Method, apparatus, computer device, and storage medium for pushing multimedia content

Abstract

The present disclosure provides a method, apparatus, computer device, and storage medium for pushing multimedia content. Among them, the method includes: obtaining historical operation information of a plurality of alternative users on target multimedia content during a target historical period, and real-time operation information on the target multimedia content; based on the historical operation information and real-time operation information respectively corresponding to the plurality of alternative users, determining a target sample user from the alternative users, and training a neural network model to be trained based on sample data composed of sample attribute information corresponding to the target sample user and multimedia attribute information of the target multimedia content to obtain a target neural network model; in response to a target user belonging to the first type triggering a preset push event, using the target neural network to determine a push strategy for pushing the target multimedia content to the target user, and pushing the target multimedia content based on the push strategy.

Description

Technical Field

[0001] The present disclosure relates to the field of machine learning technology, and more particularly, to a method, apparatus, computer device, and storage medium for pushing multimedia content. Background Art

[0002] Streaming information media is becoming increasingly popular in people's lives. Currently, related applications for streaming information media usually push multimedia content that the user may be interested in to the user on the home page after the user starts the application; and the pushed multimedia content is usually determined by using the historical records of the user's searches for the corresponding topics of the multimedia content within a certain historical period, or by using the historical operation information of the user on other related multimedia content. However, this way of pushing multimedia content is often ineffective and lacks pertinence for the user in many cases. Summary of the Invention

[0003] Embodiments of the present disclosure at least provide a method, apparatus, computer device, and storage medium for pushing multimedia content.

[0004] In a first aspect, an embodiment of the present disclosure provides a method for pushing multimedia content, including:

[0005] Obtaining historical operation information of multiple alternative users on target multimedia content in a target historical period, and real-time operation information on the target multimedia content;

[0006] Based on the historical operation information and real-time operation information respectively corresponding to multiple alternative users, determining a target sample user from the alternative users, and training a neural network model to be trained based on sample data composed of the sample attribute information corresponding to the target sample user and the multimedia attribute information of the target multimedia content, to obtain a target neural network model; wherein, the target sample user includes an alternative user whose user type is converted from a first type to a second type when the target multimedia content is pushed;

[0007] In response to a target user belonging to the first type triggering a preset push event, using the target neural network to determine a push strategy for pushing the target multimedia content to the target user, and pushing the target multimedia content based on the push strategy.

[0008] In this way, by using the historical operation information of multiple alternative users on the target multimedia content in the target historical period and the real-time operation information on the target multimedia content, the target sample users are screened from the multiple alternative users. The target sample users include alternative users whose user type is converted from the first type to the second type when the target multimedia content is pushed. Then, using the sample data composed of the sample attribute information corresponding to the target sample users and the multimedia attribute information of the target multimedia content, the neural network model to be trained is trained to obtain the target neural network model. When the target push event is triggered, the target neural network is used to determine whether to push the target multimedia content to the target user, so that the attribution prediction of the user's conversion from the first type to the second type for the target multimedia content can be more refined. According to the result of the attribution prediction, the push strategy for pushing the target multimedia content to the user is determined, improving the efficiency and pertinence of the push.

[0009] In an alternative implementation, the obtaining of the historical operation information of multiple alternative users on the target multimedia content in the target historical period includes:

[0010] Determine the object attribute information of the content object corresponding to the target multimedia content;

[0011] Based on the object attribute information, determine the target historical period corresponding to the target multimedia content, and obtain the historical operation information of multiple alternative users on the target multimedia content in the target historical period.

[0012] In an alternative implementation, the obtaining of the real-time operation information of the alternative users on the target multimedia content includes:

[0013] For each alternative user, in each operation cycle among the multiple operation cycles corresponding to the alternative user, determine the operation information of each alternative user on the target multimedia content within each operation cycle;

[0014] Based on the operation information corresponding to the multiple operation cycles respectively, obtain the real-time operation information corresponding to each alternative user.

[0015] In an alternative implementation, the determining of the target sample users from the alternative users based on the historical operation information and the real-time operation information corresponding to the multiple alternative users respectively includes:

[0016] For each alternative user among the multiple alternative users, perform fusion processing on the historical operation information and the real-time operation information corresponding to each alternative user to obtain the target operation information corresponding to each alternative user;

[0017] In response to the target operation information corresponding to any alternative user satisfying the preset conditions, determine the alternative user as the target sample user; wherein, the preset conditions satisfy the conversion of the alternative user from the first type to the second type.

[0018] In an alternative implementation manner, the first type includes: the shallow interaction population; the second type includes the interest planting grass population;

[0019] The preset conditions include at least one of the following:

[0020] The exposure times of the target multimedia content are greater than or equal to the first exposure times threshold, and the exposure times with the exposure duration greater than the first preset duration threshold are greater than the second exposure times threshold;

[0021] The play duration of the target multimedia content is greater than the first play times threshold, and the play times with the play duration greater than the second preset duration threshold are greater than the preset play times threshold;

[0022] The number of times the target multimedia content is clicked by the alternative user is greater than or equal to the preset click times threshold;

[0023] The stay duration on the advertisement landing page corresponding to the target multimedia content is greater than the preset stay duration threshold;

[0024] The number of likes of the target multimedia content by the alternative user is greater than the preset number of likes threshold;

[0025] The number of comments of the target multimedia content by the alternative user is greater than or equal to the comment times threshold;

[0026] The number of shares of the target multimedia content by the alternative user is greater than or equal to the share times threshold.

[0027] In an alternative implementation manner, the responding to the target user belonging to the first type triggering the preset push event and using the target neural network to determine the push strategy for pushing the target multimedia content to the target user includes:

[0028] In response to the target user belonging to the first type triggering the preset push event, use the target neural network to determine the prediction result that the target user is converted from the first type to the second type after pushing the target multimedia content to the target user;

[0029] Based on the prediction result, determine the push strategy for pushing the target multimedia content to the target user.

