Multimedia resource acquisition method and apparatus, device, and medium

Abstract

The present disclosure relates to a multimedia resource acquisition method, device, equipment and medium. The multimedia resource acquisition method comprises: receiving an acquisition request of a first user account for a multimedia resource; in response to the acquisition request, determining a second user account, the second user account matching corresponding characteristic data of the first user account in at least one user characteristic dimension; determining a second multimedia resource from a first multimedia resource used by the second user account; and feeding back a multimedia resource identifier of the second multimedia resource to the first user account, so that the first user account acquires a target multimedia resource according to the multimedia resource identifier. According to the multimedia resource acquisition method, device, equipment and medium of the present disclosure, the multimedia resource pre-download can be performed according to the multimedia resource use data of the user account matched in the user characteristic dimension, and the prediction hit rate of the multimedia resource can be significantly improved.

Description

Technical Field

[0001] This disclosure relates to the field of Internet technology, and more specifically, to methods, apparatus, devices and media for acquiring multimedia resources. Background Technology

[0002] In video creation, it's often necessary to add multimedia resources (such as filters, stickers, and emoticons) to enhance the video's appeal. These resources need to be downloaded to the user's local device via the internet before use, but this downloading process requires waiting. Therefore, to improve the user experience, resource packages are usually pre-downloaded when the network is less busy, eliminating the need for waiting when using the multimedia resources.

[0003] Due to storage constraints on devices, it's impossible to pre-download all multimedia resources. Therefore, it's necessary to "predict" the multimedia resources that users will use. However, the current multimedia resource pre-downloading scheme has a low prediction hit rate (i.e., the probability that the pre-downloaded resource will actually be used by the user), causing users to still have to wait for the resource package to download when they actually use the multimedia resource. Summary of the Invention

[0004] This disclosure provides methods, apparatus, devices, and media for acquiring multimedia resources, in order to at least solve the problems in the aforementioned related technologies.

[0005] According to a first aspect of the present disclosure, a method for acquiring multimedia resources is provided, comprising: receiving a request from a first user account to acquire multimedia resources; responding to the acquisition request, determining a second user account, wherein the second user account matches feature data corresponding to the first user account under at least one user feature dimension, wherein the user feature dimension is a feature category related to the usage of the multimedia resources; determining a second multimedia resource from a first multimedia resource used by the second user account; and feeding back a multimedia resource identifier of the second multimedia resource to the first user account, so that the first user account acquires the target multimedia resource based on the multimedia resource identifier.

[0006] Optionally, the acquisition request includes information about the available storage space size on the first user account side, and the step of determining the second multimedia resource from the first multimedia resources used by the second user account includes: acquiring the first multimedia resources used by the second user account; determining at least one second multimedia resource from the first multimedia resources, wherein the sum of the storage space occupied by the at least one second multimedia resource is less than the available storage space size.

[0007] Optionally, determining at least one second multimedia resource from the first multimedia resources includes: determining the usage probability of the first user account for each of the first multimedia resources based on the usage frequency of each of the first multimedia resources; and determining at least one second multimedia resource from the first multimedia resources based on the usage probability of each of the first multimedia resources.

[0008] Optionally, the acquisition request is issued during the cold start phase of the device on the first user account side.

[0009] Optionally, the acquisition request includes information about the account identifier of the first user account, and the step of determining the second user account in response to the acquisition request includes: acquiring target feature data corresponding to the first user account under each of the user feature dimensions based on the account identifier; and determining a second user account whose feature data matches the target feature data from a database, wherein the database is used to store feature data of any user account under each of the user feature dimensions and data on multimedia resources used by any user account within a historical preset time period.

[0010] Optionally, determining the probability of the first user account using each of the first multimedia resources based on the usage frequency of each of the first multimedia resources includes: determining the sum of the usage frequencies of the first multimedia resources based on the usage frequency of each of the first multimedia resources; and for any one of the first multimedia resources, determining the proportion of the usage frequency of the first multimedia resource in the sum of the usage frequencies of the first multimedia resources as the probability of the first user account using the first multimedia resource.

[0011] Optionally, the user characteristic dimensions include at least one of preferences, location, and age.

[0012] Optionally, the multimedia resource acquisition method further includes: acquiring usage data of multimedia resources corresponding to each dimension label in a preset plurality of dimensions; determining the same multimedia resources corresponding to the plurality of dimension labels in the dimension based on the usage data of the multimedia resources corresponding to each dimension label; and determining the dimension as the user feature dimension if the proportion of the number of the same multimedia resources corresponding to the plurality of dimension labels in the dimension exceeds a preset threshold.

[0013] According to a second aspect of the present disclosure, a method for acquiring multimedia resources is provided, comprising: sending an acquisition request to a first server, wherein the acquisition request is an acquisition request for multimedia resources by a first user account; receiving a multimedia resource identifier of a second multimedia resource from the first server, wherein the second multimedia resource is determined from first multimedia resources used by the second user account, the second user account is determined by the first server in response to the acquisition request, the second user account matches feature data corresponding to the first user account under at least one user feature dimension, the user feature dimension being a feature category related to the usage of the multimedia resource; and acquiring a target multimedia resource based on the multimedia resource identifier.

[0014] Optionally, sending the acquisition request to the first server includes sending the acquisition request to the first server during the cold start phase.

[0015] Optionally, obtaining the target multimedia resource based on the multimedia resource identifier includes: determining whether the multimedia resource identifier already exists; if the multimedia resource identifier does not exist, sending a target multimedia resource acquisition request to a second server, wherein the target multimedia resource acquisition request includes information about the multimedia resource identifier, so that the second server responds to the target multimedia resource acquisition request and sends the target multimedia resource to the first user account side; and receiving the target multimedia resource sent by the second server.

[0016] Optionally, sending the target multimedia resource acquisition request to the second server includes: sending the target multimedia resource acquisition request to the second server when the network is idle.

[0017] Optionally, the user characteristic dimensions include at least one of preferences, location, and age.

