Target recommendation method and device, equipment, medium and program product

Abstract

The invention discloses a target recommendation method and device, equipment, a medium and a program product, and belongs to the field of audio playing. The method comprises the steps that a first target is acquired, the first target comprises a behavior target of a music behavior historically executed by a first account on a music client, and the music behavior refers to a client behavior related to music; on the basis of the first target, a second target is inquired from a target pair of a correlation library, and the target pair comprises behavior targets of the source music behavior and the target music behavior in one behavior track; and recommending the second target on the interface of the music client. According to the method, potential recommendation requirements of the first account are mined by using massive user behavior tracks under the condition that the first target is known, so that the probability that the first account clicks the recommended second target is improved.

Description

Technical Field

[0001] The present application relates to the field of audio playback, and in particular to a target recommendation method, apparatus, device, medium, and program product. Background Art

[0002] The music client provides a function to recommend songs to users.

[0003] In related technologies, the songs recommended to users by music clients only rely on the users' historical search records or historical playback records. For example, the music client will provide songs that the user has previously searched for as recommended songs in the search portal, or the music client will recommend some popular songs or songs with similar styles to the user's historically played songs based on the user's long-term listening preferences.

[0004] However, the music client in the related art implements personalized recommendations for users, and the probability of the recommended songs being clicked by users still has room for improvement. Summary of the Invention

[0005] This application provides a target recommendation method, device, equipment, medium and program product. This application will use massive user behavior trajectories to mine the potential recommendation needs of the first account when the first target is known, so as to increase the probability of the first account clicking on the recommended second target.

[0006] According to one aspect of the present application, a target recommendation method is provided, which includes the following steps.

[0007] A first goal is obtained, where the first goal includes a behavior goal of music behaviors historically performed by the first account on the music client, where the music behavior refers to client behavior related to music.

[0008] Based on the first goal, a second goal is searched from the goal pairs in the correlation library, where the goal pair includes behavior goals of a source music behavior and a target music behavior in a behavior trajectory.

[0009] Recommend the second target on the interface of the music client.

[0010] According to another aspect of the present application, a target recommendation device is provided, which includes the following modules.

[0011] The acquisition module is used to acquire a first target, where the first target includes a behavior target of music behaviors historically performed by the first account on the music client, where the music behaviors refer to client behaviors related to music.

[0012] The query module is used to query the second target from the target pairs in the correlation library based on the first target, where the target pair includes the behavior targets of the source music behavior and the target music behavior in a behavior track.

[0013] The recommendation module is used to recommend the second target on the interface of the music client.

[0014] In an optional embodiment, the query module is further configured to query the second target from the first target pair in the correlation library based on the first target;

[0015] The first target pair includes behavioral targets of a first source music behavior and a first target music behavior in the first behavior trajectory, and the first source music behavior and the first target music behavior belong to different behavioral dimensions.

[0016] In an optional embodiment, the behavior dimensions of the first source music behavior and the first target music behavior include any two of the behaviors of playing behavior, searching behavior, commenting behavior, reading comment behavior, collecting behavior, sharing behavior, and adding songs to a playlist.

[0017] In an optional embodiment, the first source music behavior is a play behavior, and the first target music behavior is a search behavior; or,

[0018] The first source music behavior is a review reading behavior, and the first target music behavior is a search behavior; or,

[0019] The first source music behavior is a sharing behavior, and the first target music behavior is a search behavior; or

[0020] The first source music behavior is the behavior of adding songs to a playlist, and the first target music behavior is the search behavior;

[0021] Among them, the behavior targets corresponding to the playing behavior, searching behavior, sharing behavior and adding songs to playlists are songs, and the behavior target of the searching behavior is the search term.

[0022] In an optional embodiment, the query module is further configured to query the second target from the second target pairs in the correlation library based on the first target;

[0023] The second target pair includes behavioral targets of a second source music behavior and a second target music behavior in the second behavior trajectory, and the second source music behavior and the second target music behavior belong to the same behavioral dimension.

[0024] In an optional embodiment, the first target includes any one of the following:

[0025] Songs played in the history of the first account;

[0026] Search terms that were searched in the history of the first account;

[0027] Songs reviewed in the history of the first account;

[0028] The first account in history to read the songs reviewed;

[0029] Songs collected in the history of the first account;

[0030] Songs shared in the history of the first account;

[0031] Songs that have been added to playlists by the first account in history.

[0032] In an optional embodiment, the device further includes a pre-processing module. The pre-processing module is configured to count the occurrence probabilities of the target pair in the plurality of candidate target pairs;

[0033] When the occurrence probability of the target pair meets the probability condition, the target pair is added to the correlation library.

[0034] In an optional embodiment, the recommendation module is used to recommend the second target on the interface of the music client, including:

[0035] In the search box of the music client, the second target is recommended as a background word.

[0036] In an optional embodiment, the recommendation module is used to display the guessed search area on the search intermediate page provided by the music client;

[0037] In the area you guess you want to search, the second target is recommended.

[0038] In an optional embodiment, the first target includes a song selected for playback after the first account performs a search behavior; the recommendation module is configured to display a related search area on a search result page provided by the music client, the related search area being configured to display search content related to the currently playing song;

[0039] In the relevant search area, a second target is recommended.

[0040] According to one aspect of the present application, a computer device is provided, comprising: a processor and a memory, wherein the memory stores a computer program, and the computer program is loaded and executed by the processor to implement the above target recommendation method.

[0041] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and the computer program is loaded and executed by a processor to implement the above target recommendation method.

[0042] According to another aspect of the present application, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the above-described target recommendation method.

[0043] The beneficial effects brought about by the technical solutions provided in the embodiments of the present application include at least the following.

[0044] The target recommendation method provided by this application uses a query and match between target pairs in a related relationship library based on the historical behavioral target (first target) of a first account to obtain a second target for recommendation, where one target pair corresponds to a behavioral trajectory. This application utilizes a large amount of user behavior trajectories to mine the potential recommendation needs of the first account given the first target, implementing a heuristic recommendation scheme to increase the probability that the first account will click on the recommended second target. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0046] Figure 1 This is a schematic diagram of the principle of a target recommendation method provided by an embodiment of the present application.

[0047] Figure 2 This is a flowchart of a target recommendation method provided by an embodiment of the present application.

[0048] Figure 3 This is a flowchart of a target recommendation method provided by another embodiment of the present application.

[0049] Figure 4 This is a flowchart of a target recommendation method provided by another embodiment of the present application.

[0050] Figure 5 This is a flowchart of a method for recommending the second goal provided by an embodiment of the present application.

[0051] Figure 6 This is a schematic diagram of a search box provided in one embodiment of the present application.

[0052] Figure 7 This is a flowchart of a method for recommending the second goal provided by another embodiment of the present application.

[0053] Figure 8 This is a schematic diagram of a guessing search area provided by an embodiment of the present application.

[0054] Figure 9 This is a flowchart of a method for recommending the second goal provided by another embodiment of the present application.

[0055] Figure 10 This is a schematic diagram of a related search area provided by an embodiment of the present application.

