Media content recommendation method and apparatus, electronic device, and storage medium

Abstract

The present disclosure relates to a media content recommendation method, device, electronic equipment and storage medium. The media content recommendation method comprises: obtaining a content value score of first media content and obtaining related data of the first media content; determining first recommendation data according to the content value score of the first media content and the related data of the first media content; determining second recommendation data according to the first recommendation data and a received control instruction, the second recommendation data comprising a push priority of second media content, the control instruction being used to adjust a push priority of the first media content, the second media content being different from the first media content and comprising a plurality of media content; and determining and pushing target media content according to the push priority of the second media content and a preset priority threshold. Through the present disclosure, new hot content recommendation can be performed through manual intervention while ensuring efficient algorithm execution of content recommendation and meeting user individualization requirements.

Description

Technical Field

[0001] This disclosure relates to the field of smart internet TVs, and more particularly to a media content recommendation method, apparatus, electronic device, and storage medium. Background Technology

[0002] The smart internet TV industry has undergone more than a decade of development since its inception. During this process, the recommendation model for TV content operation has also shifted from initial manual operation to personalized algorithm-based recommendations.

[0003] However, traditional manual recommendation methods suffer from low efficiency and an inability to meet users' personalized needs. Algorithmic recommendation methods, on the other hand, are insensitive to new and trending content and lack flexibility. Summary of the Invention

[0004] To overcome the problems existing in related technologies, this disclosure provides a media content recommendation method, apparatus, electronic device, and storage medium.

[0005] According to a first aspect of the present disclosure, a content recommendation method is provided, comprising: obtaining a content value score of first media content and obtaining relevant data of the first media content, wherein the first media content includes multiple media content, the content value score characterizes the overall quality of the media content, and the relevant data characterizes the popularity of the media content; determining first recommendation data based on the content value score of the first media content and the relevant data of the first media content, wherein the first recommendation data includes the push priority of the first media content; determining second recommendation data based on the first recommendation data and a received control instruction, wherein the second recommendation data includes the push priority of second media content, the control instruction being used to adjust the push priority of the first media content, wherein the second media content is different from the first media content and includes multiple media content; and determining and pushing target media content based on the push priority of the second media content and a preset priority threshold.

[0006] In one embodiment, obtaining the content value score of the first media content includes: for each of the multiple media contents in the first media content, determining the content tag, traffic data, and popularity data of the media content; determining a first value score of the media content based on the content tag, the first value score representing the content quality of the media content; determining a second value score of the media content based on the traffic data, the second value score representing the platform traffic occupied by the media content; and determining a third value score of the media content based on the popularity data, the second value score representing the online popularity of the media content; and summing the first value score, the second value score, and the third value score to determine the content value score of the media content.

[0007] In one embodiment, the relevant data of the first media content includes one or more of the following: the playback penetration rate of the media content, the paid conversion rate of the media content, or the user payment data of the media content after being pushed a preset number of times.

[0008] In one embodiment, the method further includes: setting first preset media content based on the control command, and setting a priority for the first preset media content, wherein the first preset media content is different from the first media content; and / or removing recommendation data corresponding to second preset media content from the first recommendation data, wherein the first media content includes the second preset media content.

[0009] In one embodiment, pushing target media content includes: determining target traffic data for a target time period, wherein the target time period is the next time period adjacent to the current time period; determining a target recommendation count corresponding to the target traffic data based on the correspondence between traffic data and push counts; determining target push data based on current push data, a first number of currently online first-type users, a second number of currently online second-type users, the target recommendation count, and a first preset method, wherein the current push data includes a first push probability corresponding to the first-type users and a second push probability corresponding to the second-type users, and the target push data includes a first target push probability corresponding to the first-type users and a second push probability corresponding to the second-type users, wherein the first-type users are users interested in the target media content, and the second-type users are users uninterested in the media content; and pushing the target media content to the first-type users and the second-type users based on the target push data.

[0010] In one implementation, determining the target push data based on current push data, a first number of currently online first-type users, a second number of currently online second-type users, the target push count, and a first preset method includes: determining a first product of a first push probability and the first number, and determining a second product of a second push probability and the second number; in response to the sum of the first product and the second product being equal to the target push count, determining the first push probability as a first target push probability, and determining the second push probability as a second target push probability; in response to the sum of the first product and the second product being less than the target push count, increasing the first push probability. The system determines the increased first push probability and the third product of the first quantity until the sum of the third product and the second product equals the target number of pushes. The increased first push probability is then determined as the first target push probability, and the second push probability is determined as the second target push probability. In response to the sum of the first product and the second product being greater than the target number of pushes, the second push probability is reduced, and the reduced second push probability and the fourth product of the second quantity are determined until the sum of the fourth product and the first product equals the target number of pushes. The reduced second push probability is then determined as the second target push probability, and the first push probability is determined as the first target push probability.

[0011] In one embodiment, determining the target traffic data for a target time period includes: using a preset model, based on first historical traffic data, performing data fitting on the target time period to obtain fitted traffic data corresponding to the target time period, wherein the first historical traffic data includes traffic data corresponding to different time periods within a first cycle from the target time period; determining second historical traffic data for a historical time period, and performing data fitting on the historical time period using a preset model to obtain historical fitted traffic data corresponding to the historical time period, wherein the historical time period is the time period from 0:00 on the current day to a preset time interval before the current time period; adjusting the fitted traffic data according to the difference ratio between the second historical traffic data and the historical fitted traffic data to obtain the target traffic data.

[0012] According to a second aspect of the present disclosure, a content recommendation apparatus is provided, comprising: an acquisition unit, configured to acquire a content value score of first media content and acquire related data of the first media content, wherein the first media content includes multiple media contents, the content value score characterizes the overall quality of the media content, and the related data characterizes the popularity of the media content; a determination unit, configured to determine first recommendation data based on the content value score of the first media content and the related data of the first media content, wherein the first recommendation data includes a push priority of the first media content; a processing unit, configured to determine second recommendation data based on the first recommendation data and a received control instruction, wherein the second recommendation data includes a push priority of second media content, the control instruction being used to adjust the push priority of the first media content, wherein the second media content is different from the first media content and includes multiple media contents; and a push unit, configured to determine and push target media content based on the push priority of the second media content and a preset priority threshold.

[0013] In one embodiment, the acquisition unit acquires the content value score of the first media content in the following manner: for each of the multiple media contents in the first media content, the content tag, traffic data, and popularity data of the media content are determined; a first value score of the media content is determined based on the content tag, the first value score representing the content quality of the media content; a second value score of the media content is determined based on the traffic data, the second value score representing the platform traffic occupied by the media content; and a third value score of the media content is determined based on the popularity data, the second value score representing the online popularity of the media content; the sum of the first value score, the second value score, and the third value score is determined as the content value score of the media content.

[0014] In one embodiment, the relevant data of the first media content includes one or more of the following: the playback penetration rate of the media content, the paid conversion rate of the media content, or the user payment data of the media content after being pushed a preset number of times.