[0018] According to a third aspect of the present disclosure, a multimedia resource acquisition apparatus is provided, comprising: an acquisition request receiving module configured to receive an acquisition request for multimedia resources from a first user account; a user account determination module configured to determine a second user account in response to the acquisition request, wherein the second user account matches feature data corresponding to the first user account under at least one user feature dimension, wherein the user feature dimension is a feature category related to the usage of the multimedia resource; a multimedia resource determination module configured to determine a second multimedia resource from a first multimedia resource used by the second user account; and a feedback module configured to feed back a multimedia resource identifier of the second multimedia resource to the first user account, so that the first user account acquires the target multimedia resource based on the multimedia resource identifier.

[0019] Optionally, the acquisition request includes information about the available storage space size on the first user account side, and the multimedia resource determination module is configured to: acquire the first multimedia resources used by the second user account; determine at least one second multimedia resource from the first multimedia resources, wherein the sum of the storage space occupied by the at least one second multimedia resource is less than the available storage space size.

[0020] Optionally, the multimedia resource determination module is configured to: determine the usage probability of the first user account for each of the first multimedia resources based on the usage frequency of each of the first multimedia resources; and determine at least one second multimedia resource from the first multimedia resources based on the usage probability of each of the first multimedia resources.

[0021] Optionally, the acquisition request is issued during the cold start phase of the device on the first user account side.

[0022] Optionally, the acquisition request includes information about the account identifier of the first user account, and the user account determination module is configured to: acquire target feature data corresponding to the first user account under each of the user feature dimensions according to the account identifier; determine a second user account whose feature data matches the target feature data from the database, wherein the database is used to store feature data of any user account under each of the user feature dimensions and data on multimedia resources used by any user account within a historical preset time period.

[0023] Optionally, the multimedia resource determination module is configured to: determine the sum of the usage frequencies of the first multimedia resources based on the usage frequency of each of the first multimedia resources; and for any first multimedia resource, determine the proportion of the usage frequency of the first multimedia resource in the sum of the usage frequencies of the first multimedia resources as the usage probability of the first user account for the first multimedia resource.

[0024] Optionally, the user characteristic dimensions include at least one of preferences, location, and age.

[0025] Optionally, the multimedia resource acquisition device further includes: a data acquisition module configured to acquire usage data of multimedia resources corresponding to each dimension label in a preset plurality of dimensions; a same multimedia resource determination module configured to determine the same multimedia resources corresponding to the plurality of dimension labels in the dimension based on the usage data of the multimedia resources corresponding to each dimension label; and a user feature dimension determination module configured to determine the dimension as the user feature dimension if the proportion of the number of the same multimedia resources corresponding to the plurality of dimension labels in the dimension exceeds a preset threshold.

[0026] According to a fourth aspect of the present disclosure, a multimedia resource acquisition apparatus is provided, comprising: an acquisition request sending module configured to send an acquisition request to a first server, wherein the acquisition request is an acquisition request for multimedia resources by a first user account; a multimedia resource identifier receiving module configured to receive a multimedia resource identifier of a second multimedia resource from the first server, wherein the second multimedia resource is determined from first multimedia resources used by the second user account, the second user account is determined by the first server in response to the acquisition request, and the second user account matches feature data corresponding to the first user account under at least one user feature dimension, the user feature dimension being a feature category related to the usage of the multimedia resource; and a multimedia resource acquisition module configured to acquire a target multimedia resource based on the multimedia resource identifier.

[0027] Optionally, the acquisition request sending module is configured to send the acquisition request to the first server during the cold start phase.

[0028] Optionally, the multimedia resource acquisition module is configured to: determine whether the multimedia resource identifier already exists; if the multimedia resource identifier does not exist, send a target multimedia resource acquisition request to a second server, wherein the target multimedia resource acquisition request includes information about the multimedia resource identifier, so that the second server responds to the target multimedia resource acquisition request and sends the target multimedia resource to the first user account side; and receive the target multimedia resource sent by the second server.

[0029] Optionally, the multimedia resource acquisition module is configured to send the target multimedia resource acquisition request to the second server when the network is idle.

[0030] Optionally, the user characteristic dimensions include at least one of preferences, location, and age.

[0031] According to a fifth aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and at least one memory storing computer-executable instructions, wherein, when executed by the at least one processor, the computer-executable instructions cause the at least one processor to perform a multimedia resource acquisition method according to a first aspect of the present disclosure or to perform a multimedia resource acquisition method according to a second aspect of the present disclosure.

[0032] According to a sixth aspect of the present disclosure, a computer-readable storage medium storing instructions is provided, which, when executed by at least one processor, cause the at least one processor to perform a multimedia resource acquisition method according to a first aspect of the present disclosure or to perform a multimedia resource acquisition method according to a second aspect of the present disclosure.

[0033] According to a seventh aspect of the present disclosure, a computer program product is provided, wherein the instructions in the computer program product are executable by a processor of a computer device to perform a multimedia resource acquisition method according to a first aspect of the present disclosure or to perform a multimedia resource acquisition method according to a second aspect of the present disclosure.

[0034] The technical solutions provided by the embodiments of this disclosure bring at least the following beneficial effects:

[0035] According to the multimedia resource acquisition method, apparatus, device, and medium disclosed herein, multimedia resources can be pre-downloaded based on multimedia resource usage data of user accounts matched with user characteristic dimensions. Since user characteristic dimensions are related to multimedia resource usage, the prediction hit rate of multimedia resources can be significantly improved. This can avoid situations where users have to wait for the resource package to be downloaded because the pre-downloaded multimedia resources do not meet their expectations when actually using multimedia resources. In other words, it can ensure that users can quickly use multimedia resources that meet their expectations, thereby significantly improving the user experience.

[0036] Furthermore, since a request to obtain multimedia resources is sent every time the client starts cold, almost every user account can obtain the configuration data of the pre-downloaded multimedia resources. The usage of the configuration data of the pre-downloaded multimedia resources by each user account can be used as a reference for subsequent multimedia resource recommendations, which can continuously improve the prediction hit rate of the multimedia resource pre-download scheme.

[0037] In addition, since the data in the database storing multimedia resource information is updated periodically, the latest updated multimedia resources can be pre-downloaded in a timely manner, which ensures that users can use the latest multimedia resources and further improves the user experience.

[0038] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0039] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0040] Figure 1 This is an exemplary system architecture 100 that illustrates an exemplary embodiment of the present disclosure and to which it may be applied.

[0041] Figure 2 This is a flowchart illustrating a multimedia resource acquisition method according to an exemplary embodiment of the present disclosure.

