Content recommendation method and device, equipment, medium and product

Abstract

The embodiment of the invention provides a content recommendation method and device, equipment, a medium and a product. The method comprises the following steps: in response to an editing trigger operation input in a target editing scene of a client, obtaining first media content edited in the target editing scene; under the condition that the first media content comprises second media content in a first preset format, target content characteristics of the second media content are determined, target transmission content is determined according to the target content characteristics, and the target transmission content is sent to the server; and receiving target recommendation content which is fed back by the server and corresponds to the target editing scene and the target transmission content, and performing associated display on the target recommendation content and the first media content. According to the technical scheme, the effect of determining the recommended content according to the edited media content in the editing scene is achieved, the relevancy between the recommended content and the edited media content is improved, the content editing efficiency is improved, and the content creation experience is improved.

Description

Technical Field

[0001] This disclosure relates to the field of computer processing technology, and more particularly to a content recommendation method, apparatus, device, medium, and product. Background Technology

[0002] In the field of information technology, an increasing number of users are editing content through relevant platforms and publishing their edited content there. During the content editing process, users can be provided with relevant reference content to maximize the fulfillment of their content editing needs.

[0003] In related technologies, content recommendation methods often prioritize content dominated by the majority of accounts on the information exchange platform or highly popular content. In other words, the editorial reference content recommended to users is determined based on the content's popularity or click-through rate. This method may result in low relevance between the user's edited content and the recommended editorial reference content, rendering the recommended content ineffective in guiding the user's content editing process and thus impacting the user's editing efficiency and content creation experience. Summary of the Invention

[0004] This disclosure provides a content recommendation method, apparatus, device, medium, and product to achieve the effect of determining relevant recommended content based on the media content being edited in an editing scenario, thereby improving content editing efficiency and enhancing the content creation experience.

[0005] In a first aspect, embodiments of this disclosure provide a content recommendation method, the method comprising:

[0006] In response to an edit trigger operation input in the target editing scene on the client, the first media content edited in the target editing scene is obtained;

[0007] When the first media content includes second media content in a first preset format, the target content characteristics of the second media content are determined, the target transmission content is determined based on the target content characteristics, and the target transmission content is sent to the server.

[0008] The server receives target recommended content corresponding to the target editing scenario and the target transmitted content, and displays the target recommended content in association with the first media content.

[0009] Secondly, embodiments of this disclosure also provide a content recommendation device, the device comprising:

[0010] The content editing trigger module is used to respond to the editing trigger operation input in the target editing scenario on the client and obtain the first media content that is being edited in the target editing scenario;

[0011] The target content transmission module is used to determine the target content characteristics of the second media content when the first media content includes second media content in a first preset format, determine the target transmission content based on the target content characteristics, and send the target transmission content to the server.

[0012] The recommended content display module is used to receive the target recommended content corresponding to the target editing scenario and the target transmitted content from the server, and to associate and display the target recommended content with the first media content.

[0013] Thirdly, embodiments of this disclosure also provide an electronic device, the electronic device comprising:

[0014] One or more processors;

[0015] Storage device for storing one or more programs.

[0016] When the one or more programs are executed by the one or more processors, the one or more processors implement the content recommendation method as described in any of the embodiments of this disclosure.

[0017] Fourthly, embodiments of this disclosure also provide a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the content recommendation method as described in any of the embodiments of this disclosure.

[0018] Fifthly, embodiments of this disclosure also provide a computer program product, including a computer program that, when executed by a processor, implements the content recommendation method as described in any of the embodiments of this disclosure.

[0019] The technical solution of this disclosure, by responding to an edit trigger operation input in the target editing scenario on the client, obtains the first media content being edited in the target editing scenario, achieving the effect of obtaining the edited media content through simple interactive operations, and providing a data foundation for subsequent determination of recommended content; furthermore, when the first media content includes second media content in a first preset format, the target content features of the second media content are determined, the target transmission content is determined based on the target content features, and the target transmission content is sent to the server, achieving the effect of extracting features from the corresponding preset format media content on the client, and determining the transmission content sent to the server based on the extracted features. By performing feature extraction on the client, the content processing during content transmission is improved. While improving efficiency, it also ensures the security of content transmission. Furthermore, it receives target recommended content from the server that corresponds to the target editing scenario and the target transmitted content, and displays the target recommended content in association with the first media content. This solves the problem in related technologies where the relevance between recommended content and user-edited content is low, thus affecting the user's content editing efficiency. It achieves the effect of determining relevant recommended content based on the media content being edited in the editing scenario, improving the relevance between recommended content and the edited media content, increasing content editing efficiency, and enhancing the content creation experience. Moreover, by extracting features from the corresponding preset format media content on the client side and determining the content to be transmitted to the server based on the extracted features, it reduces the demand for network bandwidth and improves content transmission efficiency. Attached Figure Description

[0020] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0021] Figure 1 A schematic flowchart illustrating a content recommendation method provided in an embodiment of this disclosure;

[0022] Figure 2 A schematic diagram of an editing interface for a target editing scene provided in an embodiment of this disclosure;