[0056] Figure 11 This is a structural block diagram of a target recommendation device provided by an embodiment of the present application.

[0057] Figure 12 This is a structural block diagram of a computer device provided in one embodiment of the present application.

[0058] Figure 13 This is a structural block diagram of a computer device provided in another embodiment of the present application. DETAILED DESCRIPTION

[0059] In order to make the objectives, technical solutions and advantages of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0060] First, a brief introduction is given to the terms involved in the embodiments of this application.

[0061] Music Client: refers to a client with music playback capabilities. In this application, the music client also has a recommendation function. For example, the music client recommends songs, song styles, singers, song charts, favorite playlists, song radio stations, audiobooks, etc. to the user, making it easy for the user to quickly trigger the recommended content.

[0062] Music behavior: refers to client behaviors related to music, such as playing, searching, commenting, reading comments, adding songs to favorites, sharing, and adding songs to playlists.

[0063] Playback behavior refers to the behavior of a user account playing songs on a music client;

[0064] Search behavior refers to the behavior of a user account searching for search terms on a music client;

[0065] Comment behavior refers to the behavior of a user account commenting on a song on a music client;

[0066] Reading review behavior refers to the behavior of a user account reading song reviews on a music client;

[0067] Collection behavior refers to the act of a user account collecting songs on a music client;

[0068] Sharing behavior refers to the act of a user account sharing songs on a music client;

[0069] The act of adding a song to a playlist refers to the act of a user account adding a song to a playlist on a music client, and optionally includes the act of adding a song to an existing playlist or adding a song to a newly created playlist.

[0070] Behavioral target: In this application, the target of music behavior is called behavioral target. For example, for playing behavior, commenting behavior, reading comment behavior, collecting behavior, sharing behavior, and adding songs to playlists, the behavioral target of these music behaviors is the song; and the behavioral target of search behavior is the search term.

[0071] In the related art, the following three target recommendation schemes in music clients are provided.

[0072] In Solution 1, a keyword recommendation method based on a deep semantic model and a large language model is proposed for generating background words in the search box. Specifically, this solution involves: first, obtaining user attribute information (such as age and region) and historical behavior data (search history, click history); then, determining preferences (such as preferred song genres and singers) based on historical behavior data; then, using the deep semantic structure model to extract feature vectors of user attribute information and preferred objects; and finally, inputting the feature vectors into the large language model to generate personalized background words (such as "xxx's latest album" and "Chinese pop songs 2024" that scroll in the search box).

[0073] However, Plan 1 does not combine multi-dimensional behavioral data such as real-time playback, comment reading, etc. of users, and Plan 1 only focuses on the generation of background words in the search box, and does not involve the coordinated guidance of the search intermediate page and the search result page.

[0074] In Solution 2, a context-based search intermediate page recommendation method is proposed. Solution 2 proposes displaying recommended content on the search intermediate page (when the user enters a search term but does not submit it). Specifically, this solution includes: first, real-time analysis of the user's current search term (such as "rock") and historical search records (such as recent searches for "rock band"); then, through association rule mining technology, generating relevant recommended terms (such as "classic rock scene" and "rock music festival"); and then adjusting the display order based on the click frequency of the recommended terms and the user's profile.

[0075] However, the recommended content generated by Solution 2 is only based on the text association of the search terms, does not integrate the user's playback behavior (such as the potential demand for not searching after playing a rock song), and does not form a linkage with the background words in the search box and the related search areas in the search results page.

[0076] Solution 3 proposes a system for recommending relevant content on search results pages. This system displays relevant search terms on the search results page (e.g., after a user plays a song). Specifically, Solution 3 involves: first, generating relevant terms based on song metadata (artist, album, genre); then, adjusting recommendation weights based on the user's historical playback preferences (e.g., users who frequently play lyrical songs will be prioritized for similar content).

[0077] However, Solution 3 relies on static song metadata and does not mine implicit associations in user behavior trajectories (such as cross-behavioral data of searching for B after playing A), resulting in insufficient real-time recommendations.

[0078] Figure 1 A schematic diagram of a target recommendation method provided by an exemplary embodiment of the present application is shown. In the method provided by the embodiment of the present application, a correlation library is first constructed, which includes multiple target pairs. Then, based on the first target (the behavior target of the music behavior historically performed by the first account), a second target is retrieved from the correlation library, and the second target is recommended to the first account on the music client.

[0079] like Figure 1 As shown, Figure 1 The construction process of the correlation library is shown.

[0080] The computer device will collect a massive amount of user behavior trajectories and generate multiple candidate target pairs based on the massive amount of user behavior trajectories. Each candidate target pair in the multiple candidate target pairs corresponds to a behavior trajectory. Figure 1 The generation of candidate target pairs 1 to 9 is shown in FIG. Optionally, a candidate target pair includes a behavior target of a source music behavior and a target music behavior in a behavior track. The source music behavior refers to the music behavior performed first in the behavior track, and the target music behavior refers to the music behavior performed later in the behavior track.

[0081] Indicative, Figure 1 The figure shows the generation process of candidate target pairs 1, 5, and 9. For the behavior trajectory "play song A first, then search for B", candidate target pair 1 (song A, search term B) is generated; for the behavior trajectory "play song A first, then play song C", candidate target pair 5 (song A, song C) is generated; and for the behavior trajectory "play song A first, then search for D", candidate target pair 9 (song A, search term D) is generated.

[0082] After the computer device obtains multiple candidate target pairs, the computer device will filter out target pairs from the multiple candidate target pairs and add them to the correlation library. In one embodiment, the computer device adds target pairs from the multiple candidate target pairs whose occurrence frequency is greater than a frequency threshold to the correlation library. For example, if the computer device obtains 10,000 candidate target pairs, among which (Song A, Song B) appears 200 times, the occurrence frequency of (Song A, Song B) is greater than the frequency threshold, and the computer device adds (Song A, Song B) to the correlation library.

[0083] In another embodiment, the computer device adds the top k target pairs among the candidate target pairs to the relevant relationship library. For example, if the computer device generates 10,000 candidate target pairs, among which (Song A, Song B) appears 200 times and the frequency of occurrence of (Song A, Song B) ranks in the top k, the computer device adds (Song A, Song B) to the relevant relationship library.

[0084] like Figure 1 As shown, the computer device adds target pair 1 (song A, search word B), target pair 2 (song A, song C) and target pair 3 (song A, search word D) to the relevant relationship library 101.

[0085] Figure 1 The matching process based on the correlation library, ie, the recommendation process, is also shown.

[0086] During the recommendation process, the computer device obtains the first target 102, matches the second target 103 from the target pairs in the correlation library 101 based on the first target 102, and recommends the second target 103 on the music client.

[0087] The first target 102 is a behavior target of music behaviors performed historically by the first account, for example, the first target is a song recently played by the first account, a search term recently searched, and the like.

[0088] Illustratively, if the first target 102 is "Song A", then based on "Song A", the second target 103 "Search term B", "Song C" and "Search term D" will be matched from the relevant relationship library 101, and "Search term B", "Search term C" and "Search term D" will be recommended on the music client.