[0030] In an alternative implementation manner, the using the target neural network to determine the prediction result that the target user is converted from the first type to the second type after pushing the target multimedia content to the target user includes:

[0031] Obtain the attribute information corresponding to the target user;

[0032] Based on the attribute information and the multimedia attribute information of the target multimedia content, form data to be processed, and input the data to be processed into the target neural network to obtain the prediction result.

[0033] In an optional implementation, after pushing the target multimedia content to the target user, it further includes: obtaining the historical operation information and real-time operation information of the target user on the target multimedia content; using the historical operation information and real-time operation information of the target user on the target multimedia content to determine the conversion result of the target user from the first type to the second type.

[0034] In a second aspect, an embodiment of the present disclosure further provides a multimedia content pushing device, including:

[0035] An obtaining module, configured to obtain the historical operation information of multiple alternative users on the target multimedia content during a target historical period, and the real-time operation information on the target multimedia content;

[0036] A training module, configured to determine a target sample user from the alternative users based on the historical operation information and real-time operation information respectively corresponding to the multiple alternative users, and train a neural network model to be trained based on the sample data composed of the sample attribute information corresponding to the target sample user and the multimedia attribute information of the target multimedia content, to obtain a target neural network model; wherein, the target sample user includes an alternative user whose user type is converted from the first type to the second type when the target multimedia content is pushed;

[0037] A pushing module, configured to, in response to a preset pushing event triggered by a target user belonging to the first type, use the target neural network to determine a pushing strategy for pushing the target multimedia content to the target user, and push the target multimedia content based on the pushing strategy.

[0038] In a possible implementation, when the obtaining module obtains the historical operation information of multiple alternative users on the target multimedia content during a target historical period, it is configured to:

[0039] Determine the object attribute information of the content object corresponding to the target multimedia content;

[0040] Based on the object attribute information, determine the target historical period corresponding to the target multimedia content, and obtain the historical operation information of the multiple alternative users on the target multimedia content during the target historical period.

[0041] In a possible implementation, when obtaining the real-time operation information of the alternative users on the target multimedia content, the obtaining module is configured to:

[0042] For each of the alternative users, in each operation cycle among multiple operation cycles corresponding to the alternative user, determine the operation information of each alternative user on the target multimedia content within each operation cycle;

[0043] Based on the operation information corresponding to multiple operation cycles respectively, obtain the real-time operation information corresponding to each alternative user.

[0044] In a possible implementation, when determining a target sample user from the alternative users based on the historical operation information and real-time operation information corresponding to multiple alternative users respectively, the training module is configured to:

[0045] For each of the multiple alternative users, perform fusion processing on the historical operation information and real-time operation information corresponding to each alternative user to obtain the target operation information corresponding to each alternative user;

[0046] In response to the target operation information corresponding to any alternative user satisfying a preset condition, determine this alternative user as the target sample user; wherein, the preset condition satisfies the conversion of the alternative user from the first type to the second type.

[0047] In a possible implementation, the first type includes: shallow interaction crowd; the second type includes interest planting grass crowd;

[0048] The preset condition includes at least one of the following:

[0049] The exposure times of the target multimedia content are greater than or equal to the first exposure times threshold, and the exposure times with the exposure duration greater than the first preset duration threshold are greater than the second exposure times threshold;

[0050] The play duration of the target multimedia content is greater than the first play times threshold, and the play times with the play duration greater than the second preset duration threshold are greater than the preset play times threshold;

[0051] The number of times the target multimedia content is clicked by the alternative user is greater than or equal to the preset click times threshold;

[0052] The stay duration on the advertisement landing page corresponding to the target multimedia content is greater than the preset stay duration threshold;

[0053] The number of likes of the alternative user on the target multimedia content is greater than the preset number of likes threshold;

[0054] The number of comments of the alternative user on the target multimedia content is greater than or equal to the comment times threshold;

[0055] The sharing times of the target multimedia content by the alternative users are greater than or equal to the sharing times threshold.

[0056] In a possible implementation manner, when the pushing module determines a pushing policy for pushing the target multimedia content to the target user by using the target neural network in response to a preset pushing event triggered by a target user belonging to the first type, it is used for:

[0057] In response to a preset pushing event triggered by a target user belonging to the first type, use the target neural network to determine a prediction result that after pushing the target multimedia content to the target user, the target user is converted from the first type to the second type;

[0058] Based on the prediction result, determine a pushing policy for pushing the target multimedia content to the target user.

[0059] In a possible implementation manner, when the pushing module determines a prediction result that after pushing the target multimedia content to the target user, the target user is converted from the first type to the second type by using the target neural network, it is used for:

[0060] Obtain the attribute information corresponding to the target user;

[0061] Based on the attribute information and the multimedia attribute information of the target multimedia content, form data to be processed, and input the data to be processed into the target neural network to obtain the prediction result.

[0062] In a possible implementation manner, it further includes: a processing module, which is used for after pushing the target multimedia content to the target user, further including: obtaining the historical operation information and real-time operation information of the target user on the target multimedia content; using the historical operation information and real-time operation information of the target user on the target multimedia content to determine the conversion result of the target user from the first type to the second type.

[0063] In a third aspect, an alternative implementation manner of the present disclosure further provides a computer device, a processor, and a memory. The memory stores machine-readable instructions executable by the processor. The processor is used to execute the machine-readable instructions stored in the memory. When the machine-readable instructions are executed by the processor, the machine-readable instructions execute the steps in the first aspect or any possible implementation manner in the first aspect when executed by the processor.

[0064] Fourthly, an optional implementation manner of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run, it executes the steps in the first aspect or any possible implementation manner in the first aspect.

[0065] For the effect description of the above multimedia content push device, computer device, and computer-readable storage medium, refer to the description of the above multimedia content push method, which will not be elaborated here.

[0066] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and do not limit the technical solutions of the present disclosure.

[0067] To make the above objects, features, and advantages of the present disclosure more obvious and understandable, the following specific preferred embodiments are given, and in conjunction with the accompanying drawings, the detailed description is as follows. Description of the Drawings

[0068] To more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following briefly introduces the drawings required to be used in the embodiments. The drawings here are incorporated into the specification and constitute a part of this specification. These drawings show embodiments that conform to the present disclosure and are used together with the specification to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only show some embodiments of the present disclosure, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without creative efforts.