[0023] Figure 3 A flowchart illustrating another content recommendation method provided in this embodiment of the disclosure;

[0024] Figure 4 A schematic flowchart of the content recommendation process provided in this embodiment of the disclosure;

[0025] Figure 5A flowchart illustrating another content recommendation method provided in this embodiment of the disclosure;

[0026] Figure 6 A flowchart illustrating another content recommendation method provided in this embodiment of the disclosure;

[0027] Figure 7 This is a schematic diagram of the structure of a content recommendation device provided in an embodiment of the present disclosure;

[0028] Figure 8 This is a schematic diagram of the structure of an electronic device for implementing an embodiment of the present disclosure. Detailed Implementation

[0029] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0030] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0031] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0032] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0033] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0034] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0035] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0036] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0037] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0038] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0039] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0040] Figure 1 This is a flowchart illustrating a content recommendation method provided in an embodiment of this disclosure. This embodiment is applicable to scenarios where, during content editing, target recommended content is determined and sent to the client for content editing reference. This method can be executed by a content recommendation device, which can be implemented in software and / or hardware, optionally through an electronic device, such as a mobile terminal, PC, or server. Figure 1 As shown, the method in this embodiment may specifically include:

[0041] S110. In response to an edit trigger operation input in the target editing scene on the client, obtain the first media content that is being edited in the target editing scene.

[0042] The target editing scenario can be understood as a scenario provided to the user to support content editing. The target editing scenario can include any scenario that supports user editing, optionally including content publishing scenarios, special effects editing scenarios, or template editing scenarios. A content publishing scenario can be understood as a scenario where the edited content is published to a relevant platform. A special effects editing scenario can be understood as a scenario where special effects are created based on the edited content. A template editing scenario can be understood as a scenario where templates are created based on the edited content. An editing trigger operation can be understood as an operation that triggers the editing of related media content. An editing trigger operation can include multiple operations associated with content editing, optionally including image editing operations, text editing operations, audio editing operations, and video editing operations. Image editing operations can include image capture operations and / or image upload operations. Audio editing operations can include audio recording operations and / or audio upload operations. Video editing operations can include video capture operations and / or video upload operations. The first media content can be understood as media content edited based on the editing trigger operation and to be transmitted to the server for processing. The first media content can include media content in at least one preset format. Preset formats can include text, images, audio, and video. For example, the first media content may include a landscape image and landscape description text associated with the landscape image.

[0043] In this embodiment of the disclosure, for a target editing scenario on the client, an editing trigger operation can be input in the target editing scenario on the client. Furthermore, upon receiving the editing trigger operation input in the target editing scenario through the client, the content to be edited in the target editing scenario is determined based on the editing trigger operation, and this content is used as the first media content. The first media content is then used as the content basis for content processing based on the server.

[0044] As an optional implementation of this disclosure, when the target editing scenario is a content publishing scenario, an editing trigger operation can be input in the content publishing scenario on the client side to edit the content to be published. Furthermore, upon receiving an image editing operation and a text editing operation, the system can respond to the image editing operation and the text editing operation, determining the image to be edited in the content publishing scenario based on the image editing operation, and determining the text to be edited in the content publishing scenario based on the text editing operation. Furthermore, the edited image and text can be acquired, and the acquired image and text can be used as the first media content.

[0045] S120: If the first media content includes second media content in a first preset format, determine the target content characteristics of the second media content, determine the target transmission content based on the target content characteristics, and send the target transmission content to the server.

[0046] The first preset format can be a preset content format that requires content feature extraction on the client side. Alternatively, the first preset format can also be a content format that affects content processing efficiency or can intuitively represent specific content. The first preset format can include any format that can affect content processing efficiency or can intuitively represent specific content, and optionally, at least image formats and / or video formats. The second media content can be media content included in the first media content and in the first preset format. Optionally, if the first media content includes images, text, and video, the second media content can be the images and videos included in the first media content. For example, assuming the first media content includes a landscape image and landscape description text associated with the landscape image, the second media content can be this landscape image. Target content features can be understood as information that characterizes the key attributes and features in the media content. In this embodiment of the disclosure, in order to improve content processing efficiency, feature extraction can be performed on the second media content to extract feature information that characterizes the key attributes and features of the content in the second media content. Furthermore, the extracted feature information can be used as target content features. Target content features can be information represented in any form, and optionally, feature information based on vector representation. In other words, the target content features can be a quantitative representation of the second media content, a content feature vector. It's worth noting that converting the second media content into vector-based target content features improves content processing efficiency while avoiding potential content compliance risks and enhancing the security of content transmission between the client and server. The target transmitted content can be understood as the information ultimately sent to the server for processing.

[0047] In practical applications, when the client obtains the first media content to be edited, it is usually sent directly to the server. The server then processes the first media content to obtain recommended content corresponding to it. This recommended content is then fed back to the client. However, this content processing method requires multiple transmissions of media content between the client and server. If the obtained first media content includes second media content (such as images or videos) that affects processing efficiency or directly represents the specific content, the processing efficiency may be low, and the security of the media content may be compromised.

