0231] Processor 501 is the server's control center, connecting all components of the server using various interfaces and circuits. By running or executing software programs and / or modules stored in memory 502 and accessing data stored in memory 502, it performs various server functions and processes data, thereby performing overall server testing. Optionally, processor 501 may include one or more processing cores; preferably, processor 501 may integrate an application processor and a modem processor, with the application processor primarily processing the operating system, user interface, and application programs, while the modem processor primarily handles wireless communications. It is understood that the modem processor may not be integrated into processor 501.

[0232] Memory 502 can be used to store software programs and modules. Processor 501 executes various functional applications and data processing by running the software programs and modules stored in memory 502. Memory 502 may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as sound playback or image playback). The data storage area may store data generated based on server usage. For example, it may store legitimate keywords or data retrieved from third-party servers. Memory 502 may also include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, memory 502 may also include a memory controller to provide processor 501 with access to memory 502.

[0233] The server also includes a power supply 503 for supplying power to various components. Preferably, the power supply 503 can be logically connected to the processor 501 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. The power supply 503 can also include one or more DC or AC power supplies, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and other arbitrary components.

[0234] The server may further include an input unit 504, which may be configured to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0235] Although not shown, the server may further include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 501 in the server will load the executable files corresponding to one or more application processes into the memory 502 according to the following instructions, and the processor 501 will run the application stored in the memory 502 to implement various functions as follows:

[0236] Based on the recommendation request sent by the terminal, a user interaction tag is obtained. A playlist of songs to be recommended corresponding to the user interaction tag is obtained, the playlist including multiple songs to be recommended. From the display text of the songs to be recommended, a target display text corresponding to the user interaction tag is obtained. A recommendation message is generated based on the target display text. The recommendation message is sent to the terminal, causing the terminal to display the recommendation message.

[0237] The server can achieve the effective effects that can be achieved by any playlist recommendation device provided in the embodiments of the present invention. Please refer to the previous embodiments for details and will not be repeated here.

[0238] The server provided by the embodiment of the present invention not only simulates, extends and expands the interaction status between the user and the terminal by setting user interaction tags, thereby improving the interactivity between the user and the terminal, but also obtains the target display text according to the user interaction tags, making the recommendation information generated according to the target display text more accurate, thereby further improving the accuracy of the interaction between the terminal and the user.

[0239] The embodiment of the present invention further provides a terminal, which may be a mobile phone, a tablet computer, a micro processing box, a drone, or an image acquisition device, etc. Figure 15 As shown, it shows a schematic diagram of the structure of the terminal involved in the embodiment of the present application, specifically:

[0240] The terminal may include one or more processing core processors 601, one or more computer-readable storage media memories 602, a power supply 603, an input module 604, and a communication module 605. Those skilled in the art will appreciate that Figure 15 The terminal structure shown in the figure does not constitute a limitation on the terminal, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0241] Processor 601 is the terminal's control center, connecting all components of the terminal using various interfaces and circuits. By running or executing software programs and / or modules stored in memory 602 and accessing data stored in memory 602, it executes various terminal functions and processes data, thereby performing overall terminal testing. In some embodiments, processor 601 may include one or more processing cores. In some embodiments, processor 601 may integrate an application processor and a modem processor. The application processor primarily handles the operating system, user interface, and application programs, while the modem processor primarily handles wireless communications. It is understood that the modem processor may not be integrated into processor 601.

[0242] Memory 602 can be used to store software programs and modules. Processor 601 executes various functional applications and data processing by running the software programs and modules stored in memory 602. Memory 602 may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as sound playback or image playback); the data storage area may store data generated based on terminal usage. Memory 602 may also include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, memory 602 may also include a memory controller to provide processor 601 with access to memory 602.

[0243] The terminal also includes a power supply 603 for supplying power to various components. In some embodiments, the power supply 603 can be logically connected to the processor 601 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. The power supply 603 can also include one or more DC or AC power supplies, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and other arbitrary components.

[0244] The terminal may further include an input module 604, which may be configured to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0245] The terminal may also include a communication module 605. In some embodiments, the communication module 605 may include a wireless submodule. The terminal may perform short-range wireless transmission via the wireless submodule of the communication module 605, thereby providing wireless broadband Internet access. For example, the communication module 605 may be used to help users obtain transaction data, send and receive emails, browse web pages, and access streaming media.