[0089] Illustratively, the song A most recently played by the first account is obtained. Song A is pop music, and the "popular music chart" is matched from the correlation library 101. The "popular music chart" entry will be displayed on the interface.

[0090] It is understandable that the target recommendation method provided by this application will query and match the target pairs in the correlation library based on the historical behavioral target (first target) of the first account to obtain the second target for recommendation, where one target pair corresponds to a behavioral trajectory. This application will utilize a large amount of user behavior trajectories to mine the potential recommendation needs of the first account when the first target is known, thus implementing a heuristic recommendation scheme and increasing the probability of the first account clicking on the recommended second target.

[0091] In some embodiments, Figure 1 The target recommendation method shown is executed by a computer device. Optionally, the computer device includes at least one of a terminal and a server. In one embodiment, Figure 1 The process of building the correlation database is performed by the server, and the matching process based on the correlation database is performed by the terminal. Figure 1 The process of constructing the correlation library and the process of constructing the correlation library based on the correlation library are both executed by the server. After the server determines the second target 103, it sends the second target 103 to the music client logged in with the first account, and the music client recommends and displays the second target 103.

[0092] Optionally, the terminal can be a mobile phone, a computer, an intelligent voice interaction device, a smart home appliance, a car terminal, etc., but is not limited to this. The terminal and the server can be directly or indirectly connected through wired or wireless communication, and this application does not limit this. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0093] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions.

[0094] Moreover, when it comes to relevant information, the relevant information processors will follow the principles of legality, legitimacy and necessity, clarify the purpose, method and scope of relevant information processing, obtain the consent of the relevant information subjects, and take necessary technical and organizational measures to ensure the security of relevant information.

[0095] Figure 2A flowchart of a target recommendation method provided by an exemplary embodiment of the present application is shown, and the method is illustrated by an example of the method being executed by a computer device. The method includes:

[0096] Step 220: Obtain a first goal, where the first goal includes a behavior goal of music behaviors historically performed by the first account on the music client, where the music behaviors refer to client behaviors related to music.

[0097] The first goal includes behavior goals for music activities historically performed by the first account. The first account is the user account logged in to the music client. Optionally, the first goal includes behavior goals for music activities performed by the first account within a preset time range. For example, the first goal includes behavior goals for music activities performed by the first account within three days, i.e., the first goal is the behavior goals for music activities performed by the first account recently.

[0098] It is understandable that at this time, this application will determine the recommended target based on the most recent behavioral target of the first account, improve the real-time degree of the recommended target, and avoid recommending targets that may be of interest to early users.

[0099] Optionally, the first goal includes the behavioral goals of music behaviors performed by the first account outside the preset time range. For example, the first goal includes the behavioral goals of music behaviors performed by the first account three days ago, that is, the first goal is the behavioral goals of music behaviors performed by the first account in the early stage.

[0100] It is understandable that at this time, this application will determine the current recommendation target based on the early behavioral goals of the first account, which can avoid targets similar to those recommended by other recommendation logic types and improve the novelty of the recommendation target.

[0101] Music behavior refers to client-side behavior related to music, including playback, search, comment, review, favorite, share, and playlist addition. In some embodiments, the computer device generates a history of playback, search, comment, review, favorite, and playlist addition for the first account, provided the first account allows the collection of relevant data. When making a recommendation, the computer device retrieves the first target from this history.

[0102] Behavior target refers to the target of a music behavior. In one embodiment, the types of behavior targets include songs and search terms. Optionally, for playing, commenting, reading comments, adding to favorites, sharing, and adding songs to a playlist, the behavior targets of these music behaviors are songs.

[0103] Optionally, the action target of the search action is a search term.

[0104] In some embodiments, the first target includes any of the following:

[0105] Illustratively, the first target includes songs played historically by the first account; for example, the first target is song A played most recently by the first account.

[0106] Illustratively, the first target includes search terms historically searched by the first account; for example, the first target is search term B most recently searched by the first account.

[0107] Illustratively, the first target includes songs that the first account has commented on historically; for example, the first target is song C that the first account has commented on most recently.

[0108] Illustratively, the first target includes songs for which comments have been read in the history of the first account; for example, the first target is song D for which the first account has recently read comments.

[0109] Illustratively, the first target includes songs that the first account has collected in history; for example, the first target is song E that the first account has recently collected.

[0110] Illustratively, the first target includes songs shared historically by the first account; for example, the first target is song F recently shared by the first account.

[0111] Illustratively, the first target includes songs that the first account has historically added to the playlist; for example, the first target is song G that the first account has recently added to the playlist.

[0112] In some embodiments, the first goal includes a behavior goal whose frequency of occurrence meets a frequency condition among the behavior goals of the first account's historical music behaviors. For example, the number of times the first account has played, searched, commented, read comments, favorited, shared, and added to a playlist actions for song A is accumulated, and it is determined that the number of times song A has been triggered meets the frequency condition, and song A is determined to be the first goal.

[0113] Step 240: Based on the first goal, a second goal is searched from the goal pairs in the correlation library, where the goal pair includes the behavior goals of the source music behavior and the target music behavior in a behavior trajectory;

[0114] The correlation library is a pre-built relationship library. Optionally, the correlation library includes multiple target pairs, each corresponding to a plurality of behavior trajectories. Each behavior trajectory includes a source music behavior and a target music behavior. The source music behavior refers to the music behavior that was performed first, and the target music behavior refers to the music behavior that was performed later. A target pair includes the behavior target of the source music behavior and the behavior target of the target music behavior.

[0115] Illustratively, a behavior trajectory includes a user playing song A first, then playing song B, then the target pair corresponding to the behavior trajectory is (song A, song B). Illustratively, a behavior trajectory includes a user playing song A first, then searching for search term C, then the target pair corresponding to the behavior trajectory is (song A, search term C). Illustratively, a behavior trajectory includes a user searching for search term C first, then searching for search term D, then the target pair corresponding to the behavior trajectory is (search term C, search term D).

[0116] In one embodiment, the first target is used as the query term, and the corresponding matching term is retrieved from the target pairs in the related library as the second target. For example, if the first target is song A, song B can be retrieved from the target pair (song A, song B) in the related library, and song B is the second target. For another example, if the first target is song A, search term C can be retrieved from the target pair (song A, search term C) in the related library, and search term C is the second target. For another example, if the first target is search term C, search term D can be retrieved from the target pair (search term C, search term D) in the related library, and search term D is the second target.

[0117] Step 260: recommend the second target on the interface of the music client.

[0118] In one embodiment, a search function is provided on the music client, and the second target is recommended on the relevant visual component of the search function. In another embodiment, a recommendation page is provided on the interface of the music client, and the second target is recommended on the relevant visual component of the recommendation page.

[0119] Optionally, the second target is recommended on the interface of the music client by presenting a term. For example, if the second target is song A, the term "song A" is displayed on the interface.

[0120] Optionally, the second target can be recommended on the music client interface by presenting related covers. For example, if the second target is song A, the album cover of song A will be displayed on the interface. For example, if the second target is playlist B, the exclusive cover of playlist B will be displayed on the interface.

[0121] Optionally, special effects such as animation, shaking, highlighting, and frame breaking are used to recommend the second target.