[0042] Figure 3 This is a flowchart illustrating a multimedia resource acquisition method according to another exemplary embodiment of the present disclosure.

[0043] Figure 4 This is an overall schematic diagram illustrating an effects pre-download process according to an exemplary embodiment of the present disclosure.

[0044] Figure 5 This is a block diagram illustrating a multimedia resource acquisition apparatus according to exemplary embodiments of the present disclosure.

[0045] Figure 6 This is a block diagram illustrating a multimedia resource acquisition apparatus according to another exemplary embodiment of the present disclosure.

[0046] Figure 7 This is a block diagram illustrating an electronic device 700 according to an exemplary embodiment of the present disclosure. Detailed Implementation

[0047] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0048] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following examples do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0049] It should be noted that the phrase "at least one of several items" in this disclosure refers to three parallel cases: "any one of the several items", "a combination of any number of the several items", and "all of the several items". For example, "including at least one of A and B" includes the following three parallel cases: (1) including A; (2) including B; (3) including A and B. As another example, "performing at least one of step one and step two" indicates the following three parallel cases: (1) performing step one; (2) performing step two; (3) performing both step one and step two.

[0050] Two approaches to pre-downloading multimedia resources exist in related technologies. The first is based on the user account's local historical behavior (e.g., the number of times the multimedia resource has been used historically), pre-downloading occurs when the user enters the multimedia resource production interface. However, in some scenarios (e.g., short video creation), multimedia resources are updated very frequently, and most user accounts use new multimedia resources they have never used before. The use of new multimedia resources cannot be predicted based on the user account's local historical behavior. The second approach is based on the recent multimedia resource usage of all online user accounts, pre-downloading occurs when the user enters the multimedia resource production interface. However, due to significant differences between different user account groups (e.g., gender, age, region), there are also large differences in multimedia resource usage. Therefore, pre-downloading based on the overall recent multimedia resource usage of user accounts cannot accurately predict the multimedia resource usage preferences of user accounts across different dimensions, resulting in the user still needing to wait for the resource package to download when actually using the multimedia resource.

[0051] To address the low prediction hit rate of current multimedia resource pre-download schemes, this disclosure proposes a multimedia resource acquisition method, apparatus, device, and medium. Specifically, multimedia resources can be pre-downloaded based on multimedia resource usage data of user accounts matched with user characteristic dimensions. Since user characteristic dimensions are related to multimedia resource usage, the prediction hit rate of multimedia resources can be significantly improved. This avoids situations where users have to wait for resource packages to download because the pre-downloaded multimedia resources do not meet their expectations, thus ensuring that users can quickly access multimedia resources that meet their expectations, thereby significantly improving the user experience.

[0052] Furthermore, since a request to obtain multimedia resources is sent every time the client starts cold, almost every user account can obtain the configuration data of the pre-downloaded multimedia resources. The usage of the configuration data of the pre-downloaded multimedia resources by each user account can be used as a reference for subsequent multimedia resource recommendations, which can continuously improve the prediction hit rate of the multimedia resource pre-download scheme.

[0053] In addition, since the data in the database storing multimedia resource information is updated periodically, the latest updated multimedia resources can be pre-downloaded in a timely manner, which ensures that users can use the latest multimedia resources and further improves the user experience.

[0054] Below, we will refer to Figures 1 to 7 This invention provides a detailed description of a multimedia resource acquisition method, apparatus, device, and medium according to exemplary embodiments of the present disclosure.

[0055] Figure 1 This is an exemplary system architecture 100 that illustrates an exemplary embodiment of the present disclosure and to which it may be applied.

[0056] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, and 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, and 103 and the server 105. The network 104 may include various connection types, such as wired or wireless communication links or fiber optic cables. Users can use the terminal devices 101, 102, and 103 to interact with the server 105 through the network 104 to receive or send messages (e.g., to send requests for multimedia resources or to receive multimedia resource data). Various applications involving the display of multimedia resources, such as video playback applications and video production applications, may be installed on the terminal devices 101, 102, and 103. The terminal devices 101, 102, and 103 may be hardware or software. When the terminal devices 101, 102, and 103 are hardware, they may be various electronic devices with displays and capable of resource processing, including but not limited to smartphones, tablets, laptops, and desktop computers. When terminal devices 101, 102, and 103 are software, they can be installed in the electronic devices listed above. They can be implemented as multiple software programs or software modules (e.g., to provide distributed services) or as a single software program or software module. No specific limitations are made here.

[0057] Server 105 can be a server that provides various services, such as a backend server that supports multimedia applications installed on terminal devices 101, 102, and 103. For example, in response to a request to obtain multimedia resources, the backend server can send multimedia resource data to terminal devices 101, 102, and 103.

[0058] It should be noted that a server can be either hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When the server is software, it can be implemented as multiple software programs or software modules (e.g., used to provide distributed services), or as a single software program or software module. No specific limitations are made here.

[0059] Figure 2 This is a flowchart illustrating a multimedia resource acquisition method according to an exemplary embodiment of the present disclosure.

[0060] Reference Figure 2 In step 201, a request for multimedia resources from the first user account can be received. Multimedia resources refer to special effects in the video production scene, such as filters, stickers, emoticons, and widgets.

[0061] In step 202, in response to the acquisition request, a second user account can be determined. The second user account matches the feature data of the first user account under at least one user feature dimension. The user feature dimension is a feature category related to the usage of multimedia resources. That is, the second user account refers to a user account from other clients that are distinct from the current client, and the user feature dimension refers to multiple data aspects that constitute the user account.

[0062] According to an exemplary embodiment of this disclosure, user characteristic dimensions related to multimedia resource usage can be obtained by analyzing multimedia resource usage data for different user accounts in a data warehouse. Here, the data warehouse stores various status data (e.g., age, location, etc.) and behavioral data (e.g., multimedia resource usage, etc.) for multiple user accounts. Specifically, for any one of a set of preset dimensions, the usage data of multimedia resources corresponding to each dimension label can be obtained. Then, based on the usage data of multimedia resources corresponding to each dimension label, the same multimedia resources corresponding to multiple dimension labels in the dimension can be determined. Next, if the proportion of the number of the same multimedia resources corresponding to multiple dimension labels in the dimension exceeds a preset threshold, the dimension can be determined as a user characteristic dimension.

