Recommendation content generation method and device, equipment, readable storage medium and product

By obtaining the basic information and interactive content of media content, and automatically generating recommended content using the generation model, the problem of high difficulty in generating recommended content in media content is solved and the content quality and efficiency are improved.

CN119066263APending Publication Date: 2024-12-03DOUYIN VISION CO LTD
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202411001614.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-24
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

In the prior art, the production of recommended content of media content is difficult, and the content quality depends on the writing level of the user, resulting in poor quality of the generated recommended content.

Method used

By obtaining the basic information and interactive content of media content, the preset image generation model and text generation model are used to automatically generate recommended content, including recommended images and recommended text. Users only need to determine the media content to be recommended to automatically generate target recommended content .

Benefits of technology

It reduces the difficulty of generating recommended content, improves the quality and efficiency of recommended content, and allows users to more effectively select media content that meets actual needs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119066263A_ABST
    Figure CN119066263A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides a recommended content generation method and device, equipment, a readable storage medium and a product. The method comprises the steps that at least one piece of media content to be recommended is determined; for each media content, acquiring basic information corresponding to the media content, and acquiring at least one interactive content generated based on the media content; recommended contents corresponding to the media contents are generated based on the basic information corresponding to the media contents and the at least one interactive content, and the recommended contents comprise recommended images and recommended texts; and generating target recommendation content according to the recommendation content corresponding to each media content, and publishing the target recommendation content. Therefore, the user does not need to determine the recommendation image and write the recommendation text by himself, the target recommendation content highlighting the characteristics of the media contents can be automatically generated, the generation difficulty of the target recommendation content is reduced, and the content quality of the target recommendation content is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of data processing technology, and in particular, to a method, device, equipment, readable storage medium, and product for generating recommended content. Background Art

[0002] When a user browses media content in an application software, he or she can perform content recommendation operations on the media content that interests him or her.

[0003] In the related art, users can write recommendation texts based on the currently selected media content to be recommended and determine the recommended pictures. However, using the above method to recommend media content often makes it difficult and time-consuming to generate recommended content, and the quality of the generated recommended content is more dependent on the user's writing skills. Therefore, the recommended content generated using the above method often has poor content quality. Summary of the invention

[0004] The embodiments of the present disclosure provide a method, apparatus, device, readable storage medium and product for generating recommended content, which are used to solve the technical problem that the current generation of recommended content for media content is difficult.

[0005] In a first aspect, an embodiment of the present disclosure provides a method for generating recommended content, including:

[0006] determining at least one media content to be recommended;

[0007] For each media content, basic information corresponding to the media content is obtained, and at least one interactive content generated based on the media content is obtained;

[0008] Generate recommended content corresponding to each media content based on basic information corresponding to each media content and at least one interactive content, wherein the recommended content includes a recommended image and a recommended text;

[0009] Generate target recommended content according to the recommended content corresponding to each media content, and publish the target recommended content.

[0010] In a second aspect, an embodiment of the present disclosure provides a recommended content generating device, including:

[0011] A determination module, used to determine at least one media content to be recommended;

[0012] An acquisition module, configured to acquire, for each media content, basic information corresponding to the media content, and to acquire at least one interactive content generated based on the media content;

[0013] A processing module, configured to generate recommended content corresponding to each media content based on basic information corresponding to each media content and at least one interactive content, wherein the recommended content includes a recommended image and a recommended text;

[0014] The generating module is used to generate target recommended content according to the recommended content corresponding to each media content, and publish the target recommended content.

[0015] In a third aspect, an embodiment of the present disclosure provides an electronic device, including: a processor and a memory;

[0016] The memory stores computer-executable instructions;

[0017] The processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the recommended content generating method as described in the first aspect and various possible designs of the first aspect.

[0018] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer execution instructions. When a processor executes the computer execution instructions, the method for generating recommended content as described in the first aspect and various possible designs of the first aspect is implemented.

[0019] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, including a computer program, which, when executed by a processor, implements the recommended content generation method as described in the first aspect and various possible designs of the first aspect.

[0020] The recommended content generation method, device, equipment, readable storage medium and product provided in this embodiment can automatically generate recommended content corresponding to the media content based on the basic information and the at least one interactive content after determining at least one media content to be recommended. Then, the target media content can be generated and published based on the corresponding recommended content associated with at least one media content. The user only needs to determine at least one media content to be recommended to automatically generate the target recommended content, without having to write the recommended text and edit the recommended image by himself, which effectively reduces the difficulty of generating the target recommended content. In addition, since the recommended content associated with the media content is generated based on the basic information and interactive content associated with the media content, the recommended content includes not only the basic information of the media content, but also the personalized content generated based on the interactive content that can highlight the characteristics of the media content. Then, after publishing the target recommended content, the viewers of the target recommended content can more efficiently select the media content that is more in line with the actual needs based on the target recommended content. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0022] Figure 1 A flowchart of a method for generating recommended content provided by an embodiment of the present disclosure;

[0023] Figure 2 A schematic diagram of target recommendation content provided by an embodiment of the present disclosure;

[0024] Figure 3 A flowchart of a method for generating recommended content provided by another embodiment of the present disclosure;

[0025] Figure 4 A flowchart of a method for generating recommended content provided by another embodiment of the present disclosure;

[0026] Figure 5 A flowchart of a method for generating recommended content provided by another embodiment of the present disclosure;

[0027] Figure 6 A schematic diagram of another target recommendation content provided by an embodiment of the present disclosure;

[0028] Figure 7 A schematic diagram of the structure of a device for generating recommended content provided by an embodiment of the present disclosure;

[0029] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0031] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0032] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0033] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0034] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0035] In order to solve the technical problem that the current media content recommendation content generation is difficult, the present disclosure provides a recommendation content generation method, device, equipment, readable storage medium and product.

[0036] It should be noted that the recommended content generation method, apparatus, device, readable storage medium and product provided by the present disclosure can be applied in any scenario of media content recommendation.

[0037] With the gradual development of terminal technology, more and more application software has gradually entered the lives of users. For example, users can listen to and read books in the reading application, and users can browse video media content in the video application. When users browse media content, they can recommend the media content they like.

[0038] In the related art, users need to generate recommended images associated with media content and write recommended texts associated with media content by themselves, so the content recommendation operation is often cumbersome and difficult.

[0039] In the process of solving the above technical problems, the inventors found through research that in order to quickly generate target recommended content associated with media content, an image generation model and a text generation model can be pre-built. After determining at least one media content currently selected by the user, basic information corresponding to the media content and at least one interactive content generated for the media content can be obtained, so that recommended content associated with the media content to be recommended can be automatically generated based on the basic information and the interactive content, wherein the recommended content can include recommended images and recommended texts. Furthermore, based on the recommended images and recommended texts corresponding to each media content to be recommended, the target recommended content can be automatically generated.

[0040] Figure 1 A flowchart of a method for generating recommended content provided by an embodiment of the present disclosure is shown in FIG. Figure 1 As shown, the method includes:

[0041] Step 101: Determine at least one media content to be recommended.