[0015] In one embodiment, the processing unit is further configured to: set a first preset media content based on the control instruction, and set a priority for the first preset media content, wherein the first preset media content is different from the first media content; and / or remove recommendation data corresponding to a second preset media content from the first recommendation data, wherein the first media content includes the second preset media content.

[0016] In one embodiment, the push unit pushes target media content in the following manner: determining target traffic data for a target time period, wherein the target time period is the next time period adjacent to the current time period; determining the target recommendation count corresponding to the target traffic data based on the correspondence between traffic data and push count; determining target push data based on current push data, a first number of currently online first-type users, a second number of currently online second-type users, the target recommendation count, and a first preset method, wherein the current push data includes a first push probability corresponding to the first-type users and a second push probability corresponding to the second-type users, and the target push data includes a first target push probability corresponding to the first-type users and a second push probability corresponding to the second-type users, wherein the first-type users are users interested in the target media content, and the second-type users are users who are not interested in the media content; and pushing the target media content to the first-type users and the second-type users based on the target push data.

[0017] In one implementation, the push unit determines the target push data in the following manner based on current push data, a first number of currently online first-type users, a second number of currently online second-type users, the target push count, and a first preset method: determining a first product of a first push probability and the first number, and determining a second product of a second push probability and the second number; in response to the sum of the first product and the second product being equal to the target push count, determining the first push probability as a first target push probability, and determining the second push probability as a second target push probability; in response to the sum of the first product and the second product being less than the target push count, increasing the first push probability. The system calculates the probability of a push notification and determines the product of the increased first push probability and the first quantity, up to a third product, until the sum of the third product and the second product equals the target number of push notifications. The increased first push probability is then determined as the first target push probability, and the second push probability is determined as the second target push probability. In response to a situation where the sum of the first product and the second product exceeds the target number of push notifications, the system reduces the second push probability and determines the product of the reduced second push probability and the second quantity, up to a fourth product, until the sum of the fourth product and the first product equals the target number of push notifications. The reduced second push probability is then determined as the second target push probability, and the first push probability is determined as the first target push probability.

[0018] In one embodiment, the push unit determines the target traffic data for a target time period in the following manner: Based on first historical traffic data and using a preset model, data fitting is performed on the target time period to obtain fitted traffic data corresponding to the target time period. The first historical traffic data includes traffic data corresponding to different time periods within a first cycle from the target time period. A second historical traffic data for a historical time period is determined, and the historical time period is fitted using the preset model to obtain historical fitted traffic data corresponding to the historical time period. The historical time period is the time period between 0:00 on the current day and a preset time interval before the current time period. The fitted traffic data is adjusted according to the difference ratio between the second historical traffic data and the historical fitted traffic data to obtain the target traffic data.

[0019] According to a third aspect of the present disclosure, an electronic device is provided, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to: execute the media content recommendation method described in the first aspect or any embodiment of the first aspect.

[0020] According to a fourth aspect of the present disclosure, a storage medium is provided, the storage medium storing instructions that, when executed by a processor, enable the processor to perform the media content recommendation method described in the first aspect or any embodiment of the first aspect.

[0021] The technical solutions provided by the embodiments of this disclosure may include the following beneficial effects: For first media content, a content value score representing the first quality of the media content is obtained, and relevant data representing the popularity of the media content is obtained. Based on the content value score of the first media content and the relevant data, first recommendation data is determined, the first recommendation data including the push priority of the first media content. Based on the received control instructions, the push priority of the first media content is adjusted, and second recommendation data is determined, the second recommendation data including the push priority of second media content, the second media content being different from the first media content and including multiple media content. Based on the push priority of the second media content and a preset priority threshold, target media content is determined and pushed. Through this disclosure, while ensuring that content recommendation is executed efficiently through algorithms and meeting users' personalized requirements, it is possible to recommend new and popular content through manual intervention.

[0022] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0023] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0024] Figure 1 This is a flowchart illustrating a media content recommendation method according to an exemplary embodiment.

[0025] Figure 2 This is a flowchart illustrating a method for obtaining the content value score of first media content according to an exemplary embodiment.

[0026] Figure 3 This is a schematic diagram illustrating a method for obtaining content value scores of media content according to an exemplary embodiment of this disclosure.

[0027] Figure 4 This is a schematic diagram illustrating a method for obtaining content value scores of media content according to an exemplary embodiment of this disclosure.

[0028] Figure 5 This is a flowchart illustrating a method for setting first media content according to an exemplary embodiment.

[0029] Figure 6 This is a schematic diagram illustrating a method for setting recommended content according to control instructions based on an exemplary embodiment of this disclosure.

[0030] Figure 7 This is a flowchart illustrating a method for pushing target media content according to an exemplary embodiment.

[0031] Figure 8 This is a flowchart illustrating a method for determining target push data according to an exemplary embodiment.

[0032] Figure 9 This is a flowchart illustrating a method for determining target traffic data for a target time period according to an exemplary embodiment.

[0033] Figure 10 This is a schematic diagram illustrating a method for determining target traffic data for a target time period according to an exemplary embodiment of the present disclosure.

[0034] Figure 11 This is a schematic diagram illustrating historical traffic data according to an exemplary embodiment of the present disclosure.

[0035] Figure 12 This is a schematic diagram illustrating fitted data and actual data according to an exemplary embodiment of the present disclosure.

[0036] Figure 13 This is a schematic diagram illustrating a media content recommendation method according to an exemplary embodiment of this disclosure.

[0037] Figure 14 This is a schematic diagram illustrating an architecture for media content recommendation according to an exemplary embodiment of this disclosure.

[0038] Figure 15 This is a block diagram illustrating a media content recommendation device according to an exemplary embodiment.

[0039] Figure 16 This is a block diagram illustrating an apparatus for recommending media content according to an exemplary embodiment.

[0040] Figure 17 This is a block diagram illustrating an apparatus for recommending media content according to an exemplary embodiment. Detailed Implementation

[0041] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure.

[0042] The media content recommendation method provided in this disclosure is applied to scenarios where media content is recommended by combining algorithmic and manual methods.

[0043] The smart internet TV industry has undergone more than a decade of development since its inception. During this process, the recommendation model for TV content operation has shifted from initial manual recommendations to personalized algorithmic recommendations. Algorithmic recommendations significantly outperform traditional manual recommendations in improving recommendation efficiency, conversion rates, and optimizing user experience. However, algorithmic recommendations are not without their flaws. They face challenges such as insufficient identification of the lifecycle of new and trending content leading to inaccurate recommendations, and declining conversion rates due to overexposure of top-tier content.

[0044] In related technologies, manual recommendation, where experienced editors or operations personnel select content based on their professional knowledge, ensures the quality and suitability of the content. It can also quickly adjust recommendations according to specific contexts such as current events, holidays, and celebrations, making it more timely and targeted. Furthermore, recommendations can be set based on the overall preferences of the operations personnel. It possesses the characteristics of high professionalism and flexibility, and better reflects and conveys specific values ​​and cultural orientations. However, manual recommendation requires significant human and material resources, has limited processing speed, struggles to meet the needs of a large user base, and is influenced by personal preferences and biases, failing to fully satisfy personalized user needs. Moreover, due to human resource limitations, manual recommendation cannot achieve comprehensive coverage of massive amounts of content. Therefore, manual recommendation suffers from low efficiency, high subjectivity, and limited coverage.