[0246] Although not shown, the terminal may further include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 601 in the terminal will load the executable files corresponding to the processes of one or more application programs into the memory 602 according to the following instructions, and the processor 601 will run the application programs stored in the memory 602 to implement various functions as follows:

[0247] A recommendation request is sent to the server, so that the server obtains the user interaction tag through the recommendation request; the user interaction tag is used by the server to obtain the song list to be recommended corresponding to the user interaction tag, and the song list to be recommended includes multiple songs to be recommended; the display text of the song to be recommended is used to enable the server to obtain the target display text corresponding to the user interaction tag; the target display text is used by the server to generate recommendation information; receive the recommendation information; set the recommendation information to recommendation information in a conversation format; and scroll to display the recommendation information in the conversation format.

[0248] In one embodiment, the processor 601 further implements setting the recommended information as recommended information in a conversation format and scrolling and displaying the recommended information in the conversation format.

[0249] In one embodiment, the processor 601 further implements obtaining a play request, which is triggered when a target recommendation is selected, wherein the target recommendation is one of a plurality of dialog-formatted recommendation information, stopping scrolling of the target recommendation, and playing a song to be recommended corresponding to the target recommendation.

[0250] The terminal provided by the embodiment of the present invention not only simulates, extends and expands the interaction status between the user and the terminal by setting user interaction tags, thereby improving the interactivity between the user and the terminal, but also obtains the target display text according to the user interaction tags, making the recommendation information generated according to the target display text more accurate, thereby further improving the accuracy of the interaction between the terminal and the user.

[0251] Various operations of the embodiments are provided herein. In one embodiment, one or more operations may constitute computer-readable instructions stored on one or more computer-readable media, which, when executed by a server, will cause a computing device to perform the operations. The order in which some or all operations are described should not be interpreted as implying that these operations must be order-dependent. Those skilled in the art will appreciate alternative orderings with the benefit of this specification. Furthermore, it should be understood that not all operations must be present in each embodiment provided herein.

[0252] Furthermore, although the present disclosure has been shown and described with respect to one or more implementations, equivalent variations and modifications will occur to those skilled in the art upon reading and understanding this specification and the accompanying drawings. The present disclosure includes all such modifications and variations and is limited only by the scope of the appended claims. In particular, with respect to the various functions performed by the aforementioned components (e.g., elements, resources, etc.), terms used to describe such components are intended to correspond to any component (unless otherwise indicated) that performs the designated function of the component (e.g., which is functionally equivalent), even if structurally not equivalent to the disclosed structure that performs the function in the exemplary implementations of the present disclosure shown herein. Furthermore, although particular features of the present disclosure have been disclosed with respect to only one of several implementations, such features may be combined with one or more other features of other implementations, as may be desirable and advantageous for a given or particular application. Furthermore, to the extent that the terms "include," "have," "contain," or variations thereof are used in the detailed description or claims, such terms are intended to be inclusive in a manner similar to the term "comprising."

[0253] The functional units in the embodiments of the present invention may be integrated into a single processing module, each unit may exist physically separately, or two or more units may be integrated into a single module. The aforementioned integrated module may be implemented in the form of hardware or a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium. The aforementioned storage medium may be a read-only memory, a magnetic disk, or an optical disk, etc. The aforementioned devices or systems may execute the methods in the corresponding method embodiments.

[0254] In summary, although the present invention has been disclosed above by way of embodiments, the serial numbers preceding the embodiments are used for ease of description only and do not limit the order of the embodiments of the present invention. Furthermore, the above embodiments are not intended to limit the present invention. Persons skilled in the art may make various modifications and alterations without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention shall be determined by the scope defined in the claims.

Claims

1. A song list recommendation method, characterized in that: include: Obtaining user interaction tags based on the recommendation request sent by the terminal; wherein the user interaction tags can simulate, extend, and expand the interaction state between the user and the terminal, and the user interaction tags include time tags, mood tags, and preference tags; Obtain a song list to be recommended corresponding to the user interaction tag, wherein the song list to be recommended includes multiple songs to be recommended; Obtaining a target display text corresponding to the user interaction tag from the display text of the song to be recommended; wherein the display text includes a plurality of trigger texts, and the trigger texts are used to match the corresponding user interaction tags; generating recommendation information according to the target display text; The recommendation information is sent to the terminal, so that the terminal displays the recommendation information.

2. The song list recommendation method according to claim 1, characterized in that: Before the step of obtaining the user interaction tag according to the recommendation request sent by the terminal, the method further includes: Setting a plurality of user interaction tags according to the interaction mode between the user and the terminal, wherein each user interaction tag corresponds to an interaction mode; Set up multiple playlists to be recommended, and make each playlist to be recommended correspond to a user interaction tag.

3. The song list recommendation method according to claim 2, characterized in that: After the step of setting a plurality of playlists to be recommended and making each playlist to be recommended correspond to a user interaction tag, the method further includes: Get the trigger text from the song's presentation text; Determine a user interaction tag corresponding to the trigger text; Classify the song into the song list to be recommended corresponding to the user interaction tag.

4. The song list recommendation method according to claim 3, characterized in that: After the step of determining the user interaction tag corresponding to the trigger text, the method further includes: Obtaining lyrics containing the trigger text from the display text of the song; The lyrics content is set as the target display text of the song under the user interaction tag.

5. The song list recommendation method according to any one of claims 1 to 4, characterized in that: The step of generating recommendation information according to the target display text further includes: Obtaining singer information of the song to be recommended; Generate recommendation information in a conversational format based on the singer information and the target presentation text.

6. The song list recommendation method according to any one of claims 1 to 4, characterized in that: The user interaction tag includes a preference tag, and after the step of obtaining a song list to be recommended corresponding to the user interaction tag, wherein the song list to be recommended includes a plurality of songs to be recommended, the method further includes: The preference tag and the song list to be recommended corresponding to the preference tag are stored in the blockchain.

7. The song list recommendation method according to claim 6, characterized in that: The method further includes: comprising a plurality of song lists to be recommended; after obtaining the song list to be recommended corresponding to the user interaction tag, wherein the song list to be recommended includes a plurality of songs to be recommended; Obtaining the acquisition frequency of each to-be-recommended playlist, and determining at least two to-be-recommended playlists whose acquisition frequencies meet a preset condition; Duplicate songs to be recommended are obtained from the at least two song lists to be recommended, and the duplicate songs to be recommended are classified into the song list to be recommended corresponding to the preference tag.

8. The song list recommendation method according to claim 7, characterized in that: After the step of obtaining duplicate songs to be recommended from the at least two to-be-recommended playlists and classifying the duplicate songs to be recommended into the to-be-recommended playlist corresponding to the preference tag, the method further includes: When the repeated songs to be recommended correspond to multiple target display texts with different contents, obtaining the acquisition frequencies of the multiple target display texts with different contents; According to the acquisition frequency of the multiple target display texts with different contents, a target display text is determined from the multiple target display texts with different contents, and is used as the target display text corresponding to the repeated preset song under the preference tag.

9. A song list recommendation method, characterized in that: include: Send a recommendation request to the server, so that the server obtains a user interaction tag through the recommendation request; wherein the user interaction tag can simulate, extend and expand the interaction state between the user and the terminal, and the user interaction tag includes a time tag, a mood tag and a preference tag; the user interaction tag is used by the server to obtain a to-be-recommended song list corresponding to the user interaction tag, and the to-be-recommended song list includes multiple to-be-recommended songs; the display text of the to-be-recommended song is used by the server to obtain a target display text corresponding to the user interaction tag; wherein the display text includes multiple trigger texts, and the trigger texts are used to match the corresponding user interaction tags; the target display text is used by the server to generate recommendation information; receiving the recommendation information; Configuring the recommendation information into a conversation-formatted recommendation information; The recommended information in the conversation format is displayed in a scrolling manner.

10. The song list recommendation method according to claim 9, characterized in that: The method includes a plurality of recommended information in a dialog format, and after the step of scrolling and displaying the recommended information in the dialog format, further includes: Obtaining a play request, where the play request is triggered when target recommendation information is selected, wherein the target recommendation information is one of the plurality of conversation-formatted recommendation information; Stop scrolling the target recommendation information and play the song to be recommended corresponding to the target recommendation information.

Images