[0069] Figure 1 Shows a flowchart of a method for pushing multimedia content provided by some embodiments of the present disclosure;

[0070] Figure 2 Shows a schematic diagram of a multimedia content push device provided by some embodiments of the present disclosure;

[0071] Figure 3 Shows a schematic diagram of a computer device provided by some embodiments of the present disclosure. Detailed Embodiments

[0072] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Apparently, the described embodiments are only a part rather than all of the embodiments of the present disclosure. Components of the embodiments of the present disclosure described and illustrated herein generally may be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of the present disclosure is not intended to limit the scope of the claimed present disclosure, but merely represents selected embodiments of the present disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of the present disclosure without creative efforts fall within the scope of protection of the present disclosure.

[0073] Based on the above research, the present disclosure provides a method for pushing multimedia content. By using the historical operation information of a plurality of alternative users on target multimedia content in a target historical period and the real-time operation information on the target multimedia content, target sample users are screened from the plurality of alternative users. The target sample users include alternative users whose user type is converted from a first type to a second type when the target multimedia content is pushed. Then, a neural network model to be trained is trained using sample data composed of sample attribute information corresponding to the target sample users and multimedia attribute information of the target multimedia content to obtain a target neural network model. When a target push event is triggered, the target neural network is used to determine whether to push the target multimedia content to the target user, so as to more specifically perform attribution prediction of the target multimedia content for the conversion of the user from the first type to the second type. According to the result of the attribution prediction, a push strategy for pushing the target multimedia content to the user is determined, improving the effectiveness and pertinence of the push.

[0074] Regarding the defects existing in the above solutions, they are all results obtained by the inventors through practice and careful research. Therefore, the discovery process of the above problems and the solutions proposed by the present disclosure for the above problems in the following text should both be contributions made by the inventors to the present disclosure during the process of the present disclosure.

[0075] It should be noted that similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0076] It can be understood that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, usage scopes, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the users and the users' authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations. For example, specifically, a prompt message for requesting authorization may be sent to the users in the form of a pop-up window or information push on the page, and after the users agree, the above information is used.

[0077] For the convenience of understanding this embodiment, first, a method for pushing multimedia content disclosed in the embodiments of the present disclosure will be introduced in detail. The execution subject of the method for pushing multimedia content provided in the embodiments of the present disclosure is generally a computer device with certain computing capabilities. Such a computer device includes, for example: a terminal device, a server, or other processing devices. The terminal device may be a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementation manners, the method for pushing multimedia content may be implemented by a processor calling computer-readable instructions stored in a memory.

[0078] The following will illustrate the method for pushing multimedia content provided in the embodiments of the present disclosure.

[0079] See Figure 1 As shown in the figure, it is a flowchart of the method for pushing multimedia content provided in the embodiments of the present disclosure. The method includes steps S101 to S103, where:

[0080] S101: Obtain the historical operation information of multiple alternative users on the target multimedia content in the target historical period, and the real-time operation information on the target multimedia content;

[0081] S102: Based on the historical operation information and real-time operation information respectively corresponding to multiple alternative users, determine a target sample user from the alternative users, and train a neural network model to be trained based on the sample data composed of the sample attribute information corresponding to the target sample user and the multimedia attribute information of the target multimedia content, to obtain a target neural network model; where the target sample user includes alternative users whose user type is converted from the first type to the second type when the target multimedia content is pushed.

[0082] S103: In response to a target user belonging to the first type triggering a preset push event, use the target neural network to determine a push strategy for pushing the target multimedia content to the target user, and push the target multimedia content based on the push strategy.

[0083] The above S101 to S103 will be described in detail below.

[0084] Regarding the above S101, the multimedia content in specific implementation, for example, includes videos, short videos, advertisements, recommended texts, pictures, and combinations of at least any two of the above.

[0085] A short video is a short clip, which is a way of spreading content on the Internet. Generally, it is a video with a duration of less than 5 minutes spread on new Internet media. Compared with short videos, videos usually have a longer playing duration. An advertisement can include any one of video advertisements, graphic advertisements, etc. Generally, it is multimedia content launched by the brand side of a product for promoting the product (also known as the content object). Recommended texts, pictures, etc. can include, for example, the texts and pictures included in the notes posted by users on the multimedia content platform after using certain products.

[0086] The target multimedia content is, for example, selected from multiple multimedia contents, targeted at a certain content object, and published for a specific purpose. Among them, the content object can be understood as, for example: the object described by the multimedia content. The content object can include, for example, an entity object, such as a certain product, a certain brand, etc.; it can also be a virtual object, such as a tourist route of a certain scenic spot that can be visited, a certain service, etc.

[0087] Exemplarily, taking the content object as a certain brand product A as an example, there are multiple multimedia contents corresponding to the brand product A, and the publishing purposes corresponding to different multimedia contents can be the same or different. Exemplarily, the publishing purpose corresponding to any multimedia content includes, for example, at least one of the following: cultural popularization and knowledge introduction, "planting grass", selling, etc. Among them, taking "planting grass" as an example, "planting grass" is a popular Internet term, which means introducing a product to others and stimulating others' desire to purchase. The process of stimulating others' desire to purchase is called "planting grass". The target multimedia content includes, for example, the multimedia content corresponding to the product A with the publishing purpose of "planting grass", which includes, for example: advertisements corresponding to the product A, "planting grass" videos posted by other users, "planting grass" notes, etc.

[0088] The target historical period is, for example, a certain period within a preset duration range from the current moment. For example, taking the date corresponding to the current moment as a reference, the first N days of this date are used as the target historical period. Among them, different content objects can correspond to different target historical periods. Specifically, the embodiments of the present disclosure provide a method for obtaining historical operation information of multiple alternative users on target multimedia content in a target historical period, including:

[0089] Determine the object attribute information of the content object corresponding to the target multimedia content;

[0090] Based on the object attribute information, determine the target historical period corresponding to the target multimedia content, and obtain the historical operation information of multiple alternative users on the target multimedia content during the target period.