[0042] The execution subject of this embodiment is a recommended content generation device. The recommended content generation device can be coupled to a terminal device, so that it can automatically generate a recommended image and a recommended text corresponding to at least one media content based on a content recommendation operation triggered by a user in the terminal device. The target recommended content is generated based on the recommended image and the recommended text corresponding to at least one media content.

[0043] Alternatively, the recommended content generation device may also be coupled to a server that is in communication with the terminal device. The server may obtain a content recommendation instruction sent by the terminal device, and generate a recommended image and a recommended text corresponding to at least one media content based on the content recommendation instruction. The target recommended content is generated based on the recommended image and the recommended text corresponding to at least one media content. The target recommended content is sent to the terminal device for display.

[0044] In this embodiment, the user can browse media content in the target application. The media content includes but is not limited to book media content, video media content, audio media content, etc. The user can also recommend the media content he likes. In order to implement the recommendation operation on the media content, at least one media content to be recommended can be determined.

[0045] Optionally, a recommendation control may be pre-set. The user may initiate a content recommendation operation by triggering the recommendation control. In response to the content recommendation operation triggered by the user, a content recommendation page may be displayed. A recommended content selection control may be provided in the content recommendation page. In response to the user's triggering operation on the recommended content selection control, at least one media content that can currently be recommended may be displayed. The at least one media content may be media content that the user has historically browsed, or may be media content that the user has historically interacted with, etc., and the present disclosure does not impose any restrictions on this. In response to a selection operation triggered by the user for at least one media content, at least one media content currently selected by the user may be determined as at least one media content to be recommended.

[0046] Step 102: For each media content, basic information corresponding to the media content is obtained, and at least one interactive content generated based on the media content is obtained.

[0047] In this embodiment, in order to automatically generate target recommended content based on at least one media content, it is necessary to first obtain basic information corresponding to the media content. The basic information includes, but is not limited to, classification information, creator information, identification information, introduction information, image information, etc. For example, if the media content is a book media content, the basic information includes the book title, book classification information, author information, number of readers information, book introduction information, book cover, and other basic information of the book media content.

[0048] In addition, in order to generate personalized content that can highlight the characteristics of the media content, at least one interactive content generated based on the media content can also be obtained. The interactive information includes but is not limited to content tagging data generated by historical users based on the media content and evaluation information published by users for the media content. Still taking the media content as book media content as an example, the interactive content includes but is not limited to evaluation information published by historical users based on the media content and tagging content added by users for paragraphs in the book media content.

[0049] Step 103: Generate recommended content corresponding to each media content based on basic information corresponding to each media content and at least one interactive content, wherein the recommended content includes a recommended image and a recommended text.

[0050] In this embodiment, after respectively acquiring basic information corresponding to the media content and at least one interactive content, recommended content corresponding to the media content can be generated based on the basic information corresponding to the media content and at least one interactive content, wherein the recommended content includes a recommended image and a recommended text.

[0051] Optionally, a recommendation image corresponding to the media content may be generated based on the basic information. A recommendation text may be generated based on the recommendation information and at least one interactive information.

[0052] Step 104: Generate target recommended content according to the recommended content corresponding to each media content, and publish the target recommended content.

[0053] In this embodiment, after obtaining the recommended image and the recommended text corresponding to each media content, target recommended content may be generated based on the recommended image and the recommended text associated with the at least one media content, and the target recommended content may be published.

[0054] Figure 2 A schematic diagram of target recommendation content provided by an embodiment of the present disclosure, such as Figure 2 As shown, the target recommended content 21 may include at least one recommended image 22 and at least one recommended text 23 corresponding to a media content. The user may switch and view different recommended images 22 by triggering a sliding operation in the recommended image 22 area.

[0055] The recommended content generation method provided in this embodiment can automatically generate recommended content corresponding to the media content based on the basic information and the at least one interactive content after determining at least one media content to be recommended. Then, the target media content can be generated and published based on the corresponding recommended content associated with at least one media content. The user only needs to determine at least one media content to be recommended to automatically generate the target recommended content, without having to write the recommended text and edit the recommended image by himself, which effectively reduces the difficulty of generating the target recommended content. In addition, since the recommended content associated with the media content is generated based on the basic information and interactive content associated with the media content, the recommended content includes not only the basic information of the media content, but also the personalized content generated based on the interactive content that can highlight the characteristics of the media content. Then, after publishing the target recommended content, the viewers of the target recommended content can more efficiently select the media content that is more in line with the actual needs based on the target recommended content.

[0056] Figure 3 A flowchart of a method for generating recommended content provided by another embodiment of the present disclosure is provided. Based on any of the above embodiments, Figure 3 As shown, step 103 includes:

[0057] Step 301: For each media content, generate a recommended image associated with the media content based on basic information corresponding to the media content.

[0058] Step 302: Generate a recommendation text associated with the media content based on basic information corresponding to the media content and at least one interactive content.

[0059] Step 303: Generate recommended content corresponding to the media content according to the recommended image and the recommended text.

[0060] In this embodiment, in order to implement an effective recommendation operation for at least one currently selected media content, a recommendation image of the media content may be generated, in which image information, brief introduction information, category information, and other contents associated with the media content are displayed.

[0061] Optionally, after obtaining the basic information corresponding to the media content, a content-associated recommended image may be generated based on the basic information. A recommended text associated with the media content may be generated based on the basic information corresponding to the media content and at least one interactive content. After obtaining the recommended image and recommended text corresponding to each media content respectively, an aggregation operation may be performed on the recommended image and recommended text associated with at least one media content to generate target recommended content.

[0062] Further, based on any of the above embodiments, step 102 includes:

[0063] Acquire the basic information from preset parameters associated with the media content, wherein the basic information includes one or more of a content title, content parameters, introduction information, and a cover image;

[0064] Step 201:

[0065] The basic information is input into a preset image generation model to obtain a recommended image output by the image generation model, wherein the recommended image includes one or more of the content title, content parameters, introduction information and cover image, and the color of the recommended image matches the color of the cover image.

[0066] In this embodiment, each media content corresponds to a pre-stored preset parameter, wherein the preset parameter includes basic parameters such as content title, content parameter, introduction information, etc. The basic information is obtained from the preset parameters associated with the media content, wherein the basic information includes one or more of the content title, content parameter, introduction information, and cover image.

[0067] Furthermore, an image generation model may be pre-set. The image generation model may be obtained by iterative training using a preset training data set. The training data set includes at least one set of training data, each set of training data includes at least one basic information associated with preset media content, and a recommended image associated with the preset media content. After model training is performed using the training data set, the image generation model can quickly and accurately generate a recommended image based on at least one basic information associated with the media content.

[0068] Therefore, after obtaining the basic information corresponding to the media content, the basic information can be input into the preset image generation model to obtain the recommended image output by the image generation model, wherein the recommended image includes one or more of the content title, content parameters, introduction information, and cover image. In order to improve the display effect of the recommended image and make the overall color of the recommended image more harmonious, the color of the recommended image matches the color of the cover image.

