CN115114534A - Music recommendation method, server and storage medium - Google Patents
Music recommendation method, server and storage medium Download PDFInfo
- Publication number
- CN115114534A CN115114534A CN202210859750.9A CN202210859750A CN115114534A CN 115114534 A CN115114534 A CN 115114534A CN 202210859750 A CN202210859750 A CN 202210859750A CN 115114534 A CN115114534 A CN 115114534A
- Authority
- CN
- China
- Prior art keywords
- song
- user
- characteristic information
- listening
- songs
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
- G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
- G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/48—Indexing scheme relating to G06F9/48
- G06F2209/484—Precedence
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses a music recommendation method, a server and a readable storage medium, wherein the method comprises the following steps: acquiring user characteristic information and song listening characteristic information of a user; inputting the user characteristic information and the song listening characteristic information into a pre-trained target calculation model to obtain a probability value of the song listening intention of the user; screening out a first song set from a song collection list of a user according to the probability value of the listening intention; extracting characteristic information of songs to be recommended from each song to be recommended in a recommended song set, and inputting the characteristic information of a user, the characteristic information of listening to songs, the first song set and the characteristic information of the songs to be recommended into a pre-trained song recommendation model to obtain a second song set; and the first song set and the second song set are subjected to fusion processing to obtain a target song set, and the target song set is pushed to the user terminal, so that the song listening requirements of the user in different environments are met, and the songs are more effectively recommended to the user.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a music recommendation method, a server, and a storage medium.
Background
With the continuous development of internet technology, a user can acquire information which is recommended by a recommendation system and is possibly interested by the user from a large amount of information, and the recommendation system plays an increasingly important role in many applications. Among them, in an application of song recommendation, such as music software, songs are generally recommended to a user according to a history of songs listened to by the user. However, in the actual use process, the requirements of users for listening to songs in different environments are different, and the current song recommendation mode is mainly to recommend songs to users according to historical songs listened to by the users, and is single and poor in recommendation effect. Therefore, how to recommend songs to a user more efficiently is very important.
Disclosure of Invention
The embodiment of the invention provides a music recommendation method, a server and a storage medium, songs are recommended to a user by combining a collected song list and a recommended song set, the song listening requirements of the user in different environments are met, and the songs can be more effectively recommended to the user.
In a first aspect, an embodiment of the present invention provides a music recommendation method, including:
acquiring user characteristic information and song listening characteristic information of a user;
inputting the user characteristic information and the song listening characteristic information into a pre-trained target calculation model to obtain a probability value of the song listening intention of the user, and screening out a first song set from a song collection list of the user according to the probability value of the song listening intention;
extracting characteristic information of songs to be recommended from each song to be recommended in a recommended song set, and inputting the user characteristic information, the song listening characteristic information, the first song set and the characteristic information of the songs to be recommended into a pre-trained song recommendation model to obtain a second song set;
and performing fusion processing on the first song set and the second song set to obtain a target song set, and pushing the target song set to a user terminal corresponding to the user.
In a second aspect, an embodiment of the present invention provides a music recommendation apparatus, including:
the acquisition unit is used for acquiring user characteristic information and song listening characteristic information of a user;
the screening unit is used for inputting the user characteristic information and the song listening characteristic information into a pre-trained target calculation model to obtain a probability value of the song listening intention of the user and screening out a first song set from a song collection list of the user according to the probability value of the song listening intention;
the determining unit is used for extracting the characteristic information of the songs to be recommended from each song to be recommended in the recommended song set, and inputting the user characteristic information, the song listening characteristic information, the first song set and the characteristic information of the songs to be recommended into a pre-trained song recommendation model to obtain a second song set;
and the pushing unit is used for performing fusion processing on the first song set and the second song set to obtain a target song set and pushing the target song set to a user terminal corresponding to the user.
In a third aspect, an embodiment of the present invention provides a server, where the server includes: a processor and a memory, the processor to perform:
acquiring user characteristic information and song listening characteristic information of a user;
inputting the user characteristic information and the song listening characteristic information into a pre-trained target calculation model to obtain a probability value of the song listening intention of the user, and screening out a first song set from a song collection list of the user according to the probability value of the song listening intention;
extracting characteristic information of songs to be recommended from each song to be recommended in a recommended song set, and inputting the user characteristic information, the song listening characteristic information, the first song set and the characteristic information of the songs to be recommended into a pre-trained song recommendation model to obtain a second song set;
and performing fusion processing on the first song set and the second song set to obtain a target song set, and pushing the target song set to a user terminal corresponding to the user.
In a fourth aspect, the present invention further provides a computer-readable storage medium, where program instructions are stored, and when the program instructions are executed, the computer-readable storage medium is configured to implement the method according to the first aspect.
The embodiment of the invention can acquire the user characteristic information and the song listening characteristic information of the user; inputting the user characteristic information and the song listening characteristic information into a pre-trained target calculation model to obtain a probability value of the song listening intention of the user, and screening out a first song set from a song collection list of the user according to the probability value of the song listening intention; extracting characteristic information of songs to be recommended from each song to be recommended in a recommended song set, and inputting the characteristic information of a user, the characteristic information of listening to songs, a first song set and the characteristic information of the songs to be recommended into a pre-trained song recommendation model to obtain a second song set; and performing fusion processing on the first song set and the second song set to obtain a target song set, and pushing the target song set to a user terminal corresponding to the user. By combining the collected song list and the recommended song set, the song recommending method for the user meets the song listening requirements of the user in different environments, and can recommend songs to the user more effectively.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic structural diagram of a music recommendation system according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating a music recommendation method according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a DNN structure;
FIG. 4 is a schematic diagram illustrating training of a target calculation model according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a song recommendation model training scheme according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a music recommendation device according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of a server according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
At present, in a scene that a user listens to songs through music software, the user can select songs to listen to from the song listening functions of the music software, the music software generally has two functions of a song collection list and a song recommendation list (namely a recommended song set), songs in the song collection list are added by the user, and songs in the song recommendation list are recommended by the music software according to the preference of the user for listening to the songs. In some embodiments, the user's preferences for listening to songs may be determined by the music software based on historical songs listened to by the user. The user can listen to the songs in the song collection list of the music software, and the user can also listen to the songs recommended by the song recommendation list of the music software.