[0091] Exemplarily, the object attribute information of the content object corresponding to the target multimedia content includes, for example: the object category to which the target multimedia content belongs, whether it has seasonality, service life, etc. Specifically, it can be set according to actual needs. Taking the object attribute information including service life as an example, if the content object of the target multimedia content is a product with a long service life such as a mobile phone or a digital camera, the duration of the corresponding target historical period is 30 days; if the content object of the target multimedia content is a product with a short service life such as food or skin care products, the duration of the corresponding target historical period is 14 days; for another example, taking the object attribute information including whether it has seasonality as an example, if the content object of the target multimedia content is a seasonal product such as fruits, the duration of the corresponding target historical period is 7 days; if the content object corresponding to the target multimedia content is other products without seasonality, the duration of the corresponding target historical period is 15 days.

[0092] The specific duration of the target historical period can be set according to actual needs, and the embodiments of the present disclosure do not make any limitations.

[0093] When determining the object attribute information of the content object corresponding to the target multimedia content, for example, the content object can be determined first, and then the target multimedia content can be determined from the multimedia content corresponding to the content object according to the publishing purpose of the multimedia content corresponding to the content object.

[0094] When the push system pushes multimedia content, push information will be generated. In this push information, it includes the first identification information corresponding to the target multimedia content, the second identification information of the user to whom the target multimedia content is pushed, and the push time. Using the first identification information and the push time, the push information corresponding to the target multimedia content in the target historical period is screened. Then, the second identification information is read from the push information corresponding to the target multimedia content in the target historical period that is screened out, and the user corresponding to this second identification information is used as the alternative user.

[0095] After determining the alternative users, the target push information corresponding to the alternative users for the target multimedia content can be screened out from the push information corresponding to the target multimedia content in the target historical period by using the second identification information corresponding to the alternative users. In addition, in the push information, it also includes the operation information of the alternative users on the target multimedia content after receiving the pushed target multimedia content, such as: whether to click, the duration of clicking to play, whether to like, whether to comment, whether to share, etc. Then, using the screened target push information, the historical operation information of the alternative users on the target multimedia content in the target historical period is obtained.

[0096] Exemplarily, assume the target multimedia content includes: a 1 ~a m; For the target multimedia content ai, the target historical period includes: T1 - T2; where T1 is the start time of the target historical period; T2 is the end time of the target historical period.

[0097] From the push information of the multimedia content, according to the push time t corresponding to each push information, as well as the start time T1 and end time T2 of the target historical period, filter the push information P1 belonging to the target historical period.

[0098] Then, using the first identification information of the target multimedia content ai, filter the push information P2 corresponding to the target multimedia content ai from the push information P1.

[0099] Then, for the push information in P2, read the second identification information carried in each piece, and then according to the second identification information, filter all the target push information P3 corresponding to the second identification information from P2.

[0100] Then, using the operation information of the alternative user U1 corresponding to the second identification information carried in the target push information P3, obtain the historical operation information of the alternative user U1 on the target multimedia content during the target historical period.

[0101] Among them, the historical operation information includes, for example, at least one of the following:

[0102] s1: The number of exposures of the target multimedia content, and / or, the duration of each exposure.

[0103] Here, the number of exposures of the target multimedia content, for example, includes the number of times shown on the terminal screen corresponding to the alternative user, and the duration of each display.

[0104] Exemplarily, since when pushing multimedia content to users, multiple multimedia contents are usually pushed; the multiple multimedia contents are arranged on the page in a certain way; and the display screen of the terminal device cannot display all the pushed multimedia contents at once in many cases. If a multimedia content is shown on the display screen of the terminal device, it is considered that the multimedia content has been exposed; if a multimedia content is pushed to the user but not shown on the display screen of the terminal device, it is considered that it has not been exposed.

[0105] The duration of exposure, that is, the display duration of the multimedia content on the display screen.

[0106] s2: The number of times the target multimedia content is played, or the duration of each play.

[0107] Here, after the multimedia content is pushed to the user, the user can trigger the play of the multimedia content through operations such as clicking. After each play, the duration of this play can also be recorded.

[0108] s3: The number of times the target multimedia content is clicked by the alternative user.

[0109] Here, after the multimedia content is pushed to the user, the user can trigger the playback of the target multimedia content through a click operation; or for some automatically played multimedia content, the user can trigger entering an introduction page such as an advertisement landing page of the multimedia content through a click.

[0110] s4: The residence duration of the advertisement landing page corresponding to the target multimedia content.

[0111] Here, after the target multimedia content is displayed on the display screen of the terminal device, the user can enter the advertisement landing page corresponding to the target multimedia content through operations such as clicking and swiping. At this time, the residence duration of the advertisement landing page corresponding to the target multimedia content can be recorded.

[0112] s5: The number of likes of the target multimedia content by the alternative user.

[0113] s6: The number of comments on the target multimedia content by the alternative user.

[0114] s7: The number of shares of the target multimedia content by the alternative user.

[0115] In another embodiment of the present disclosure, a specific method for obtaining the real-time operation information of the alternative user for the target multimedia content is further provided, including:

[0116] For each alternative user, in each operation cycle among a plurality of operation cycles corresponding to the alternative user, determine the operation information of each alternative user for the target multimedia content within each operation cycle;

[0117] Based on the operation information corresponding to each of the multiple operation cycles, obtain the real-time operation information corresponding to each alternative user.

[0118] In a specific implementation, among the multiple operation cycles corresponding to the alternative user, for example, it can be multiple operation cycles within 1 day after the target historical period. The duration of each operation cycle is 1 minute, 2 minutes, etc., and can be specifically determined according to actual needs.

[0119] For example, taking the duration of each operation cycle as 1 minute as an example, within 1 day after the target historical period, when pushing the target multimedia content to the alternative user, corresponding push events can also be generated; in each operation cycle, obtain the real-time push information of the target multimedia content in this operation cycle. Then use the real-time push information to obtain the operation information of the alternative user for the target multimedia content within this operation cycle.