[0069] The recommended content generation method provided in this embodiment pre-sets an image generation model, so that after capturing basic information corresponding to the media content, the basic information can be automatically input into the image generation model to obtain a recommended image output by the image generation model, thereby improving the efficiency and accuracy of recommended image generation.

[0070] Further, based on any of the above embodiments, step 202 includes:

[0071] For each media content, the basic information associated with the media content and the at least one interactive content are input into a preset text generation model to obtain a recommended text generated by the text generation model.

[0072] In this embodiment, a text generation model may be pre-set. The text generation model may be obtained by iterative training using a preset training data set. The training data set includes at least one set of training data, each set of training data includes at least one basic information and at least one interactive information associated with preset media content, and recommended text associated with the preset media content. After model training is performed using the training data set, the text generation model can quickly and accurately generate recommended text based on at least one basic information and at least one interactive information associated with the media content.

[0073] Therefore, after obtaining basic information and at least one interactive content corresponding to the media content, the basic information and at least one interactive content may be input into a preset text generation model to obtain a recommended text corresponding to the media content.

[0074] The recommended content generation method provided in this embodiment can automatically generate a recommended text based on the text generation model, basic information associated with the media content, and at least one interactive content by presetting a text generation model, without the need for the user to write the recommended text. In addition, since the recommended text is generated based on the basic information associated with the media content and the interactive content, the recommended text includes not only the basic information of the media content, but also personalized content generated based on the interactive content that can highlight the characteristics of the media content.

[0075] Optionally, based on any of the above embodiments, after step 103, the method further includes:

[0076] Obtaining edited content determined by the user based on the recommended content.

[0077] An editing operation is performed on the recommended content based on the edited content to obtain edited recommended content.

[0078] Step 104 includes:

[0079] The target recommended content is generated based on each edited recommended content.

[0080] In this embodiment, after the recommended content is generated, the user can also adjust the recommended content according to actual needs to obtain recommended content that better meets the user's personalized needs.

[0081] Optionally, after generating the recommended content, the user can also edit the recommended content. The edited content determined by the user based on the recommended content can be obtained. The edited content includes but is not limited to adding content, deleting content, adjusting the order of sentences in the recommended text, modifying content, etc.

[0082] After the edited content is acquired, the recommended content may be edited based on the edited content to obtain the edited recommended content, and then the target recommended content may be generated based on the edited recommended content associated with at least one media content.

[0083] The recommended content generation method provided in this embodiment edits the recommended content based on the editing content determined by the user, so that the finally generated target recommended content is more in line with the personalized needs of the user and the content quality of the target recommended content is improved.

[0084] Figure 4 A flowchart of a method for generating recommended content provided by another embodiment of the present disclosure is provided. Based on any of the above embodiments, Figure 4 As shown, step 102 includes:

[0085] Step 401: Obtain brief introduction information and / or classification label information associated with the media content from preset parameters associated with the media content, and determine the brief introduction information and / or classification label information as the basic information.

[0086] Step 402: Filter at least one interactive data associated with the media content according to a preset filtering condition to obtain the at least one interactive information.

[0087] In this embodiment, in order to generate a more accurate recommendation text, at least one basic information and at least one interactive information associated with the media content may be obtained.

[0088] Optionally, at least one basic information may be obtained from preset parameters associated with the media content, wherein the basic information includes brief introduction information and / or classification label information associated with the media content.

[0089] Furthermore, when browsing media content, users can generate interactive information for the media content. For example, when the media content is a book media content, the interactive information includes but is not limited to the underlining marks made by users for some segments of the book media content and the comments posted by users for the book media content. In order to obtain more effective interactive information, a screening condition can be set in advance, and at least one interactive data associated with the media content can be screened according to the preset screening condition to obtain at least one interactive information.

[0090] The recommended content generation method provided in this embodiment can obtain more diverse second related information by acquiring at least one basic information corresponding to the media content and the interactive information corresponding to the media content, and can then automatically generate a recommended text with richer content and higher quality based on the second related information.

[0091] Optionally, based on any of the above embodiments, the interaction data includes at least one content tag data generated by a user for at least part of the media content. Step 402 includes:

[0092] Determine the historical pageviews corresponding to each content tag data.

[0093] The content marking data whose historical browsing volume is greater than a preset quantity threshold in the at least one content marking data is determined as the interactive information.

[0094] In this embodiment, when a user browses media content, at least one content marking data may be generated for at least part of the content in the media content. Taking the media content as book media content as an example, the content marking data may be marking data obtained by the user underlining some sentences in the book media content. Taking the media content as video media content as an example, the content marking data may be marking data such as comments, saves, etc., made by the user for a video segment in the video media content.

[0095] In order to obtain better quality content from at least one piece of content mark data generated by the user in history, the historical browsing volume corresponding to each piece of content mark data can be determined, and the content mark data with a historical browsing volume greater than a preset threshold value in at least one piece of content mark data is determined as interactive information.

[0096] For example, at least one piece of content mark data may be sorted according to the order of historical page views in the at least one piece of content mark data from large to small, and the top ten pieces of content mark data with higher rankings are determined as interactive information.

[0097] The recommended content generation method provided in this embodiment determines content marking data with a historical browsing volume greater than a preset threshold value in the content marking data historically generated by the user as interactive information, thereby filtering highlight content in the media content, and then generating a recommended text that more accurately describes the media content based on the interactive information.

[0098] Optionally, based on any of the above embodiments, the interactive data includes multiple graphic and text evaluation data published by multiple historical users on the media content. Step 402 includes:

[0099] A preset text recognition model is used to screen multiple graphic and text evaluation data that meet a first preset condition in the interactive data to obtain multiple first interactive data, wherein the first preset condition includes that the amount of data contained in the graphic and text evaluation data meets a preset data amount condition, and the graphic and text evaluation data does not include negative emotional content.

[0100] Determine the associated parameters corresponding to each first interactive data, and filter the multiple first interactive data based on preset interactive conditions and the associated parameters to obtain multiple second interactive data, wherein the associated parameters include data volume information, interactive parameters and browsing parameters of the first interactive data.

[0101] The plurality of second interactive data are screened using a preset screening word set to obtain the interactive information.

[0102] In this embodiment, when browsing media content, users can publish graphic evaluation data for the media content. Taking the media content as book media content as an example, the user can publish evaluation content such as "rich content, tight rhythm, and outstanding character setting" for the book media content. Therefore, high-quality content can be screened from the graphic evaluation data to generate recommended text.

[0103] Optionally, a plurality of graphic and text evaluation data satisfying a first preset condition in the interactive data may be screened by a preset text recognition model to obtain a plurality of first interactive data, wherein the first preset condition includes that the amount of data contained in the graphic and text evaluation data satisfies a preset data amount condition, and the graphic and text evaluation data does not include negative emotional content. Taking the media content as book media content as an example, the first preset condition may be to select 20 comments with non-negative emotions and information content in the graphic and text evaluation data as interactive information.