[0048] To address the above issues, in this embodiment of the disclosure, when the first media content being edited in the target editing scenario is obtained, format detection can be performed on the content included in the first media content. Furthermore, if the first media content includes second media content with a first preset format, feature extraction can be performed on the second media content to obtain target content features of the second media content. Further, the target transmission content to be finally sent to the server can be determined based on the target content features. Then, the target transmission content can be sent to the server for processing based on the server, to obtain content associated with the target transmission content.

[0049] It should be noted that the method for determining the target content features of the second media content may include at least one, optionally including feature extraction of the second media content based on a pre-trained content extraction model; or, processing the second media content according to a feature extraction algorithm, etc.

[0050] It should also be noted that there are several ways to determine the target transmission content based on the target content characteristics. Optional methods include content replacement based on the target content characteristics, or content splicing based on the target content characteristics, etc.

[0051] As an optional implementation of this embodiment, when the first media content includes second media content in a first preset format, the second media content can be input into a pre-trained feature extraction model to extract features from the second media content based on the feature extraction model and output target content features. Further, the second media content in the first media content can be replaced with the target content features, and the replaced first media content can be used as the target transmission content and sent to the server.

[0052] As another optional implementation of this disclosure, if the first media content includes second content in a first preset format, the second media content can be input into a pre-trained feature extraction model to extract features from the second media content based on the feature extraction model and output target content features. Further, format detection can be performed on the first media content. If it is determined that the first media content includes third media content in other formats, the third media content and the target content features can be used as the target transmission content. If it is determined that the first media content does not include third media content in other formats, the target content features can be used as the target transmission content. Then, the target transmission content is sent to the server.

[0053] In this embodiment of the disclosure, if the first media content does not include the second media content in the first preset format, the first media content can be used as the target transmission content and sent to the server.

[0054] S130: Receive the target recommended content corresponding to the target editing scenario and target transmission content from the server, and display the target recommended content in association with the first media content.

[0055] The target recommended content can be understood as the display content that meets the interactive requirements of the input object triggering the editing operation. Alternatively, the target recommended content can also be understood as the display content that is ultimately recommended and displayed in the corresponding client. In this embodiment of the disclosure, the target recommended content can be candidate transmission content among the candidate recommended content associated with the target editing scenario that has a content relevance to the target transmission content that meets a preset similarity threshold. Optionally, the target recommended content includes recommended editing content associated with the first media content. Recommended editing content can be understood as content recommended to the user for reference when the user edits the first media content again. Recommended editing content can include multiple pieces of information for optimizing the first media content, optionally including recommended editing text and / or effect editing templates. Recommended editing text can be understood as text recommended to the client as a reference for content editing. Recommended editing text can include multiple pieces of text that serve as a reference for content editing, optionally including the recommended content title of the first media content, recommended polishing text, and recommended topics related to the first media content. The recommended content title can be understood as text recommended to the client as a reference content title for the first media content. Recommended polished text can be understood as text recommended to the client to polish or optimize the text edited in the primary media content. Optionally, the recommended polished text can be text obtained by stylizing the text in the primary media content based on a preset style type, or text obtained by processing the text in the primary media content based on a text generation model, etc. Recommended topics can be understood as text recommended to the client as related reference topics for the primary media content. Effect editing templates can be understood as display effect templates recommended to the client as a reference for content editing. Effect editing templates can include multiple elements related to the edited media content, optionally including effect template images, effect template text, and effect template effects, etc.

[0056] In practical applications, when determining the target recommended content to the client, multiple candidate recommended content items with high popularity and / or high click-through rates are typically selected from pre-stored candidate recommended content, and these selected candidate recommended content items are then used as the target recommended content. However, this method of determining recommended content may result in a low relevance between the content edited by the user and the target recommended content. The target recommended content may not serve as a reference for the user's content editing process, thus affecting the user's content editing efficiency and content creation experience.

[0057] To address the above issues, in this embodiment, when the server receives the target transmitted content, it can perform content analysis based on the target transmitted content determined by the server in the target editing scenario. This analysis identifies at least one candidate recommended content with a high content relevance to the target transmitted content from pre-stored candidate recommended content. The identified candidate recommended content is then used as the target recommended content and fed back to the client. Furthermore, when the client receives the target recommended content, it can input content editing operations on the target recommended content. Further, the target recommended content and the first media content can be associated and displayed based on the content editing operations.

[0058] As an optional implementation of this embodiment, when the target content to be transmitted is sent to the server, multiple candidate recommended contents associated with the target editing scene can be obtained from the server's pre-stored database. Further, the server can determine the content relevance between the target content and each candidate recommended content to obtain multiple content relevance scores. Further, the target content relevance score that meets a preset similarity threshold can be determined from the multiple content relevance scores, and the candidate recommended content corresponding to the target content relevance score can be used as the target recommended content corresponding to the target content to be transmitted. The server then feeds back the target recommended content to the client. Further, when the client receives the target recommended content fed back from the server, the target recommended content can be displayed in association with the first media content.