However, in actual use, the user may sometimes listen to different types of songs over time, for example, the user prefers to listen to songs in the song recommendation list at 7-9 a.m. and prefers to listen to songs in the song collection list at 7-9 a.m. Therefore, the user prefers to listen to the collected songs in the song collection list sometimes and prefers to listen to the recommended songs in the song recommendation list sometimes, so that the user can know that the requirements of the song collection list and the song recommendation list exist.
The embodiment of the invention provides a music recommendation method aiming at the condition that the requirements of the user on a song collection list and a song recommendation list exist.
In the process of the music recommendation method, a user can acquire the number of user assets of the user in music software by clicking a music recommendation mode in the music software in a user terminal, generate a music recommendation request according to the number of the user assets, and send the music recommendation request to a server. After receiving the music recommendation request, the server may determine whether the number of the user assets in the music recommendation request is greater than a preset number threshold, and if the determination result is that the number of the user assets is greater than the preset number threshold, calculate a probability value of the music listening intention of the user through the target calculation model. After calculating the probability value of the user's intention to listen to the song, a first song set can be screened out from the song collection list through a shuffling algorithm according to the probability value of the intention to listen to the song, and in some embodiments, the shuffling algorithm can be a fisher-yates shuffle algorithm; meanwhile, the user characteristic information, the song listening characteristic information, the first song set and the song characteristic information to be recommended can be input into a pre-trained song recommendation model to obtain a second song set. And finally, fusing the first song set and the second song set to obtain a target song set. The server can send the target song set to the user terminal and recommend the target song set to a user corresponding to the user terminal. According to the embodiment of the invention, songs can be more effectively recommended to the user by combining the collected song list and the recommended song set to recommend songs to the user.
The music recommendation method provided by the embodiment of the invention can be applied to a music recommendation system, the system comprises music recommendation equipment and a user terminal, the music recommendation equipment can be arranged in a server, and in some embodiments, the server can comprise but is not limited to intelligent terminal equipment such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a vehicle-mounted intelligent terminal and an intelligent watch. In some embodiments, one or more databases are included in the server and may be used to store content such as audio files, songs, and the like. In some embodiments, the server may be a cloud-based server. In some embodiments, the server may be a single server, or may be one or more clusters of servers that are a series of servers, or in some embodiments, the server may be another device with computing capabilities. In some embodiments, the user terminal may include, but is not limited to, a smart terminal device such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a vehicle-mounted smart terminal, and a smart watch; in some embodiments, a client of music class, such as music software, may be installed on the user terminal.
The following describes schematically a music recommendation system according to an embodiment of the present invention with reference to fig. 1.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a music recommendation system according to an embodiment of the present invention, where the system includes a user terminal 11 and a server 12, and in some embodiments, the user terminal 11 and the server 12 may establish a communication connection in a wireless communication manner; in some scenarios, the user terminal 11 and the server 12 may also establish a communication connection through wired communication.
In the embodiment of the invention, a server 12 can obtain user characteristic information and song listening characteristic information of a user, which are sent by the user through a user terminal 11, wherein the user characteristic information comprises user identification information and/or user portrait characteristic information, the song listening characteristic information comprises one or more of song listening type information, song listening time information, song cutting information and song listening quantity information, the song listening type information comprises collected song information and recommended song information, and the song listening time information comprises one or more of song listening duration, current time, song listening start time and current time interval; the server 12 can input the user characteristic information and the song listening characteristic information into a pre-trained target calculation model to obtain the probability value of the song listening intention of the user; the server 12 can screen out a first song set from a song collection list of the user according to the probability value of the listening intention, extract the characteristic information of the song to be recommended from each song to be recommended in the recommended song set, and input the characteristic information of the user, the characteristic information of the listening song, the first song set and the characteristic information of the song to be recommended into a pre-trained song recommendation model to obtain a second song set; the server 12 may perform fusion processing on the first song set and the second song set to obtain a target song set, and push the target song set to the user terminal 11 corresponding to the user, and the user terminal 11 may output the recommendation result, that is, the target song set, to the user. In some embodiments, the output mode may be an interface displayed on the user terminal 11, in some embodiments, the output mode may also be a voice prompt, in other embodiments, the output mode may also be other modes, and the output mode is not specifically limited in the embodiments of the present invention.
Therefore, the embodiment of the invention can more accurately and effectively recommend the songs preferred by the user to the user by combining the songs collected by the user and the recommended songs, thereby improving the accuracy and the effectiveness of the song recommendation.
The following describes schematically a music recommendation method provided by an embodiment of the present invention with reference to fig. 2.
Referring to fig. 2 specifically, fig. 2 is a flowchart illustrating a music recommendation method according to an embodiment of the present invention, where the music recommendation method according to the embodiment of the present invention may be executed by a music recommendation device, where the music recommendation device is disposed in a server, and a specific explanation of the server is as described above. Specifically, the method of the embodiment of the present invention includes the following steps.
S201: and acquiring user characteristic information and song listening characteristic information of the user.
In some embodiments, the music recommendation device may obtain user characteristic information and song listening characteristic information of the user, where the user characteristic information includes user identification information and/or user portrait characteristic information, and in some embodiments, the song listening characteristic information includes one or more of song listening type information, song listening time information, song cutting information, and song listening quantity information, the song listening type information includes collected song information and recommended song information, and the song listening time information includes one or more of song listening duration, current time, song listening start time, and time interval of the current time. In some embodiments, the user characteristic information and the song listening characteristic information are vector information.