[0120] Then, for the alternative user, using the operation information corresponding to multiple operation cycles respectively, minute-level aggregation processing is performed to obtain the real-time operation information of the alternative user for the target multimedia content.

[0121] Here, the operation information in each piece of real-time push information recorded, for example, includes: the number of clicks on the target multimedia content, and the playing duration, etc.

[0122] The information types included in the real-time operation information may also include at least one of the above s1 to s7.

[0123] In this way, based on the above embodiments, the historical operation information of multiple alternative users for the target multimedia content in the target historical period and the real-time operation information of the target multimedia content can be obtained.

[0124] Regarding the above S102, in specific implementation, when determining the target sample user from the alternative users based on the historical operation information and real-time operation information corresponding to multiple alternative users respectively, for example, the following method can be adopted:

[0125] For each alternative user among the multiple alternative users, the historical operation information and real-time operation information corresponding to each alternative user are fused to obtain the target operation information corresponding to each alternative user;

[0126] In response to the target operation information corresponding to any alternative user satisfying the preset condition, this alternative user is determined as the target sample user; wherein, the preset condition satisfies that the alternative user is converted from the first type to the second type.

[0127] Specifically, the information types included in the historical operation information and real-time operation information may be the same, different, or only partially the same, and can be specifically determined according to actual needs, and the embodiments of the present disclosure do not make limitations.

[0128] Exemplarily, in the case where the information types included in the historical operation information and real-time operation information are the same, when fusing the historical operation information and implementation operation corresponding to each alternative user, for example, for each information type, the values of the historical operation information and real-time operation information under this information type can be added.

[0129] In the case where the information types included in the historical operation information and real-time operation information are completely different, for example, the historical operation information and real-time operation information can be subjected to information type merging processing.

[0130] When part of the information types included in the historical operation information and the real-time operation information are the same, for the same information type, add the values of the historical operation information and the real-time operation information under this information type. For different information types, perform information type merging processing on the historical operation information and the real-time operation information.

[0131] After performing fusion processing on the historical operation information and the real-time operation information to obtain the target operation information, it is possible to determine whether the target operation information meets the preset conditions.

[0132] According to the O-5A population stratification model, that is, according to the degree of relationship between the population and the brand, users are divided into different stages of O, A1-A5, that is, the type of each user belongs to at least one of the above 6 types.

[0133] Among them, O (Opportunity) refers to the public domain population.

[0134] A1 (Aware) refers to the passive exposure population.

[0135] A2 (Appeal) refers to the shallow interaction population.

[0136] A3 (Ask) refers to the interest planting grass population.

[0137] A4 (Act) refers to the brand first purchase population.

[0138] A5 (Advocate) refers to the brand repeat purchase population.

[0139] In the embodiments of the present disclosure, the first type, for example, is any one of the above 6 types except O and except A5.

[0140] The second type is different from the first type. For example, when the first type is A1, the second type is A2; when the first type is A2, the second type is A3; when the first type is A3, the second type is A4; when the first type is A4, the second type is A5. Specifically, according to different requirements, the first type and the second type can be set. For the differences between the first type and the second type, the determined preset conditions are also different.

[0141] Exemplarily, for the case where the first type is A2 and the second type is A3, the preset conditions include, for example, at least one of the following:

[0142] h1: The exposure times of the target multimedia content are greater than or equal to the first exposure times threshold, and the number of exposure times with an exposure duration greater than the first preset duration threshold is greater than the second exposure times threshold.

[0143] If the number of exposures of the target multimedia content ≥ 11 times, and the number of exposures with an exposure duration greater than 5s ≥ 2 times.

[0144] h2: The playing duration of the target multimedia content is greater than the first playing times threshold, and the number of playing times with a playing duration greater than the second preset duration threshold is greater than the preset playing times threshold.

[0145] If the playing duration of the target multimedia content > 1 minute, and the number of playing times with a playing duration greater than 5s ≥ 2 times.

[0146] h3: The number of times the target multimedia content is clicked by the alternative user is greater than or equal to the preset click times threshold.

[0147] If the number of times the target multimedia content is clicked by the alternative user ≥ 2 times.

[0148] h4: The dwell time of the advertising landing page corresponding to the target multimedia content is greater than the preset dwell time threshold.

[0149] If the dwell time of the advertising landing page corresponding to the target multimedia content > 1 minute.

[0150] h5: The number of likes of the target multimedia content by the alternative user is greater than the preset like times threshold.

[0151] If the number of likes of the target multimedia content by the alternative user ≥ 2 times.

[0152] h6: The number of comments of the target multimedia content by the alternative user is greater than or equal to the comment times threshold.

[0153] If the number of comments of the target multimedia content by the alternative user ≥ 1 time.

[0154] h7: The number of shares of the target multimedia content by the alternative user is greater than or equal to the share times threshold.

[0155] If the number of shares of the target multimedia content by the alternative user ≥ 1 time.

[0156] Specifically, the above thresholds are only for illustration, and other specific values can also be adopted, which can be specifically set according to actual needs, and the embodiments of the present disclosure do not make limitations.

[0157] When the target operation information corresponding to a certain alternative user satisfies at least one of the above h1~h7, the alternative user is determined as the target sample user, that is, it indicates that due to the push of the target multimedia content to the alternative user, the target sample user has changed from the shallow interaction crowd to the interest planting grass crowd for the content object corresponding to the target multimedia content.

[0158] After determining the target sample users, sample data is constituted based on the sample attribute information corresponding to the target sample users and the multimedia attribute information of the target multimedia content.

[0159] Here, the sample attribute information includes, for example: the historical operation information of the target sample users on the target multimedia content in the target historical period, and / or other attribute information, such as the login times of the target sample users, the browsing duration of the multimedia content delivery platform, the purchase information of the product, etc., which is specifically determined according to actual needs and is not limited in the embodiments of the present disclosure.