[0059] It should be noted that the number of target recommended content items returned by the server can be one or more. When there is only one target recommended content item, the first media content can be edited based on that item to associate and display the target recommended content with the first media content. When there are multiple target recommended content items, they can be displayed in descending order of relevance. Furthermore, the client can receive content selection operations for the target recommended content and determine the final target recommended content to be displayed based on these operations. Further, the first media content can be edited based on the target recommended content to associate and display the target recommended content with the first media content.

[0060] For example, in order to more clearly illustrate the technical solutions provided by the embodiments of this disclosure, the target editing scenario is an information publishing scenario, which will be used as an example for explanation. Figure 2 This is a schematic diagram of an editing interface for a target editing scene provided in an embodiment of this disclosure. For example... Figure 2As shown in Figure a, the first media content being edited in the editing interface includes the image 21 and the text 22 being edited. When an editing operation related to a topic associated with the first media content is detected—that is, when the user enters "#" in the edited text—feature extraction can be performed on the image 21 on the client side to obtain target content features. These target content features and the edited text 22 are then sent to the server as target transmission content. Further, the server receives five recommended topics corresponding to the target transmission content, sorted from highest to lowest relevance between the recommended topics and the target transmission content: Recommended Topic 1, Recommended Topic 2, Recommended Topic 3, Recommended Topic 4, and Recommended Topic 5. Further, when a user selects Recommended Topic 1, Recommended Topic 1 is added to the edited text to associate and display it with the first media content. Figure 2 As shown in Figure b, the editing interface includes the first media content to be edited, which includes the image 23 to be edited. Upon detecting an editing operation on the title of the first media content, feature extraction can be performed on the image 23 to obtain target content features, which are then sent to the server as the target transmission content. Then, upon receiving three recommended content titles corresponding to the target transmission content from the server, these titles are sorted in descending order of relevance between the recommended content titles and the target transmission content: Recommended Content Title 1, Recommended Content Title 2, and Recommended Content Title 3. Furthermore, upon detecting a user selection trigger on Recommended Content Title 2, Recommended Content Title 2 is added to the edited text to associate and display it with the first media content. Figure 2 As shown in Figure c, the first media content to be edited in the editing interface includes the image 24 to be edited. Upon detecting an editing operation on the image, feature extraction can be performed on the image 24 on the client side to obtain target content features, which are then sent to the server as the target transmission content. Further, the server receives four effect editing templates corresponding to the target transmission content, ordered from highest to lowest content relevance between the effect editing templates and the target transmission content: Effect Editing Template 1, Effect Editing Template 2, Effect Editing Template 3, and Effect Editing Template 4. Further, upon detecting a user selection trigger operation on Effect Editing Template 3, the template image in Effect Editing Template 3 is replaced with the image 24 to associate Effect Editing Template 3 with the first media content for display.

[0061] The technical solution of this disclosure, by responding to an edit trigger operation input in the target editing scenario on the client, obtains the first media content being edited in the target editing scenario, achieving the effect of obtaining the edited media content through a simple interactive operation, and providing a data foundation for subsequently determining recommended content; furthermore, when the first media content includes second media content in a first preset format, the target content features of the second media content are determined, the target transmission content is determined based on the target content features, and the target transmission content is sent to the server, realizing the effect of extracting features from the corresponding preset format media content on the client, and determining the transmission content sent to the server based on the extracted features. By performing feature extraction on the client, content transmission is achieved. The process improves content processing efficiency while ensuring content transmission security. Furthermore, it receives target recommended content from the server, corresponding to the target editing scenario and target transmitted content, and displays this recommended content in association with the first media content. This solves the problem of low relevance between recommended content and user-edited content in related technologies, which affects user content editing efficiency. It achieves the effect of determining relevant recommended content based on the media content being edited in the editing scenario, thereby improving content editing efficiency and enhancing the content creation experience. Moreover, by extracting features from media content in corresponding preset formats on the client side and determining the content to be sent to the server based on the extracted features, it reduces network bandwidth requirements and improves content transmission efficiency.

[0062] Figure 3 This is a flowchart illustrating another content recommendation method provided in this embodiment. Based on the above embodiments, the technical solution of this embodiment further refines the method for determining the target content features. Determining the target content features of the second media content includes: determining the target content features of the second media content through a target feature extraction model deployed on the client. For detailed implementation methods, please refer to the description of this embodiment. Technical features that are the same as or similar to those in the foregoing embodiments will not be repeated here. Figure 3 As shown, the method in this embodiment may specifically include:

[0063] S210, In response to an edit trigger operation input in the target editing scene on the client, obtain the first media content that is being edited in the target editing scene.

[0064] S220. When the media content includes second media content in a first preset format, the target content features of the second media content are determined by the target feature extraction model deployed on the client, the target transmission content is determined based on the target content features, and the target transmission content is sent to the server.