In some embodiments, the user identification information includes, but is not limited to, a user name, and the user profile characteristic information includes, but is not limited to, one or more of a user age, gender, user listening preferences, and the like. In some embodiments, the song listening type information is 1 or 0, and the song listening type information is determined according to the historical song listening records of the user within a preset time range from the current time and is used for indicating whether the song is a song in the song collection list. If the historical song listening record is a song in the song collection list, the song listening type information is collected song information and takes 1, and if the historical song listening record is not a song in the song collection list, the song listening type information is recommended song information and takes 0. In some embodiments, the song listening time information may be obtained by a time stamp. In some embodiments, the listening characteristics information may further include song basic information, such as song basic information may include, but is not limited to, one or more of a song identification, a language identification, a singer identification, and the like.
In one embodiment, before acquiring user characteristic information and song listening characteristic information, when receiving a music recommendation request sent by a user terminal corresponding to a user, music recommendation equipment can acquire the number of songs in a song collection list of the user and judge whether the number of songs in the song collection list of the user is greater than a preset number threshold; if the judgment result is yes, the steps of obtaining the user characteristic information and the song listening characteristic information can be executed; if not, outputting prompt information, wherein the prompt information is used for instructing a user to add songs to the song collection list, and sending the music recommendation request after the number of the songs in the song collection list is larger than a preset number threshold.
For example, assuming that the preset number threshold is 5, when the server receives a music recommendation request sent by a user terminal corresponding to the user, it may be determined whether the number of songs in the song collection list of the user is greater than 5, and if the number of songs in the song collection list is greater than 5, it may be determined to perform the steps of obtaining the user characteristic information and listening to the song characteristic information. If the number of songs in the song collection list is less than or equal to 5, a prompt may be output for instructing the user to add songs to the song collection list until the number of songs in the song collection list is greater than 5.
In one embodiment, the music recommendation request carries user information and user song listening information; when the music recommendation device obtains the user characteristic information and the song listening characteristic information, the music recommendation device can extract user vector information and song listening vector information from the user information and the song listening information carried by the music recommendation request, namely the user vector information is determined as the user characteristic information, and the song listening vector information is determined as the song listening characteristic information.
In some embodiments, when the music recommendation device extracts the user vector information and the song listening vector information from the user information and the song listening information carried in the music recommendation request, the user vector information and the song listening vector information can be obtained by adopting a preset feature extraction model. In some embodiments, the preset feature extraction model may be obtained by training a neural network model, and the feature extraction model is not specifically limited in the embodiments of the present invention. In some embodiments, the Neural network model adopted in the embodiments of the present invention may be Deep Neural Networks (DNNs), a structure of the DNNs may be illustrated by taking fig. 3 as an example, fig. 3 is a schematic structural diagram of a DNN, as shown in fig. 7, a schematic structural diagram of a DNN with three layers is shown, and Neural network layers inside the DNN may be classified into three types: the input layer, the hidden layer and the output layer, generally speaking, the first layer is the input layer, the last layer is the output layer, the middle layers are all the hidden layers, and the layers are all connected, that is, any neuron of the ith layer is connected with any neuron of the (i + 1) th layer.
S202: inputting the user characteristic information and the song listening characteristic information into a pre-trained target calculation model to obtain a probability value of the song listening intention of the user, and screening out a first song set from a song collection list of the user according to the probability value of the song listening intention.
In the embodiment of the invention, the music recommendation equipment can input the user characteristic information and the song listening characteristic information into a pre-trained target calculation model to obtain the probability value of the song listening intention of the user, and a first song set is screened out from a song collection list of the user according to the probability value of the song listening intention. In some embodiments, the pre-trained target computation model may be trained by a neural network model. In certain embodiments, the neural network model employed by embodiments of the present invention may include, but is not limited to, DNN.
In one embodiment, when the music recommendation device inputs the user characteristic information and the song listening characteristic information into a pre-trained target calculation model to obtain the probability value of the song listening intention of the user, the music recommendation device can input the user characteristic information and the song listening characteristic information into the pre-trained target calculation model to predict and obtain the first number of songs collected in a song listening collection list of the user and the second number of songs recommended in a song listening recommendation list of the user; and determining the probability value of the song listening intention of the user as the ratio value of the first song quantity to the second song quantity. In some embodiments, the listening intention probability value is used to indicate a probability value that the user prefers to listen to songs of the song collection list.
For example, the music recommendation device inputs the user characteristic information and the song listening characteristic information acquired from the music recommendation request sent by the user 1 into a pre-trained target calculation model, and predicts that the first song quantity of the songs collected in the song listening collection list of the user 1 is 10 and the second song quantity of the songs recommended in the song listening list of the user 1 is 20, then the ratio value of the first song quantity 10 to the second song quantity 20 can be determined to be 1/2, and therefore the probability value of the song listening intention of the user 1 can be determined to be 0.5.
In one embodiment, when the probability value of the intention to listen to the song of the user is greater than a first preset threshold, the probability value of the intention to listen to the song is confirmed to be the first threshold, and when the probability value of the intention to listen to the song of the user is smaller than a second preset threshold, the probability value of the intention to listen to the song is confirmed to be the second threshold, wherein the first preset probability is greater than the second preset probability. For example, assuming that the probability value of the listening intention is P, the first preset threshold is 0.8, and the second preset threshold is 0.2, when P is greater than 0.8, it is determined that the value of P is 0.8, and when P is less than 0.2, it is determined that the value of P is 0.2.