[0122] Optionally, in addition to recommending the second target in a visual manner on the interface, the second target can also be prompted by playing sound effects. For example, if the second target is song A, when the second target is displayed on the interface for the first time, the sound effect "Your exclusive recommendation has been generated, song A, try it" is also played.

[0123] In summary, the target recommendation method provided by this application will query and match the target pairs in the correlation library based on the historical behavioral target (first target) of the first account to obtain the second target for recommendation, where one target pair corresponds to a behavioral trajectory. This application will utilize a large amount of user behavior trajectories to mine the potential recommendation needs of the first account when the first target is known, thus implementing a heuristic recommendation scheme and increasing the probability of the first account clicking on the recommended second target.

[0124] In one embodiment, if there are m target pairs associated with a first target in the correlation library, then based on the first target, m second targets can be matched from the correlation library. Optionally, for the m second targets, n cluster centers are obtained by clustering the feature vectors of the m second targets, and the n cluster centers correspond to n clusters. For cluster center i, the characteristic distance between the feature vector corresponding to each second target in cluster i and cluster center i is calculated, and the second target whose characteristic distance meets the distance condition is selected as the final recommended second target.

[0125] Illustratively, feature extraction is performed on each second target to obtain m feature vectors. Using a clustering algorithm, these m feature vectors are clustered to obtain n cluster centers. For cluster i, the vector distance between the feature vector corresponding to each second target in cluster i and cluster center i is calculated. Optionally, the second target whose vector distance is less than a distance threshold is selected as the final recommended second target. For example, the second target whose vector distance is less than a first distance value is selected as the final recommended second target.

[0126] Optionally, the second target with the smallest vector distance among the top k is used as the final recommended second target. For example, the second target corresponding to the minimum vector distance is used as the final recommended second target.

[0127] Repeat the above operation for n cluster centers.

[0128] To sum up, in the above embodiment, after querying multiple second targets, the clustering algorithm is used to determine the second target closest to the cluster center as the final recommended target. The above embodiment comprehensively considers the overall distribution of the multiple matched second targets, making the final determined second target more representative, thereby increasing the probability of users clicking on the second target.

[0129] The process of establishing a correlation database

[0130] According to the above introduction, the correlation library includes multiple target pairs corresponding to multiple behavior trajectories.

[0131] In one embodiment, a computer device generates multiple candidate target pairs from a massive amount of user behavior trajectories, counts the probability of occurrence of each candidate target pair in the multiple candidate target pairs, and adds the target pairs whose occurrence frequency meets the frequency condition in the multiple candidate target pairs to a correlation library. In this application, the computer device will integrate multi-dimensional behaviors such as playback behavior, search behavior, and comment behavior, and generate candidate target pairs based on the user behavior trajectories composed of multi-dimensional behaviors. This application will analyze various behavioral data such as user playback behavior, search behavior, and reading comment behavior, mine the correlations therein, and construct a correlation library containing various correlations such as songs and songs, songs and search terms, and search terms and search terms, to provide a data basis for the subsequent recommendation process.

[0132] For example, for the playback behavior, the computer device generates a candidate target pair (song A, song B) based on the user's behavior trajectory of playing song A first and then playing song B;

[0133] For example, with respect to the search behavior, the computer device generates a candidate target pair (search term C, search term D) based on the user searching for C and then searching for D;

[0134] For example, for the behavior of playing first and searching later, the computer device generates a candidate target pair (song A, search term C) based on the user's behavior trajectory of playing song A first and searching for C later.

[0135] For example, for a behavior of first reading comments on song A and then searching for C, the computer device generates a candidate target pair (song A, search term C) based on the user's behavior trajectory of first reading comments on song A and then searching for C.

[0136] And so on, no more listing.

[0137] Based on the above-mentioned process of establishing the correlation library, it can be seen that the target pairs in the correlation library are derived from behavioral trajectories of the same behavioral dimension (for example, behavioral trajectories generated only by playback behavior, behavioral trajectories that only rely on search behavior) and behavioral trajectories across behavioral dimensions (for example, behavioral trajectories of playing songs first and then searching, behavioral trajectories of reading song reviews first and then searching). Compared with the related art that only relies on behavioral data of one behavioral dimension for target recommendation, this application integrates multi-dimensional behavioral data and can recommend a more accurate second target.

[0138] In one embodiment, machine learning algorithms can be introduced when building a correlation database to conduct more in-depth analysis and processing of user behavior data, thereby improving the accuracy and efficiency of correlation mining. For example, association rule mining algorithms (such as the Apriori algorithm) can be used to mine frequent item sets and associations in user behavior trajectories. Another example is using a deep learning model to model user behavior patterns and predict users' potential listening needs, thereby building a more accurate correlation database.

[0139] based on Figure 2 In the illustrated alternative embodiment, Figure 3 A flowchart of a target recommendation method provided by an exemplary embodiment of the present application is shown, and the method is illustrated by an example of the method being executed by a computer device. The method includes:

[0140] Step 320: Obtain a first goal, where the first goal includes a behavior goal of music behaviors that the first account has historically performed on the music client. Music behaviors refer to client behaviors related to music.

[0141] For the relevant introduction of step 320, please refer to the above step 220.

[0142] Step 340: Based on the first goal, query the second goal from the first goal pair in the correlation library; the first goal pair includes the behavior goals of the first source music behavior and the first target music behavior in the first behavior trajectory, and the first source music behavior and the first target music behavior belong to different behavior dimensions;

[0143] In this embodiment, the correlation library includes a first target pair, the first target pair corresponds to the first behavior trajectory, the first behavior trajectory refers to a behavior trajectory in which the first source music behavior and the first target music behavior belong to different behavior dimensions, and the first target pair includes the behavior targets of the first source music behavior and the first target music behavior. For example, the first source music behavior includes playing song A (belonging to the playing behavior), and the first target music behavior includes searching C (belonging to the searching behavior). In this case, the candidate target pair corresponding to the first behavior trajectory is (song A, search term C). For another example, the first source music behavior includes reading comments on song A (belonging to the reading comment behavior), and the first target music behavior includes searching D (belonging to the searching behavior). In this case, the target pair corresponding to the first behavior trajectory is (song A, search term D).

[0144] Optionally, the behavior dimensions of the first source music behavior and the first target music behavior include any two of the behaviors of playing, searching, commenting, reading comments, collecting, sharing, and adding songs to a playlist.

[0145] In one embodiment, the first source music behavior is a play behavior, and the first target music behavior is a search behavior; the behavior target corresponding to the play behavior is a song, and the behavior target of the search behavior is a search term.

[0146] In one embodiment, the first source music behavior belongs to a review reading behavior, and the first target music behavior belongs to a search behavior; the behavior target corresponding to the review reading behavior is a song, and the behavior target of the search behavior is a search term.

[0147] In one embodiment, the first source music behavior is a sharing behavior, and the first target music behavior is a search behavior; the behavior target corresponding to the sharing behavior is a song, and the behavior target of the search behavior is a search term.