[0065] The target feature extraction model can be a neural network model that takes media content as input and extracts features from it. In this embodiment, to reduce the computational resource requirements of the neural network model deployed on the client and to reduce the energy consumption of feature extraction based on the client, the target feature extraction model can be a lightweight neural network model capable of performing feature extraction operations. Optionally, the target feature extraction model is determined based on a reference feature extraction model; the number of parameters in the reference feature extraction model is greater than the number of parameters in the target feature extraction model. The number of parameters in the reference feature extraction model can reflect its model complexity. The number of parameters in the reference feature extraction model can be set to a larger value, i.e., a more complex model can be selected. The specific value of the number of parameters in the reference feature extraction model can be set according to actual needs and is not specifically limited here; for example, it can be several gigabytes. The number of parameters in the target feature extraction model can be a smaller value than the number of parameters in the reference feature extraction model. Its specific value can be a preset value and is also determined according to the deployed client, and is not specifically limited here; for example, it can be 3.9M, 5M, or 10M, etc.

[0066] Optionally, the target feature extraction model is the target feature extraction model of the reference feature extraction model; the target feature extraction model is obtained by knowledge distillation of the reference feature extraction model. The reference feature extraction model can be a deep neural network model deployed on the server for training the target feature extraction model. The reference feature extraction model can be a neural network model with a relatively complex model structure. It can be understood that the reference feature extraction model is a large and complex model that has been fully trained and has good performance. During knowledge distillation, the reference feature extraction model can guide the training of the target feature extraction model, enabling it to approach the performance of the reference feature extraction model. The target feature extraction model is a smaller and simpler model, typically with fewer parameters and a simpler model structure. Knowledge distillation is a technique that transfers knowledge learned from a large model with a relatively complex model structure (i.e., the reference feature extraction model) to a smaller model with a simpler model structure (i.e., the target feature extraction model) to achieve model compression and lightweighting. While the reference feature extraction model usually achieves high accuracy, its training requires significant resources and time, whereas the target feature extraction model trains quickly and consumes fewer resources, its accuracy is often lower than that of the reference feature extraction model. Therefore, knowledge distillation guides the training of the target feature extraction model by allowing a reference feature extraction model, enabling the target feature extraction model to achieve the desired model processing effect with limited resources. Optionally, knowledge distillation includes various distillation methods such as response-based knowledge distillation, feature-based knowledge distillation, relation-based knowledge distillation, offline distillation, online distillation, and self-distillation.

[0067] In this embodiment of the disclosure, before applying the target feature extraction model provided in this embodiment, a knowledge distillation can be performed on the reference feature extraction model to obtain the target feature extraction model. Optionally, the knowledge distillation process of the reference feature extraction model is as follows: constructing training samples for training the reference feature extraction model, wherein the training samples include sample media content in a first preset format and actual content features corresponding to the sample media content; training the reference feature extraction model based on the training samples; constructing the target feature extraction model to be trained based on the reference feature extraction model; inputting the sample media content in the training samples into the target feature extraction model to be trained to obtain model prediction features, and inputting the sample media content in the training samples into the reference feature extraction model to obtain model output features; determining a first loss value based on the model prediction features and the actual content features in the sample media content, and determining a second loss value based on the model prediction features and the model output features; correcting the model parameters in the target feature extraction model to be trained based on the first loss value and the second loss value, and using the convergence of the loss function in the target feature extraction model to be trained as the training objective to obtain the target feature extraction model.

[0068] As an optional implementation of this disclosure, after training the target feature extraction model, the target feature extraction model can be deployed on the client. Furthermore, after obtaining the first media content through the client and determining that the first media content includes second media content in a first preset format, the second media content can be input into the target feature extraction model. Then, features can be extracted from the second media content based on the target feature extraction model, and target content features can be output. Furthermore, target transmission content can be determined based on the target content features, and the target transmission content can be sent to the server.

[0069] S230: Receive the target recommended content corresponding to the target editing scenario and target transmission content from the server, and display the target recommended content in association with the first media content.

[0070] For example, Figure 4 This is a schematic flowchart illustrating the content recommendation process provided in an embodiment of this disclosure. Figure 4As shown, the user triggers an edit operation through client input and obtains an editing draft (i.e., the first media content) in the target editing scenario, which includes video, images, and text. Further, the video and images included in the editing draft can be used as the second media content, and the video is frame-by-frame extracted based on the client to obtain at least one video frame. Then, the at least one video frame and the image from the editing draft are input into a target feature extraction model deployed on the client to obtain visual feature vectors (i.e., target content features) corresponding to the video and image. Further, the visual feature vectors and the text included in the editing draft can be used as the target transmission content, and the target transmission content is sent to the server. Further, the target transmission content can be processed based on a content recommendation service deployed on the server to obtain target recommended content. Further, the target recommended content can be fed back to the client so that the user can edit the editing draft again based on the target recommended content.

[0071] The technical solution of this disclosure, when the media content includes second media content in a first preset format, determines the target content features of the second media content by using a target feature extraction model deployed on the client, determines the target transmission content based on the target content features, and sends the target transmission content to the server. This achieves the effect of feature extraction of media content in the corresponding preset format based on the feature extraction model deployed on the client, reduces the demand for network bandwidth, reduces the energy consumption of the server, improves the content transmission efficiency, and enhances the security and privacy of data transmission.