In one embodiment, the music recommendation device may obtain a first training data set before inputting the user characteristic information and the singing listening characteristic information into a pre-trained target calculation model to obtain a singing listening intention probability value of the user, where the first training data set includes a plurality of first training data, and the plurality of first training data includes first training user characteristic information and first training singing listening characteristic information; inputting a plurality of first training data in a first training data set into a preset first deep neural network model for training to obtain a first loss function value; adjusting a first model parameter of the first deep neural network model according to the first loss function value; inputting a plurality of first training data in a first training data set into the first deep neural network model after the first model parameters are adjusted for retraining; and when the first loss function value obtained by retraining is smaller than a first preset threshold value, determining to obtain a target calculation model.
Specifically, the description may be given by taking fig. 4 as an example, where fig. 4 is a schematic training diagram of a target computation model provided in an embodiment of the present invention, a first training data set 41 is input into a preset first feature extraction model 42 to obtain first training user feature information and first training singing feature information, where the first training data set 41 includes user identification information, user portrait information, singing type information, singing time information, singing cutting information, singing number information, and other information, and the first user feature information and the first training singing feature information are input into a first deep neural network model 43 for training to obtain a first loss function value 44; adjusting a first model parameter of the first deep neural network model 43 according to the first loss function value 44; inputting a plurality of first training data into the first deep neural network model 43 with the first model parameters adjusted for retraining; and when the retrained first loss function value 44 is smaller than a first preset threshold value, determining to obtain a target calculation model.
In one embodiment, when the music recommendation device screens out a first song set from a song collection list of a user according to the probability value of the intention to listen to the songs, a song priority list can be randomly selected from the song collection list by using a shuffling algorithm; determining the quantity to be screened according to the probability value of the listening intention and the quantity of the songs collected in the song priority list; and screening a first song set from the song priority list according to the quantity to be screened.
In one embodiment, the music recommendation device may swap (or not swap) the last song with one of any n-1 songs before, then swap the next to last song with one of any n-2 songs before when randomly selecting a priority list of songs from the song collection list using a shuffling algorithm that ensures that the probability of each element at each position is equal.
For example, assuming the initial ordering of songs in the song collection list as song 0, song 1, song 2, song 3, song 4, and designated by numeral 01234, the step of randomly selecting a priority list of songs from the song collection list is:
randomly selecting a number (such as 3) from the 5 positions (including 0 and 4) of [0,4] and exchanging with the number 4 to obtain 01243, wherein the probability of placing 3 in the number 4 position is 1/5; randomly selecting a number (such as 0) from the 4 positions (including 0 and 3) of [0,3] and exchanging number 3 to obtain 41203, wherein the probability of 0 being placed in the 3 rd position is (4/5) × (1/4) ═ 1/5; 21403 is obtained by randomly selecting one number (for example, 0) from the 3 positions [0,2] (including 0 and 2) and exchanging with the number 2, wherein the probability of the position 4 of the number 2 is (4/5) × (3/4) × (1/3) ═ 1/5; randomly selecting one number (for example, 0) from the 2 positions (including 0 and 1) of [0,1] and exchanging with number 1 to obtain 12403, wherein the probability of placing 2 in the number 1 position is (4/5) × (3/4) × (2/3) × (1/2) ═ 1/5; the number (for example, 0) and number 0 are randomly selected from the 1 positions [0,0] (including 0 and 0), and 12403 is obtained, and the probability of placing 1 in the 0 th position is (4/5) × (3/4) × (2/3) × (1/2) ═ 1/5. Thus, a song priority list of song 1, song 2, song 4, song 0, song 3 may be obtained.
In one embodiment, when the music recommendation device determines the quantity to be filtered according to the probability value of the intention to listen to the songs and the quantity of the songs collected in the song priority list, the quantity to be filtered can be determined according to the product of the probability value of the intention to listen to the songs and the quantity of the songs collected in the song priority list.
S203: extracting the characteristic information of the songs to be recommended from each song to be recommended in the recommended song set, and inputting the user characteristic information, the song listening characteristic information, the first song set and the song characteristic information to be recommended into a pre-trained song recommendation model to obtain a second song set.
In the embodiment of the invention, the music recommendation equipment can obtain the recommended song set, extract the characteristic information of the songs to be recommended from each song to be recommended in the recommended song set, and input the user characteristic information, the song listening characteristic information, the first song set and the song characteristic information to be recommended into a pre-trained song recommendation model to obtain the second song set. In some embodiments, the pre-trained song recommendation model may include, but is not limited to, DNN.
In one embodiment, when the music recommendation device inputs the user characteristic information, the song listening characteristic information, the first song set and the characteristic information of the songs to be recommended into the pre-trained song recommendation model to obtain the second song set, the music recommendation device can input the user characteristic information, the song listening characteristic information, the first song set and the characteristic information of the songs to be recommended into the pre-trained song recommendation model to obtain a recommendation score value corresponding to each song to be recommended in the recommended song set; and sequencing the songs to be recommended according to the recommendation score value corresponding to each song to be recommended from large to small, and determining the top M songs to be recommended to form a second song set, wherein M is a positive integer.
For example, assuming that the value of M is 5, the music recommendation apparatus may input the user characteristic information of the user 1, the song listening characteristic information, the first song set of the user 1, and the characteristic information of the song to be recommended into a pre-trained song recommendation model, and obtain that the recommendation score value corresponding to song 1 is 80, the recommendation score value corresponding to song 2 is 82, the recommendation score value corresponding to song 3 is 83, the recommendation score value corresponding to song 4 is 81, the recommendation score value corresponding to song 5 is 79, the recommendation score value corresponding to song 6 is 84, the recommendation score value corresponding to song 7 is 78, the recommendation score value corresponding to song 8 is 85, the recommendation score value corresponding to song 9 is 86, and the recommendation score value corresponding to song 10 is 88 in the set of 10 songs to be recommended. According to the recommendation score value corresponding to each song to be recommended, sequencing the songs to be recommended from large to small in sequence as follows: song 10, song 9, song 8, song 6, song 3, song 2, song 4, song 1, song 5, and song 7, then the top 5 songs of song 10, song 9, song 8, song 6, and song 3 to be recommended may be determined to be the second set of songs.