[0104] Furthermore, interaction conditions may be preset. The associated parameters corresponding to each first interaction data are determined, and a plurality of first interaction data are screened based on the preset interaction conditions and associated parameters to obtain a plurality of second interaction data, wherein the associated parameters include data volume information, interaction parameters, and browsing parameters of the first interaction data. Taking the media content as book media content as an example, the interaction condition may be to select graphic comments with more than 30 words, more than 3 likes, at least one reply content, and a user reading time of more than one hour in the first interaction data as the second interaction data.

[0105] Since the second interactive data published by the user in the past has relatively rich content, a filter word set may be pre-set to further filter the second interactive data to obtain interactive information.

[0106] Further, based on any of the above embodiments, the screening word set includes a positive sub-word set and a negative sub-word set.

[0107] The filtering operation on the plurality of second interactive data using a preset filtering word set to obtain the interactive information includes:

[0108] A filtering operation is performed on the second interaction data including the second interaction data with the vocabulary in the negative subword set in the plurality of second interaction data to obtain a plurality of filtered second interaction data.

[0109] The second interaction data including the vocabulary in the positive subword set in the filtered plurality of second interaction data is determined as the interaction information.

[0110] In this embodiment, since the second interactive data published by the user in the past has relatively rich content, a filter word set may be pre-set to perform further filter operations on the second interactive data.

[0111] For example, for a book media content in the update state, the comments posted by users on the book media content include but are not limited to negative comments such as slow update speed, bad ending, lack of words, watery, abandoned, etc. It can also include positive comments such as good writing, compact plot, recommended, and good-looking.

[0112] In order to realize the generation of the recommended text for the media content, a negative sub-word set and a positive sub-word set can be pre-set, and the second interactive data can be further screened by the negative sub-word set and the positive sub-word set. Among them, the negative sub-word set includes negative words such as slow update speed, bad ending, poor words, water, ink, repetition, abandoned text, etc., and the positive sub-word set includes positive words such as good writing, compact plot, recommendation, good-looking, content, and good character setting. Users can also update and adjust the words in the negative sub-word set and the positive sub-word set according to actual needs, and the present disclosure does not limit this.

[0113] Optionally, a filtering operation can be performed on the second interaction data including the vocabulary in the negative subword set in the multiple second interaction data to obtain the filtered multiple second interaction data. Among them, it can be determined that the second interaction data includes the vocabulary in the negative subword set, and the multiple second interaction data are filtered. The second interaction data including the vocabulary in the positive subword set in the multiple filtered second interaction data are determined as interaction information. Among them, it can be determined that the multiple second interaction data including the vocabulary in the positive subword set in the multiple filtered second interaction data, the multiple second interaction data are retained, and the other second interaction data are filtered to obtain interaction information.

[0114] The recommended content generation method provided in this embodiment obtains interactive information by filtering multiple graphic and text evaluation data published by historical users on the media content, thereby obtaining interactive information that can accurately describe the media content. Further, based on the interactive information, more accurate recommended text can be generated.

[0115] Figure 5 A flowchart of a method for generating recommended content provided by another embodiment of the present disclosure is provided. Based on any of the above embodiments, Figure 5 As shown, step 104 includes:

[0116] Step 501: Determine a determination order corresponding to the at least one media content.

[0117] Step 502: Sorting the recommended images associated with the at least one media content based on the determined order to obtain the sorted recommended images.

[0118] Step 503: Display the sorted recommended images in a preset first display area.

[0119] Step 504: perform a splicing operation on the recommendation text corresponding to the at least one media content based on the determined order to obtain a spliced ​​recommendation text.

[0120] Step 505: Display the spliced ​​recommendation text in a preset second display area to obtain the target recommended content.

[0121] In this embodiment, after the recommended image and the recommended text associated with at least one media content are generated respectively, the target recommended content may be generated based on the recommended image and the recommended text associated with the at least one media content.

[0122] Optionally, the determination order of the user in determining at least one media content can be determined. Based on the determination order, the recommended images associated with the at least one media content are sorted to obtain the sorted recommended images. The sorted recommended images can be displayed in a stacked manner. The user can view different recommended images by sliding in a preset direction. Alternatively, at least one recommended image can also be spliced ​​into the same image according to the determination order, so that the user can view multiple recommended images on the same image. The present disclosure does not limit this.

[0123] Furthermore, the recommended text corresponding to the at least one media content may be spliced ​​based on the determined order to obtain the spliced ​​recommended text. Since the spliced ​​recommended text is long, the user may view all the recommended texts by sliding.

[0124] Optionally, the sorted recommended images can be displayed in a preset first display area. The spliced ​​recommended text is displayed in a preset second display area to obtain the target recommended content. The first display area and the second display area can be arranged vertically, or the first display area and the second display area can be arranged horizontally. The present disclosure does not limit this. In addition, the user can also adjust the display size and display position of the first display area and the second display area according to actual needs, and the present disclosure does not limit this.

[0125] The recommended content generation method provided in this embodiment sorts the recommended images and splices the recommended texts according to the determined order corresponding to the at least one media content, so that the user can browse the recommended images and recommended texts associated with multiple media contents in the target recommended content in an orderly manner, and more recommended contents can be displayed within a limited display page.

[0126] Further, based on any of the above embodiments, after step 104, the method further includes:

[0127] A trigger control corresponding to the media content associated with each recommended image is displayed in a display area associated with the recommended image, and the trigger control is configured to display the media content in response to a trigger operation of a user after the target recommended content is published.

[0128] In this embodiment, after the target recommended content is published, in order to facilitate the user to view at least one media content in the target recommended content, a trigger control associated with the media content may be added to the target recommended content.

[0129] Optionally, after the recommended images corresponding to at least one media content are sorted based on the determined order, for each recommended image associated with the media content, a trigger control corresponding to the media content may be displayed in the display area associated with the recommended image. In order to avoid the trigger control from blocking the recommended image, the trigger control may be displayed in an edge area such as the lower left corner of the recommended image. Alternatively, the user may also adjust the display position of the trigger control according to actual needs, which is not limited in the present disclosure.

[0130] Therefore, after the target recommended content is published, when other users browse the target recommended content, if they are interested in a certain media content, they can view the media content by triggering the trigger operation associated with the media content.

[0131] The recommended content generation method provided in this embodiment improves the efficiency of content recommendation by displaying trigger controls corresponding to media content associated with each recommended image in the display area associated with the recommended image, so that users can quickly view media content of interest while browsing target recommended content.

[0132] Further, based on any of the above embodiments, after performing a splicing operation on the recommendation texts corresponding to the at least one media content based on the determined order to obtain the spliced ​​recommendation texts, the method further includes:

[0133] For the recommended text corresponding to each media content in the spliced ​​recommended text, a trigger control corresponding to the media content is displayed in a display area associated with the recommended text, and the trigger control is configured to display the media content in response to a user's trigger operation after the target recommended content is released.