[0045] Among related technologies, algorithmic recommendation methods can process large amounts of data, providing users with fast and personalized content recommendations. Based on user behavior and preferences, these recommendations can more accurately meet user needs, reduce human intervention, and lower operating costs. They are characterized by high accuracy and efficiency. However, algorithmic recommendation methods struggle to cope with unexpected events and special dates / situations, potentially leading to recommendations that do not match the user's actual needs. They are also often slow to react to newly emerging trending content, affecting recommendation effectiveness and exhibiting a lack of flexibility and insufficient recognition of new content.

[0046] In view of this, this disclosure proposes a method for media content recommendation. For a first media content, a content value score representing the first quality of the media content is obtained, along with relevant data representing the popularity of the media content. Based on the content value score and relevant data of the first media content, first recommendation data is determined, including the push priority of the first media content. The push priority of the first media content is adjusted according to received control instructions to determine second recommendation data, which includes the push priority of second media content. The second media content is distinct from the first media content and includes multiple media content items. Based on the push priority of the second media content and a preset priority threshold, target media content is determined and pushed. Through this disclosure, while ensuring efficient content recommendation through algorithms and meeting users' personalized requirements, it is possible to recommend new and popular content through manual intervention.

[0047] Figure 1 This is a flowchart illustrating a media content recommendation method according to an exemplary embodiment. For example... Figure 1 As shown, the method includes steps S101 to S104.

[0048] In step S101, the content value score of the first media content is obtained, and the relevant data of the first media content is obtained. The first media content includes multiple media content. The content value score represents the overall quality of the media content, and the relevant data represents the popularity of the media content.

[0049] In step S102, first recommendation data is determined based on the content value score of the first media content and the relevant data of the first media content. The first recommendation data includes the push priority of the first media content.

[0050] In step S103, second recommendation data is determined based on the first recommendation data and the received control instruction. The second recommendation data includes the push priority of the second media content. The control instruction is used to adjust the push priority of the first media content. The second media content is different from the first media content and includes multiple media content.

[0051] In step S104, the target media content is determined and pushed according to the push priority of the second media content and the preset priority threshold.

[0052] In this embodiment, media content recommendation is performed by combining algorithmic and manual recommendation methods. The recommendation algorithm calculates the value score of existing media content (first media content, including TV dramas, movies, animations, variety shows, etc.) on the video platform (smart internet TV platform) to obtain a content value score representing the overall quality of the media content. It can also obtain relevant data representing the degree of recommendation of media content by acquiring user-end data. It is understood that both the degree of recommendation and the overall quality of media content can serve as the basis for media content recommendation. Therefore, after determining the content value score and relevant data of the first media content, this disclosure uses the recommendation algorithm to determine the push priority (first recommendation data) of each media content within the first media content based on the content value score and relevant data. It is understood that the recommendation algorithm has certain limitations; it is not sensitive to new and trending content and lacks predictive ability. This disclosure can further adjust the first recommendation data obtained by the algorithm based on user-sent control commands, such as adjusting the push priority of each media content within the first media content to obtain second media content. Through this disclosure, while ensuring efficient content recommendation through the algorithm and meeting users' personalized requirements, it is possible to recommend new and trending content through manual intervention.

[0053] It is understandable that video platforms contain a massive amount of media content, but when users browse media content through video platforms, the content they can view on the recommendation page is relatively limited. Therefore, this disclosure sets a preset priority threshold to further filter the second media content, and selects the media content in the second media content whose push priority meets the priority threshold requirements as the target media content for recommendation.

[0054] In this embodiment, for first media content, a content value score representing the first quality of the media content is obtained, and relevant data representing the popularity of the media content is obtained. Based on the content value score and relevant data of the first media content, first recommendation data is determined, which includes the push priority of the first media content. The push priority of the first media content is adjusted according to received control instructions to determine second recommendation data, which includes the push priority of second media content. The second media content is different from the first media content and includes multiple media content. Based on the push priority of the second media content and a preset priority threshold, target media content is determined and pushed. This disclosure combines algorithmic and manual recommendation methods for media content recommendation, ensuring efficient content recommendation through algorithms and meeting users' personalized requirements while enabling the recommendation of new and popular content through manual intervention.

[0055] It is understandable that when evaluating the overall quality of media content, it is necessary to evaluate it from different dimensions. This disclosure obtains the value score of each dimension of the media content, and then determines the content value score of the media content based on the value score of each dimension.

[0056] Figure 2 This is a flowchart illustrating a method for obtaining the content value score of first media content according to an exemplary embodiment. Figure 2 As shown, the method includes steps S201 to S203.

[0057] In step S201, for each piece of media content among the multiple pieces of media content in the first media content, the content tag, traffic data, and popularity data of the media content are determined.

[0058] In step S202, a first value score for the media content is determined based on the content tags. The first value score represents the content quality of the media content. A second value score for the media content is determined based on traffic data. The second value score represents the platform traffic occupied by the media content. A third value score for the media content is determined based on popularity data. The second value score represents the online popularity of the media content.

[0059] In step S203, the sum of the first value score, the second value score, and the third value score is determined as the content value score of the media content.

[0060] In this embodiment, for the first media content, value scores are obtained from multiple dimensions, including content quality, platform traffic, and online popularity. For the content quality dimension, content tags (such as director, lead actor, genre, and subject matter) are obtained, and a first value score representing the content quality is determined based on these tags. For the platform traffic dimension, traffic data (such as program exposure and revenue) is obtained, and a second value score representing the platform traffic is determined based on this data. For the online popularity, popularity data (such as program popularity and actor popularity) is obtained, and a third value score representing the online popularity is determined based on this data. The first, second, and third value scores are then used to determine the content value score.

[0061] In this embodiment, media content is evaluated across different dimensions. The disclosure obtains a value score for each dimension of the media content and combines these scores to derive a recommendation criterion (content value score). This allows for the recommendation of high-quality media content that aligns with user preferences.

[0062] In one embodiment of this disclosure, such as Figure 3 The diagram illustrates a method for obtaining content value scores for media content. This disclosure employs the following approach: Media content is acquired, and its tags are obtained. These tags can be directly used for media content recommendation / operation. Content tags include factual tags, model tags, and predictive tags. Factual tags include year, synopsis, director, IP, and production company. Model tags include genre, subject matter, tag weight, actor level, and safety level. Predictive tags include initial audience rating, dynamic rating, and content value score. Content quality value (first value score) is obtained based on factual tags (content tags). Platform traffic value (second value score) is obtained based on information such as holiday activity periods, subject matter preferences, willingness to pay, program exposure, and revenue (traffic data). External sentiment value (third value score) is determined based on information such as actor popularity and program popularity (popularity data). A content value system is obtained based on content quality value, platform traffic value, and external sentiment value, and then quantified to obtain the content value score. Among them, the content value score can be applied to the recommendation algorithm to observe the experimental effect, can be directly applied to the operation and weight adjustment to observe the rationality of the weight adjustment, and can also predict the program's paid conversion efficiency to observe the accuracy.

[0063] In one embodiment of this disclosure, value scores for different dimensions can be obtained through different models, such as... Figure 4 The diagram illustrates a method for obtaining content value scores for media content. The data to be processed includes: content quality (director, production company, initial rating, popular topics, scores) (content tags), platform traffic (historical revenue, holidays, member activity cycles) (traffic data), and public opinion heat (program popularity, actor popularity, box office revenue, "want to see" index) (heat data). Models used to obtain the corresponding value scores include linear regression models, SVM models, tree models, and MLP models. For each dimension of data, after determining the appropriate model through feature selection, the content value score is calculated using the model.

[0064] The following embodiments further illustrate the relevant data of media content.

[0065] In one embodiment of this disclosure, the relevant data of the first media content includes one or more of the following: the playback penetration rate of the media content, the paid conversion rate of the media content, or the user payment data of the media content after being pushed a preset number of times.

[0066] In this embodiment, the playback penetration rate of media content is the percentage of users viewing that content out of the total number of users, representing the popularity of the media content. The paid conversion rate of media content reflects users' willingness to pay for the content, also representing its popularity. Furthermore, user payment data after a preset number of pushes of media content represents the revenue generated from pushing the content, also representing its popularity. This disclosure uses data reflecting the popularity of media content as relevant data. Based on this data, a recommendation basis for media content is obtained, ensuring that the recommended media content matches user preferences.

[0067] Understandably, in daily life, there are often unexpected events that can gain immense popularity in a short period of time. Recommendation algorithms often fail to recognize and recommend such new content. This disclosure allows for adjustments to the algorithm's output via commands, ensuring that media content that is likely to gain significant popularity is promptly pushed to users.

[0068] Figure 5 This is a flowchart illustrating a method for setting first media content according to an exemplary embodiment. Figure 5 As shown, the method includes steps S301 to S302.

[0069] In step S301, first recommendation data is determined based on the content value score of the first media content and related data of the first media content. The first recommendation data includes the push priority of the first media content.

[0070] In step S302, based on control instructions, a first preset media content is set, and a priority is set for the first preset media content. The first preset media content is different from the first media content, and / or the recommendation data corresponding to the second preset media content is removed from the first recommendation data. The first media content includes the second preset media content.

[0071] In this embodiment, operators can adjust the first recommendation data via commands, such as raising or lowering the push priority of certain media content. They can also directly set new media content (a first preset media content identical to the first media content) in the recommendation data and assign a priority to the new media content. Alternatively, they can remove some media content (a second preset media content) from the first recommendation data. This allows for rapid adjustment of recommended content based on current events, festivals, and other specific scenarios, ensuring that media content potentially gaining significant popularity is promptly pushed to users, or responding to emergencies and special dates / situations, better reflecting and conveying specific values ​​and cultural orientations.

[0072] In one embodiment of this disclosure, such as Figure 6The diagram illustrates a method for setting recommended content based on control instructions. Through this disclosure, operators can issue control instructions via a pre-defined backend window, adjust weights using algorithms, and set the proportion of manual intervention. A specific window (Channel Today) determines the expected total UV resources and the expected remaining UV resources. Through manual intervention in the program pool, programs can be selected by serial number, program name, or program ID to adjust the daily UV allocation and determine information such as today's expected total exposure UV lower limit (ten thousand), today's expected remaining exposure UV lower limit (ten thousand), today's exposure UV (ten thousand), today's playback UV (ten thousand), and today's sales revenue (yuan).

[0073] It is understandable that the frequency of use of video platforms (smart TVs) varies at different times of the day, and the traffic data generated by users browsing media content also varies. Therefore, the recommended intensity of media content disclosed in this publication will also vary for different time periods.

[0074] Figure 7 This is a flowchart illustrating a method for pushing target media content according to an exemplary embodiment. For example... Figure 7 As shown, the method includes steps S401 to S404.

[0075] In step S401, the target traffic data for the target time period is determined. The target time period is the next time period adjacent to the current time period.

[0076] In step S402, the target recommendation count corresponding to the target traffic data is determined based on the correspondence between traffic data and push count.

[0077] In step S403, the target push data is determined based on the current push data, the first number of currently online first-type users, the second number of currently online second-type users, the target recommendation count, and the first preset method.

[0078] The current push data includes the first push probability corresponding to the first type of user and the second push probability corresponding to the second type of user. The target push data includes the first target push probability corresponding to the first type of user and the second push probability corresponding to the second type of user. The first type of user is the user who is interested in the target media content, and the second type of user is the user who is not interested in the media content.

[0079] In step S404, target media content is pushed to the first type of users and the second type of users based on the target push data.

[0080] In this embodiment, considering that the usage frequency of the video platform (smart network TV) varies at different time periods (such as working hours, after-get off work hours, and holidays), the traffic data generated by users browsing media content also varies. Therefore, the traffic data for a future period (target time period) is predicted based on historical traffic data (target traffic data), and the corresponding number of recommendations is determined (target recommendation number). Content recommendations are then made based on the predicted traffic data. This ensures that the traffic consumed by recommending media content matches the user's actual browsing activity.

[0081] The following embodiments illustrate a method for determining target push data.

[0082] Figure 8 This is a flowchart illustrating a method for determining target push data according to an exemplary embodiment. Figure 8 As shown, the method includes steps S501, S502A, S502B and S502C.

[0083] In step S501, a first product of a first push probability and a first quantity is determined, and a second product of a second push probability and a second quantity is determined.

[0084] In step S502A, in response to the sum of the first product and the second product being equal to the target number of pushes, the first push probability is determined as the first target push probability, and the second push probability is determined as the second target push probability.

[0085] In step S502B, in response to the sum of the first product and the second product being less than the target number of pushes, the first push probability is increased, and the increased first push probability is multiplied by the third product of the first number until the sum of the third product and the second product equals the target number of pushes. The increased first push probability is then determined as the first target push probability, and the second push probability is determined as the second target push probability.

[0086] In step S502C, in response to the sum of the first product and the second product being greater than the target number of pushes, the second push probability is reduced, and the fourth product of the reduced second push probability and the second number is determined until the sum of the fourth product and the first product equals the target number of pushes. The reduced second push probability is then determined as the second target push probability, and the first push probability is determined as the first target push probability.

[0087] In this embodiment of the disclosure, when the sum of the first product and the second product equals the target number of pushes, the number of pushes meets the expectation. Therefore, the first push probability is determined as the first target push probability, and the second push probability is determined as the second target push probability.

[0088] In this embodiment of the disclosure, if the sum of the first product and the second product is less than the target number of pushes, it indicates that the number of recommendations does not meet expectations. Therefore, the recommendation probability corresponding to the interested audience is increased, and the target media content is recommended more times to the interested audience. It can be understood that if the recommendation probability corresponding to the interested audience (first recommendation probability) is increased to the highest value (1), and the number of recommendations still does not meet expectations, then the recommendation probability corresponding to the uninterested audience (second recommendation probability) is increased.

[0089] In this embodiment of the disclosure, if the sum of the first product and the second product is greater than the target number of pushes, it indicates that too many recommendations would lead to resource waste. Therefore, the recommendation probability corresponding to the uninterested group is reduced, and the target media content is recommended fewer times to the interested group. It can be understood that if the recommendation probability (second recommendation probability) corresponding to the uninterested group is reduced to the minimum value (0), but the number of recommendations is still higher than the target number of recommendations, then the recommendation probability (first recommendation probability) corresponding to the interested group is reduced.

[0090] In an exemplary embodiment of this disclosure, the first target recommendation probability and the second target recommendation probability are set in the following manner:

[0091] (1) Divide users into interested users and uninterested users, and push notifications to interested users within time period i according to the probability of each user. Push notifications to users who are not interested within time period i If distribution proceeds, the expected distribution of media content is as follows:

[0092]

[0093] Where i represents a certain time period, This represents the number of users interested in watching media content within time period i (the first number of users in the first category). This represents the number of users who are not interested in watching media content during time period i (the second number of users in the second category).

[0094] (2) Assuming that the percentage of users interested in watching media content in the next time period i+1 is the same as that in the previous time period, the estimated number of users interested in watching media content in time period i+1 is:

[0095]

[0096] Where i+1 represents the next time period corresponding to time period i. For time period i+1, estimate the number of users interested in watching media content, num i Let be the total number of users within time period i, and num be the total number of users within time period i. i+1 This represents the total number of users within segment i+1.

[0097] Similarly, the expected average number of users exposed within time period i+1 is:

[0098]

[0099] in, This represents the expected average number of users exposed within the time period i+1. This refers to the probability of pushing content to users who are interested in watching media content within a time period i+1. This refers to the probability of pushing content to users who are not interested in watching media content within a time period i+1. num represents the number of users interested in watching media content within time period i+1. i+1 Total number of users within time period i+1.

[0100] (3) The calculation yields:

[0101]

[0102] Where expected_uv is the expected exposure data, exposed_uv is the already exposed data, and num i+1 Let num be the total number of users within time period i+1. j Let be the total number of users in the time period after i+1, and T be the time period after i+1. This represents the total number of users from time period i+1 to time period T. This refers to the probability of pushing content to users who are interested in watching media content within a time period i+1. This refers to the probability of pushing content to users who are not interested in watching media content within a time period i+1. The estimated number of users interested in watching media content for the time period i+1.

[0103] Further calculations yielded the following:

[0104]

[0105] Where expected_uv is the expected exposure data, exposed_uv is the already exposed data, and num j Let be the total number of users in the time period after i+1, and T be the time period after i+1. This represents the total number of users from time period i+1 to time period T. This refers to the probability of pushing content to users who are interested in watching media content within a time period i+1. To determine the probability of pushing content to users who are not interested in watching media content within time period i+1, num i Let i be the total number of users within time period i. This represents the number of users who are interested in watching media content within time period i.

[0106] The above formula simplifies to:

[0107]

[0108] Where 'a' represents the number of users interested in watching the media content, and 'b' represents the number of users not interested in watching the media content. This refers to the probability of pushing content to users who are interested in watching media content within a time period i+1. This represents the probability of pushing content to users who are not interested in watching media content within the time period i+1, where c is the total number of users.

[0109] (4) Ultimately, this is transformed into an online learning problem. Based on the data from the previous time period, an estimate is made. and There are three scenarios:

[0110] Keep the distribution probability unchanged for interested and uninterested users.

[0111] Prioritize increasing the probability of pushing to interested users (first push probability); only after this probability exceeds 1 should you increase the probability of pushing to uninterested users.

[0112] Prioritize reducing the probability of uninterested users (secondary push probability), and only reduce the probability of interested users if the probability is less than 0.

[0113] The following embodiments of this disclosure illustrate a method for determining target traffic data for a target time period.

[0114] Figure 9 This is a flowchart illustrating a method for determining target traffic data for a target time period according to an exemplary embodiment. Figure 9 As shown, the method includes steps S601 to S603.

[0115] In step S601, a preset model is used to fit the target time period based on the first historical traffic data to obtain the fitted traffic data corresponding to the target time period. The first historical traffic data includes traffic data corresponding to different time periods within a first cycle from the target time period.

[0116] In step S602, the second historical traffic data for the historical time period is determined, and the historical time period is fitted with a preset model to obtain the historical fitted traffic data corresponding to the historical time period. The historical time period is the time period between 0:00 on the current day and the preset time interval before the current time period.

[0117] In step S603, the fitted flow data is adjusted according to the difference ratio between the second historical flow data and the historical fitted flow data to obtain the target flow data.

[0118] In this embodiment, the time-series fitting employs a preset model, eliminating errors in the actual value by performing rolling calculations on the data within the first period. Historical traffic data for a historical time period (e.g., from 00:00 to 2 hours prior to the current time) and time-series traffic data for the same period are used to calculate the difference ratio between the fitted data and the actual data. The remaining traffic obtained from the time-series fitting is multiplied by this coefficient to perform remaining traffic adjustment calculations, yielding the optimized remaining traffic (target traffic data). Through this disclosure, the overall traffic prediction result is very close to the actual value, effectively solving the problem of inaccurate traffic prediction on specific dates (e.g., holidays).

[0119] In one embodiment of this disclosure, such as Figure 10 The diagram illustrates the method for determining target traffic data for a target time period. The target traffic data is determined as follows: The overall mechanism employs a time-series fitting + mean-based fallback approach. Time-series fitting uses the Prophet model (preset model), which eliminates errors in the actual values ​​by performing rolling calculations on data from the first year (the first cycle). Further coefficient optimization is then performed. The actual values ​​(historical traffic data) from 00:00 to 2 hours prior to the current time (considering delayed reporting) are compared with the time-series fitted values ​​(fitted traffic data) for the same period to obtain a difference ratio. This ratio represents the difference between the fitted data and the actual data. The remaining traffic derived from the time-series fitting is multiplied by this coefficient to adjust the remaining traffic, resulting in the optimized remaining traffic (target traffic data). This method calculates the new coefficients and corresponding remaining traffic every hour, resulting in an overall traffic prediction result that closely approximates the actual value, effectively solving the problem of inaccurate traffic predictions during holidays. Considering the high real-time requirements of time-series prediction, failure to produce prediction data in a timely manner would impact the overall accuracy of the engine. Therefore, mean-based prediction is used as a fallback solution. The mean forecasting scheme estimates remaining traffic based on the average of weekdays or weekends over the past week, and minimizes the error in the actual value caused by historical data by shortening the data collection cycle. The actual forecast results are very close to the actual values.

[0120] In an exemplary embodiment of this disclosure, such as Figure 11 The diagram illustrates historical traffic data, which includes traffic data corresponding to different time periods within a past time cycle.

[0121] In an exemplary embodiment of this disclosure, such as Figure 12As shown in the diagram of the fitted data and the actual data, there will be a deviation between the traffic data fitted by the preset model and the actual collected traffic data. Therefore, the fitted traffic data needs to be corrected according to the actual collected traffic data to make it closer to the real situation.

[0122] In an exemplary embodiment of this disclosure, such as Figure 13 The diagram illustrates a media content recommendation method. This scheme includes the following steps: acquiring media assets for content such as TV dramas, movies, animation, variety shows, children's content, and vertical categories; using these assets and real-time monitoring data (playback penetration rate, paid conversion rate, and pay-per-thousand impressions) for recommendations; determining a content value system based on media assets combined with ratings, quality, tags, playback UV, and paid data, and providing a basis for recommendations; manually intervening in the algorithm based on the content and recommendation basis output by the recommendation module, and empowering the algorithm's output (three-stage rocket, content planning, re-promotion of older dramas, user segmentation, public opinion trends, and material rotation) to obtain output data; the algorithm processing the content and recommendation basis output by the recommendation module, as well as real-time human intervention (model iteration, profiling system, content recall, and user identity), and receiving further human empowerment to obtain output; allocating traffic based on the data, recommending content to user terminals, and monitoring data in real-time on user terminals. The media content recommendation method includes six core components: 1. Manual intervention configuration: The configuration backend provides a manual intervention configuration page for channel content; 2. Content value score assessment: Value score tags are applied to both manual intervention and algorithm recommendation scenarios; 3. Intervention traffic prediction: Real-time remaining traffic estimation maximizes traffic utilization efficiency; 4. Intelligent traffic distribution: Programs are evenly distributed according to the manual intervention traffic allocation ratio; 5. Scientific experimental verification: The effectiveness of different recommendation modules, such as manual intervention and pure algorithm recommendation, is verified; 6. Visualized real-time data dashboard: The configuration backend and data platform provide real-time feedback dashboards to ensure fast, accurate, and precise manual intervention. This solution establishes a new platform model that works in conjunction with algorithms from scratch, achieving the system goal of efficient, safe, and scientific intervention. Key capabilities are built, including: In terms of system efficiency: Automated capabilities such as scheduled intervention stoppage and scheduled removal of fixed positions; daily data reports on the intervention system at the channel level. In terms of configuration security: Error-proofing strategies to prevent configuration from being blocked in cases of abnormal content status or lack of necessary materials; the ability to remind responsible personnel of abnormal situations such as content going offline; and the ability to quickly distribute data to internal devices for preview after intervention. In terms of scientific and human intervention: content selection scenarios; data display such as content value score and sales forecast helps humans judge the value level of content; the system actively captures recent popular programs, themes, tags and other dimensions for reference; intervention configuration scenarios; while providing the best intervention ratio (highest ECPM) prediction while estimating traffic in real time, it helps humans better set intervention rules.

[0123] In an exemplary embodiment of this disclosure, for example, Figure 14 This is a schematic diagram illustrating an architecture for media content recommendation according to an exemplary embodiment of this disclosure. The overall architecture of the media content recommendation system in this solution includes an application layer, a gateway layer, an online service layer, an operation layer, and a data processing layer. The gray boxes in the online service layer, operation layer, and data processing layer represent the service content involved in the media recommendation method of this disclosure.

[0124] In this embodiment, for first media content, a content value score representing the first quality of the media content is obtained, and relevant data representing the popularity of the media content is obtained. Based on the content value score and relevant data of the first media content, first recommendation data is determined, which includes the push priority of the first media content. The push priority of the first media content is adjusted according to received control instructions to determine second recommendation data, which includes the push priority of second media content. The second media content is different from the first media content and includes multiple media content. Based on the push priority of the second media content and a preset priority threshold, target media content is determined and pushed. This disclosure ensures efficient content recommendation through algorithms while meeting users' personalized requirements, and also enables the recommendation of new and popular content through manual intervention.

[0125] In this disclosed embodiment, the entire engine's entire chain is connected, successfully upgrading the configuration platform, content value, and server architecture. A "volume retention model" chain is introduced and put into use on the previous algorithm recommendation architecture.

[0126] This disclosure proposes an innovative intelligent traffic engine for internet TVs, combining algorithmic recommendation with manual weight adjustment. Through a strategy of human-assisted algorithmic input, it achieves maximum rational allocation of traffic, improves content distribution efficiency, and thereby drives increased playback penetration and pay-per-thousand impressions. The aim is to realize a novel internet TV algorithmic recommendation model, effectively integrating manual and algorithmic recommendation methods. Both leverage their respective advantages in the content recommendation process, achieving a synergy between humans and algorithms to reach the optimal solution for content recommendation. The engine designed in this disclosure is primarily applied to content recommendation scenarios on intelligent internet TVs: after a user turns on the device and browses content data across channels, the engine combines the current channel's manual intervention configuration and algorithmic recommendation exposure, performing complex calculations and traffic allocation to provide the user with a final personalized content recommendation.

[0127] Based on the same concept, this disclosure also provides a media content recommendation device 100.

[0128] It is understood that the media content recommendation device 100 provided in this disclosure includes hardware structures and / or software modules corresponding to each function in order to achieve the above-mentioned functions. In conjunction with the units and algorithm steps of the various examples disclosed in this disclosure, this disclosure can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the technical solutions of this disclosure.

[0129] Figure 15 This is a block diagram illustrating a media content recommendation device 100 according to an exemplary embodiment. (Refer to...) Figure 15 The device includes an acquisition unit 101, a determination unit 102, a processing unit 103, and a push unit 104.

[0130] The acquisition unit 101 is used to acquire the content value score of the first media content and acquire relevant data of the first media content. The first media content includes multiple media content. The content value score represents the overall quality of the media content, and the relevant data represents the popularity of the media content.

[0131] The determining unit 102 is used to determine the first recommendation data based on the content value score of the first media content and the relevant data of the first media content. The first recommendation data includes the push priority of the first media content.

[0132] The processing unit 103 is used to determine second recommendation data based on the first recommendation data and the received control instructions. The second recommendation data includes the push priority of the second media content. The control instructions are used to adjust the push priority of the first media content. The second media content is different from the first media content and includes multiple media content.

[0133] The push unit 104 is used to determine and push target media content based on the push priority of the second media content and a preset priority threshold.

[0134] In one embodiment, the acquisition unit 101 acquires the content value score of the first media content in the following manner: For each piece of media content among multiple pieces of media content in the first media content, the content tag, traffic data, and popularity data of the media content are determined. A first value score is determined based on the content tag, representing the content quality of the media content. A second value score is determined based on the traffic data, representing the platform traffic occupied by the media content. A third value score is determined based on the popularity data, representing the online popularity of the media content. The sum of the first value score, the second value score, and the third value score is determined as the content value score of the media content.

[0135] In one implementation, the relevant data of the first media content includes one or more of the following: the playback penetration rate of the media content, the paid conversion rate of the media content, or the user payment data of the media content after being pushed a preset number of times.

[0136] In one embodiment, the processing unit 103 is further configured to: set first preset media content based on control instructions, and set a priority for the first preset media content, wherein the first preset media content is different from the first media content; and / or remove recommendation data corresponding to second preset media content from the first recommendation data, wherein the first media content includes the second preset media content.

[0137] In one embodiment, the push unit 104 pushes target media content in the following manner: It determines target traffic data for a target time period, where the target time period is the next time period adjacent to the current time period. Based on the correspondence between traffic data and push counts, it determines the target recommendation count corresponding to the target traffic data. Based on the current push data, the first number of currently online first-type users, the second number of currently online second-type users, the target recommendation count, and a first preset method, it determines target push data. The current push data includes a first push probability corresponding to first-type users and a second push probability corresponding to second-type users. The target push data includes a first target push probability corresponding to first-type users and a second push probability corresponding to second-type users. First-type users are those interested in the target media content, and second-type users are those not interested in the media content. Based on the target push data, it pushes the target media content to both first-type and second-type users.

[0138] In one embodiment, the push unit 104 determines the target push data based on the current push data, the first number of currently online first-type users, the second number of currently online second-type users, the target push count, and a first preset method: It determines a first product of a first push probability and a first quantity, and a second product of a second push probability and a second quantity. In response to the sum of the first and second products equaling the target push count, the first push probability is determined as a first target push probability, and the second push probability is determined as a second target push probability. In response to the sum of the first and second products being less than the target push count, the first push probability is increased, and a third product of the increased first push probability and the first quantity is determined, until the sum of the third and second products equals the target push count. The increased first push probability is then determined as the first target push probability, and the second push probability is determined as the second target push probability. In response to the fact that the sum of the first product and the second product is greater than the target number of pushes, the second push probability is reduced, and the fourth product of the reduced second push probability and the second number is determined until the sum of the fourth product and the first product equals the target number of pushes. The reduced second push probability is then determined as the second target push probability, and the first push probability is determined as the first target push probability.

[0139] In one embodiment, the push unit 104 determines the target traffic data for a target time period as follows: Based on first historical traffic data and using a preset model, data fitting is performed on the target time period to obtain fitted traffic data corresponding to the target time period. The first historical traffic data includes traffic data corresponding to different time periods within a first cycle from the target time period. Second historical traffic data for a historical time period is determined, and the historical time period is fitted using the preset model to obtain historical fitted traffic data corresponding to the historical time period. The historical time period is the time period from 0:00 on the current day to a preset time interval before the current time period. The fitted traffic data is adjusted according to the difference ratio between the second historical traffic data and the historical fitted traffic data to obtain the target traffic data.

[0140] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0141] Figure 16 This is a block diagram illustrating an apparatus 200 for media content recommendation according to an exemplary embodiment. The apparatus 200 can be provided as a terminal. For example, the apparatus 200 can be a mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical device, fitness device, personal digital assistant, etc.

[0142] Reference Figure 16The device 200 may include one or more of the following components: processing component 202, memory 204, power component 206, multimedia component 208, audio component 210, input / output (I / O) interface 212, sensor component 214, and communication component 216.

[0143] Processing component 202 typically controls the overall operation of device 200, such as operations associated with display, telephone calls, data communication, camera operation, and recording. Processing component 202 may include one or more processors 220 to execute instructions to perform all or part of the steps of the methods described above. Furthermore, processing component 202 may include one or more modules to facilitate interaction between processing component 202 and other components. For example, processing component 202 may include a multimedia module to facilitate interaction between multimedia component 208 and processing component 202.

[0144] Memory 204 is configured to store various types of data to support the operation of device 200. Examples of such data include instructions for any application or method operating on device 200, contact data, phonebook data, messages, pictures, videos, etc. Memory 204 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0145] The power supply component 206 provides power to the various components of the device 200. The power supply component 206 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power to the device 200.

[0146] Multimedia component 208 includes a screen that provides an output interface between the device 200 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of the touch or swipe action but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 208 includes a front-facing camera and / or a rear-facing camera. When the device 200 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or the rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0147] Audio component 210 is configured to output and / or input audio signals. For example, audio component 210 includes a microphone (MIC) configured to receive external audio signals when device 200 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 204 or transmitted via communication component 216. In some embodiments, audio component 210 also includes a speaker for outputting audio signals.

[0148] I / O interface 212 provides an interface between processing component 202 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0149] Sensor assembly 214 includes one or more sensors for providing status assessments of various aspects of device 200. For example, sensor assembly 214 may detect the on / off state of device 200, the relative positioning of components such as the display and keypad of device 200, changes in the position of device 200 or a component of device 200, the presence or absence of user contact with device 200, the orientation or acceleration / deceleration of device 200, and temperature changes of device 200. Sensor assembly 214 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 214 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 214 may also include an accelerometer, a gyroscope, a magnetometer, a pressure sensor, or a temperature sensor.

[0150] Communication component 216 is configured to facilitate wired or wireless communication between device 200 and other devices. Device 200 can access wireless networks based on communication standards, such as WiFi, 2G, or 3G, or combinations thereof. In one exemplary embodiment, communication component 216 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 216 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0151] In an exemplary embodiment, the apparatus 200 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the methods described above.

[0152] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 204 including instructions, which can be executed by a processor 220 of the device 200 to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0153] Figure 17 This is a block diagram illustrating an apparatus 300 for media content recommendation according to an exemplary embodiment. For example, apparatus 300 may be provided as a server. (Refer to...) Figure 17 The device 300 includes a processing component 322, which further includes one or more processors, and memory resources represented by memory 332 for storing instructions, such as application programs, that can be executed by the processing component 322. The application programs stored in memory 332 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 322 is configured to execute instructions to perform the aforementioned media content recommendation method.

[0154] Device 300 may also include a power supply component 326 configured to perform power management of device 300, a wired or wireless network interface 350 configured to connect device 300 to a network, and an input / output (I / O) interface 358. Device 300 may operate on an operating system stored in memory 332, such as Windows Server™, MacOSX™, Unix™, Linux™, FreeBSD™, or similar.

[0155] It is understood that in this disclosure, "multiple" refers to two or more, and other quantifiers are similar. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. The singular forms "a," "the," and "the" are also intended to include the plural forms unless the context clearly indicates otherwise.

[0156] It is further understood that the terms "first," "second," etc., are used to describe various types of information, but this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another, and do not indicate a specific order or degree of importance. In fact, the expressions "first," "second," etc., are completely interchangeable. For example, without departing from the scope of this disclosure, first information can also be referred to as second information, and similarly, second information can also be referred to as first information.

[0157] It is further understood that the terms “center,” “longitudinal,” “lateral,” “front,” “rear,” “up,” “down,” “left,” “right,” “vertical,” “horizontal,” “top,” “bottom,” “inner,” and “outer,” etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this embodiment and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation.

[0158] It can be further understood that, unless otherwise specified, "connection" includes both direct connections where no other components exist between the two parties and indirect connections where other components exist between them.

[0159] It is further understood that although operations are described in a specific order in the accompanying drawings in the embodiments of this disclosure, this should not be construed as requiring these operations to be performed in the specific order or serial order shown, or requiring all of the shown operations to be performed to obtain the desired result. In certain environments, multitasking and parallel processing may be advantageous.

[0160] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein.

[0161] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A media content recommendation method, characterized by, The method comprises: obtaining a content value score of first media content and obtaining related data of the first media content, the first media content comprising a plurality of media content, the content value score representing the comprehensive quality of the media content, and the related data representing the popularity of the media content; determining first recommendation data according to the content value score of the first media content and the related data of the first media content, the first recommendation data comprising a push priority of the first media content; determining second recommendation data according to the first recommendation data and a received control instruction, the second recommendation data comprising a push priority of second media content, the control instruction being used to adjust the push priority of the first media content, and the second media content being different from the first media content and comprising a plurality of media content; determining target media content according to the push priority of the second media content and a preset priority threshold; performing data fitting on a target time period based on first historical traffic data through a preset model to obtain fitting traffic data corresponding to the target time period, the first historical traffic data comprising traffic data corresponding to different time periods within a first period from the target time period, determining second historical traffic data of a historical time period, and performing data fitting on the historical time period through the preset model to obtain historical fitting traffic data corresponding to the historical time period, the historical time period being a time period between 0 o'clock of the current day and a preset time interval before the current time period, adjusting the fitting traffic data according to a difference ratio between the second historical traffic data and the historical fitting traffic data to obtain target traffic data, and the target time period being a next time period adjacent to the current time period; determining a target recommendation number corresponding to the target traffic data according to a corresponding relationship between traffic data and push numbers; determining target push data according to current push data, a first number of first type users currently online, a second number of second type users currently online, the target recommendation number, and a first preset mode, wherein the current push data comprises a first push probability corresponding to the first type users and a second push probability corresponding to the second type users, the target push data comprises a first target push probability corresponding to the first type users and a second target push probability corresponding to the second type users, the first type users are users interested in the target media content, and the second type users are users not interested in the media content; pushing the target media content to the first type users and the second type users according to the target push data; wherein the method further comprises: setting first preset media content based on the control instruction and setting a priority for the first preset media content, the first preset media content being different from the first media content; and / or removing, in the first recommendation data, recommendation data corresponding to second preset media content, the first media content comprising the second preset media content.

2. The method of claim 1, wherein, The method further comprises: For each of the plurality of media contents in the first media content, determine a content label, traffic data and heat data of the media content; According to the content label, determine a first value score of the media content, the first value score representing the content quality of the media content, according to the traffic data, determine a second value score of the media content, the second value score representing the platform traffic occupied by the media content, and according to the heat data, determine a third value score of the media content, the second value score representing the online heat of the media content; The sum of the first value score, the second value score and the third value score is determined as the content value score of the media content.

3. The method of claim 1, wherein, The related data of the first media content includes one or more of the following data: the playback penetration rate of the media content, the paid conversion rate of the media content or the user payment data of the media content under the condition of pushing a preset number of times.

4. The method of claim 1, wherein, The target pushing data is determined according to the current pushing data, the first number of the first type of users currently online, the second number of the second type of users currently online, the target recommendation number and the first preset mode, comprising: Determine the first product of the first pushing probability and the first number, and determine the second product of the second pushing probability and the second number; In response to the sum of the first product and the second product being equal to the target recommendation number, the first pushing probability is determined as the first target pushing probability, and the second pushing probability is determined as the second target pushing probability; In response to the sum of the first product and the second product being less than the target recommendation number, the first pushing probability is increased, and the third product of the increased first pushing probability and the first number is determined until the sum of the third product and the second product is equal to the target recommendation number, the increased first pushing probability is determined as the first target pushing probability, and the second pushing probability is determined as the second target pushing probability; In response to the sum of the first product and the second product being greater than the target recommendation number, the second pushing probability is reduced, and the fourth product of the reduced second pushing probability and the second number is determined until the sum of the fourth product and the first product is equal to the target recommendation number, the reduced second pushing probability is determined as the second target pushing probability, and the first pushing probability is determined as the first target pushing probability.

5. A media content recommendation apparatus, characterized by, Comprising: An acquisition unit is configured to acquire a content value score of a first media content and acquire related data of the first media content, the first media content comprising a plurality of media contents, the content value score representing the comprehensive quality of the media content, and the related data representing the popularity of the media content; A determination unit is configured to determine first recommendation data according to the content value score of the first media content and the related data of the first media content, the first recommendation data comprising a pushing priority of the first media content; The processing unit is configured to determine second recommendation data according to the first recommendation data and a received control instruction, the second recommendation data including a push priority of second media content, the control instruction being used to adjust the push priority of the first media content, and the second media content being different from the first media content and including a plurality of media content. The push unit is configured to determine target media content according to the push priority of the second media content and a preset priority threshold, perform data fitting on a target time period based on first historical traffic data corresponding to different time periods within a first period from the target time period by using a preset model, obtain fitting traffic data corresponding to the target time period, determine second historical traffic data of a historical time period, and perform data fitting on the historical time period by using the preset model to obtain historical fitting traffic data corresponding to the historical time period, the historical time period being a time period between 0 o'clock of the current day and a preset time interval before the current time period, adjust the fitting traffic data according to a difference ratio between the second historical traffic data and the historical fitting traffic data to obtain target traffic data, and the target time period being a next time period adjacent to the current time period. The target recommendation number corresponding to the target traffic data is determined according to a correspondence between traffic data and a push number. The target push data is determined according to current push data, a first number of first-type users currently online, a second number of second-type users currently online, the target recommendation number, and a first preset manner, the current push data including a first push probability corresponding to the first-type users and a second push probability corresponding to the second-type users, the target push data including a first target push probability corresponding to the first-type users and a second target push probability corresponding to the second-type users, the first-type users being users interested in the target media content, and the second-type users being users not interested in the media content. The target media content is pushed to the first-type users and the second-type users according to the target push data. The processing unit is further configured to set first preset media content based on the control instruction, set a priority for the first preset media content, the first preset media content being different from the first media content, and remove, in the first recommendation data, recommendation data corresponding to second preset media content, the first media content including the second preset media content.

6. An electronic device, comprising: The processor is configured to perform the media content recommendation method in any one of claims 1 to 4. The storage medium stores instructions, and when the instructions in the storage medium are executed by the processor, the processor can perform the media content recommendation method in any one of claims 1 to 4. The storage medium stores instructions, and when the instructions in the storage medium are executed by the processor, the processor can perform the media content recommendation method in any one of claims 1 to 4. ​ 7. A storage medium, characterized by ​

Images