In one embodiment, before inputting the user characteristic information, the song listening characteristic information, the first song set and the song characteristic information to be recommended into a pre-trained song recommendation model to obtain a second song set, the music recommendation device may obtain a second training data set, where the second training data set includes a plurality of second training data, and the plurality of second training data includes one or more of second training user characteristic information, second training song listening characteristic information, and training song listening intention song information; inputting a plurality of second training data in a second training data set into a second deep neural network model for training to obtain a second loss function value; adjusting a second model parameter of the second deep neural network model according to the second loss function value; inputting a plurality of second training data in a second training data set into a second deep neural network model after second model parameters are adjusted for retraining; and when the second loss function value obtained by retraining is smaller than a second preset threshold value, determining to obtain a song recommendation model. In some embodiments, training the listening intention song information may include, but is not limited to, training a probability value of the user's listening intention.
Specifically, the description may be given by taking fig. 5 as an example, where fig. 5 is a schematic training diagram of a song recommendation model provided in an embodiment of the present invention, a second training data set 51 is input to a preset second feature extraction model 52 to obtain second training user feature information, second training song listening feature information, and a probability value of training song listening intention, where the second training data set 51 includes user identification information, user portrait information, song listening type information, song listening time information, song cutting information, song listening quantity information, song listening intention song information, and the second user feature information, the second training song listening feature information, and the probability value of training song listening intention are input to a second deep neural network model 53 for training to obtain a second loss function value 54; adjusting a second model parameter of the second deep neural network model 53 according to the second loss function value 54; inputting a plurality of second training data into the second deep neural network model 53 with the second model parameters adjusted for retraining; and when the second loss function value 54 obtained by retraining is smaller than a second preset threshold value, determining to obtain a song recommendation model.
S204: and performing fusion processing on the first song set and the second song set to obtain a target song set, and pushing the target song set to a user terminal corresponding to the user.
In the embodiment of the invention, the music recommendation device can perform fusion processing on the first song set and the second song set to obtain the target song set, and pushes the target song set to the user terminal corresponding to the user.
In an embodiment, when the music recommendation device performs fusion processing on the first song set and the second song set to obtain the target song set, the music recommendation device may perform fusion processing on the first song set and the second song set according to a first preset weight of the first song set and a second preset weight of the second song set to obtain the target song set. In other embodiments, the music recommendation device may further perform fusion processing on the first song set and the second song set in other manners, and the manner of performing fusion processing on the first song set and the second song set in the embodiment of the present invention is not particularly limited.
The embodiment of the invention can input the user characteristic information and the song listening characteristic information into a pre-trained target calculation model to obtain the probability value of the song listening intention of the user; screening out a first song set from a song collection list of a user according to the probability value of the listening intention; inputting the user characteristic information, the song listening characteristic information, the first song set and the characteristic information of the songs to be recommended into a pre-trained song recommendation model to obtain a second song set; and performing fusion processing on the first song set and the second song set to obtain a target song set, and pushing the target song set to a user terminal corresponding to the user. By adopting the mode of combining the listening intention of the user at different time, the user collection of songs and the recommendation of songs, the songs which accord with the user preference at different time periods can be more accurately and effectively recommended to the user, the listening requirements of the user at different time periods are met, and the accuracy and the effectiveness of song recommendation are improved.
Referring to fig. 6, fig. 6 is a schematic structural diagram of a music recommendation device according to an embodiment of the present invention. Specifically, the music recommendation device is disposed in a server, and the music recommendation device includes: an acquisition unit 601, a screening unit 602, a determination unit 603, and a pushing unit 604;
an obtaining unit 601, configured to obtain user characteristic information and song listening characteristic information of a user;
a screening unit 602, configured to input the user characteristic information and the song listening characteristic information into a pre-trained target calculation model, obtain a probability value of the user's intention to listen to a song, and screen a first song set from a song collection list of the user according to the probability value of the intention to listen to a song;
the determining unit 603 is configured to extract feature information of songs to be recommended from each song to be recommended in the recommended song set, and input the user feature information, the listening feature information, the first song set, and the feature information of songs to be recommended into a pre-trained song recommendation model to obtain a second song set;
and the pushing unit 604 is configured to perform fusion processing on the first song set and the second song set to obtain a target song set, and push the target song set to a user terminal corresponding to the user.
Further, the screening unit 602 inputs the user characteristic information and the song listening characteristic information into a pre-trained target calculation model, and when obtaining the probability value of the user's intention to listen to a song, is specifically configured to:
inputting the user characteristic information and the song listening characteristic information into a pre-trained target calculation model, and predicting to obtain a first song quantity of songs collected in a song listening collection list of the user and a second song quantity of songs recommended in a recommended song list of the user;
and determining the ratio value of the first song quantity to the second song quantity as the probability value of the user's intention to listen to the songs.
Further, when the screening unit 602 screens out the first song set from the song collection list of the user according to the probability value of the intention to listen to the song, it is specifically configured to:
randomly selecting a song priority list from the song collection list by using a shuffling algorithm;
determining the quantity to be screened according to the probability value of the listening intention and the quantity of the songs collected in the song priority list;
and screening the first song set from the song priority list according to the quantity to be screened.