[0134] In this embodiment, after the target recommended content is published, in order to facilitate the user to view at least one media content in the target recommended content, a trigger control associated with the media content may be added to the target recommended content.

[0135] Optionally, after performing a splicing operation on the recommended text corresponding to at least one media content based on the determined order to obtain the spliced ​​recommended text, for each recommended text associated with the media content, a trigger control corresponding to the media content can be displayed in the display area associated with the recommended text. Thus, after the target recommended content is published, when other users browse the target recommended content, if they are interested in a certain media content, they can view the media content by triggering the trigger operation associated with the media content.

[0136] Figure 6 A schematic diagram of another target recommendation content provided by an embodiment of the present disclosure is shown in FIG. Figure 6 As shown, the target recommended content 61 may include at least one recommended image 62 arranged in a certain order, and at least one recommended text 63 corresponding to the media content spliced ​​in the certain order. The display area associated with each recommended image 62 displays a trigger control 64 corresponding to the media content associated with the recommended image. The display area associated with the recommended text 63 displays a trigger control 65 corresponding to the media content. Thus, the user can view the media content by triggering the trigger control corresponding to the media content.

[0137] The recommended content generation method provided in this embodiment displays the trigger control corresponding to the media content in the display area associated with the recommended text for the recommended text corresponding to each media content in the spliced ​​recommended text, so that the user can quickly view the media content of interest while browsing the target recommended content, thereby improving the efficiency of content recommendation.

[0138] Further, based on any of the above embodiments, the method further includes:

[0139] A target image determined by the user is acquired.

[0140] The target image is displayed before the ranked recommended images.

[0141] In this embodiment, the user can set the first picture in the target recommended content according to actual needs.

[0142] Optionally, a target image determined by a user may be obtained, wherein the target image may be collected by the user in real time, or may be obtained by the user in a preset storage path, and the present disclosure does not impose any limitation on this.

[0143] After the recommended images corresponding to at least one media content are sorted, the target image can be displayed before the sorted recommended images. Therefore, after the target recommended content is released, the target image determined by the user can be the first image corresponding to the target recommended content. The user can view the recommended image corresponding to at least one media content by switching operations.

[0144] The recommended content generation method provided in this embodiment enriches the display style of the target recommended content by using the target image determined by the user as the first image before all recommended images, so that the target recommended content can better meet the personalized needs of the user and improve the user experience.

[0145] Figure 7 A schematic diagram of the structure of a recommended content generating device provided by an embodiment of the present disclosure, such as Figure 7 As shown, the device includes: a determination module 71, an acquisition module 72, a processing module 73, and a generation module 74. The determination module 71 is used to determine at least one media content to be recommended. The acquisition module 72 is used to obtain basic information corresponding to each media content, and to obtain at least one interactive content generated based on the media content. The processing module 73 is used to generate recommended content corresponding to the media content based on the basic information corresponding to each media content and at least one interactive content, wherein the recommended content includes a recommended image and a recommended text. The generation module 74 is used to generate target recommended content according to the recommended content corresponding to each media content, and publish the target recommended content.

[0146] Further, based on any of the above embodiments, the processing module is used to: for each media content, generate a recommended image associated with the media content based on basic information corresponding to the media content; generate recommended text associated with the media content based on the basic information corresponding to the media content and at least one interactive content; and generate recommended content corresponding to the media content based on the recommended image and the recommended text.

[0147] Further, based on any of the above embodiments, the processing module is used to: obtain the basic information from the preset parameters associated with the media content, wherein the basic information includes one or more of the content title, content parameters, brief information, and cover image. Input the basic information into a preset image generation model to obtain a recommended image output by the image generation model, wherein the recommended image includes one or more of the content title, content parameters, brief information, and cover image, and the color of the recommended image matches the color of the cover image.

[0148] Further, based on any of the above embodiments, the processing module is used to: for each media content, input the basic information associated with the media content and the at least one interactive content into a preset text generation model to obtain the recommended text generated by the text generation model.

[0149] Further, based on any of the above embodiments, the acquisition module is used to obtain the brief introduction information and / or classification label information associated with the media content in the preset parameters associated with the media content, and determine the brief introduction information and / or classification label information as the basic information; and perform a filtering operation on at least one interactive data associated with the media content according to preset filtering conditions to obtain the at least one interactive information.

[0150] Further, based on any of the above embodiments, the interaction data includes at least one content tag data generated by a user for at least part of the media content. The processing module is used to: determine the historical page views corresponding to each content tag data. The content tag data whose historical page views are greater than a preset number threshold in the at least one content tag data is determined as the interaction information.

[0151] Further, on the basis of any of the above embodiments, the interactive data includes multiple graphic and text evaluation data published by multiple historical users for the media content. The processing module is used to: filter the multiple graphic and text evaluation data that meet the first preset condition in the interactive data through a preset text recognition model to obtain multiple first interactive data, wherein the first preset condition includes that the amount of data contained in the graphic and text evaluation data meets the preset data amount condition, and the graphic and text evaluation data does not include negative emotional content. Determine the associated parameters corresponding to each first interactive data, and filter the multiple first interactive data based on the preset interactive condition and the associated parameters to obtain multiple second interactive data, wherein the associated parameters include the data amount information of the first interactive data, interactive parameters and browsing parameters. Filter the multiple second interactive data through a preset filtering word set to obtain the interactive information.

[0152] Further, based on any of the above embodiments, the screening word set includes a positive subword set and a negative subword set. The processing module is used to: filter the second interaction data including the words in the negative subword set in the plurality of second interaction data to obtain the filtered plurality of second interaction data. The second interaction data including the words in the positive subword set in the filtered plurality of second interaction data is determined as the interaction information.

[0153] Further, based on any of the above embodiments, the generation module is used to: determine a determination order corresponding to the at least one media content. Sort the recommended images associated with the at least one media content based on the determination order to obtain the sorted recommended images. Display the sorted recommended images in a preset first display area. Splice the recommended texts corresponding to the at least one media content based on the determination order to obtain the spliced ​​recommended texts. Display the spliced ​​recommended texts in a preset second display area to obtain the target recommended content.

[0154] Furthermore, based on any of the above embodiments, the device also includes: a display module, which is used to display a trigger control corresponding to the media content associated with the recommended image in the display area associated with each recommended image, and the trigger control is configured to display the media content in response to a user's trigger operation after the target recommended content is released.

[0155] Furthermore, based on any of the above embodiments, the device also includes: a display module, which is used to display a trigger control corresponding to the media content in a display area associated with the recommended text corresponding to each media content in the spliced ​​recommended text, and the trigger control is configured to display the media content in response to a user's trigger operation after the target recommended content is released.

[0156] Further, based on any of the above embodiments, the device further comprises: an acquisition module, configured to acquire the target image determined by the user. An acquisition module, configured to display the target image before the ranked recommended images.

[0157] Further, based on any of the above embodiments, the device further includes: an acquisition module, configured to acquire edited content determined by the user based on the recommended content; an editing module, configured to edit the recommended content based on the edited content to obtain the edited recommended content; and a generation module, configured to generate the target recommended content based on each edited recommended content.

[0158] The device provided in this embodiment can be used to execute the technical solution of the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be repeated here.

[0159] In order to implement the above embodiments, the embodiments of the present disclosure further provide a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the method for generating recommended content as described in any of the above embodiments is implemented.

[0160] In order to implement the above embodiments, the embodiments of the present disclosure further provide a computer program product, including a computer program, and when the computer program is executed by a processor, the method for generating recommended content as described in any of the above embodiments is implemented.

[0161] In order to implement the above embodiment, the present disclosure also provides an electronic device, including: a processor and a memory;

[0162] The memory stores computer-executable instructions;

[0163] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the recommended content generating method as described in any of the above embodiments.

[0164] Figure 8 The electronic device 800 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure, and the electronic device 800 may be a terminal device or a server. The terminal device may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, personal digital assistants (PDAs), tablet computers (Portable Android Devices, PADs), portable multimedia players (Portable Media Players, PMPs), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 8 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0165] like Figure 8 As shown, the electronic device 800 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage device 808 to a random access memory (RAM) 803. Various programs and data required for the operation of the electronic device 800 are also stored in the RAM 803. The processing device 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0166] Typically, the following devices may be connected to the I / O interface 805: input devices 806 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 807 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 808 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 809. The communication device 809 may allow the electronic device 800 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 8 The electronic device 800 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0167] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 809, or installed from a storage device 808, or installed from a ROM 802. When the computer program is executed by the processing device 801, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0168] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0169] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0170] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method shown in the above embodiment.

[0171] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may 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 may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0172] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0173] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware. The name of a unit does not limit the unit itself in some cases. For example, the first acquisition unit may also be described as a "unit for acquiring at least two Internet Protocol addresses".

[0174] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0175] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0176] In a first aspect, according to one or more embodiments of the present disclosure, a method for generating recommended content is provided, comprising:

[0177] determining at least one media content to be recommended;

[0178] For each media content, basic information corresponding to the media content is obtained, and at least one interactive content generated based on the media content is obtained;

[0179] Generate recommended content corresponding to each media content based on basic information corresponding to each media content and at least one interactive content, wherein the recommended content includes a recommended image and a recommended text;

[0180] Generate target recommended content according to the recommended content corresponding to each media content, and publish the target recommended content.

[0181] According to one or more embodiments of the present disclosure, generating recommended content corresponding to each media content based on basic information corresponding to each media content and at least one interactive content includes:

[0182] For each media content, generating a recommended image associated with the media content based on basic information corresponding to the media content;

[0183] Generating a recommendation text associated with the media content based on basic information corresponding to the media content and at least one interactive content;

[0184] Generate recommended content corresponding to the media content according to the recommended image and the recommended text.

[0185] According to one or more embodiments of the present disclosure, the acquiring basic information corresponding to the media content includes:

[0186] Acquire the basic information from preset parameters associated with the media content, wherein the basic information includes one or more of a content title, content parameters, introduction information, and a cover image;

[0187] The generating a recommended image associated with the media content based on basic information corresponding to the media content includes:

[0188] The basic information is input into a preset image generation model to obtain a recommended image output by the image generation model, wherein the recommended image includes one or more of the content title, content parameters, introduction information and cover image, and the color of the recommended image matches the color of the cover image.

[0189] According to one or more embodiments of the present disclosure, generating a recommendation text associated with the media content based on basic information corresponding to the media content and at least one interactive content includes:

[0190] For each media content, the basic information associated with the media content and the at least one interactive content are input into a preset text generation model to obtain a recommended text generated by the text generation model.

[0191] According to one or more embodiments of the present disclosure, the acquiring basic information corresponding to the media content, and acquiring at least one interactive content generated based on the media content, includes:

[0192] Acquire brief introduction information and / or classification label information associated with the media content from preset parameters associated with the media content, and determine the brief introduction information and / or classification label information as the basic information;

[0193] A screening operation is performed on at least one interactive data associated with the media content according to a preset screening condition to obtain the at least one interactive information.

[0194] According to one or more embodiments of the present disclosure, the interaction data includes at least one piece of content tag data generated by a user for at least part of the media content;

[0195] The filtering operation on at least one interactive data associated with the media content according to a preset filtering condition to obtain the at least one interactive information includes:

[0196] Determine the historical pageviews corresponding to each content tag data;

[0197] The content marking data whose historical browsing volume is greater than a preset quantity threshold in the at least one content marking data is determined as the interactive information.

[0198] According to one or more embodiments of the present disclosure, the interactive data includes a plurality of graphic and text evaluation data published by a plurality of historical users on the media content;

[0199] The filtering operation on at least one interactive data associated with the media content according to a preset filtering condition to obtain the at least one interactive information includes:

[0200] A plurality of pieces of graphic and text evaluation data that meet a first preset condition in the interactive data are screened by a preset text recognition model to obtain a plurality of first interactive data, wherein the first preset condition includes that the amount of data contained in the graphic and text evaluation data meets a preset data amount condition, and the graphic and text evaluation data does not include negative emotional content;

[0201] Determine the associated parameters corresponding to each first interactive data, and perform a screening operation on the plurality of first interactive data based on the preset interactive conditions and the associated parameters to obtain a plurality of second interactive data, wherein the associated parameters include data volume information, interactive parameters, and browsing parameters of the first interactive data;

[0202] The plurality of second interactive data are screened using a preset screening word set to obtain the interactive information.

[0203] According to one or more embodiments of the present disclosure, the screening word set includes a positive sub-word set and a negative sub-word set;

[0204] The filtering operation on the plurality of second interactive data using a preset filtering word set to obtain the interactive information includes:

[0205] Performing a filtering operation on the second interaction data including the second interaction data with the vocabulary in the negative subword set among the plurality of second interaction data to obtain a plurality of filtered second interaction data;

[0206] The second interaction data including the vocabulary in the positive subword set in the filtered plurality of second interaction data is determined as the interaction information.

[0207] According to one or more embodiments of the present disclosure, generating target recommended content according to the recommended content corresponding to each media content includes:

[0208] Determining a determination order corresponding to the at least one media content;

[0209] Sorting the recommended images associated with the at least one media content based on the determined order to obtain the sorted recommended images;

[0210] Displaying the sorted recommended images in a preset first display area;

[0211] Performing a splicing operation on the recommendation text corresponding to the at least one media content based on the determined order to obtain a spliced ​​recommendation text;

[0212] The spliced ​​recommendation text is displayed in a preset second display area to obtain the target recommendation content.

[0213] According to one or more embodiments of the present disclosure, after generating target recommended content according to the recommended content corresponding to each media content, the method further includes:

[0214] A trigger control corresponding to the media content associated with each recommended image is displayed in a display area associated with the recommended image, and the trigger control is configured to display the media content in response to a trigger operation of a user after the target recommended content is published.

[0215] According to one or more embodiments of the present disclosure, after performing a splicing operation on the recommendation text corresponding to the at least one media content based on the determined order to obtain the spliced ​​recommendation text, the method further includes:

[0216] For the recommended text corresponding to each media content in the spliced ​​recommended text, a trigger control corresponding to the media content is displayed in a display area associated with the recommended text, and the trigger control is configured to display the media content in response to a user's trigger operation after the target recommended content is released.

[0217] According to one or more embodiments of the present disclosure, the method further includes:

[0218] Acquire the target image determined by the user;

[0219] The target image is displayed before the ranked recommended images.

[0220] According to one or more embodiments of the present disclosure, after generating the recommended content corresponding to the media content based on the basic information corresponding to each media content and at least one interactive content, the method further includes:

[0221] Acquire editing content determined by the user based on the recommended content;

[0222] Performing an editing operation on the recommended content based on the edited content to obtain edited recommended content;

[0223] Generating target recommended content according to the recommended content corresponding to each media content includes:

[0224] The target recommended content is generated based on each edited recommended content.

[0225] In a second aspect, according to one or more embodiments of the present disclosure, a recommended content generating device is provided, including:

[0226] A determination module, used to determine at least one media content to be recommended;

[0227] An acquisition module, configured to acquire, for each media content, basic information corresponding to the media content, and to acquire at least one interactive content generated based on the media content;

[0228] A processing module, configured to generate recommended content corresponding to each media content based on basic information corresponding to each media content and at least one interactive content, wherein the recommended content includes a recommended image and a recommended text;

[0229] The generating module is used to generate target recommended content according to the recommended content corresponding to each media content, and publish the target recommended content.

[0230] According to one or more embodiments of the present disclosure, the processing module is used to:

[0231] For each media content, generating a recommended image associated with the media content based on basic information corresponding to the media content;

[0232] Generating a recommendation text associated with the media content based on basic information corresponding to the media content and at least one interactive content;

[0233] Generate recommended content corresponding to the media content according to the recommended image and the recommended text.

[0234] According to one or more embodiments of the present disclosure, the processing module is used to:

[0235] Acquire the basic information from preset parameters associated with the media content, wherein the basic information includes one or more of a content title, content parameters, introduction information, and a cover image;

[0236] The basic information is input into a preset image generation model to obtain a recommended image output by the image generation model, wherein the recommended image includes one or more of the content title, content parameters, introduction information and cover image, and the color of the recommended image matches the color of the cover image.

[0237] According to one or more embodiments of the present disclosure, the processing module is used to:

[0238] For each media content, the basic information associated with the media content and the at least one interactive content are input into a preset text generation model to obtain a recommended text generated by the text generation model.

[0239] According to one or more embodiments of the present disclosure, the acquisition module is used to:

[0240] Acquire brief introduction information and / or classification label information associated with the media content from preset parameters associated with the media content, and determine the brief introduction information and / or classification label information as the basic information;

[0241] A screening operation is performed on at least one interactive data associated with the media content according to a preset screening condition to obtain the at least one interactive information.

[0242] According to one or more embodiments of the present disclosure, the interaction data includes at least one piece of content tag data generated by a user for at least part of the media content;

[0243] The processing module is used to:

[0244] Determine the historical pageviews corresponding to each content tag data;

[0245] The content marking data whose historical browsing volume is greater than a preset quantity threshold in the at least one content marking data is determined as the interactive information.

[0246] According to one or more embodiments of the present disclosure, the interactive data includes a plurality of graphic and text evaluation data published by a plurality of historical users on the media content;

[0247] The processing module is used to:

[0248] A plurality of pieces of graphic and text evaluation data that meet a first preset condition in the interactive data are screened by a preset text recognition model to obtain a plurality of first interactive data, wherein the first preset condition includes that the amount of data contained in the graphic and text evaluation data meets a preset data amount condition, and the graphic and text evaluation data does not include negative emotional content;

[0249] Determine the associated parameters corresponding to each first interactive data, and perform a screening operation on the plurality of first interactive data based on the preset interactive conditions and the associated parameters to obtain a plurality of second interactive data, wherein the associated parameters include data volume information, interactive parameters, and browsing parameters of the first interactive data;

[0250] The plurality of second interactive data are screened using a preset screening word set to obtain the interactive information.

[0251] According to one or more embodiments of the present disclosure, the screening word set includes a positive sub-word set and a negative sub-word set;

[0252] The processing module is used to:

[0253] Performing a filtering operation on the second interaction data including the second interaction data with the vocabulary in the negative subword set among the plurality of second interaction data to obtain a plurality of filtered second interaction data;

[0254] The second interaction data including the vocabulary in the positive subword set in the filtered plurality of second interaction data is determined as the interaction information.

[0255] According to one or more embodiments of the present disclosure, the generating module is used to:

[0256] Determining a determination order corresponding to the at least one media content;

[0257] Sorting the recommended images associated with the at least one media content based on the determined order to obtain the sorted recommended images;

[0258] Displaying the sorted recommended images in a preset first display area;

[0259] Performing a splicing operation on the recommendation text corresponding to the at least one media content based on the determined order to obtain a spliced ​​recommendation text;

[0260] The spliced ​​recommendation text is displayed in a preset second display area to obtain the target recommendation content.

[0261] According to one or more embodiments of the present disclosure, the device further includes:

[0262] A display module is used to display a trigger control corresponding to the media content associated with each recommended image in a display area associated with the recommended image, and the trigger control is configured to display the media content in response to a user's trigger operation after the target recommended content is released.

[0263] According to one or more embodiments of the present disclosure, the device further includes:

[0264] A display module is used to display a trigger control corresponding to each media content in the spliced ​​recommendation text in a display area associated with the recommendation text, wherein the trigger control is configured to display the media content in response to a user's trigger operation after the target recommended content is released.

[0265] According to one or more embodiments of the present disclosure, the device further includes:

[0266] An acquisition module, used for acquiring the target image determined by the user;

[0267] The acquisition module is used to display the target image before the ranked recommended images.

[0268] According to one or more embodiments of the present disclosure, the device further includes:

[0269] Acquire editing content determined by the user based on the recommended content;

[0270] Performing an editing operation on the recommended content based on the edited content to obtain edited recommended content;

[0271] The generating module is used for:

[0272] The target recommended content is generated based on each edited recommended content.

[0273] In a third aspect, according to one or more embodiments of the present disclosure, there is provided an electronic device, comprising: at least one processor and a memory;

[0274] The memory stores computer-executable instructions;

[0275] The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor performs the recommended content generating method as described in the first aspect and various possible designs of the first aspect.

[0276] In a fourth aspect, according to one or more embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer execution instructions. When a processor executes the computer execution instructions, the method for generating recommended content as described in the first aspect and various possible designs of the first aspect is implemented.