[0072] Figure 5 This is a flowchart illustrating another content recommendation method provided in this embodiment. Based on the above embodiments, the technical solution of this embodiment further refines the method for determining the target transmission content. Determining the target transmission content based on target content characteristics includes: if the first media content includes third media content in a second preset format, sending the third media content and the target content characteristics to the server; and / or, if the first media content does not include third media content in a second preset format, sending the target content characteristics to the server. For detailed implementation methods, please refer to the description of this embodiment. Technical features that are the same as or similar to those in the foregoing embodiments will not be repeated here. Figure 5 As shown, the method in this embodiment may specifically include:

[0073] S310, In response to an edit trigger operation input in the target editing scene on the client, obtain the first media content that is being edited in the target editing scene.

[0074] S320. If the media content includes second media content in a first preset format, determine the target content feature of the second media content; if the first media content includes third media content in a second preset format, use the third media content and the target content feature as target transmission content; and / or, if the first media content does not include third media content in a second preset format, use the target content feature as target transmission content and send the target transmission content to the server.

[0075] The second preset format can be a preset content format that does not require content feature extraction on the client side. Optionally, the first preset format includes at least image and / or video formats. The second preset format includes at least text formats. The third media content is the media content included in the first media content and whose content format is the second preset format.

[0076] As an optional implementation of this embodiment, if the target content characteristics of the second media content are determined, the content format of the first media content can be detected again. Furthermore, if it is determined that the first media content includes third media content in a second preset format, the target content characteristics and the third media content can be used as target transmission content, and the target transmission content can be sent to the server. And / or, if it is determined that the first media content does not include third media content in a second preset format, the target content characteristics can be used as target transmission content and sent to the server.

[0077] S330: Receive the target recommended content corresponding to the target editing scenario and target transmission content from the server, and display the target recommended content in association with the first media content.

[0078] The technical solution of this disclosure, by using the third media content and target content features as target transmission content when the first media content includes third media content of a second preset format; and / or, when the first media content does not include third media content of the second preset format, using target content features as target transmission content and sending the target transmission content to the server, achieves the effect of determining the transmission content to be transmitted to the server based on the extracted content features when the acquired media content includes content of different formats. This achieves the effect of targeted processing of multimodal media content based on the client, enhancing the intelligence of the content processing method.

[0079] Figure 6This is a flowchart illustrating another content recommendation method provided in this embodiment. Based on the above embodiments, the technical solution of this embodiment further refines the method for determining the target transmission content. Determining the target transmission content based on target content features includes: replacing the second media content in the first media content with the target content features to obtain the target transmission content. For detailed implementation methods, please refer to the description of this embodiment. Technical features that are the same as or similar to those in the foregoing embodiments will not be repeated here. Figure 6 As shown, the method in this embodiment may specifically include:

[0080] S410, In response to an edit trigger operation input in the target editing scene on the client, obtain the first media content that is being edited in the target editing scene.

[0081] S420: If the first media content includes second media content in a first preset format, determine the target content feature of the second media content, replace the second media content in the first media content with the target content feature to obtain the target transmission content, and send the target transmission content to the server.

[0082] In this embodiment of the disclosure, when the target content characteristics of the second media content are determined, the second media content in the first media content can be directly replaced with the target content characteristics to obtain the replaced first media content, and the replaced first media content is used as the target transmission content. Further, the target transmission content is sent to the server.

[0083] S430: Receive the target recommended content corresponding to the target editing scenario and target transmission content from the server, and display the target recommended content in association with the first media content.

[0084] The technical solution of this disclosure replaces the second media content in the first media content with the target content features to obtain the target transmission content, and sends the target transmission content to the server. This achieves the effect of directly replacing content based on the content features when the content features corresponding to the media content in the preset format are obtained. This enhances the convenience of the content processing method, improves the efficiency of determining the transmission content, and thus achieves the effect of improving the efficiency of determining the recommended content while ensuring the relevance between the recommended content and the edited content.

[0085] Figure 7 This is a schematic diagram of the structure of a content recommendation device provided in an embodiment of this disclosure, as shown below. Figure 7As shown, the device includes: a content editing trigger module 510, a target content transmission module 520, and a recommended content display module 530. The content editing trigger module 510 is used to respond to an editing trigger operation input in a target editing scenario on the client side, and acquire the first media content being edited in the target editing scenario. The target content transmission module 520 is used to determine the target content characteristics of the second media content when the first media content includes second media content in a first preset format, determine the target transmission content based on the target content characteristics, and send the target transmission content to the server. The recommended content display module 530 is used to receive the target recommended content corresponding to the target editing scenario and the target transmission content from the server, and associate the target recommended content with the first media content for display.