Further, when the determining unit 603 inputs the user characteristic information, the song listening characteristic information, the first song set, and the song characteristic information to be recommended into a pre-trained song recommendation model to obtain a second song set, the determining unit is specifically configured to:
inputting the user characteristic information, the song listening characteristic information, the first song set and the song characteristic information to be recommended into a pre-trained song recommendation model to obtain a recommendation score value corresponding to each song to be recommended in the song set to be recommended;
and sequencing the songs to be recommended according to the recommendation score value corresponding to each song to be recommended from large to small, and determining the top M songs to be recommended to form the second song set, wherein M is a positive integer.
Further, the pushing unit 604 performs fusion processing on the first song set and the second song set to obtain a target song set, and is specifically configured to:
and according to the first preset weight of the first song set and the second preset weight of the second song set, carrying out fusion processing on the first song set and the second song set to obtain the target song set.
Further, the screening unit 602 inputs the user characteristic information and the song listening characteristic information into a pre-trained target calculation model, and before obtaining the probability value of the user's intention to listen to the song, further:
acquiring a first training data set, wherein the first training data set comprises a plurality of first training data, and the plurality of first training data comprise first training user characteristic information and first training singing listening characteristic training information;
inputting the plurality of first training data in the first training data set into a preset first deep neural network model for training to obtain a first loss function value;
adjusting a first model parameter of the first deep neural network model according to the first loss function value;
inputting the plurality of first training data in the first training data set into the first deep neural network model with the first model parameters adjusted for retraining;
and when the first loss function value obtained by retraining is smaller than a first preset threshold value, determining to obtain the target calculation model.
Further, the determining unit 603 inputs the user characteristic information, the song listening characteristic information, the first song set, and the song characteristic information to be recommended into a pre-trained song recommendation model, and before obtaining a second song set, is further configured to:
acquiring a second training data set, wherein the second training data set comprises a plurality of second training data, and the plurality of second training data comprise one or more of second training user characteristic information, second training song listening characteristic information and training song listening intention song information;
inputting the plurality of second training data in the second training data set into a second deep neural network model for training to obtain a second loss function value;
adjusting a second model parameter of the second deep neural network model according to the second loss function value;
inputting the plurality of second training data in the second training data set into a second deep neural network model with the second model parameters adjusted for retraining;
and when the second loss function value obtained by retraining is smaller than a second preset threshold value, determining to obtain the song recommendation model.
Further, before the obtaining unit 601 obtains the user characteristic information and the song listening characteristic information of the user, it is further configured to:
when a music recommendation request sent by a user terminal corresponding to the user is received, acquiring the number of songs in a song collection list of the user, and judging whether the number of songs in the song collection list of the user is larger than a preset number threshold value or not;
if the judgment result is yes, the step of acquiring the user characteristic information and the song listening characteristic information is executed;
and if not, outputting prompt information, wherein the prompt information is used for indicating the user to add the songs to the song collection list, and sending the music recommendation request after the number of the songs in the song collection list is larger than the preset number threshold.
The embodiment of the invention can input the user characteristic information and the song listening characteristic information into a pre-trained target calculation model to obtain the probability value of the song listening intention of the user; screening out a first song set from a song collection list of the user according to the probability value of the listening intention; inputting the user characteristic information, the song listening characteristic information, the first song set and the song characteristic information to be recommended into a pre-trained song recommendation model to obtain a second song set; and performing fusion processing on the first song set and the second song set to obtain a target song set, and pushing the target song set to a user terminal corresponding to the user. By the method, the song listening requirements of the user in different environments are met, and the songs can be effectively recommended to the user.
Referring to fig. 7, fig. 7 is a schematic structural diagram of a server according to an embodiment of the present invention. Specifically, the server includes: memory 701, processor 702.
In one embodiment, the server further includes a data interface 703, and the data interface 703 is used for transferring data information between the server and other devices.
The memory 701 may include a volatile memory (volatile memory); the memory 701 may also include a non-volatile memory (non-volatile memory); the memory 701 may also comprise a combination of memories of the kind described above. The processor 702 may be a Central Processing Unit (CPU). The processor 702 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a Programmable Logic Device (PLD), or a combination thereof. The PLD may be a Complex Programmable Logic Device (CPLD), a field-programmable gate array (FPGA), or any combination thereof.
The memory 701 is used for storing programs, and the processor 702 may call the programs stored in the memory 701 to execute the following steps:
acquiring user characteristic information and song listening characteristic information of a user;
inputting the user characteristic information and the song listening characteristic information into a pre-trained target calculation model to obtain a probability value of the song listening intention of the user, and screening out a first song set from a song collection list of the user according to the probability value of the song listening intention;
extracting characteristic information of songs to be recommended from each song to be recommended in a recommended song set, and inputting the user characteristic information, the song listening characteristic information, the first song set and the characteristic information of the songs to be recommended into a pre-trained song recommendation model to obtain a second song set;
and performing fusion processing on the first song set and the second song set to obtain a target song set, and pushing the target song set to a user terminal corresponding to the user.
Further, the processor 702 inputs the user characteristic information and the song listening characteristic information into a pre-trained target calculation model, and when obtaining the probability value of the user's intention to listen to songs, the processor is specifically configured to:
inputting the user characteristic information and the song listening characteristic information into a pre-trained target calculation model, and predicting to obtain a first song quantity of songs collected in a song listening collection list of the user and a second song quantity of songs recommended in a recommended song list of the user;
and determining the ratio value of the first song quantity to the second song quantity as the probability value of the user's intention to listen to the songs.
Further, when the processor 702 selects the first song set from the song collection list of the user according to the probability value of the intention to listen to songs, the method is specifically configured to:
randomly selecting a song priority list from the song collection list by using a shuffling algorithm;
determining the quantity to be screened according to the probability value of the listening intention and the quantity of the songs collected in the song priority list;
and screening the first song set from the song priority list according to the quantity to be screened.