[0063] For example, the age dimension includes labels such as children, teenagers, young adults, middle-aged, and elderly. Therefore, the multimedia resource usage of five types of user accounts can be analyzed under the age dimension. If at least 80% of user accounts in each category tend to use the same multimedia resources, then user accounts under the age dimension are considered to have commonalities in their multimedia resource selection, and age can be used as a dimension for matching user accounts in the process of acquiring multimedia resources. In other words, under the same dimension, if the proportion of user accounts using the same multimedia resources in each user account category exceeds a certain threshold, then the correlation between that dimension and the selection of multimedia resources is considered to be higher. Based on this principle, at least one user characteristic dimension related to multimedia resource usage can be obtained.

[0064] According to exemplary embodiments of this disclosure, at least one user characteristic dimension may include at least one of preferences, location, and age.

[0065] Here, preferences refer to the user account's interests based on various behavioral data. These preferences can be comprehensively understood from various aspects such as the user's publicly disclosed personal information, liked works, viewing time, and comment content, categorizing users into multiple interest groups such as art, sports, and beauty. Location refers to the actual location of the user account, which can be obtained through the user's publicly disclosed location information. It should be noted that all user information disclosed herein (including but not limited to user device information and user personal information) is information authorized by the user or fully authorized by all parties.

[0066] According to an exemplary embodiment of this disclosure, the aforementioned acquisition request may be issued during the cold start phase of the device on the first user account side. A cold start is a method of application startup where the application process is disconnected and then restarted, during which all data in memory is lost. Since application use requires a cold start, almost every user account can issue a request to acquire multimedia resources (though there may be exceptions such as no network). Thus, almost every user account can obtain the configuration data for pre-downloaded multimedia resources. Furthermore, each user account's usage of the pre-downloaded multimedia resource configuration data can be used as a reference for subsequent multimedia resource recommendations, continuously improving the prediction hit rate of the multimedia resource pre-download scheme and maintaining a consistent user experience throughout the multimedia resource acquisition process.

[0067] According to an exemplary embodiment of this disclosure, the aforementioned acquisition request may include information about an account identifier of a first user account. Based on the account identifier, target feature data corresponding to the first user account under each user feature dimension can be acquired. Then, a second user account whose feature data matches the target feature data can be determined from the database. The database stores feature data of any user account under each user feature dimension and data on multimedia resources used by any user account within a historical preset time period.

[0068] Specifically, during each cold start, the client sends a request to the configuration distribution server for the first user account to obtain multimedia resources. This request may include the user ID (i.e., account identifier). The configuration distribution server is used to distribute multimedia resource configurations to the client.

[0069] After receiving a request, the configuration distribution server first extracts at least one feature data from the user ID, including preferences, location, and age. Any big data analysis scheme from related technologies can be used to extract this feature data, and this disclosure does not limit this approach. Then, based on the obtained feature data, a second user account with the same feature data can be matched against a database storing multimedia resource information. This allows the acquisition of multimedia resource usage data for the second user account. Here, user accounts with the same feature data can be considered similar users (i.e., their selection and use of multimedia resources are similar). Obtaining target multimedia resource data based on the multimedia resource usage data of similar users increases the probability of the obtained target multimedia resource data being used, thereby improving the user's multimedia resource experience.

[0070] According to an exemplary embodiment of this disclosure, the data in the database storing multimedia resource information is periodically updated. Specifically, the usage of multimedia resources changes in real time. Therefore, to improve the pre-download hit rate of multimedia resources, the data in the database storing multimedia resource information can be periodically updated, for example, every 6 hours, 12 hours, 24 hours, etc., without limitation. The data in the database can be cleaned (i.e., the data is re-examined and verified, duplicate data is deleted, and existing errors are corrected to ensure data consistency), and the data can be aggregated according to three dimensions: preference, age, and location (i.e., the data is selected, analyzed, and categorized to obtain the target result, mainly referring to any data transformation process that can generate scalar values ​​from arrays). Here, data cleaning and data aggregation can adopt any scheme from related technologies, without limitation.

[0071] In step 203, the second multimedia resource can be determined from the first multimedia resources used by the second user account.

[0072] According to an exemplary embodiment of this disclosure, the aforementioned acquisition request may include information regarding the available storage space size on the first user account side. First multimedia resources used by the second user account can be acquired. Then, at least one second multimedia resource can be determined from the first multimedia resources, wherein the sum of the storage space occupied by the at least one second multimedia resource is less than the available storage space size.

[0073] According to an exemplary embodiment of this disclosure, the configuration distribution server can determine the usage probability of a first user account for each first multimedia resource based on the usage frequency of each first multimedia resource. Next, at least one second multimedia resource can be determined from the first multimedia resources based on the usage probability of each first multimedia resource.

[0074] According to an exemplary embodiment of this disclosure, the sum of the usage frequencies of the first multimedia resources can be determined based on the usage frequency of each first multimedia resource. Then, for any given first multimedia resource, the proportion of the usage frequency of that first multimedia resource in the sum of the usage frequencies of the first multimedia resources can be determined as the usage probability of the first user account for that first multimedia resource.

[0075] Furthermore, multimedia resource IDs can be used for sorting. Due to limited client storage space, the configuration distribution server also determines the number of multimedia resources to be distributed based on the client's storage space size. For example, if the multimedia resource sequence arranged from high to low usage probability is [3,19,109,233,81…], and the configuration distribution server determines that 3 multimedia resources can be distributed based on the client's storage space size, then the distributed multimedia resource IDs will be [3,19,109].

[0076] In step 204, the multimedia resource identifier of the second multimedia resource can be fed back to the first user account so that the first user account can obtain the target multimedia resource based on the multimedia resource identifier. That is, the target multimedia resource data can be sent to the client so that the client can obtain the target multimedia resource based on the target multimedia resource data.

[0077] According to exemplary embodiments of this disclosure, a client can request a resource management server to pre-download a target multimedia resource based on target multimedia resource data (e.g., multimedia resource ID) when the network is idle. After downloading, the resource is decompressed and cached on the client's disk. When a user account uses multimedia resources in a video production scenario, if the multimedia resource has already been pre-downloaded, it can be directly loaded from the disk into memory for use. Since the pre-downloaded multimedia resource is based on multimedia resource usage data of similar user accounts, it has a higher probability of being used. In many video production scenarios, users do not need to wait for multimedia resources to download, thus improving the user experience.

[0078] Figure 3 This is a flowchart illustrating a multimedia resource acquisition method according to another exemplary embodiment of the present disclosure.

[0079] Reference Figure 3 In step 301, a request can be sent to the first server. This request is a request from the first user account for multimedia resources. Here, multimedia resources refer to special effects in a video production scene, such as filters, stickers, emoticons, and widgets.

[0080] According to an exemplary embodiment of this disclosure, a request to acquire multimedia resources can be sent to the first server during the cold start phase. Since all applications require a cold start, almost every user account can send a request to acquire multimedia resources (even in exceptional circumstances such as no network access), thereby maintaining a consistent user experience throughout the multimedia resource acquisition process.

[0081] In step 302, a multimedia resource identifier for a second multimedia resource can be received from the first server. The second multimedia resource is determined from first multimedia resources used by a second user account. The second user account is determined by the first server in response to a request. The second user account matches the first user account in at least one user feature dimension, where the user feature dimension is a feature category related to the usage of multimedia resources. Here, the user feature dimension refers to multiple data aspects constituting a user account.

[0082] According to an exemplary embodiment of this disclosure, dimensions can be obtained by analyzing multimedia resource usage data for different user accounts in a data warehouse. Here, the data warehouse stores various status data (e.g., age, location, etc.) and behavioral data (e.g., multimedia resource usage, etc.) for multiple user accounts. Specifically, multiple dimensions related to multimedia resource usage can be preset, and the correlation between multimedia resource usage and the preset multiple dimensions can be analyzed. At least one dimension with a correlation that meets expectations is determined as a user feature dimension that can be used for user account matching, wherein each dimension corresponds to different classification labels.

[0083] For example, the age dimension includes labels such as children, teenagers, young adults, middle-aged, and elderly. Therefore, the multimedia resource usage of five types of user accounts can be analyzed under the age dimension. If at least 80% of user accounts in each category tend to use the same multimedia resources, then user accounts under the age dimension are considered to have commonalities in their multimedia resource selection, and age can be used as a dimension for matching user accounts in the process of acquiring multimedia resources. In other words, the higher the proportion of user accounts using the same multimedia resources in each user account category under the same dimension, the higher the correlation between that dimension and the selection of multimedia resources. Based on this principle, at least one user characteristic dimension related to multimedia resource usage can be obtained.

[0084] According to exemplary embodiments of this disclosure, at least one user characteristic dimension may include at least one of preferences, location, and age.

[0085] Here, preferences refer to the user account's interests based on various behavioral data. These preferences can be comprehensively understood from various aspects such as the user's publicly disclosed personal information, liked works, viewing time, and comment content, categorizing users into multiple interest groups such as art, sports, and beauty. Location refers to the actual location of the user account, which can be obtained through the user's publicly disclosed location information. It should be noted that all user information disclosed herein (including but not limited to user device information and user personal information) is information authorized by the user or fully authorized by all parties.

[0086] In step 303, the target multimedia resource can be obtained based on the multimedia resource identifier, that is, the target multimedia resource can be obtained based on the target multimedia resource data. Here, the target multimedia resource data received from the server is, for example, a multimedia resource ID.

[0087] According to exemplary embodiments of this disclosure, it can be determined whether a multimedia resource identifier already exists. If the multimedia resource identifier does not exist, a target multimedia resource acquisition request can be sent to a second server. The target multimedia resource acquisition request may include information about the multimedia resource identifier, causing the second server to send the target multimedia resource to the first user account in response to the request. Then, the target multimedia resource sent by the second server can be received.

[0088] Here, when the network is idle, a request to acquire the target multimedia resource can be sent to the second server. Specifically, since the application may undergo multiple cold starts, the process of acquiring multimedia resources may be repeated multiple times. Therefore, duplicate multimedia resource data may be received from the server. So, after receiving the target multimedia resource data, the client can first check whether the corresponding multimedia resource ID already exists locally. If it does not exist, it can request the resource management server to pre-download the target multimedia resource when the network is idle, and then decompress and cache it to the client's disk after the download is complete, thus avoiding resource waste caused by repeated downloads.

[0089] In some embodiments, if some of the received multimedia resource data exists while others do not, and the client has available storage space, the client can send another request to the server to retrieve the multimedia resources after receiving the multimedia resource data. Upon receiving this request, the server selects multimedia resource data that its storage space can accommodate from the pre-sorted multimedia resource sequence and sends it to the client, thereby further increasing the probability of multimedia resource usage and improving the user's multimedia resource experience. For example, if the multimedia resource sequence is [3,19,109,233,81…], and the client's storage space can store three multimedia resources, and the first two of the sent multimedia resource IDs [3,19,109] already exist, then [233,81] can be sent to the client again.

[0090] When a user account uses multimedia resources in a video production scenario, if the multimedia resources have been pre-downloaded, they can be directly loaded from the disk into memory for use. Since pre-downloaded multimedia resources are based on multimedia resource usage data of user accounts similar to the client's user account, they are more likely to be used. In many video production scenarios, users do not need to wait for multimedia resources to download, improving the user experience. Furthermore, the multimedia resources used by a user account and the number of times they are used are reported to a data warehouse. A daily scheduled task cleans the data in the data warehouse, aggregating the cleaned data according to three dimensions: preference, location, and age, and storing it in a database that stores multimedia resource information. This greatly ensures that the multimedia resource information stored in the database is up-to-date, further increasing the probability of the acquired multimedia resources being used and enhancing the user experience.

[0091] To provide a clearer picture of the solution disclosed herein, the following description of the multimedia resource acquisition solution will be provided in conjunction with the pre-downloading of special effects in a short video production scenario.

[0092] Figure 4This is an overall schematic diagram illustrating an effects pre-download process according to an exemplary embodiment of the present disclosure.

[0093] Reference Figure 4 During each cold start, the client sends a request to the configuration distribution server to retrieve special effects, carrying the user account ID. Upon receiving this request, the configuration distribution server extracts three feature data related to effect usage: preference, location, and age. These feature data are obtained through analysis of effect usage data from a data warehouse for different user accounts. Furthermore, the data in the data warehouse can be cleaned and aggregated according to the three dimensions of preference, location, and age to create a database storing effect information (i.e., effect usage data, including user account information, the effects used by the user account, and the number of times the effect was used). The configuration distribution server then matches user accounts similar to the current client's user account (including multiple user accounts with identical feature data) from the database storing effect information based on the extracted feature data, thereby obtaining data on effect usage by similar user accounts.

[0094] Then, the configuration distribution server sorts the effects used by similar user accounts according to their usage probability, obtaining an effect usage sequence. It then selects a target number of effects from the first position of this sequence, based on the client's storage space, and distributes the corresponding effect IDs to the client. Afterward, the client checks if the received effect ID already exists locally. If not, it requests the resource management server to pre-download the effect corresponding to the received effect ID when the network is idle, and decompresses and caches it on the disk.

[0095] When a user account selects and uses special effects in a short video creation scenario, if the effect has already been downloaded, it is directly loaded from disk into memory and used. If it has not been downloaded, it needs to wait for the download to complete before use. Here, the special effects used by the user account and the number of times they are used are reported to the data warehouse. There are also daily scheduled tasks to clean the data in the data warehouse and aggregate the data according to the determined dimensions before sending it to the database storing special effects information, so that the information in the database is always up-to-date.

[0096] Figure 5 This is a block diagram illustrating a multimedia resource acquisition apparatus according to exemplary embodiments of the present disclosure.

[0097] Reference Figure 5 The multimedia resource acquisition device 500 according to an exemplary embodiment of the present disclosure may include a data acquisition request receiving module 501, a user account determination module 502, a multimedia resource determination module 503, and a feedback module 504.

[0098] The request receiving module 501 is configured to receive a request from a first user account for multimedia resources.

[0099] User account determination module 502 is configured to determine a second user account in response to an acquisition request. The second user account matches the feature data of the first user account under at least one user feature dimension, wherein the user feature dimension is a feature category related to the use of multimedia resources.

[0100] The multimedia resource determination module 503 is configured to determine the second multimedia resource from the first multimedia resources used by the second user account;

[0101] Feedback module 504 is configured to provide a multimedia resource identifier of the second multimedia resource to the first user account, so that the first user account can obtain the target multimedia resource based on the multimedia resource identifier.

[0102] because Figure 2 The multimedia resource acquisition method shown can be obtained by Figure 5 The multimedia resource acquisition device 500 shown is used to perform this operation, and the acquisition request receiving module 501, user account determination module 502, multimedia resource determination module 503, and feedback module 504 can respectively execute the corresponding functions. Figure 2 The operations corresponding to steps 201, 202, 203, and 204 in the text, therefore, regarding Figure 5 For any details regarding the operations performed by the various modules within the framework, please refer to the documentation. Figure 2 The corresponding descriptions will not be repeated here.

[0103] Furthermore, it should be noted that although the multimedia resource acquisition device 500 is described above as being divided into modules for performing corresponding processes, those skilled in the art will understand that the processes performed by these modules can also be performed without any specific module division or clear boundaries between the modules. In addition, the multimedia resource acquisition device 500 may also include other modules, such as a data processing module and a storage module.

[0104] Figure 6 This is a block diagram illustrating a multimedia resource acquisition apparatus according to another exemplary embodiment of the present disclosure.

[0105] Reference Figure 6 The multimedia resource acquisition device 600 according to an exemplary embodiment of the present disclosure may include a request acquisition request sending module 601, a multimedia resource identifier receiving module 602, and a multimedia resource acquisition module 603.

[0106] The request sending module 601 is configured to send a request to the first server, wherein the request is a request from the first user account for multimedia resources.

[0107] The multimedia resource identifier receiving module 602 is configured to receive a multimedia resource identifier of a second multimedia resource from the first server, wherein the second multimedia resource is determined from the first multimedia resources used by the second user account, the second user account is determined by the first server in response to the acquisition request, and the second user account matches the feature data corresponding to the first user account under at least one user feature dimension, wherein the user feature dimension is a feature category related to the usage of the multimedia resource.

[0108] The multimedia resource acquisition module 603 is configured to acquire the target multimedia resource based on the multimedia resource identifier.

[0109] because Figure 3 The multimedia resource acquisition method shown can be obtained by Figure 6 The multimedia resource acquisition device 600 shown is used to perform this operation, and the request acquisition request sending module 601, the multimedia resource identifier receiving module 602, and the multimedia resource acquisition module 603 can respectively execute the corresponding functions. Figure 3 The operations corresponding to steps 301, 302, and 303 in the text, therefore, regarding Figure 6 For any details regarding the operations performed by the various modules within the framework, please refer to the documentation. Figure 3 The corresponding descriptions will not be repeated here.

[0110] Furthermore, it should be noted that although the multimedia resource acquisition device 600 is described above as being divided into modules for performing corresponding processes, those skilled in the art will understand that the processes performed by these modules can also be performed without any specific module division or clear boundaries between the modules. In addition, the multimedia resource acquisition device 600 may also include other modules, such as a data processing module and a storage module.

[0111] Figure 7 This is a block diagram illustrating an electronic device 700 according to an exemplary embodiment of the present disclosure.

[0112] Reference Figure 7 The electronic device 700 includes at least one memory 701 and at least one processor 702. The at least one memory 701 stores a set of computer-executable instructions. When the set of computer-executable instructions is executed by the at least one processor 702, a multimedia resource acquisition method according to an exemplary embodiment of the present disclosure is performed.

[0113] As an example, electronic device 700 may be a PC, tablet, personal digital assistant, smartphone, or other device capable of executing the aforementioned set of instructions. Here, electronic device 700 is not necessarily a single electronic device, but may be a collection of any devices or circuits capable of executing the aforementioned instructions (or instruction sets) individually or in combination. Electronic device 700 may also be part of an integrated control system or system manager, or may be configured to interconnect with a portable electronic device locally or remotely (e.g., via wireless transmission) through an interface.

[0114] In electronic device 700, processor 702 may include a central processing unit (CPU), a graphics processing unit (GPU), a programmable logic device, a dedicated processor system, a microcontroller, or a microprocessor. By way of example and not limitation, processor may also include analog processors, digital processors, microprocessors, multi-core processors, processor arrays, network processors, etc.

[0115] The processor 702 can execute instructions or code stored in the memory 701, which can also store data. Instructions and data can also be sent and received via a network through a network interface device, which can employ any known transmission protocol.

[0116] The memory 701 can be integrated with the processor 702, for example, by placing RAM or flash memory within an integrated circuit microprocessor. Alternatively, the memory 701 can include a separate device, such as an external disk drive, a storage array, or other storage device usable by any database system. The memory 701 and the processor 702 can be operatively coupled, or can communicate with each other, for example, via I / O ports, network connections, etc., enabling the processor 702 to read files stored in the memory.

[0117] In addition, the electronic device 700 may also include a video display (such as a liquid crystal display) and a user interaction interface (such as a keyboard, mouse, touch input device, etc.). All components of the electronic device 700 can be interconnected via a bus and / or network.

[0118] According to exemplary embodiments of the present disclosure, a computer-readable storage medium storing instructions may also be provided, wherein when the instructions are executed by at least one processor, they cause at least one processor to perform a multimedia resource acquisition method according to the present disclosure. Examples of computer-readable storage media herein include: read-only memory (ROM), random access programmable read-only memory (PROM), electrically erasable programmable read-only memory (EEPROM), random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), flash memory, non-volatile memory, CD-ROM, CD-R, CD+R, CD-RW, CD+RW, DVD-ROM, DVD-R, DVD+R, DVD-RW, DVD+RW, DVD-RAM, BD-ROM, BD-R, BD-R LTH, BD-RE, Blu-ray or optical disc storage, hard disk drive (HDD), solid-state drive (SSD), card storage (such as multimedia cards, secure digital (SD) cards, or ultra-fast digital (XD) cards), magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid-state drive, and any other device configured to store a computer program and any associated data, data files, and data structures in a non-transitory manner and to provide the computer program and any associated data, data files, and data structures to a processor or computer so that the processor or computer can execute the computer program. The computer program in the aforementioned computer-readable storage medium can run in an environment deployed in computer devices such as clients, hosts, agent devices, servers, etc. Furthermore, in one example, the computer program and any associated data, data files, and data structures are distributed across a networked computer system, such that the computer program and any associated data, data files, and data structures are stored, accessed, and executed in a distributed manner through one or more processors or computers.

[0119] According to exemplary embodiments of the present disclosure, a computer program product may also be provided, wherein the instructions in the computer program product are executable by a processor of a computer device to perform a multimedia resource acquisition method according to exemplary embodiments of the present disclosure.

[0120] According to the multimedia resource acquisition method, apparatus, device, and medium disclosed herein, multimedia resources can be pre-downloaded based on multimedia resource usage data of user accounts matched with user characteristic dimensions. Since user characteristic dimensions are related to multimedia resource usage, the prediction hit rate of multimedia resources can be significantly improved. This can avoid situations where users have to wait for the resource package to be downloaded because the pre-downloaded multimedia resources do not meet their expectations when actually using multimedia resources. In other words, it can ensure that users can quickly use multimedia resources that meet their expectations, thereby significantly improving the user experience.

[0121] Furthermore, since a request to obtain multimedia resources is sent every time the client starts cold, almost every user account can obtain the configuration data of the pre-downloaded multimedia resources. The usage of the configuration data of the pre-downloaded multimedia resources by each user account can be used as a reference for subsequent multimedia resource recommendations, which can continuously improve the prediction hit rate of the multimedia resource pre-download scheme.

[0122] In addition, since the data in the database storing multimedia resource information is updated periodically, the latest updated multimedia resources can be pre-downloaded in a timely manner, which ensures that users can use the latest multimedia resources and further improves the user experience.

[0123] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0124] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A method of acquiring a multimedia resource, characterized by, The method comprises: receiving an acquisition request of a multimedia resource by a first user account; in response to the acquisition request, determining a second user account, the second user account corresponding to feature data of the first user account in at least one user feature dimension, wherein the user feature dimension is a feature category related to use of the multimedia resource; determining a second multimedia resource from first multimedia resources used by the second user account; feeding back a multimedia resource identifier of the second multimedia resource to the first user account, so that the first user account acquires a target multimedia resource according to the multimedia resource identifier; wherein the multimedia resource acquisition method further comprises: for any dimension in a plurality of preset dimensions, acquiring use data of multimedia resources corresponding to each dimension label in the dimension, wherein each dimension label is a value label in the dimension; determining the same multimedia resource corresponding to a plurality of dimension labels in the dimension according to the use data of the multimedia resources corresponding to each dimension label; in a case where the proportion of the number of the same multimedia resources corresponding to a plurality of dimension labels in the dimension in the number of multimedia resources corresponding to each dimension label exceeds a preset threshold, determining the dimension as the user feature dimension; wherein the acquisition request is issued in a cold start phase of a device on the first user account side; the multimedia resource acquisition method further comprises: acquiring use of the target multimedia resource by the first user account as reference information; based on the reference information, performing subsequent multimedia resource recommendation.

2. The multimedia resource acquisition method of claim 1, wherein, The acquisition request includes information about the size of the available storage space on the first user account side, and the determination of the second multimedia resource from the first multimedia resources used by the second user account comprises: acquiring the first multimedia resources used by the second user account; determining at least one second multimedia resource from the first multimedia resources, the at least one second multimedia resource occupying a storage space smaller than the available storage space.

3. The multimedia resource acquisition method of claim 2, wherein, The determination of at least one second multimedia resource from the first multimedia resources comprises: determining the use probability of each first multimedia resource by the first user account according to the use frequency of each first multimedia resource; determining at least one second multimedia resource from the first multimedia resources according to the use probability of each first multimedia resource.

4. The multimedia resource acquisition method of claim 1, wherein, The acquisition request includes information about the account identifier of the first user account, and the determination of the second user account in response to the acquisition request comprises: acquiring target feature data corresponding to the first user account in each user feature dimension according to the account identifier; determining a second user account with feature data matching the target feature data from a database, wherein the database is used to store feature data of any user account in each user feature dimension and data of multimedia resources used by the any user account in a historical preset time period.