[0086] The technical solution of this disclosure, by responding to an edit trigger operation input in the target editing scenario on the client, obtains the first media content being edited in the target editing scenario, achieving the effect of obtaining the edited media content through a simple interactive operation, and providing a data foundation for subsequently determining recommended content; furthermore, when the first media content includes second media content in a first preset format, the target content features of the second media content are determined, the target transmission content is determined based on the target content features, and the target transmission content is sent to the server, achieving the effect of extracting features from the corresponding preset format media content on the client, and determining the transmission content sent to the server based on the extracted features. By performing feature extraction on the client, content... During transmission, the system improves content processing efficiency while ensuring content transmission security. Furthermore, it receives target recommended content from the server, corresponding to the target editing scenario and the target transmitted content, and displays this recommended content in association with the first media content. This solves the problem of low relevance between recommended content and user-edited content in related technologies, which affects user content editing efficiency. It achieves the effect of determining relevant recommended content based on the media content being edited in the editing scenario, improving content editing efficiency and enhancing the content creation experience. Moreover, by extracting features from the corresponding preset format media content on the client side and determining the content to be sent to the server based on the extracted features, it reduces network bandwidth requirements and improves content transmission efficiency.

[0087] Based on any optional technical solution in the embodiments of this disclosure, optionally, the target content transmission module 520 is specifically used to determine the target content features of the second media content through a target feature extraction model deployed on the client; wherein, the target feature extraction model is determined according to a reference feature extraction model; the number of parameters of the reference feature extraction model is greater than the number of parameters of the target feature extraction model.

[0088] Based on any optional technical solution in the embodiments of this disclosure, optionally, the target feature extraction model is obtained by knowledge distillation of the reference feature extraction model.

[0089] Based on any optional technical solution in the embodiments of this disclosure, optionally, the target content transmission module 520 includes: a first content transmission unit and / or a second content transmission unit. The first content transmission unit is used to, when the first media content includes third media content of a second preset format, use the third media content and the target content feature as target transmission content; and / or, the second content transmission unit is used to, when the first media content does not include third media content of the second preset format, use the target content feature as target transmission content.

[0090] Based on any optional technical solution in the embodiments of this disclosure, optionally, the first preset format includes at least an image format and / or a video format; the second preset format includes at least a text format.

[0091] Based on any optional technical solution in the embodiments of this disclosure, optionally, the target content transmission module 520 includes: a transmission content determination unit. The transmission content determination unit is used to replace the second media content in the first media content with the target content feature to obtain the target transmission content.

[0092] Based on any optional technical solution in the embodiments of this disclosure, optionally, the target recommended content includes recommended editable content associated with the first media content; the recommended editable content includes recommended editable text and / or effect editable templates.

[0093] Based on any optional technical solution in the embodiments of this disclosure, optionally, the recommended edit text includes the recommended content title of the first media content, the recommended polishing text, and the recommended topic associated with the first media content.

[0094] The content recommendation device provided in this disclosure can execute the content recommendation method provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects for executing the content recommendation method.

[0095] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the protection scope of the embodiments of this disclosure.

[0096] The following is for reference. Figure 8 It illustrates an electronic device suitable for implementing embodiments of the present disclosure (e.g., Figure 8 The diagram below shows the structure of the terminal device or server 600. The terminal device in this embodiment may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and vehicle terminals (e.g., vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 8 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0097] like Figure 8 As shown, electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 601, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 602 or a program loaded from storage device 606 into random access memory (RAM) 603. RAM 603 also stores various programs and data required for the operation of electronic device 600. Processing device 601, ROM 602, and RAM 603 are interconnected via bus 604. Input / output (I / O) interface 605 is also connected to bus 604.

[0098] Typically, the following devices can be connected to I / O interface 605: input devices 606 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 607 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 606 including, for example, magnetic tapes, hard disks, etc.; and communication devices 609. Communication device 609 allows electronic device 600 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 8 An electronic device 600 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0099] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 609, or installed from storage device 606, or installed from ROM 602. When the computer program is executed by processing device 601, it performs the functions defined in the methods of embodiments of this disclosure.

[0100] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0101] The electronic device provided in this disclosure and the content recommendation method provided in the above embodiments belong to the same inventive concept. Technical details not described in detail in this disclosure can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0102] This disclosure provides a computer storage medium storing a computer program that, when executed by a processor, implements the content recommendation method provided in the above embodiments.

[0103] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0104] According to one or more embodiments of this disclosure, [Example 1] provides a content recommendation method, including: in response to an edit trigger operation input in a target editing scenario on a client, obtaining first media content being edited in the target editing scenario; if the media content includes second media content in a first preset format, determining target content features of the second media content, determining target transmission content based on the target content features, and sending the target transmission content to a server; receiving target recommended content corresponding to the target editing scenario and the target transmission content from the server, and displaying the target recommended content in association with the first media content.

[0105] According to one or more embodiments of this disclosure, [Example 2] provides the method of Example 1, which further includes: optionally, determining the target content features of the second media content includes: determining the target content features of the second media content by means of a target feature extraction model deployed on the client; wherein the target feature extraction model is determined according to a reference feature extraction model; and the number of parameters of the reference feature extraction model is greater than the number of parameters of the target feature extraction model.

[0106] According to one or more embodiments of this disclosure, Example 3 provides the method of Example 2, which further includes: optionally, the target feature extraction model is obtained by knowledge distillation of the reference feature extraction model.