Further, the processor 702 inputs the user characteristic information, the song listening characteristic information, the first song set, and the song characteristic information to be recommended into a pre-trained song recommendation model, and when a second song set is obtained, the processor is specifically configured to:
inputting the user characteristic information, the song listening characteristic information, the first song set and the song characteristic information to be recommended into a pre-trained song recommendation model to obtain a recommendation score value corresponding to each song to be recommended in the song set to be recommended;
and sequencing the songs to be recommended according to the recommendation score value corresponding to each song to be recommended from large to small, and determining the top M songs to be recommended to form the second song set, wherein M is a positive integer.
Further, when the processor 702 performs fusion processing on the first song set and the second song set to obtain a target song set, the method is specifically configured to:
and according to the first preset weight of the first song set and the second preset weight of the second song set, carrying out fusion processing on the first song set and the second song set to obtain the target song set.
Further, the processor 702 inputs the user characteristic information and the song listening characteristic information into a pre-trained target calculation model, and before obtaining the probability value of the user's intention to listen to the song, further:
acquiring a first training data set, wherein the first training data set comprises a plurality of first training data, and the plurality of first training data comprise first training user characteristic information and first training singing listening characteristic training information;
inputting the plurality of first training data in the first training data set into a preset first deep neural network model for training to obtain a first loss function value;
adjusting a first model parameter of the first deep neural network model according to the first loss function value;
inputting the plurality of first training data in the first training data set into the first deep neural network model with the first model parameters adjusted for retraining;
and when the first loss function value obtained by retraining is smaller than a first preset threshold value, determining to obtain the target calculation model.
Further, the processor 702 inputs the user characteristic information, the song listening characteristic information, the first song set, and the song characteristic information to be recommended into a pre-trained song recommendation model, and before obtaining a second song set, the processor is further configured to:
acquiring a second training data set, wherein the second training data set comprises a plurality of second training data, and the plurality of second training data comprise one or more of second training user characteristic information, second training song listening characteristic information and training song listening intention song information;
inputting the plurality of second training data in the second training data set into a second deep neural network model for training to obtain a second loss function value;
adjusting a second model parameter of the second deep neural network model according to the second loss function value;
inputting the plurality of second training data in the second training data set into a second deep neural network model with the second model parameters adjusted for retraining;
and when the second loss function value obtained by retraining is smaller than a second preset threshold value, determining to obtain the song recommendation model.
Further, before the processor 702 obtains the user characteristic information and the song listening characteristic information of the user, it is further configured to:
when a music recommendation request sent by a user terminal corresponding to the user is received, acquiring the number of songs in a song collection list of the user, and judging whether the number of songs in the song collection list of the user is greater than a preset number threshold value or not;
if the judgment result is yes, the step of acquiring the user characteristic information and the song listening characteristic information is executed;
and if not, outputting prompt information, wherein the prompt information is used for indicating the user to add the songs to the song collection list, and sending the music recommendation request after the number of the songs in the song collection list is larger than the preset number threshold.
The embodiment of the invention can input the user characteristic information and the song listening characteristic information into a pre-trained target calculation model to obtain the probability value of the song listening intention of the user; screening out a first song set from a song collection list of the user according to the probability value of the listening intention; inputting the user characteristic information, the song listening characteristic information, the first song set and the characteristic information of the songs to be recommended into a pre-trained song recommendation model to obtain a second song set; and performing fusion processing on the first song set and the second song set to obtain a target song set, and pushing the target song set to a user terminal corresponding to the user. By the method, the requirement of listening to songs of the user in different environments is met, and the songs can be effectively recommended to the user.
The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the method described in the embodiment corresponding to fig. 2 of the present invention is implemented, and the apparatus according to the embodiment corresponding to the present invention described in fig. 6 may also be implemented, which is not described herein again.
The computer readable storage medium may be an internal storage unit of the device according to any of the foregoing embodiments, for example, a hard disk or a memory of the device. The computer readable storage medium may also be an external storage device of the device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), etc. provided on the device. Further, the computer-readable storage medium may also include both an internal storage unit and an external storage device of the apparatus. The computer-readable storage medium is used for storing the computer program and other programs and data required by the terminal. The computer readable storage medium may also be used to temporarily store data that has been output or is to be output.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
While the invention has been described with reference to a number of embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A music recommendation method, comprising:
acquiring user characteristic information and song listening characteristic information of a user;
inputting the user characteristic information and the song listening characteristic information into a pre-trained target calculation model to obtain a probability value of the song listening intention of the user, and screening out a first song set from a song collection list of the user according to the probability value of the song listening intention;
extracting characteristic information of songs to be recommended from each song to be recommended in a recommended song set, and inputting the user characteristic information, the song listening characteristic information, the first song set and the characteristic information of the songs to be recommended into a pre-trained song recommendation model to obtain a second song set;
and performing fusion processing on the first song set and the second song set to obtain a target song set, and pushing the target song set to a user terminal corresponding to the user.
2. The method of claim 1, wherein the inputting the user characteristic information and the singing listening characteristic information into a pre-trained target calculation model to obtain the probability value of the singing listening intention of the user comprises:
inputting the user characteristic information and the song listening characteristic information into a pre-trained target calculation model, and predicting to obtain a first song quantity of songs collected in a song listening collection list of the user and a second song quantity of songs recommended in a recommended song listening list of the user;
and determining the ratio value of the first song quantity to the second song quantity as the probability value of the user's intention to listen to the songs.
3. The method of claim 2, wherein the screening out a first set of songs from the user's song collection list according to the probability value of listening to songs comprises:
randomly selecting a song priority list from the song collection list by using a shuffling algorithm;
determining the number to be screened according to the probability value of the listening intention and the number of the songs collected in the song priority list;
and screening the first song set from the song priority list according to the quantity to be screened.