5. The multimedia resource acquisition method of claim 3, wherein, The use probability of the first user account for each of the first multimedia resources is determined according to the use frequency of each of the first multimedia resources. The sum of the use frequencies of the first multimedia resources is determined according to the use frequency of each of the first multimedia resources. For any of the first multimedia resources, the proportion of the use frequency of the first multimedia resource in the sum of the use frequencies of the first multimedia resources is determined as the use probability of the first user account for the first multimedia resource.

6. The multimedia resource acquisition method of claim 4, wherein, The user feature dimension includes at least one of preference, location, and age.

7. A method of acquiring a multimedia resource, characterized by, It includes: sending an acquisition request to a first server, wherein the acquisition request is an acquisition request of a first user account for a multimedia resource; receiving a multimedia resource identifier of a second multimedia resource from the first server, wherein the second multimedia resource is determined from the first multimedia resource used by a second user account, the second user account is determined by the first server in response to the acquisition request, the second user account matches the characteristic data corresponding to the first user account in at least one user feature dimension, and the user feature dimension is a characteristic category related to the use of the multimedia resource; acquiring a target multimedia resource according to the multimedia resource identifier; wherein the user feature dimension is determined by: for any dimension in a preset plurality of dimensions, acquiring use data of multimedia resources corresponding to each dimension label in the dimension, wherein each dimension label is each value label under the dimension; determining the same multimedia resource corresponding to a plurality of dimension labels in the dimension according to the use data of the multimedia resources corresponding to each dimension label; in a case where the proportion of the number of the same multimedia resources corresponding to a plurality of dimension labels in the dimension in the number of multimedia resources corresponding to each dimension label exceeds a preset threshold, determining the dimension as the user feature dimension; wherein the sending of the acquisition request to the first server includes: sending the acquisition request to the first server in a cold start phase; The multimedia resource acquisition method further includes: acquiring and sending the use of the target multimedia resource by the first user account to the first server as reference information, so that the first server performs subsequent multimedia resource recommendation based on the reference information.

8. The multimedia resource acquisition method of claim 7, wherein, The acquiring of the target multimedia resource according to the multimedia resource identifier includes: determining whether the multimedia resource identifier already exists; in the case where the multimedia resource identifier does not exist, sending a target multimedia resource acquisition request to a second server, wherein the target multimedia resource acquisition request includes information about the multimedia resource identifier, so that the second server sends the target multimedia resource to the first user account side in response to the target multimedia resource acquisition request; receiving the target multimedia resource sent by the second server.

9. The multimedia resource acquisition method of claim 8, wherein, The sending of the target multimedia resource acquisition request to the second server includes: In a case that the network is idle, the target multimedia resource acquisition request is sent to the second server.

10. A multimedia resource acquisition apparatus characterized by comprising: The method comprises: receiving, by an acquisition request receiving module, an acquisition request for a multimedia resource by a first user account; determining, by a user account determining module, a second user account in response to the acquisition request, the second user account matching corresponding feature data of the first user account in at least one user feature dimension, wherein the user feature dimension is a feature category related to use of the multimedia resource; determining, by a multimedia resource determining module, a second multimedia resource from first multimedia resources used by the second user account; feeding back, by a feedback module, a multimedia resource identifier of the second multimedia resource to the first user account, so that the first user account acquires a target multimedia resource according to the multimedia resource identifier; The multimedia resource acquisition device further comprises: acquiring, by a use data acquisition module, use data of multimedia resources corresponding to each dimension label in any of a plurality of preset dimensions, wherein each dimension label is a value label in the dimension; determining, by a same multimedia resource determining module, same multimedia resources corresponding to a plurality of dimension labels in the dimension according to use data of multimedia resources corresponding to each dimension label; determining, by a user feature dimension determining module, the dimension as the user feature dimension in a case that a proportion of a number of the same multimedia resources corresponding to the plurality of dimension labels in a number of multimedia resources corresponding to each dimension label exceeds a preset threshold value; The acquisition request is sent in a cold start phase of a device on the first user account side; The multimedia resource acquisition device is further configured to: acquire use of the target multimedia resource by the first user account as reference information; perform subsequent multimedia resource recommendation based on the reference information.

11. A multimedia resource acquisition apparatus characterized by comprising: The method comprises: sending, by an acquisition request sending module, an acquisition request to a first server, wherein the acquisition request is an acquisition request for a multimedia resource by a first user account; receiving, by a multimedia resource identifier receiving module, a multimedia resource identifier of a second multimedia resource from the first server, wherein the second multimedia resource is determined from first multimedia resources used by a second user account, the second user account is determined by the first server in response to the acquisition request, the second user account matches corresponding feature data of the first user account in at least one user feature dimension, and the user feature dimension is a feature category related to use of the multimedia resource; acquiring, by a multimedia resource acquisition module, a target multimedia resource according to the multimedia resource identifier; The user feature dimension is determined by the following method: For any one of a plurality of preset dimensions, obtain usage data of multimedia resources corresponding to each dimension label in the dimension, wherein each dimension label is a value label under the dimension; According to the usage data of the multimedia resources corresponding to each dimension label, determine the same multimedia resources corresponding to a plurality of dimension labels in the dimension; In a case where the proportion of the number of the same multimedia resources corresponding to a plurality of dimension labels in the dimension in the number of multimedia resources corresponding to each dimension label exceeds a preset threshold value, determine that the dimension is the user feature dimension; The obtaining request sending module is configured to: send the obtaining request to the first server in a cold start phase; The multimedia resource obtaining apparatus is further configured to: a resource usage obtaining module configured to obtain and send, to the first server, usage of the target multimedia resource by the first user account as reference information, so that the first server performs subsequent multimedia resource recommendation based on the reference information.

12. An electronic device, comprising: comprise: at least one processor; at least one memory storing computer-executable instructions; wherein the computer-executable instructions, when executed by the at least one processor, cause the at least one processor to perform the multimedia resource obtaining method of any one of claims 1 to 6 or the multimedia resource obtaining method of any one of claims 7 to 9.

13. A computer-readable storage medium storing instructions, wherein the instructions, when executed by a processor, cause the processor to perform operations comprising: when executed by at least one processor, cause the at least one processor to perform the multimedia resource obtaining method of any one of claims 1 to 6 or the multimedia resource obtaining method of any one of claims 7 to 9.

Images