[0148] In one embodiment, the first source music behavior is an behavior of adding a song to a playlist, and the first target music behavior is a search behavior; the behavior target corresponding to the behavior of adding a song to a playlist is the song, and the behavior target of the search behavior is the search term.

[0149] It can be understood that the first target pair corresponding to the first behavior trajectory includes behavioral targets of different dimensions of behavior, that is, the present application realizes the integration of behavioral data of multiple dimensions to generate target pairs. In the subsequent recommendation process, the recommended targets will be matched based on the target pairs. Compared with the related technology that only relies on single-dimensional behavioral data such as historical search records or historical playback records, the present application integrates multi-dimensional behavioral data and can more accurately recommend recommended targets that users may click.

[0150] Step 360: recommend the second target on the interface of the music client.

[0151] For the relevant introduction of step 360, please refer to the above step 260.

[0152] based on Figure 2 In the illustrated alternative embodiment, Figure 4 A flowchart of a target recommendation method provided by an exemplary embodiment of the present application is shown, and the method is illustrated by an example of the method being executed by a computer device. The method includes:

[0153] Step 420: Obtain a first goal, where the first goal includes a behavior goal of music behaviors that the first account has historically performed on the music client. Music behaviors refer to client behaviors related to music.

[0154] For the relevant introduction of step 420, please refer to the above step 220.

[0155] Step 440: Based on the first goal, a second goal is retrieved from a second goal pair in the correlation library; the second goal pair includes the behavior goals of the second source music behavior and the second target music behavior in the second behavior trajectory, and the second source music behavior and the second target music behavior belong to the same behavior dimension;

[0156] In this embodiment, the correlation library includes a second target pair, which corresponds to a second behavior trajectory. The second behavior trajectory refers to a behavior trajectory in which the second source music behavior and the second target music behavior belong to the same behavior dimension. For example, the second source music behavior includes playing song A (belonging to the play behavior) and the second target music behavior includes playing song B (belonging to the play behavior). In this case, the target pair corresponding to the second behavior trajectory is (song A, song B).

[0157] Step 460: recommend the second target on the interface of the music client.

[0158] For the related introduction of step 420 , please refer to the above step 260 .

[0159] Next, we will introduce a method for recommending a second target on the interface of the music client.

[0160] based on Figure 2 In the illustrated alternative embodiment, step 260 may include: Figure 5 Step 520 is shown.

[0161] Step 520: In the search box of the music client, the second target is recommended as a background word.

[0162] A search box is provided on the music client for users to search. Users can enter search terms in the search box. Optionally, the search box is located on the homepage of the music client. Background words refer to the terms that are not highlighted in the search box. Optionally, background words are displayed as the background in the search box. Figure 6 As shown, Figure 6 A search box 601 of a home page and a second target as a background word in the search box 601 are shown.

[0163] Optionally, in the search box of the music client, a second target is scrolled and exposed.

[0164] Optionally, the second target is permanently displayed in the search box of the music client.

[0165] Optionally, in the search box of the music client, the second target is scrollingly exposed within a first time period, and then the second target is fixedly displayed within a second time period.

[0166] Optionally, within the search box of the music client, a second duration for displaying the second target is determined based on the time the first account stays on the page. Alternatively, a frequency of switching between scrolling exposure and fixed display of the second target is determined based on the time the first account stays on the page.

[0167] based on Figure 2 In the illustrated alternative embodiment, step 260 includes the following steps: Figure 7 Steps 720 and 740 are shown.

[0168] Step 720: On the search intermediate page provided by the music client, the guessed search area is displayed;

[0169] A search box is provided on the music client. When a first account triggers the search box, the user enters a search intermediate page. The search box on the search intermediate page is used to receive a search term entered by the first account. The search intermediate page also displays a "Guess what you want to search" area, which displays recommended search terms.

[0170] Step 740: Recommend a second target in the area you guessed you would like to search.

[0171] Optionally, in the "Guess what you want to search" area, the entries containing the second target are displayed. Optionally, in the "Guess what you want to search" area, the cover corresponding to the second target is displayed. Figure 8 As shown, Figure 8 The entry containing the second target is shown in the guess you want to search area 801. The guess you want to search area 801 also provides a refresh control for refreshing the targets recommended in the guess you want to search area.

[0172] Optionally, in the "Guess what you want to search" area, multimedia information such as the entry containing the second target, the cover corresponding to the second target, and the song introduction corresponding to the second target is displayed.

[0173] based on Figure 2 In the illustrated optional embodiment, the first target includes the song selected for playback after the first account performs a search action, and step 260 includes Figure 9 Steps 920 and 940 are shown.

[0174] Step 920: Displaying a related search area on the search results page provided by the music client. The related search area is used to display search content related to the currently playing song.

[0175] When a first account enters a search term on the search intermediate page and triggers a search, a search results page is displayed, providing multiple search results. The multiple search results include multiple songs. In response to the first account triggering the playback of one of the songs, a related search area corresponding to the song (i.e., the currently playing song) is displayed. The related search area is used to display recommended targets related to the currently playing song.

[0176] For example, if the currently playing song is pop music, the "Pop Music Chart" will be displayed in the related search area; for another example, if the currently playing music is song A by singer 1, another song B by singer 1 will be displayed in the related search area.

[0177] Optionally, the related search area is located below the currently playing song.

[0178] Optionally, the related search area is displayed on the search results page in the form of a pop-up window, floating bar, etc.

[0179] Optionally, the priority of the search results displayed on the search results page is associated with at least one of the duration and number of times each search result has been played. For example, if the search results page displays five search results, search result A, search result B, search result C, search result D, and search result E are displayed in order of the number of times they have been played.

[0180] Optionally, the number of search results displayed on the search results page is associated with at least one of the duration and number of times the search results were played. For example, if a total of m candidate search results are found, and the play duration and / or play count of n search results do not meet the conditions, then mn search results will be displayed on the search results page.

[0181] Step 940: recommend a second target in the relevant search area.

[0182] Optionally, in the related search area, the entries containing the second target are displayed. Optionally, in the related search area, the cover corresponding to the second target is displayed. Figure 10 As shown, Figure 10 The terms including the second target are shown in the related search area 1001 .

[0183] It should be noted that the target recommendation method provided in this application can be applied to at least one of the following: recommending as a background word in the search box, recommending in the "Guess What You Want to Search" area on the search page, and recommending in the "Related Search" area on the search results page. When the target recommendation method provided in this application is applied to all three of the above functional scenarios, the target recommendation method provided in this application combines the above three functional scenarios, avoiding the independent operation of the three functional scenarios, and realizing data interoperability and scenario collaboration among the three functional scenarios, so that the targets recommended by each of the three functional scenarios have associated logic.

[0184] In addition, the above three functional scenarios constitute the search guidance link when users search. If the target recommendation method provided by this application is adopted in all three functional scenarios, the efficiency of users reaching the target content can be improved.

[0185] In one embodiment, the present application provides a target recommendation method. Next, the target recommendation method provided by the present application will be introduced from two stages: data mining and online strategy.