[0160] The multimedia attribute information of the target multimedia content includes, for example: the total playback duration of the target multimedia content, the content volume of the text, the title of the target multimedia content, the delivery frequency of the target multimedia content, etc., which can also be specifically determined according to actual needs and is not limited in the embodiments of the present disclosure.

[0161] After constituting the sample data, the sample data is used as positive sample data. At the same time, non-target sample users among the alternative users can be randomly sampled, and negative sample data is constituted by using the sample attribute information corresponding to the randomly sampled alternative users and the multimedia attribute information of the target multimedia content, so that the positive sample data and the negative sample data maintain a certain proportion, and the positive sample data and the negative sample data are used to train the neural network to be trained to obtain the target neural network.

[0162] Among them, the target neural network can predict the specific prediction result that a user will be converted from the first type to the second type after pushing the target multimedia content to a certain user.

[0163] Regarding the above S103: The preset push events include, for example: entering the information flow push platform corresponding to the target multimedia content; performing a preset operation on the information display page corresponding to the corresponding terminal device, such as a sliding operation in a preset direction, a double-click operation, or an operation to enter the information display page, etc.; receiving a search operation of a content object corresponding to the target multimedia content from the search bar, etc., which is specifically set according to actual needs and is not limited in the embodiments of the present disclosure.

[0164] When using the target neural network to determine the push strategy for pushing the target multimedia content to the target user, the following method can be adopted, for example:

[0165] In response to the target user belonging to the first type triggering the preset push event, use the target neural network to determine the prediction result that the target user will be converted from the first type to the second type after pushing the target multimedia content to the target user;

[0166] Based on the prediction result, determine a push strategy for pushing the target multimedia content to the target user.

[0167] Specifically, for example, the attribute information corresponding to the target user can be obtained;

[0168] Based on the attribute information and the multimedia attribute information of the target multimedia content, form the data to be processed, and input the data to be processed into the target neural network to obtain the prediction result.

[0169] Here, the attribute information corresponding to the target user is, for example, similar to the information type of the sample attribute information corresponding to the target sample user, and will not be elaborated here.

[0170] The obtained prediction result includes: for example, it includes yes or no. Among them, "yes" means that after pushing the target multimedia content to this user, it can be converted from the first type to the second type; "no" means that after pushing the target multimedia content to this user, it will not be converted from the first type to the second type.

[0171] In addition, the prediction result also includes, for example: the probability of converting from the first type to the second type after pushing the multimedia content to this user. It is specifically determined according to actual needs.

[0172] For different types of prediction results, the determined push strategies can also be different.

[0173] Exemplarily, for the case where the prediction result includes yes or no, the determined push strategy includes, for example: push, or not push.

[0174] That is, in the case where the push strategy is "push", for example, the target multimedia content can be pushed to the target user.

[0175] In the case where the push strategy is "not push", the target multimedia content is not pushed to this target user. In this way, in the case where the prediction result is no, it is possible to avoid ineffective pushing to users and improve the pertinence of the pushed multimedia content.

[0176] For the case where the prediction result includes the probability of converting from the first type to the second type after pushing the multimedia content to this user, the push strategy includes, for example: whether to push, and in the case of pushing, the corresponding push frequency, or the number of pushes, etc.

[0177] Push the target multimedia content to the target user according to the specific push strategy. In this way, it is possible to continuously increase the probability of the target user converting from the first type to the second type.

[0178] In another embodiment of the present disclosure, after pushing the target multimedia content to the target user, it further includes: obtaining historical operation information and real-time operation information of the target user on the target multimedia content; using the historical operation information and real-time operation information of the target user on the target multimedia content to determine the conversion result of the target user from the first type to the second type.

[0179] Here, the method for obtaining the historical operation information and real-time operation information of the target user on the target multimedia content, and the historical operation information and real-time operation information corresponding to the alternative users is similar, and will not be elaborated in the embodiments of the present disclosure.

[0180] When using the historical operation information and real-time operation information of the target user on the target multimedia content to determine the conversion result of the target user from the first type to the second type, for example, the historical operation information and real-time operation information of the target user on the target multimedia content can be fused and processed, and then it is judged whether the preset conditions are met. If the preset conditions are met, it is determined that the conversion result of the target user from the first type to the second type is "conversion successful"; if the preset conditions are not met, it is determined that the conversion result of the target user from the first type to the second type is "conversion failed".

[0181] In this way, the conversion results of the target users can be collected as new samples to retrain the target neural network again to continuously improve the performance of the target neural network. In addition, the number of converted target users can be counted and disclosed in real time, which is convenient for using the disclosed data to adjust the specific delivery strategy of the target multimedia content in real time.

[0182] Those skilled in the art can understand that in the above method of the specific implementation manner, the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined according to its function and possible internal logic.

[0183] Based on the same inventive concept, the embodiments of the present disclosure also provide a multimedia content push device corresponding to the multimedia content push method. Since the principle of solving problems by the device in the embodiments of the present disclosure is similar to the above multimedia content push method in the embodiments of the present disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be elaborated.

[0184] Refer to Figure 2 As shown, it is a schematic diagram of a multimedia content push device provided by an embodiment of the present disclosure. The device includes:

[0185] An obtaining module 21, configured to obtain historical operation information of multiple alternative users on the target multimedia content during a target historical period, and real-time operation information on the target multimedia content;

[0186] A training module 22, configured to determine a target sample user from the alternative users based on the historical operation information and real-time operation information respectively corresponding to multiple alternative users, and train a neural network model to be trained based on the sample data composed of the sample attribute information corresponding to the target sample user and the multimedia attribute information of the target multimedia content, so as to obtain a target neural network model; wherein, the target sample user includes an alternative user whose user type is converted from a first type to a second type when the target multimedia content is pushed to the user.

[0187] A pushing module 23, configured to, in response to a target user belonging to the first type triggering a preset pushing event, use the target neural network to determine a pushing strategy for pushing the target multimedia content to the target user, and push the target multimedia content based on the pushing strategy.