[0107] According to one or more embodiments of this disclosure, Example 4 provides the method of Example 1, which further includes: optionally, determining the target transmission content based on the target content features includes: if the first media content includes third media content of a second preset format, taking the third media content and the target content features as the target transmission content; and / or, if the first media content does not include third media content of a second preset format, taking the target content features as the target transmission content.

[0108] According to one or more embodiments of this disclosure, Example 5 provides the method of Example 4, which further includes: optionally, the first preset format includes at least an image format and / or a video format; the second preset format includes at least a text format.

[0109] According to one or more embodiments of this disclosure, Example Six provides the method of Example One, which further includes: optionally, determining the target transmission content based on the target content feature includes: replacing the second media content in the first media content with the target content feature to obtain the target transmission content.

[0110] According to one or more embodiments of this disclosure, Example 7 provides the method of Example 1, which further includes: optionally, the target recommended content includes recommended edit content associated with the first media content; the recommended edit content includes recommended edit text and / or effect edit templates.

[0111] According to one or more embodiments of this disclosure, Example 8 provides the method of Example 7, which further includes: optionally, the recommended edit text includes the recommended content title of the first media content, the recommended polishing text, and the recommended topic associated with the first media content.

[0112] According to one or more embodiments of this disclosure, [Example Nine] provides a content recommendation device, comprising: a content editing trigger module, configured to, in response to an editing trigger operation input in a target editing scenario on a client, acquire first media content being edited in the target editing scenario; a target content transmission module, configured to, when the media content includes second media content in a first preset format, determine target content features of the second media content, determine target transmission content based on the target content features, and send the target transmission content to a server; and a recommended content display module, configured to receive target recommended content corresponding to the target editing scenario and the target transmission content from the server, and associate and display the target recommended content with the first media content.

[0113] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0114] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0115] The aforementioned computer-readable medium carries one or more programs. When the electronic device executes the one or more programs, the electronic device causes the following: in response to an edit trigger operation input in a target editing scenario on a client, to acquire first media content being edited in the target editing scenario; if the media content includes second media content in a first preset format, to determine target content features of the second media content, to determine target transmission content based on the target content features, and to send the target transmission content to a server; to receive target recommended content corresponding to the target editing scenario and the target transmission content from the server, and to associate and display the target recommended content with the first media content.

[0116] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0117] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0118] The units described in the embodiments of this disclosure can be implemented in software or in hardware. The names of the units are not necessarily limiting in certain circumstances; for example, a content editing trigger module can also be described as "a module for acquiring the first media content being edited in the target editing scenario".

[0119] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0120] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0121] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0122] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0123] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A content recommendation method, characterized in that, include: In response to an edit trigger operation input in the target editing scene on the client, the first media content edited in the target editing scene is obtained; When the first media content includes second media content in a first preset format, the target content characteristics of the second media content are determined, the target transmission content is determined based on the target content characteristics, and the target transmission content is sent to the server. The server receives target recommended content corresponding to the target editing scenario and the target transmitted content, and displays the target recommended content in association with the first media content.

2. The content recommendation method according to claim 1, characterized in that, The determination of the target content characteristics of the second media content includes: The target content features of the second media content are determined by a target feature extraction model deployed on the client; wherein the target feature extraction model is determined based on a reference feature extraction model; the number of parameters of the reference feature extraction model is greater than the number of parameters of the target feature extraction model.

3. The content recommendation method according to claim 2, characterized in that, The target feature extraction model is obtained by knowledge distillation of the reference feature extraction model.

4. The content recommendation method according to claim 1, characterized in that, Determining the target transmission content based on the target content features includes: When the first media content includes third media content in a second preset format, the third media content and the target content features are used as the target transmission content; and / or, If the first media content does not include third media content in the second preset format, the target content features are taken as the target transmission content.

5. The content recommendation method according to claim 4, characterized in that, The first preset format includes at least image and / or video formats; the second preset format includes at least text formats.

6. The content recommendation method according to claim 1, characterized in that, Determining the target transmission content based on the target content features includes: The target transmission content is obtained by replacing the second media content in the first media content with the target content feature.

7. The content recommendation method according to claim 1, characterized in that, The target recommended content includes recommended editable content associated with the first media content; the recommended editable content includes recommended editable text and / or effect editable templates.

8. The content recommendation method according to claim 7, characterized in that, The recommended edit text includes the title of the recommended content of the first media content, the recommended polished text, and the recommended topic related to the first media content.

9. A content recommendation device, characterized in that, include: The content editing trigger module is used to respond to the editing trigger operation input in the target editing scenario on the client and obtain the first media content that is being edited in the target editing scenario; The target content transmission module is used to determine the target content characteristics of the second media content when the first media content includes second media content in a first preset format, determine the target transmission content based on the target content characteristics, and send the target transmission content to the server. The recommended content display module is used to receive the target recommended content corresponding to the target editing scenario and the target transmitted content from the server, and to associate and display the target recommended content with the first media content.

10. An electronic device, characterized in that, The electronic device includes: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the content recommendation method as described in any one of claims 1-8.

11. A storage medium containing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a computer processor, are used to perform the content recommendation method as described in any one of claims 1-8.

12. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the content recommendation method as described in any one of claims 1-8.

Images