[0186] Data Mining

[0187] By analyzing various behavioral data of users on the music platform, we can mine the correlations and build a correlation database. The specific behavioral data mining methods are as follows:

[0188] Playback behavior mining: focus on the behavior of users playing song A and then continuing to play song B. In the massive user behavior data, statistics on this behavior<A,B> The probability of the correlation occurring. When the probability is large enough, it is determined that song A and song B have a certain correlation, and the correlation is recorded in the correlation database, such as <song A, song B>.

[0189] Search behavior mining: This includes user searches for A and then B. The probability of the "search A, search B" relationship occurring in massive amounts of data is counted. If the probability meets the criteria, the "search term A, song B" relationship is recorded in the relationship database.

[0190] Mining search behavior after reading reviews: When a user reads a review of song A and then searches for song B, we analyze the correlation between <song A, search term B>. If the probability of occurrence is high enough, we add <song A, search term B> to the correlation database.

[0191] By mining the above-mentioned various behavioral data, a correlation database containing various correlations is eventually constructed to provide data support for subsequent online strategies.

[0192] Online Strategy

[0193] Based on the user's most recently played songs and most recently searched terms, we search for relevant content in the relevant relationship database and deliver it through the following three modules to guide user searches:

[0194] Background Word Function Module: Within the search box on the music platform homepage, relevant content retrieved from the related relationship library is displayed in a rolling manner. This related content can include song titles, search terms, and other content related to the user's recently played or searched songs. For example, if a user recently played song A, and the related relationship library contains song B and search term B, these contents will scroll within the search box, proactively providing users with possible search directions and guiding them in their search, changing the previous model of passively waiting for user input.

[0195] Guess what you want to search function module: When a user enters the search intermediate page, the system extracts relevant content from the related relationship library based on the user's recent behavior (including playback behavior and search behavior) and displays it. For example, if a user recently searched for "popular music" and played several popular songs, this module will display other search terms related to "popular music", such as "popular music charts", "latest popular songs", etc., or other song titles related to the popular songs played, helping users quickly find content of interest and initiate further searches.

[0196] · Related search function module on the results page: When a user retrieves and plays a song, the page for the current song will expand to display related search terms. These terms are related content retrieved from the related relationship library based on the currently playing song. For example, if a user plays song A, and the related relationship library contains song B and search term B related to song A, these related search terms will be displayed on the playback page of song A. Users can directly click on these terms to search for related songs, making it convenient for users to quickly explore other related song content after listening to the current song.

[0197] To sum up, this application is different from the traditional personalized recommendation system. Instead, it uses heuristic search to explore potential listening needs based on the behavioral trajectory clues of a large number of users, and provides real-time search guidance based on the user's current recent behavioral data.

[0198] Figure 11 The following is a structural block diagram of a target recommendation device provided by an exemplary embodiment of the present application, wherein the device includes:

[0199] An acquisition module 1101 is configured to acquire a first target, where the first target includes a behavior target of a music behavior historically performed by the first account on a music client, where the music behavior refers to a client behavior related to music;

[0200] A query module 1102 is configured to query a second target from a target pair in a correlation library based on the first target, where the target pair includes a behavior target of a source music behavior and a target music behavior in a behavior trajectory;

[0201] The recommendation module 1103 is used to recommend the second target on the interface of the music client.

[0202] In an optional embodiment, the query module 1102 is configured to query a second target from a first target pair in a correlation library based on the first target;

[0203] The first target pair includes behavioral targets of a first source music behavior and a first target music behavior in the first behavior trajectory, and the first source music behavior and the first target music behavior belong to different behavioral dimensions.

[0204] In an optional embodiment, the behavior dimensions of the first source music behavior and the first target music behavior include any two of the behaviors of playing behavior, searching behavior, commenting behavior, reading comment behavior, collecting behavior, sharing behavior, and adding songs to a playlist.

[0205] In an optional embodiment, the first source music behavior is a play behavior, and the first target music behavior is a search behavior; or,

[0206] The first source music behavior is a review reading behavior, and the first target music behavior is a search behavior; or,

[0207] The first source music behavior is a sharing behavior, and the first target music behavior is a search behavior; or

[0208] The first source music behavior is the behavior of adding songs to a playlist, and the first target music behavior is the search behavior;

[0209] Among them, the behavior targets corresponding to the playing behavior, searching behavior, sharing behavior and adding songs to playlists are songs, and the behavior target of the searching behavior is the search term.

[0210] In an optional embodiment, the query module 1102 is configured to query a second target from a second target pair in a related relationship library based on the first target;

[0211] The second target pair includes behavioral targets of a second source music behavior and a second target music behavior in the second behavior trajectory, and the second source music behavior and the second target music behavior belong to the same behavioral dimension.

[0212] In an optional embodiment, the first target includes any one of the following:

[0213] Songs played in the history of the first account;

[0214] Search terms that were searched in the history of the first account;

[0215] Songs reviewed in the history of the first account;

[0216] The first account in history to read the songs reviewed;

[0217] Songs collected in the history of the first account;

[0218] Songs shared in the history of the first account;

[0219] Songs that have been added to playlists by the first account in history.

[0220] In an optional embodiment, the apparatus further includes a pre-processing module 1104. The pre-processing module 1104 is configured to count the occurrence probabilities of the target pair in the plurality of candidate target pairs;

[0221] When the occurrence probability of the target pair meets the probability condition, the target pair is added to the correlation library.

[0222] In an optional embodiment, the recommendation module 1103 is further configured to recommend the second target as a background word in the search box of the music client.

[0223] In an optional embodiment, the recommendation module 1103 is further configured to display the guessed search area on the search intermediate page provided by the music client;

[0224] In the area you guess you want to search, the second target is recommended.

[0225] In an optional embodiment, the first target includes a song selected for playback after the first account performs a search behavior; the recommendation module 1103 is further configured to display a related search area on a search result page provided by the music client, the related search area being configured to display search content related to the currently playing song;

[0226] In the relevant search area, a second target is recommended.

[0227] In summary, the target recommendation device provided by this application will query and match the target pairs in the correlation library based on the behavioral target (first target) of the first account's history to obtain the second target for recommendation, where one target pair corresponds to a behavioral trajectory. This application will utilize a large amount of user behavior trajectories to mine the potential recommendation needs of the first account when the first target is known, thus implementing a heuristic recommendation scheme and increasing the probability of the first account clicking on the recommended second target.

[0228] Figure 12The following is a block diagram of a computer device 1200 according to an exemplary embodiment of the present application. Computer device 1200 may be a portable mobile terminal, such as a smartphone, tablet computer, MP3 player (Moving Picture Experts Group Audio Layer III), MP4 player (Moving Picture Experts Group Audio Layer IV), laptop computer, or desktop computer. Computer device 1200 may also be referred to as user equipment, portable terminal, laptop terminal, desktop terminal, or other similar names.

[0229] Typically, the computer device 1200 includes a processor 1201 and a memory 1202 .

[0230] The processor 1201 may include one or more processing cores, such as a 4-core processor, a 12-core processor, etc. The processor 1201 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), or PLA (Programmable Logic Array). The processor 1201 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 1201 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 1201 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0231] Memory 1202 may include one or more computer-readable storage media, which may be non-transitory. Memory 1202 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices and flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in memory 1202 is used to store at least one instruction, which is used to be executed by processor 1201 to implement the target recommendation method provided in the method embodiment of the present application.