4. The method according to claim 1, wherein the inputting the user characteristic information, the song listening characteristic information, the first song set and the song characteristic information to be recommended into a pre-trained song recommendation model to obtain a second song set comprises:
inputting the user characteristic information, the song listening characteristic information, the first song set and the song characteristic information to be recommended into a pre-trained song recommendation model to obtain a recommendation score value corresponding to each song to be recommended in the song set to be recommended;
and sequencing the songs to be recommended according to the recommendation score value corresponding to each song to be recommended from large to small, and determining the top M songs to be recommended to form the second song set, wherein M is a positive integer.
5. The method of claim 1, wherein the fusing the first song set and the second song set to obtain a target song set comprises:
and according to the first preset weight of the first song set and the second preset weight of the second song set, carrying out fusion processing on the first song set and the second song set to obtain the target song set.
6. The method of claim 1, wherein before inputting the user characteristic information and the song listening characteristic information into a pre-trained target calculation model and obtaining the probability value of the user's intention to listen to songs, the method further comprises:
acquiring a first training data set, wherein the first training data set comprises a plurality of first training data, and the plurality of first training data comprise first training user characteristic information and first training singing listening characteristic information;
inputting the plurality of first training data in the first training data set into a preset first deep neural network model for training to obtain a first loss function value; adjusting a first model parameter of the first deep neural network model according to the first loss function value; inputting the plurality of first training data in the first training data set into the first deep neural network model with the first model parameters adjusted for retraining;
and when the first loss function value obtained by retraining is smaller than a first preset threshold value, determining to obtain the target calculation model.
7. The method according to claim 1, wherein before inputting the user characteristic information, the song listening characteristic information, the first song set and the song characteristic information to be recommended into a pre-trained song recommendation model to obtain a second song set, the method further comprises:
acquiring a second training data set, wherein the second training data set comprises a plurality of second training data, and the plurality of second training data comprise one or more of second training user characteristic information, second training song listening characteristic information and training song listening intention song information;
inputting the plurality of second training data in the second training data set into a second deep neural network model for training to obtain a second loss function value; adjusting a second model parameter of the second deep neural network model according to the second loss function value; inputting the plurality of second training data in the second training data set into the second deep neural network model after the second model parameters are adjusted for retraining;
and when the second loss function value obtained by retraining is smaller than a second preset threshold value, determining to obtain the song recommendation model.
8. The method according to claim 1, wherein before obtaining the user characteristic information and the song listening characteristic information of the user, the method further comprises:
when a music recommendation request sent by a user terminal corresponding to the user is received, acquiring the number of songs in a song collection list of the user, and judging whether the number of songs in the song collection list of the user is greater than a preset number threshold value or not;
if the judgment result is yes, the step of acquiring the user characteristic information and the song listening characteristic information is executed;
and if not, outputting prompt information, wherein the prompt information is used for indicating the user to add the songs to the song collection list, and sending the music recommendation request after the number of the songs in the song collection list is larger than the preset number threshold.
9. A server, comprising a processor, an input device, an output device, and a memory, the processor, the input device, the output device, and the memory being interconnected, wherein the memory is configured to store a computer program, the computer program comprising a program, the processor being configured to invoke the program to perform the method of any of claims 1-8.
10. A computer-readable storage medium, having stored thereon program instructions for implementing the method of any one of claims 1-8 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210859750.9A CN115114534A (en) | 2022-07-21 | 2022-07-21 | Music recommendation method, server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210859750.9A CN115114534A (en) | 2022-07-21 | 2022-07-21 | Music recommendation method, server and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115114534A true CN115114534A (en) | 2022-09-27 |
Family
ID=83334909
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210859750.9A Pending CN115114534A (en) | 2022-07-21 | 2022-07-21 | Music recommendation method, server and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115114534A (en) |
-
2022
- 2022-07-21 CN CN202210859750.9A patent/CN115114534A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110012356B (en) | Video recommendation method, device and equipment and computer storage medium | |
| CN106326391B (en) | Multimedia resource recommendation method and device | |
| CN110727868B (en) | Object recommendation method, device and computer-readable storage medium | |
| CN109344314B (en) | Data processing method and device and server | |
| CN111209477B (en) | Information recommendation method and device, electronic equipment and storage medium | |
| CN109241451B (en) | Content combination recommendation method and device and readable storage medium | |
| CN113505272B (en) | Control method and device based on behavior habit, electronic equipment and storage medium | |
| CN110413867B (en) | Method and system for content recommendation | |
| CN110413888A (en) | A kind of books recommended method and device | |
| CN111797320A (en) | Data processing method, device, equipment and storage medium | |
| CN112085058A (en) | Object combination recall method and device, electronic equipment and storage medium | |
| CN111523035A (en) | Recommendation method, device, server and medium for APP browsing content | |
| CN112100221A (en) | Information recommendation method and device, recommendation server and storage medium | |
| CN110598105A (en) | Recommendation method, device, equipment and medium based on probability sampling | |
| CN113656699B (en) | User feature vector determining method, related equipment and medium | |
| CN114398973A (en) | Media content label identification method, device, equipment and storage medium | |
| CN111324725B (en) | Topic acquisition method, terminal and computer readable storage medium | |
| CN115114534A (en) | Music recommendation method, server and storage medium | |
| CN113593546B (en) | Terminal equipment awakening method and device, storage medium and electronic device | |
| CN114969427A (en) | Singing list generation method and device, electronic equipment and storage medium | |
| CN114418624A (en) | Item recommendation method and device, electronic equipment and readable medium | |
| CN114677168A (en) | Resource recommendation method, device, equipment and medium | |
| CN113901261A (en) | Abnormal object cluster positioning method and device, electronic equipment and storage medium | |
| CN113111273A (en) | Information recommendation method and device, electronic equipment and storage medium | |
| CN112257781A (en) | Model training method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |