Content recommendation method and device, readable medium and electronic equipment

Abstract

The invention relates to a content recommendation method and device, a readable medium and electronic equipment, and aims to display different content materials to different users and meet creation requirements of the different users. The content recommendation method comprises the steps that a content request sent by terminal equipment is received, the content request carries target information used for being matched with recommended content, and the target information comprises attribute information of historical delivery content and / or historical interaction information in a content material page displayed by the terminal equipment; target recommendation content is obtained according to the target information and a content recommendation model, the target recommendation content comprises target content materials and analysis information for the target content materials, and the content recommendation model is used for matching recommendation content according to input information; and pushing the target recommended content to the terminal equipment, so that the terminal equipment displays the target recommended content on the content material page.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technologies, and in particular, to a content recommendation method, apparatus, readable medium, and electronic device. Background Art

[0002] Content creation platforms can provide rich content materials to help users inspire their creativity and assist them in content creation.

[0003] In related technologies, content creation platforms usually simply classify and display content materials according to general categories, resulting in basically the same content materials obtained by users of the same category, which cannot effectively inspire new ideas, and further leads to homogenization of created content and cannot meet the creative needs of different users. Summary of the Invention

[0004] This Summary of the Invention section is provided to introduce concepts in a brief form, which will be described in detail in the following Detailed Description section. This Summary of the Invention section is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to be used to limit the scope of the claimed technical solution.

[0005] In a first aspect, the present disclosure provides a content recommendation method, which includes:

[0006] Receiving a content request sent by a terminal device, where the content request carries target information for matching recommended content, and the target information includes attribute information of historical delivered content and / or historical interaction information in a content material page displayed on the terminal device;

[0007] Obtaining target recommended content according to the target information and a content recommendation model, where the target recommended content includes target content materials and analysis information for the target content materials, and the content recommendation model is used to match recommended content according to the input information;

[0008] Pushing the target recommended content to the terminal device so that the terminal device displays the target recommended content on the content material page.

[0009] In a second aspect, the present disclosure provides a content recommendation apparatus, which includes:

[0010] A receiving module, configured to receive a content request sent by a terminal device, where the content request carries target information for matching recommended content, and the target information includes attribute information of historical delivered content and / or historical interaction information in a content material page displayed on the terminal device;

[0011] A model recommendation module, configured to obtain target recommended content according to the target information and a content recommendation model, where the target recommended content includes target content materials and analysis information for the target content materials, and the content recommendation model is configured to match recommended content according to the input information;

[0012] A pushing module, configured to push the target recommended content to the terminal device, so that the terminal device displays the target recommended content on the content material page.

[0013] In a third aspect, the present disclosure provides a computer-readable medium, on which a computer program is stored, and when the program is executed by a processing device, the steps of the method described in any one of the first aspects are implemented.

[0014] In a fourth aspect, the present disclosure provides an electronic device, including:

[0015] A storage device, on which a computer program is stored;

[0016] A processing device, configured to execute the computer program in the storage device to implement the steps of the method described in any one of the first aspects.

[0017] Through the above technical solutions, a content request sent by a terminal device is received, the content request carries target information for matching recommended content, and then target recommended content is obtained according to the target information and a content recommendation model, and then the target recommended content is pushed to the terminal device, so that the terminal device displays the target recommended content on the content material page. By using this method, since the historical delivery content and historical interaction information corresponding to different users are different, the content materials displayed on the terminal devices of different users are different, which can help users inspire new ideas, avoid homogenization of created content, and meet the creation needs of different users. In addition, the content material page also displays analysis information for the content materials, which can reduce the user's cognitive threshold, improve the usability of the materials, and further improve the content creation efficiency.

[0018] Other features and advantages of the present disclosure will be described in detail in the subsequent specific implementation part. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In combination with the drawings and with reference to the following specific implementation manners, the above and other features, advantages, and aspects of the embodiments of the present disclosure will become more obvious. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic, and the original elements and elements are not necessarily drawn to scale. In the drawings:

[0020] Figure 1 is a flowchart of a content recommendation method provided according to an exemplary embodiment;

[0021] Figure 2It is a schematic diagram of a material library construction process provided according to an exemplary embodiment;

[0022] Figure 3 It is a schematic diagram of a model recommendation process provided according to an exemplary embodiment;

[0023] Figure 4 It is a schematic diagram of a content recommendation device provided according to an exemplary embodiment;

[0024] Figure 5 It is a block diagram of an electronic device provided according to an exemplary embodiment. Detailed implementation manners

[0025] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not used to limit the protection scope of the present disclosure.

[0026] It should be understood that the various steps recorded in the method embodiments of the present disclosure can be executed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this regard.

[0027] As used herein, the term "including" and its variants are open-ended, that is, "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0028] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order of functions executed by these devices, modules or units or their interdependent relationships.

[0029] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly stated in the context, it should be understood as "one or more".

[0030] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0031] It should be understood that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, usage scopes, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to users and the authorization of users should be obtained through appropriate means in accordance with relevant laws and regulations.

[0032] For example, when responding 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 by the user 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, an application program, a server, or a storage medium that performs the operations of the technical solutions of the present disclosure according to the prompt message.

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

[0034] It should be understood that the above process of notifying and obtaining user authorization is only illustrative and does not limit the implementation manner of the present disclosure, and other manners that meet relevant laws and regulations can also be applied to the implementation manner of the present disclosure.

[0035] At the same time, it should be understood that the data involved in the present technical solution (including but not limited to the data itself, the acquisition or use of the data) should comply with the requirements of corresponding laws, regulations and related regulations.

[0036] In the related art, content materials are usually classified and displayed according to general categories, resulting in basically the same content materials obtained by users of the same category, and the update timeliness is low, which cannot effectively inspire new inspirations, and then leads to the homogenization of the created content and cannot meet the creation needs of different users. In addition, the content materials lack guiding information and the usability is poor, resulting in users being difficult to determine whether the content materials meet their own creation needs and the content creation efficiency is low.

[0037] In view of this, the present disclosure provides a content recommendation method, device, readable medium and electronic device to solve the above technical problems.

[0038] It should be understood that the content recommendation method of the present disclosure can be applied to a content creation platform, which is used to provide content materials to users, inspire users' creation inspirations and perform content creation. The content materials can be video materials, graphic and text materials, picture materials, etc., and the created content can include video content, graphic and text content, picture content, etc. The present disclosure does not limit this.

[0039] The following further explains the embodiments of the present disclosure in conjunction with the accompanying drawings.

[0040] Figure 1 It is a flowchart of a content recommendation method shown according to an exemplary embodiment of the present disclosure. Referring to Figure 1 , the content recommendation method includes:

[0041] S101: Receive a content request sent by a terminal device, where the content request carries target information for matching recommended content.

[0042] Among them, the target information includes attribute information of historical delivered content and / or historical interaction information in the content material page displayed by the terminal device.

[0043] S102: Obtain target recommended content according to the target information and the content recommendation model.

[0044] Among them, the target recommended content includes target content materials and analysis information for the target content materials, and the content recommendation model is used to match recommended content according to the input information.

[0045] S103: Push the target recommended content to the terminal device so that the terminal device displays the target recommended content in the content material page.

[0046] By adopting the above method, since the historical delivered content and historical interaction information corresponding to different users are different, the content materials displayed by the terminal devices of different users are different, which can help users inspire new inspirations, avoid the homogenization of created content, and meet the creation needs of different users. In addition, the content material page also displays analysis information for the content materials, which can reduce the user's cognitive threshold, improve the usability of the materials, and thus improve the content creation efficiency.

[0047] In a possible manner, the content recommendation method further includes: obtaining initial content materials, where the initial content materials include delivered content and diverse interest content; analyzing the initial content materials to obtain analysis information for the initial content materials, and storing the initial content materials and the analysis information for the initial content materials in a content material library, and the content material library is used for the content recommendation model to match target recommended content.

[0048] Exemplarily, referring to Figure 2, taking content materials as an example of video materials, the content already delivered is the video content created and delivered by users through a content creation platform, that is, the video stream being delivered. Diversified interest content can be topic, video, graphic, image and other interest content obtained from different channels. For example, it can be content with high view counts or search counts on the Internet, or content with a high growth rate of view counts or search counts, that is, content of interest to Internet users. The present disclosure places no limitation thereon. Moreover, in order to ensure the timeliness of content materials, content materials published within a preset time period can also be selected, such as content materials published within one month. The present disclosure places no limitation thereon.

[0049] Exemplarily, by analyzing the initial content materials, such as analyzing the posterior information, shot information, and element information of the video content, where the posterior information represents the delivery data such as the click count, comment count, and play count of the video content, analysis information for the initial content materials is obtained and stored together in a content material library for a content recommendation model to match target recommended content.

[0050] In a possible manner, analyzing the initial content materials to obtain analysis information for the initial content materials may include: analyzing the initial content materials to obtain at least one of the content type information, content object information, content generation strategy, content tag information, and delivery object information of the initial content materials as the analysis information for the initial content materials.

[0051] Exemplarily, the content type information can be roughly divided into two major types: content already delivered and diversified interest content, and then further divided into video type, graphic type, image type, etc. The present disclosure places no limitation thereon. The content object information refers to the main object of the initial content materials. For example, the main object of food video content is food. The content generation strategy can be information related to content creation such as content shooting techniques, editing techniques, and layout methods. The present disclosure places no limitation thereon. The delivery object information refers to the user information to which the content is delivered. For example, the delivery object is video platform users in regions A and B. The present disclosure places no limitation thereon.

[0052] Exemplarily, the content tag information can be feature - type tags, overall content tags, picture tags, etc. For example, video content tags, video plot tags, video type tags, graphic collection format tags, tags indicating whether graphics are spliced, graphic content tags, tags indicating the display form of the main body in the graphics, graphic scene tags, picture layout tags, picture scene tags, picture entity tags, and so on. The present disclosure places no limitation thereon.

[0053] Thus, by analyzing the initial content material, analysis information such as the content type information, content object information, content generation strategy, content tag information, and delivery object information of the initial content material is obtained, which facilitates the subsequent content recommendation model to more accurately match the target recommended content, and is also convenient for display on the content material page for users to understand the content material, reducing the user's cognitive threshold.

[0054] It should be understood that analysis information such as content type information, content object information, content generation strategy, content tag information, and delivery object information is usually directly carried in the attribute information of the content material. Therefore, it can be directly obtained by analyzing the attribute information of the content material. For information not carried in the attribute information of the content material, it can be obtained by analyzing with a pre-trained content analysis model.

[0055] In a possible way, analyzing the initial content material to obtain analysis information for the initial content material may include: analyzing the initial content material with a content analysis model to obtain at least one of the content structure information, content recommendation reason, and content theme information of the initial content material as the analysis information for the initial content material, and the content analysis model is used to analyze the input content material.

[0056] Exemplarily, the content analysis model can analyze the input content material to obtain information such as the content structure information, content recommendation reason, and content theme information of the content material. Taking the content material as video content as an example, the content structure information represents the video structure, such as the beginning, middle, end, etc. The content recommendation reason can be a reason related to the delivery data, such as a high click-through rate, or a reason related to the content, such as the video picture being aesthetically pleasing, etc. The present disclosure does not limit this. The content theme information is used to characterize the content theme.

[0057] Among them, the content analysis model can be a large model, a neural network model, etc. One model can be used to analyze information such as the content structure information, content recommendation reason, and content theme information of the content material at the same time, or multiple models can be used to separately analyze information such as the content structure information, content recommendation reason, and content theme information of the content material. Specifically, the corresponding training data can be constructed according to the requirements to train the content analysis model. The present disclosure does not limit this.

[0058] It should be understood that the above analysis information is only for exemplary illustration and can be determined according to specific requirements. The present disclosure does not limit this. For example, the category information to which the content material belongs can also be determined according to the content object information.

[0059] In possible ways, according to the target information and the content recommendation model, the target recommended content can be obtained, which may include: obtaining candidate content materials matching the target information from the content material library through the content recommendation model, and determining the target recommended content according to the candidate content materials. The content material library is used to store content materials and analysis information for the content materials.

[0060] Exemplarily, referring to Figure 3 , candidate content materials matching the target information can be obtained from the content material library through the content recommendation model, and then the target recommended content can be determined according to the candidate content materials. In this way, different recommended contents can be matched according to the requests of different users, so as to help users inspire new inspirations, avoid homogenization of created content, and meet the creation needs of different users.

[0061] It should be understood that since the initial content materials themselves contain attribute information, the content recommendation model can also perform matching based on the attribute information of the initial content materials. However, the content material library includes content materials and analysis information for the content materials, and more analysis information can be obtained. Therefore, more accurate matching can be performed based on the content material library, which can be specifically determined according to requirements, and the present disclosure does not limit this.

[0062] In possible ways, the attribute information of the historical delivered content includes the category information and / or the delivery object information of the historical delivered content. Obtaining candidate content materials matching the target information from the content material library through the content recommendation model may include: using the content recommendation model to regard the content materials in the content material library that match the category information of the historical delivered content as candidate content materials; and / or, using the content recommendation model to regard the content materials in the content material library that match the delivery object information of the historical delivered content as candidate content materials.

[0063] Exemplarily, continuing to refer to Figure 3 , content matching is performed through the content recommendation model. The historical delivered contents of different users are different, and the historical delivered content can represent the delivery needs of the users. For example, the historical delivered content of a certain user is video content of food category delivered to area A, then video materials of food category for area A can be matched, etc., and the present disclosure does not limit this. Thus, different recommended contents can be matched according to the historical delivered contents of different users to meet the creation needs of different users.

[0064] Furthermore, the latest historical delivered content can also be selected for matching, such as the historical delivered content in the recent 7 days or 30 days for matching, or the historical delivered content with the highest delivery volume can be selected for matching, and the present disclosure does not limit this.

[0065] Among possible ways, the category information of historical delivery content includes multi-level category information. Through a content recommendation model, content materials in the content material library that match the category information of historical delivery content are used as candidate content materials, which may include: obtaining, through the content recommendation model, first materials in the content material library that match the first-level category information of historical delivery content; if the number of first materials is greater than or equal to a first preset number, then using the first materials as candidate content materials; or, if the number of first materials is less than the first preset number, obtaining, through the content recommendation model, second materials in the content material library that match the second-level category information of historical delivery content, and when the number of second materials is greater than or equal to the first preset number, using the second materials as candidate content materials. The category corresponding to the first-level category information belongs to the category corresponding to the second-level category information.

[0066] It should be understood that the category information of historical delivery content may include multi-level category information. For example, the category of potato chips belongs to the category of snacks, and the category of snacks belongs to the category of food, etc. The present disclosure places no restrictions on this.

[0067] Exemplarily, a first preset number can be set as the minimum recommended number. If the materials corresponding to the matched first-level category are fewer than the minimum recommended number, continue to match the upper-level category until the matched materials are greater than or equal to the minimum recommended number. This can ensure the quantity of recommended content and effectively inspire users' creative inspiration.

[0068] Among possible ways, the historical interaction information includes at least one of historical material usage information, historical material browsing information, and historical material collection information. Obtaining candidate content materials that match the target information from the content material library through a content recommendation model may include: determining historical interaction materials based on the historical interaction information; and through the content recommendation model, determining the content materials in the content material library that match the historical interaction materials as candidate content materials.

[0069] Exemplarily, historical interaction materials can be determined based on the historical interaction information of a user on a content creation platform, such as historical used materials, historical browsed materials, historical collected materials, etc. The present disclosure places no restrictions on this, where historical used materials mean that the user creates content based on this material. Furthermore, content materials that match the historical interaction materials are recommended as candidate content materials, such as content materials in the same category as the historical interaction materials. The present disclosure places no restrictions on this. Thus, different recommended content can be matched based on the historical interaction information of different users to meet the creative needs of different users.

[0070] In a possible way, obtaining candidate content materials that match the target information from the content material library through a content recommendation model may include: determining, through the content recommendation model, initial candidate content materials that meet the interaction index conditions from the content material library, and determining the content materials that match the target information in the initial candidate content materials as candidate content materials. The interaction index conditions include at least one of historical delivery index conditions, interaction feedback index conditions, and content level index conditions.

[0071] Exemplarily, continuing to refer to Figure 3 , the content materials can be screened. The historical delivery index can be the delivery volume of the content materials, the interaction feedback index can be the click-through rate growth rate, and the content level index is used to represent the priority of the content materials being recommended. For example, an original video has a higher level than a homogeneous video and is more suitable for being recommended, etc. Specifically, it can be set according to requirements, and the present disclosure does not limit this.

[0072] By setting the interaction index conditions, content materials that meet the interaction index conditions can be matched. For example, content materials with a high delivery volume, content materials with a high click-through rate growth rate, or content materials with a high recommendation priority can be matched. Specifically, it can be set according to requirements or according to user requests, and the present disclosure does not limit this.

[0073] It should be noted that content materials that meet the interaction index conditions can be screened first, and then candidate content materials can be obtained through category information matching, historical interaction material matching, etc. Or category information matching, historical interaction material matching, etc. can be performed first, and then candidate content materials that meet the interaction index conditions can be screened from them. Specifically, it can be set according to requirements, and the present disclosure does not limit this.

[0074] In addition, content materials that the user has marked as disliked on the content material page can also be reduced or not recommended, and the present disclosure does not limit this.

[0075] In a possible way, obtaining candidate content materials that match the target information from the content material library through a content recommendation model may include: obtaining, through the content recommendation model, first content materials that match the target information from the content material library, and second content materials that are similar to the first content materials, and using the first content materials and the second content materials as candidate content materials.

[0076] Exemplarily, continuing to refer to Figure 3, through the content recommendation model for similar content matching. Taking the first content material as an example of the content materials of the same category information, content materials of similar category information can be further matched according to the first content material. For example, if the first content material is a content material of potato chips category, content materials of cookie category can also be matched. Or, taking the first content material as an example of the content materials of the same delivery area. For example, if the first content material is a content material delivered in area A, and area A is adjacent to area B, then content materials delivered in area B can also be matched, and so on. The present disclosure does not limit this.

[0077] In this way, based on the content materials of exact match, similar content materials can be matched, so as to obtain more recommended content and effectively stimulate the user's creative inspiration.

[0078] In a possible way, according to the target information and the content recommendation model, the target recommended content can be obtained, which may include: obtaining the first candidate recommended content according to the target information and the content recommendation model; for each first candidate recommended content, determining the sorting index value of the first candidate recommended content, and the sorting index value is determined based on at least one of the delivery index, timeliness index, and relevance index to the content request of the first candidate recommended content; sorting the first candidate recommended content according to the sorting index value to obtain the target recommended content.

[0079] Exemplarily, continuing to refer to Figure 3 , the candidate recommended content can also be sorted to obtain the target recommended content. The weights of the delivery index, timeliness index, and relevance index to the content request can be set according to requirements. Then, the delivery index is multiplied by the delivery index weight, the timeliness index is multiplied by the timeliness index weight, and the relevance index is multiplied by the relevance index weight. Finally, the sum of the three products is obtained as the sorting index value. The present disclosure does not limit the calculation method of the sorting index value, and it can be specifically set according to requirements. For example, the sorting index value can be determined according to the delivery index and the timeliness index.

[0080] Among them, the delivery index can be the delivery volume, click volume, etc. of the content material. The timeliness index represents the newness and oldness of the content material, that is, the timeliness index of the newly released content is high. The relevance index can refer to the degree of relevance between the content material and the content request. For example, the relevance of the content materials of the same category is higher than that of the similar categories. Of course, sorting can also be based on other indexes, and the present disclosure does not limit this.

[0081] Thus, the candidate content materials can be sorted according to the sorting index value to obtain the target recommended content. Since the sorting index values of different users are different, even if different users match the same content materials, the displayed target recommended content can also be different to meet the creative needs of different users.

[0082] In possible ways, based on the target information and the content recommendation model, the target recommended content can be obtained, which may include: obtaining the second candidate recommended content according to the target information and the content recommendation model; grouping the second candidate recommended content according to the analysis information corresponding to the content materials in the second candidate recommended content to obtain multiple groups of target recommended content. Pushing the target recommended content to the terminal device so that the terminal device displays the target recommended content on the content material page may include: pushing multiple groups of target recommended content to the terminal device so that the terminal device displays multiple groups of target recommended content grouped on the content material page.

[0083] Exemplarily, the candidate recommended content can be grouped according to the analysis information corresponding to the content materials in the candidate recommended content to obtain multiple groups of target recommended content, such as aggregating recommended content of the same category, and the present disclosure is not limited thereto. Furthermore, the target recommended content can be grouped and displayed on the terminal device. For example, the target recommended content of the same group can be aggregated into a material collection card for display, which is convenient for users to centrally view the target recommended content of the same group and effectively inspires users' creative inspiration.

[0084] It should be noted that the terminal device displays the content materials and the analysis information for the content materials on the content material page, which not only facilitates users to understand information such as the type, theme, and structure of the content materials, reduces the user's cognitive threshold, but also can effectively inspire users' creative inspiration by combining the content materials already placed in the content materials and diverse interest content materials.

[0085] In possible ways, the content recommendation method further includes: after receiving the interaction feedback information sent by the terminal device for the target recommended content, updating and training the content recommendation model according to the interaction feedback information and the target recommended content to obtain a new content recommendation model.

[0086] Exemplarily, it can continue to refer to Figure 3 , a training data set can be constructed according to the content recommendation model and the interaction feedback information for the target recommended content, and then the content recommendation model can be updated and trained to obtain a new content recommendation model. For example, if a user uses the recommended content materials for content creation, positive samples can be constructed, and if the user does not use the recommended content materials for content creation, negative samples can be constructed, and then optimized training can be performed according to the positive and negative samples, so as to continuously optimize the content recommendation model.

[0087] By adopting the above method, the creative needs of users can be determined based on information such as the user's historical placed content and historical interaction information, and then content matching and sorting can be performed based on the user's creative needs and the content recommendation model to recommend diverse, timely, and highly relevant content materials to users. And the content analysis model can be used to analyze the content materials to reduce the user's cognitive threshold.

[0088] Based on the same inventive concept, the present disclosure also provides a content recommendation device. Referring to Figure 4 , the content recommendation device 400 includes:

[0089] A receiving module 401, configured to receive a content request sent by a terminal device, where the content request carries target information for matching recommended content, and the target information includes attribute information of historical delivered content and / or historical interaction information in a content material page displayed by the terminal device;

[0090] A model recommendation module 402, configured to obtain target recommended content according to the target information and a content recommendation model, where the target recommended content includes target content materials and analysis information for the target content materials, and the content recommendation model is used to match recommended content according to input information;

[0091] A pushing module 403, configured to push the target recommended content to the terminal device, so that the terminal device displays the target recommended content in the content material page.

[0092] By using the above device, since the historical delivered content and historical interaction information corresponding to different users are different, the content materials displayed by the terminal devices of different users are different, thereby helping users to inspire new ideas, avoiding homogenization of created content, and meeting the creation needs of different users. In addition, the content material page also displays analysis information for the content materials, which can reduce the user's cognitive threshold, improve the availability of the materials, and further improve the content creation efficiency.

[0093] Optionally, the model recommendation module 402 is configured to:

[0094] Obtain candidate content materials matching the target information from a content material library through the content recommendation model, and determine the target recommended content according to the candidate content materials, where the content material library is used to store content materials and analysis information for the content materials.

[0095] Optionally, the attribute information of the historical delivered content includes category information of the historical delivered content and / or delivery object information;

[0096] The model recommendation module 402 includes:

[0097] A category matching module, configured to use the content recommendation model to use the content materials in the content material library that match the category information of the historical delivered content as the candidate content materials; and / or,

[0098] An object matching module, configured to use the content recommendation model to use the content materials in the content material library that match the delivery object information of the historical delivered content as the candidate content materials.

[0099] Optionally, the category information of the historical delivered content includes multi-level category information, and the category matching module is used for:

[0100] Obtain a first material matching the first-level category information of the historical delivered content from the content material library through the content recommendation model;

[0101] If the number of the first materials is greater than or equal to a first preset number, use the first materials as the candidate content materials; or,

[0102] If the number of the first materials is less than the first preset number, obtain second materials matching the second-level category information of the historical delivered content from the content material library through the content recommendation model, and when the number of the second materials is greater than or equal to the first preset number, use the second materials as the candidate content materials, and the category corresponding to the first-level category information belongs to the category corresponding to the second-level category information.

[0103] Optionally, the historical interaction information includes at least one of historical material usage information, historical material browsing information, and historical material collection information, and the model recommendation module 402 is used for:

[0104] Determine historical interaction materials according to the historical interaction information;

[0105] Determine the content materials in the content material library that match the historical interaction materials as the candidate content materials through the content recommendation model.

[0106] Optionally, the model recommendation module 402 is used for:

[0107] Determine initial candidate content materials that meet the interaction index conditions from the content material library through the content recommendation model, and determine the content materials in the initial candidate content materials that match the target information as the candidate content materials, where the interaction index conditions include at least one of historical delivery index conditions, interaction feedback index conditions, and content level index conditions.

[0108] Optionally, the model recommendation module 402 is used for:

[0109] Obtain a first content material matching the target information from the content material library through the content recommendation model, and a second content material similar to the first content material, and use the first content material and the second content material as the candidate content materials.

[0110] Optionally, the model recommendation module 402 is used for:

[0111] Obtain the first candidate recommended content according to the target information and the content recommendation model;

[0112] For each of the first candidate recommended contents, determine the sorting index value of the first candidate recommended content, where the sorting index value is determined based on at least one of the placement index, timeliness index, and relevance index to the content request of the first candidate recommended content;

[0113] Sort the first candidate recommended contents according to the sorting index value to obtain the target recommended content.

[0114] Optionally, the model recommendation module 402 is used to:

[0115] Obtain the second candidate recommended content according to the target information and the content recommendation model;

[0116] Group the second candidate recommended contents according to the analysis information corresponding to the content materials in the second candidate recommended contents to obtain multiple groups of target recommended contents;

[0117] The push module 403 is used to:

[0118] Push the multiple groups of target recommended contents to the terminal device, so that the terminal device displays the multiple groups of target recommended contents in groups on the content material page.

[0119] Optionally, the content recommendation device 400 further includes:

[0120] An acquisition module, configured to acquire initial content materials, where the initial content materials include released contents and diversified interest contents;

[0121] An analysis module, configured to analyze the initial content materials to obtain analysis information for the initial content materials, and store the initial content materials and the analysis information for the initial content materials in a content material library, where the content material library is used for the content recommendation model to match the target recommended content.

[0122] Optionally, the analysis module is used to:

[0123] Analyze the initial content materials to obtain at least one of the content type information, content object information, content generation strategy, content label information, and placement object information of the initial content materials as the analysis information for the initial content materials.

[0124] Optionally, the analysis module is used to:

[0125] Analyze the initial content material through a content analysis model to obtain at least one of the content structure information, content recommendation reasons, and content theme information of the initial content material as the analysis information for the initial content material. The content analysis model is used to analyze the input content material.

[0126] Optionally, the content recommendation device 400 further includes a model training module, and the model training module is used for:

[0127] After receiving the interaction feedback information sent by the terminal device for the target recommended content, update and train the content recommendation model according to the interaction feedback information and the target recommended content to obtain a new content recommendation model.

[0128] Regarding the device in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated herein.

[0129] Based on the same concept, an embodiment of the present disclosure further provides a computer-readable medium, on which a computer program is stored, and when the program is executed by a processing device, the steps of the above content recommendation method are implemented.

[0130] Based on the same concept, an embodiment of the present disclosure further provides an electronic device, including:

[0131] A storage device, on which a computer program is stored;

[0132] A processing device, configured to execute the computer program in the storage device to implement the steps of the above content recommendation method.

[0133] Next, refer to Figure 5 , which shows a schematic structural diagram of an electronic device 500 suitable for implementing the embodiments of the present disclosure. The terminal device in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The electronic device shown is only an example and should not impose any limitation on the functions and usage scope of the embodiments of the present disclosure.

[0134] As Figure 5As shown, the electronic device 500 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 501, which may perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0135] Generally, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or wirelesly to exchange data. Although Figure 5 the electronic device 500 with various devices is shown, it should be understood that it is not required to implement or have all the shown devices. Instead, more or fewer devices may be implemented or had.

[0136] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart may 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 non-transitory computer-readable medium, and the computer program includes program codes for performing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above functions defined in the method of the embodiment of the present disclosure are executed.

[0137] It should be noted that the above-mentioned computer-readable medium in the present disclosure can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can 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, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device. In the present disclosure, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, in which computer-readable program code is carried. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, and this computer-readable signal medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0138] In some embodiments, communication can be carried out using any currently known or future-developed network protocol such as HTTP (HyperText Transfer Protocol), and can be interconnected with digital data communication in any form or medium (for example, a communication network). Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), the Internet (for example, the Internet), and end-to-end networks (for example, ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0139] The above-mentioned computer-readable medium can be included in the above-mentioned electronic device; it can also exist separately without being assembled into the electronic device.

[0140] The above computer-readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: receive a content request sent by a terminal device, the content request carrying target information for matching recommended content, the target information including attribute information of historical delivered content and / or historical interaction information in a content material page displayed by the terminal device; obtain target recommended content according to the target information and a content recommendation model, the target recommended content including target content materials and analysis information for the target content materials, the content recommendation model being used to match recommended content according to input information; and push the target recommended content to the terminal device so that the terminal device displays the target recommended content in the content material page.

[0141] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages or combinations thereof. The programming languages include, but are not limited to, object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).

[0142] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0143] The modules involved in the embodiments of the present disclosure can be implemented in software or in hardware. In some cases, the name of a module does not constitute a limitation on the module itself.

[0144] The functions described above herein can be performed, at least in part, by one or more hardware logic components. By way of example, and without limitation, the types of hardware logic components that can be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0145] In the context of the present disclosure, a machine-readable medium may be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. 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, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0146] The above description is only a preferred embodiment of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosure concept. For example, the technical solutions formed by mutually replacing the above features with the technical features (but not limited to) having similar functions disclosed in the present disclosure.

[0147] In addition, although the operations are depicted in a particular order, this should not be construed as requiring that the operations be performed in the particular order shown or in sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present disclosure. Certain features described in the context of separate embodiments may also be implemented combinatorially in a single embodiment. Conversely, the various features described in the context of a single embodiment may also be implemented separately or in any suitable sub-combination in multiple embodiments.

[0148] Although the subject matter has been described in language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. On the contrary, the specific features and acts described above are merely example forms for implementing the claims. Regarding the apparatus in the above embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments related to the method, and will not be elaborated here.

Claims

1. A content recommendation method, characterized in that, The content recommendation method includes: Receiving a content request sent by a terminal device, where the content request carries target information for matching recommended content, and the target information includes attribute information of historical delivered content and / or historical interaction information in a content material page displayed by the terminal device; Obtaining target recommended content according to the target information and a content recommendation model, where the target recommended content includes target content materials and analysis information for the target content materials, and the content recommendation model is used to match recommended content according to the input information; Pushing the target recommended content to the terminal device so that the terminal device displays the target recommended content in the content material page.

2. The content recommendation method according to claim 1, characterized in that, The obtaining target recommended content according to the target information and the content recommendation model includes: Obtaining candidate content materials matching the target information from a content material library through the content recommendation model, and determining the target recommended content according to the candidate content materials, where the content material library is used to store content materials and analysis information for the content materials.

3. The content recommendation method according to claim 2, characterized in that, The attribute information of the historical delivered content includes category information of the historical delivered content and / or delivery object information; The obtaining candidate content materials matching the target information from the content material library through the content recommendation model includes: Taking, through the content recommendation model, the content materials in the content material library that match the category information of the historical delivered content as the candidate content materials; and / or, Taking, through the content recommendation model, the content materials in the content material library that match the delivery object information of the historical delivered content as the candidate content materials.

4. The content recommendation method according to claim 3, characterized in that The category information of the historical delivered content includes multi-level category information. The taking, through the content recommendation model, the content materials in the content material library that match the category information of the historical delivered content as the candidate content materials includes: Obtaining, through the content recommendation model, first materials in the content material library that match the first-level category information of the historical delivered content; If the number of the first materials is greater than or equal to a first preset number, taking the first materials as the candidate content materials; or, If the number of the first materials is less than the first preset number, obtaining, through the content recommendation model, second materials in the content material library that match the second-level category information of the historical delivered content, and when the number of the second materials is greater than or equal to the first preset number, taking the second materials as the candidate content materials, where the category corresponding to the first-level category information belongs to the category corresponding to the second-level category information.

5. The content recommendation method according to claim 2, wherein The historical interaction information includes at least one of historical material usage information, historical material browsing information, and historical material collection information. The obtaining candidate content materials matching the target information from the content material library through the content recommendation model includes: Determining historical interaction materials according to the historical interaction information; Determining, through the content recommendation model, the content materials in the content material library that match the historical interaction materials as the candidate content materials.

6. The content recommendation method according to claim 2, characterized in that, The obtaining of candidate content materials matching the target information from the content material library through the content recommendation model includes: Through the content recommendation model, initial candidate content materials that meet the interaction index conditions are determined from the content material library, and the content materials in the initial candidate content materials that match the target information are determined as the candidate content materials. The interaction index conditions include at least one of historical delivery index conditions, interaction feedback index conditions, and content level index conditions.

7. The content recommendation method according to claim 2, wherein The obtaining of candidate content materials matching the target information from the content material library through the content recommendation model includes: Through the content recommendation model, first content materials matching the target information and second content materials similar to the first content materials are obtained from the content material library, and the first content materials and the second content materials are used as the candidate content materials.

8. The content recommendation method according to any one of claims 1-7, characterized in that, The obtaining of target recommended content according to the target information and the content recommendation model includes: According to the target information and the content recommendation model, first candidate recommended content is obtained; For each of the first candidate recommended content, a sorting index value of the first candidate recommended content is determined. The sorting index value is determined based on at least one of the delivery index, timeliness index, and relevance index of the first candidate recommended content to the content request; The first candidate recommended content is sorted according to the sorting index value to obtain the target recommended content.

9. The content recommendation method according to any one of claims 1-7, characterized in that The obtaining of target recommended content according to the target information and the content recommendation model includes: According to the target information and the content recommendation model, second candidate recommended content is obtained; According to the analysis information corresponding to the content materials in the second candidate recommended content, the second candidate recommended content is grouped to obtain multiple groups of target recommended content; The pushing of the target recommended content to the terminal device so that the terminal device displays the target recommended content on the content material page includes: The multiple groups of target recommended content are pushed to the terminal device so that the terminal device displays the multiple groups of target recommended content in groups on the content material page.

10. The content recommendation method according to any one of claims 1-7, characterized in that The content recommendation method further includes: Obtaining initial content materials, where the initial content materials include delivered content and diverse interest content; Analyzing the initial content materials to obtain analysis information for the initial content materials, and storing the initial content materials and the analysis information for the initial content materials in the content material library, where the content material library is used for the content recommendation model to match the target recommended content.

11. The content recommendation method according to claim 10, characterized in that, The analyzing of the initial content materials to obtain analysis information for the initial content materials includes: Analyzing the initial content materials to obtain at least one of the content type information, content object information, content generation strategy, content label information, and delivery object information of the initial content materials as the analysis information for the initial content materials.

12. The content recommendation method according to claim 10, characterized in that The analyzing of the initial content materials to obtain analysis information for the initial content materials includes: Analyze the initial content material through a content analysis model to obtain at least one of the content structure information, content recommendation reasons, and content theme information of the initial content material as the analysis information for the initial content material. The content analysis model is used to analyze the input content material.

13. The content display method according to any one of claims 1-7, characterized in that, The content recommendation method further includes: After receiving the interaction feedback information for the target recommended content sent by the terminal device, update and train the content recommendation model according to the interaction feedback information and the target recommended content to obtain a new content recommendation model.

14. A content recommendation device, characterized in that, The content recommendation device includes: A receiving module, configured to receive a content request sent by a terminal device. The content request carries target information for matching recommended content, and the target information includes attribute information of historical delivered content and / or historical interaction information in the content material page displayed by the terminal device; A model recommendation module, configured to obtain target recommended content according to the target information and a content recommendation model. The target recommended content includes a target content material and analysis information for the target content material. The content recommendation model is used to match recommended content according to the input information; A pushing module, configured to push the target recommended content to the terminal device, so that the terminal device displays the target recommended content on the content material page.

15. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by a processing device, it implements the steps of the method according to any one of claims 1-13.

16. An electronic device, characterized in that, It includes: A storage device, on which a computer program is stored; A processing device, configured to execute the computer program in the storage device to implement the steps of the method according to any one of claims 1-13.

Images