[0188] In a possible implementation manner, when obtaining the historical operation information of multiple alternative users on the target multimedia content in a target historical period, the obtaining module 21 is configured to:

[0189] Determine the object attribute information of the content object corresponding to the target multimedia content;

[0190] Based on the object attribute information, determine the target historical period corresponding to the target multimedia content, and obtain the historical operation information of multiple alternative users on the target multimedia content in the target historical period.

[0191] In a possible implementation manner, when obtaining the real-time operation information of the alternative users on the target multimedia content, the obtaining module 21 is configured to:

[0192] For each alternative user, in each operation cycle among multiple operation cycles corresponding to the alternative user, determine the operation information of each alternative user on the target multimedia content in each operation cycle;

[0193] Based on the operation information corresponding to multiple operation cycles respectively, obtain the real-time operation information corresponding to each alternative user.

[0194] In a possible implementation manner, when determining a target sample user from the alternative users based on the historical operation information and real-time operation information respectively corresponding to multiple alternative users, the training module 22 is configured to:

[0195] For each alternative user among multiple alternative users, perform fusion processing on the historical operation information and real-time operation information corresponding to each alternative user to obtain the target operation information corresponding to each alternative user;

[0196] In response to the target operation information corresponding to any alternative user satisfying the preset condition, determine the alternative user as the target sample user; wherein, the preset condition satisfies that the alternative user is converted from the first type to the second type.

[0197] In a possible implementation manner, the first type includes: shallow interaction population; the second type includes interest planting grass population;

[0198] The preset condition includes at least one of the following:

[0199] The exposure times of the target multimedia content are greater than or equal to the first exposure times threshold, and the exposure times with the exposure duration greater than the first preset duration threshold are greater than the second exposure times threshold;

[0200] The play duration of the target multimedia content is greater than the first play times threshold, and the play times with the play duration greater than the second preset duration threshold are greater than the preset play times threshold;

[0201] The number of times the target multimedia content is clicked by the alternative user is greater than or equal to the preset click times threshold;

[0202] The stay duration on the advertisement landing page corresponding to the target multimedia content is greater than the preset stay duration threshold;

[0203] The number of likes of the target multimedia content by the alternative user is greater than the preset number of likes threshold;

[0204] The number of comments of the target multimedia content by the alternative user is greater than or equal to the comment times threshold;

[0205] The number of shares of the target multimedia content by the alternative user is greater than or equal to the share times threshold.

[0206] In a possible implementation manner, when the push module 23 determines the push strategy for pushing the target multimedia content to the target user by using the target neural network in response to the target user belonging to the first type triggering the preset push event, it is used for:

[0207] In response to the target user belonging to the first type triggering the preset push event, use the target neural network to determine the prediction result that the target user is converted from the first type to the second type after pushing the target multimedia content to the target user;

[0208] Based on the prediction result, determine the push strategy for pushing the target multimedia content to the target user.

[0209] In a possible implementation manner, when the pushing module 23 uses the target neural network to determine the prediction result that after pushing the target multimedia content to the target user, the target user is converted from the first type to the second type, it is used for:

[0210] Obtain the attribute information corresponding to the target user;

[0211] Based on the attribute information and the multimedia attribute information of the target multimedia content, form the data to be processed, and input the data to be processed into the target neural network to obtain the prediction result.

[0212] In a possible implementation manner, it further includes: a processing module 24, which is used for, after pushing the target multimedia content to the target user, further including: obtaining the historical operation information and real-time operation information of the target user on the target multimedia content; using the historical operation information and real-time operation information of the target user on the target multimedia content to determine the conversion result of the target user from the first type to the second type.

[0213] For the description of the processing flow of each module in the device and the interaction flow between each module, reference can be made to the relevant description in the above method embodiments, which will not be elaborated here.

[0214] The embodiments of the present disclosure further provide a computer device, as Figure 3 shown, which is a schematic structural diagram of the computer device provided by the embodiments of the present disclosure, including:

[0215] A processor 31 and a memory 32; the memory 32 stores machine-readable instructions executable by the processor 31, and the processor 31 is used to execute the machine-readable instructions stored in the memory 32. When the machine-readable instructions are executed by the processor 31, the processor 31 executes the following steps:

[0216] Obtain the historical operation information of multiple alternative users on the target multimedia content in the target historical period and the real-time operation information on the target multimedia content;

[0217] Based on the historical operation information and real-time operation information respectively corresponding to multiple alternative users, determine a target sample user from the alternative users, and train a neural network model to be trained based on the sample data composed of the sample attribute information corresponding to the target sample user and the multimedia attribute information of the target multimedia content to obtain a target neural network model; wherein, the target sample user includes alternative users whose user type is converted from the first type to the second type when being pushed the target multimedia content.

[0218] In response to a preset push event triggered by a target user belonging to the first type, the target neural network is used to determine a push strategy for pushing the target multimedia content to the target user, and the target multimedia content is pushed based on the push strategy.

[0219] The above-mentioned memory 32 includes a memory 321 and an external memory 322; the memory 321 here is also called an internal memory, which is used to temporarily store the operation data in the processor 31 and the data exchanged with the external memory 322 such as a hard disk. The processor 31 exchanges data with the external memory 322 through the memory 321.

[0220] The specific execution process of the above instructions can refer to the steps of the multimedia content push method described in the embodiments of the present disclosure, and will not be elaborated here.

[0221] The embodiments of the present disclosure further provide a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, it executes the steps of the multimedia content push method described in the above method embodiments. Among them, the storage medium can be a volatile or non-volatile computer-readable storage medium.

[0222] The embodiments of the present disclosure further provide a computer program product, which carries program codes. The instructions included in the program codes can be used to execute the steps of the multimedia content push method described in the above method embodiments. Specifically, reference can be made to the above method embodiments, and details will not be elaborated here.

[0223] Among them, the above computer program product can be specifically implemented by means of hardware, software, or a combination thereof. In an alternative embodiment, the computer program product is specifically embodied as a computer storage medium. In another alternative embodiment, the computer program product is specifically embodied as a software product, such as a Software Development Kit (SDK), etc.