[0232] In some embodiments, computer device 1200 may optionally include a peripheral device interface 1203 and at least one peripheral device. Processor 1201, memory 1202, and peripheral device interface 1203 may be connected via a bus or signal lines. Each peripheral device may be connected to peripheral device interface 1203 via a bus, signal lines, or circuit boards. For example, the peripheral device may include at least one of a radio frequency circuit 1204, a display screen 1205, a camera assembly 1206, an audio circuit 1207, and a power supply 1208.

[0233] The peripheral device interface 1203 can be used to connect at least one I / O (Input / Output)-related peripheral device to the processor 1201 and the memory 1202. In some embodiments, the processor 1201, the memory 1202, and the peripheral device interface 1203 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 1201, the memory 1202, and the peripheral device interface 1203 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0234] The RF circuit 1204 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 1204 communicates with communication networks and other communication devices via electromagnetic signals. The RF circuit 1204 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals into electrical signals. Optionally, the RF circuit 1204 includes an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, and the like. The RF circuit 1204 can communicate with other terminals via at least one wireless communication protocol. Such wireless communication protocols include, but are not limited to, the World Wide Web, metropolitan area networks, intranets, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and / or WiFi (Wireless Fidelity) networks. In some embodiments, the RF circuit 1204 may also include circuitry related to Near Field Communication (NFC), although this application does not limit this.

[0235] The display screen 1205 is used to display a UI (User Interface). The UI may include graphics, text, icons, videos, and any combination thereof. When the display screen 1205 is a touch screen display, the display screen 1205 also has the ability to collect touch signals on the surface or above the surface of the display screen 1205. The touch signal can be input as a control signal to the processor 1201 for processing. In this case, the display screen 1205 can also be used to provide virtual buttons and / or virtual keyboards, also known as soft buttons and / or soft keyboards. In some embodiments, there can be one display screen 1205, which is set on the front panel of the computer device 1200; in other embodiments, there can be at least two display screens 1205, which are respectively set on different surfaces of the computer device 1200 or in a folding design; in other embodiments, the display screen 1205 can be a flexible display screen, which is set on the curved surface or folding surface of the computer device 1200. Even more, the display screen 1205 can be set to a non-rectangular irregular shape, that is, a special-shaped screen. The display screen 1205 can be made of materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0236] The camera assembly 1206 is used to capture images or videos. Optionally, the camera assembly 1206 includes a front camera and a rear camera. Typically, the front camera is arranged on the front panel of the terminal, and the rear camera is arranged on the back of the terminal. In some embodiments, there are at least two rear cameras, which are any one of a main camera, a depth of field camera, a wide-angle camera, and a telephoto camera, so as to realize the fusion of the main camera and the depth of field camera to realize the background blur function, the fusion of the main camera and the wide-angle camera to realize panoramic shooting and VR (Virtual Reality) shooting function or other fusion shooting functions. In some embodiments, the camera assembly 1206 may also include a flash. The flash can be a monochrome temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm light flash and a cold light flash, which can be used for light compensation at different color temperatures.

[0237] The audio circuit 1207 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, and convert the sound waves into electrical signals that are input into the processor 1201 for processing, or input into the radio frequency circuit 1204 to achieve voice communication. For the purpose of stereo sound collection or noise reduction, there may be multiple microphones, each located in different parts of the computer device 1200. The microphone may also be an array microphone or an omnidirectional collection microphone. The speaker is used to convert electrical signals from the processor 1201 or the radio frequency circuit 1204 into sound waves. The speaker may be a traditional thin film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can not only convert electrical signals into sound waves audible to humans, but also convert electrical signals into sound waves inaudible to humans for purposes such as distance measurement. In some embodiments, the audio circuit 1207 may also include a headphone jack.

[0238] Power supply 1208 is used to power various components in computer device 1200. Power supply 1208 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When power supply 1208 includes a rechargeable battery, the rechargeable battery can be wired or wirelessly rechargeable. A wired rechargeable battery is charged via a wired line, while a wireless rechargeable battery is charged via a wireless coil. The rechargeable battery can also support fast charging technology.

[0239] In some embodiments, the computer device 1200 further includes one or more sensors 1209 , including but not limited to an acceleration sensor 1210 , a gyroscope sensor 1211 , a pressure sensor 1212 , an optical sensor 1213 , and a proximity sensor 1214 .

[0240] The accelerometer 1210 can detect the magnitude of acceleration along the three coordinate axes of the coordinate system established by the computer device 1200. For example, the accelerometer 1210 can be used to detect the components of gravity acceleration along the three coordinate axes. The processor 1201 can control the display screen 1205 to display the user interface in a landscape or portrait view based on the gravity acceleration signal collected by the accelerometer 1210. The accelerometer 1210 can also be used to collect game or user motion data.

[0241] The gyroscope sensor 1211 can detect the orientation and rotation angle of the computer device 1200. It can also work with the accelerometer 1210 to collect 3D motions of the user on the computer device 1200. Based on the data collected by the gyroscope sensor 1211, the processor 1201 can implement the following functions: motion sensing (e.g., changing the UI based on the user's tilt), image stabilization during shooting, game control, and inertial navigation.

[0242] The pressure sensor 1212 can be installed on the side frame of the computer device 1200 and / or below the display screen 1205. When the pressure sensor 1212 is installed on the side frame of the computer device 1200, it can detect the user's grip signal of the computer device 1200. The processor 1201 can perform left and right hand recognition or shortcut operations based on the grip signal collected by the pressure sensor 1212. When the pressure sensor 1212 is installed below the display screen 1205, the processor 1201 controls the operational controls on the UI interface based on the user's pressure operation on the display screen 1205. The operational controls include at least one of a button control, a scroll bar control, an icon control, and a menu control.

[0243] Optical sensor 1213 is used to detect ambient light intensity. In one embodiment, processor 1201 can control the display brightness of display screen 1205 based on the ambient light intensity detected by optical sensor 1213. For example, when the ambient light intensity is high, the display brightness of display screen 1205 is increased; when the ambient light intensity is low, the display brightness of display screen 1205 is decreased. In another embodiment, processor 1201 can also dynamically adjust the shooting parameters of camera assembly 1206 based on the ambient light intensity detected by optical sensor 1213.

[0244] Proximity sensor 1214, also known as a distance sensor, is typically located on the front panel of computer device 1200. Proximity sensor 1214 is used to detect the distance between the user and the front of computer device 1200. In one embodiment, when proximity sensor 1214 detects that the distance between the user and the front of computer device 1200 is gradually decreasing, processor 1201 controls display screen 1205 to switch from the screen-on state to the screen-off state. When proximity sensor 1214 detects that the distance between the user and the front of computer device 1200 is gradually increasing, processor 1201 controls display screen 1205 to switch from the screen-off state to the screen-on state.

[0245] Those skilled in the art will understand that Figure 12 The structure shown in the figure does not constitute a limitation on the computer device 1200, and the computer device 1200 may include more or fewer components than shown in the figure, or combine some components, or adopt a different component arrangement.

[0246] Figure 1313 is a schematic diagram illustrating the structure of a computer device according to an exemplary embodiment. The computer device 1300 includes a central processing unit (CPU) 1301, a system memory 1304 including a random access memory (RAM) 1302 and a read-only memory (ROM) 1303, and a system bus 1305 connecting the system memory 1304 and the CPU 1301. The computer device 1300 also includes a basic input / output system (I / O system) 1306 for facilitating information transmission between various components within the computer device, and a mass storage device 1307 for storing an operating system 1313, application programs 1314, and other program modules 1315.

[0247] The basic input / output system 1306 includes a display 1308 for displaying information and an input device 1309, such as a mouse or keyboard, for user input. Both the display 1308 and the input device 1309 are connected to the central processing unit 1301 via an input / output controller 1310 connected to the system bus 1305. The basic input / output system 1306 may also include an input / output controller 1310 for receiving and processing input from a variety of other devices, such as a keyboard, mouse, or electronic stylus. Similarly, the input / output controller 1310 also provides output to a display screen, printer, or other types of output devices.

[0248] The mass storage device 1307 is connected to the central processing unit 1301 via a mass storage controller (not shown) connected to the system bus 1305. The mass storage device 1307 and its associated computer-readable medium provide non-volatile storage for the computer device 1300. In other words, the mass storage device 1307 may include computer-readable media (not shown) such as a hard disk or a CD-ROM drive.

[0249] Without loss of generality, the computer device readable medium may include computer device storage media and communication media. Computer device storage media include volatile and non-volatile, removable and non-removable media implemented by any method or technology for storing information such as computer device readable instructions, data structures, program modules or other data. Computer device storage media include RAM, ROM, Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), CD-ROM, Digital Video Disc (DVD) or other optical storage, tape cassettes, magnetic tapes, disk storage or other magnetic storage devices. Of course, those skilled in the art will appreciate that the computer device storage media is not limited to the above-mentioned ones. The above-mentioned system memory 1304 and mass storage device 1307 can be collectively referred to as memory.

[0250] According to various embodiments of the present disclosure, the computer device 1300 may also be connected to a remote computer device on a network such as the Internet for operation. That is, the computer device 1300 may be connected to the network 1311 via the network interface unit 1312 connected to the system bus 1305, or the network interface unit 1312 may be used to connect to other types of networks or remote computer device systems (not shown).

[0251] The memory further includes one or more programs, which are stored in the memory. The central processing unit 1301 implements all or part of the steps of the above-mentioned target recommendation method by executing the one or more programs.

[0252] The present application also provides a computer-readable storage medium, which stores at least one instruction, at least one program, code set or instruction set. The at least one instruction, the at least one program, the code set or instruction set is loaded and executed by a processor to implement the target recommendation method provided by the above method embodiment.

[0253] The present application provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the target recommendation method provided by the above method embodiment.

[0254] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0255] Those skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware, or by a program to instruct the relevant hardware, and the program may be stored in a computer-readable storage medium, which may be a read-only memory, a disk, or an optical disk, etc.

[0256] The above description is merely an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A target recommendation method, characterized in that: The method comprises: Obtaining a first goal, where the first goal includes a behavior goal of a music behavior historically performed by the first account on a music client, where the music behavior refers to a client behavior related to music; Based on the first goal, a second goal is searched from a goal pair in a correlation library, wherein the goal pair includes a behavior goal of a source music behavior and a target music behavior in a behavior trajectory; The second target is recommended on the interface of the music client.

2. The method according to claim 1, characterized in that The querying of a second target from target pairs in a related relationship library based on the first target includes: Based on the first target, query the second target from the first target pairs in the correlation library; The first target pair includes behavior targets of a first source music behavior and a first target music behavior in a first behavior trajectory, and the first source music behavior and the first target music behavior belong to different behavior dimensions.

3. The method according to claim 2, characterized in that The behavior dimensions of the first source music behavior and the first target music behavior include any two of the behaviors of playing, searching, commenting, reading comments, collecting, sharing, and adding songs to a playlist.

4. The method according to claim 3, characterized in that The first source music behavior belongs to the play behavior, and the first target music behavior belongs to the search behavior; or The first source music behavior belongs to the review reading behavior, and the first target music behavior belongs to the search behavior; or The first source music behavior belongs to the sharing behavior, and the first target music behavior belongs to the searching behavior; or The first source music behavior belongs to the behavior of adding a song to a playlist, and the first target music behavior belongs to the search behavior; Among them, the behavior targets corresponding to the playing behavior, the searching behavior, the sharing behavior and the behavior of adding songs to a playlist are songs, and the behavior target of the searching behavior is a search term.

5. The method according to claim 1, wherein The querying of a second target from target pairs in a related relationship library based on the first target includes: Based on the first target, query the second target from the second target pairs in the correlation library; The second target pair includes behavior targets of a second source music behavior and a second target music behavior in a second behavior trajectory, and the second source music behavior and the second target music behavior belong to the same behavior dimension.

6. The method according to any one of claims 1 to 5, characterized in that: The first goal includes any one of the following: the songs played historically by the first account; Search terms that the first account has searched in the past; Songs reviewed by the first account in the past; Songs that the first account has historically read and commented on; Songs collected historically by the first account; Songs shared historically by the first account; Songs that the first account has historically added to playlists.

7. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: Counting the occurrence probability of the target pair in multiple candidate target pairs; When the occurrence probability of the target pair meets the probability condition, the target pair is added to the correlation library.

8. The method according to any one of claims 1 to 5, characterized in that: The recommending the second target on the interface of the music client includes: In the search box of the music client, the second target is recommended as a background word.

9. The method according to any one of claims 1 to 5, characterized in that: The recommending the second target on the interface of the music client includes: On the search middle page provided by the music client, a guessed search area is displayed; In the guessed search area, the second target is recommended.

10. The method according to any one of claims 1 to 5, characterized in that: The first target includes songs selected for playback after the first account performs a search behavior; The recommending the second target on the interface of the music client includes: On the search results page provided by the music client, a related search area is displayed, wherein the related search area is used to display search content related to the currently playing song; The second target is recommended in the relevant search area.

11. A target recommendation device, characterized in that: The device comprises: an acquisition module, configured to acquire a first target, wherein the first target includes a behavior target of a music behavior historically performed by the first account on the music client, wherein the music behavior refers to a client behavior related to music; A query module, configured to query a second target from a target pair in a correlation library based on the first target, wherein the target pair includes behavior targets of a source music behavior and a target music behavior in a behavior trajectory; A recommendation module is used to recommend the second target on the interface of the music client.

12. A computer device, characterized in that: The computer device includes: a processor and a memory, the memory stores a computer program, and the computer program is loaded and executed by the processor to implement the target recommendation method according to any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and the computer program is loaded and executed by a processor to implement the target recommendation method according to any one of claims 1 to 10.

14. A computer program product, characterized in that The computer program product includes computer instructions, which are stored in a computer-readable storage medium. The processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the target recommendation method according to any one of claims 1 to 10.

Images