[0277] In a fifth aspect, according to one or more embodiments of the present disclosure, a computer program product is provided, including a computer program, which, when executed by a processor, implements the recommended content generation method as described in the first aspect and various possible designs of the first aspect.

[0278] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0279] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0280] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, 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. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A method for generating recommended content, characterized in that: include: determining at least one media content to be recommended; For each media content, basic information corresponding to the media content is obtained, and at least one interactive content generated based on the media content is obtained; Generate recommended content corresponding to each media content based on basic information corresponding to each media content and at least one interactive content, wherein the recommended content includes a recommended image and a recommended text; Generate target recommended content according to the recommended content corresponding to each media content, and publish the target recommended content.

2. The method according to claim 1, characterized in that The generating of recommended content corresponding to each media content based on basic information corresponding to each media content and at least one interactive content includes: For each media content, generating a recommended image associated with the media content based on basic information corresponding to the media content; Generating a recommendation text associated with the media content based on basic information corresponding to the media content and at least one interactive content; Generate recommended content corresponding to the media content according to the recommended image and the recommended text.

3. The method according to claim 2, characterized in that The obtaining of basic information corresponding to the media content includes: Acquire the basic information from preset parameters associated with the media content, wherein the basic information includes one or more of a content title, content parameters, introduction information, and a cover image; The generating a recommended image associated with the media content based on basic information corresponding to the media content includes: The basic information is input into a preset image generation model to obtain a recommended image output by the image generation model, wherein the recommended image includes one or more of the content title, content parameters, introduction information and cover image, and the color of the recommended image matches the color of the cover image.

4. The method according to claim 2, characterized in that: The generating a recommendation text associated with the media content based on the basic information corresponding to the media content and at least one interactive content includes: For each media content, the basic information associated with the media content and the at least one interactive content are input into a preset text generation model to obtain a recommended text generated by the text generation model.

5. The method according to claim 1, characterized in that The obtaining of basic information corresponding to the media content, and obtaining at least one interactive content generated based on the media content, includes: Acquire brief introduction information and / or classification label information associated with the media content from preset parameters associated with the media content, and determine the brief introduction information and / or classification label information as the basic information; A screening operation is performed on at least one interactive data associated with the media content according to a preset screening condition to obtain the at least one interactive information.

6. The method according to claim 5, characterized in that The interactive data includes at least one piece of content marking data generated by a user for at least part of the media content; The filtering operation on at least one interactive data associated with the media content according to a preset filtering condition to obtain the at least one interactive information includes: Determine the historical pageviews corresponding to each content tag data; The content marking data whose historical browsing volume is greater than a preset quantity threshold in the at least one content marking data is determined as the interactive information.

7. The method according to claim 5, characterized in that The interactive data includes a plurality of graphic and text evaluation data published by a plurality of historical users on the media content; The filtering operation on at least one interactive data associated with the media content according to a preset filtering condition to obtain the at least one interactive information includes: A plurality of pieces of graphic and text evaluation data that meet a first preset condition in the interactive data are screened by a preset text recognition model to obtain a plurality of first interactive data, wherein the first preset condition includes that the amount of data contained in the graphic and text evaluation data meets a preset data amount condition, and the graphic and text evaluation data does not include negative emotional content; Determine the associated parameters corresponding to each first interactive data, and perform a screening operation on the plurality of first interactive data based on the preset interactive conditions and the associated parameters to obtain a plurality of second interactive data, wherein the associated parameters include data volume information, interactive parameters, and browsing parameters of the first interactive data; The plurality of second interactive data are screened using a preset screening word set to obtain the interactive information.

8. The method according to claim 7, characterized in that The screening word set includes a positive subword set and a negative subword set; The filtering operation on the plurality of second interactive data using a preset filtering word set to obtain the interactive information includes: Performing a filtering operation on the second interaction data including the second interaction data with the vocabulary in the negative subword set among the plurality of second interaction data to obtain a plurality of filtered second interaction data; The second interaction data including the vocabulary in the positive subword set in the filtered plurality of second interaction data is determined as the interaction information.

9. The method according to any one of claims 1 to 8, characterized in that: Generating target recommended content according to the recommended content corresponding to each media content includes: Determining a determination order corresponding to the at least one media content; Sorting the recommended images associated with the at least one media content based on the determined order to obtain the sorted recommended images; Displaying the sorted recommended images in a preset first display area; Performing a splicing operation on the recommendation text corresponding to the at least one media content based on the determined order to obtain a spliced ​​recommendation text; The spliced ​​recommendation text is displayed in a preset second display area to obtain the target recommendation content.

10. The method according to claim 9, characterized in that After generating target recommended content according to the recommended content corresponding to each media content, the method further includes: A trigger control corresponding to the media content associated with each recommended image is displayed in a display area associated with the recommended image, and the trigger control is configured to display the media content in response to a trigger operation of a user after the target recommended content is published.

11. The method according to claim 9, characterized in that After performing a splicing operation on the recommendation texts corresponding to the at least one media content based on the determined order to obtain the spliced ​​recommendation texts, the method further includes: For the recommended text corresponding to each media content in the spliced ​​recommended text, a trigger control corresponding to the media content is displayed in a display area associated with the recommended text, and the trigger control is configured to display the media content in response to a user's trigger operation after the target recommended content is released.

12. The method according to claim 9, characterized in that The method further comprises: Acquire a target image determined by a user; The target image is displayed before the ranked recommended images.

13. The method according to any one of claims 1 to 8, characterized in that: After generating the recommended content corresponding to the media content based on the basic information corresponding to each media content and at least one interactive content, the method further includes: Acquire editing content determined by the user based on the recommended content; Performing an editing operation on the recommended content based on the edited content to obtain edited recommended content; Generating target recommended content according to the recommended content corresponding to each media content includes: The target recommended content is generated based on each edited recommended content.

14. A recommended content generating device, characterized in that: include: A determination module, used to determine at least one media content to be recommended; An acquisition module, configured to acquire, for each media content, basic information corresponding to the media content, and to acquire at least one interactive content generated based on the media content; A processing module, configured to generate recommended content corresponding to each media content based on basic information corresponding to each media content and at least one interactive content, wherein the recommended content includes a recommended image and a recommended text; The generating module is used to generate target recommended content according to the recommended content corresponding to each media content, and publish the target recommended content.

15. An electronic device, characterized in that: include: Processor and memory; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the recommended content generating method according to any one of claims 1 to 13.

16. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions. When a processor executes the computer-executable instructions, the method for generating recommended content according to any one of claims 1 to 13 is implemented.

17. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for generating recommended content according to any one of claims 1 to 13 is implemented.

Citation Information

Patent Citations

  • Book review generation method and device, computer equipment and readable medium

    CN110019726A

  • Introduction information generation method and device

    CN110264315A

  • Recommendation comment generation method, device, equipment, medium and computer program product

    CN112541120A

  • Method and equipment for acquiring recommended image information of target book

    CN114297506A

  • Book recommendation information generation method and device, equipment and medium

    CN114880458A