[0224] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems and devices described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein. In several embodiments provided in the present disclosure, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For another example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some communication interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0225] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0226] In addition, in each embodiment of the present disclosure, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0227] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such an understanding, the technical solution of the present disclosure, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present disclosure. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0228] Finally, it should be noted that the above-described embodiments are only specific embodiments of the present disclosure, used to illustrate the technical solutions of the present disclosure, rather than limiting them. The protection scope of the present disclosure is not limited thereto. Although the present disclosure has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that any person skilled in the art within the technical scope disclosed by the present disclosure can still modify the technical solutions described in the foregoing embodiments or can easily think of changes, or perform equivalent replacements on some of the technical features; and these modifications, changes or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should all be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A method for pushing multimedia content, characterized in that, it includes: Obtain the historical operation information of multiple alternative users on the target multimedia content in the target historical period, and the real-time operation information on the target multimedia content; Based on the historical operation information and real-time operation information corresponding to multiple alternative users respectively, determine a target sample user from the alternative users, and train a neural network model to be trained based on the sample data composed of the sample attribute information corresponding to the target sample user and the multimedia attribute information of the target multimedia content to obtain a target neural network model; wherein, the target sample user includes an alternative user whose user type is converted from the first type to the second type when the target multimedia content is pushed; In response to a target user belonging to the first type triggering a preset push event, use the target neural network to determine a push strategy for pushing the target multimedia content to the target user, and push the target multimedia content based on the push strategy.

2. The method according to claim 1, characterized in that, the obtaining of the historical operation information of multiple alternative users on the target multimedia content in the target historical period includes: Determine the object attribute information of the content object corresponding to the target multimedia content; Based on the object attribute information, determine the target historical period corresponding to the target multimedia content, and obtain the historical operation information of multiple alternative users on the target multimedia content in the target historical period.

3. The method according to claim 1 or 2, characterized in that, the obtaining of the real-time operation information of the alternative users on the target multimedia content includes: For each alternative user, in each operation cycle corresponding to the alternative user, determine the operation information of each alternative user on the target multimedia content in each operation cycle; Based on the operation information corresponding to multiple operation cycles respectively, obtain the real-time operation information corresponding to each alternative user.

4. The method according to any one of claims 1-3, characterized in that, the determining of the target sample user from the alternative users based on the historical operation information and real-time operation information corresponding to multiple alternative users respectively includes: For each alternative user among multiple alternative users, perform fusion processing on the historical operation information and real-time operation information corresponding to each alternative user to obtain the target operation information corresponding to each alternative user; In response to the target operation information corresponding to any alternative user satisfying a preset condition, determine this alternative user as the target sample user; wherein, the preset condition satisfies that the alternative user is converted from the first type to the second type.

5. The method according to claim 4, characterized in that, the first type includes: shallow interaction crowd; the second type includes interest planting grass crowd; the preset condition includes at least one of the following: The exposure times of the target multimedia content are greater than or equal to the first exposure times threshold, and the exposure times with an exposure duration greater than the first preset duration threshold are greater than the second exposure times threshold; The playing duration of the target multimedia content is greater than the first playing times threshold, and the number of playing times with the playing duration greater than the second preset duration threshold is greater than the preset playing times threshold; The number of times the target multimedia content is clicked by the alternative users is greater than or equal to the preset click times threshold; The residence duration of the advertising landing page corresponding to the target multimedia content is greater than the preset residence duration threshold; The number of likes of the target multimedia content by the alternative users is greater than the preset number of likes threshold; The number of comments of the target multimedia content by the alternative users is greater than or equal to the comment times threshold; The number of shares of the target multimedia content by the alternative users is greater than or equal to the share times threshold.

6. The method according to any one of claims 1-3, wherein, responding to a preset push event triggered by a target user belonging to the first type, and using the target neural network to determine a push strategy for pushing the target multimedia content to the target user, includes: responding to a preset push event triggered by a target user belonging to the first type, and using the target neural network to determine a prediction result that the target user is converted from the first type to the second type after pushing the target multimedia content to the target user; based on the prediction result, determining a push strategy for pushing the target multimedia content to the target user.

7. The method according to claim 6, wherein, the using the target neural network to determine a prediction result that the target user is converted from the first type to the second type after pushing the target multimedia content to the target user includes: obtaining the attribute information corresponding to the target user; constituting data to be processed based on the attribute information and the multimedia attribute information of the target multimedia content, and inputting the data to be processed into the target neural network to obtain the prediction result.

8. The method according to claim 1, wherein, after pushing the target multimedia content to the target user, further includes: obtaining the historical operation information and real-time operation information of the target user on the target multimedia content; using the historical operation information and real-time operation information of the target user on the target multimedia content to determine the conversion result of the target user from the first type to the second type.

9. A multimedia content push device, wherein, includes: an acquisition module, configured to acquire the historical operation information of multiple alternative users on the target multimedia content in a target historical period and the real-time operation information on the target multimedia content; a training module, configured to determine target sample users from the alternative users based on the historical operation information and real-time operation information respectively corresponding to the multiple alternative users, and train a neural network model to be trained based on the sample data composed of the sample attribute information corresponding to the target sample users and the multimedia attribute information of the target multimedia content, to obtain a target neural network model; wherein, the target sample users include alternative users whose user type is converted from the first type to the second type when being pushed the target multimedia content; A push module, configured to, in response to a target user belonging to the first type triggering a preset push event, use the target neural network to determine a push policy for pushing the target multimedia content to the target user, and push the target multimedia content based on the push policy.

10. A computer device, characterized in that it includes: a processor and a memory, where the memory stores machine-readable instructions executable by the processor, and the processor is configured to execute the machine-readable instructions stored in the memory. When the machine-readable instructions are executed by the processor, the processor performs the steps of the method for pushing multimedia content according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, and when the computer program is run by a computer device, the computer device performs the steps of the method for pushing multimedia content according to any one of claims 1 to 8.

Images