Method and apparatus for pushing television playing content, and electronic device and medium

Abstract

Disclosed in the present invention are a method and apparatus for pushing television playing content, and an electronic device and a medium. The method comprises: acquiring recommendation data of a television viewport exposure recommendation position, and performing data feature extraction processing, so as to obtain playing content feature data; assigning weights to the playing content feature data, and constructing a television playing content reporting contribution degree value and a television playing content viewing contribution degree value; collecting user viewing content behavior data, and determining a user dynamic operation recommendation degree coefficient; and performing weighted calculation processing on the television playing content reporting contribution degree value, the television playing content viewing contribution degree value and the user dynamic operation recommendation degree coefficient, and updating the recommendation data of the television viewport exposure recommendation position on the basis of a calculation result. The present invention can improve the configuration efficiency and a trending content updating speed, and push content in real time on the basis of changes in terms of user interests, thereby improving the user experience, and the present invention can be widely used in the technical field of network television service recommendation.

Description

Method, device, electronic device and medium for pushing television broadcast content Technical Field

[0001] The present invention relates to the technical field of network television service recommendation, and in particular to a method, device, electronic device and medium for pushing television broadcast content. Background Art

[0002] Interactive Internet Television (IPTV) is a new technology that uses broadband networks to integrate Internet, multimedia, communications and other technologies to provide home users with a variety of interactive services including digital television. It provides a more personalized, real-time and high-definition viewing experience, and can also recommend program content information based on users' viewing preferences in real time. At this stage, the relevant technologies mainly use manual configuration by product business personnel and simple recommendation strategies for similar content based on users' favorites or historical data of viewing and clicking.

[0003] The existing TV content recommendation method based on manual configuration by product business personnel actually makes recommendations based on the layout content information of TV programs. It mainly recommends TV program content by analyzing the layout, color, font, picture and other visual elements of TV programs, as well as text information such as program type, theme, emotion, etc. However, since the layout content is manually configured by business personnel, the configuration efficiency is low, hot spots are not updated in a timely manner, the recommended content is narrow, and the content is outdated. The program content seen by users is basically the same, and users are tired of watching it. At the same time, new or high-quality content cannot be presented to users in a timely and efficient manner, and user perception is poor.

[0004] Existing strategies that recommend similar content based on user favorites or historical data, such as viewing and clickthrough data, mostly focus on similar content or the same genre. While these historical records represent user interests to a certain extent, they also limit recommended content and products to that specific niche. This can lead to users receiving information that is too limited, or recommendations that are repetitive of content they've already viewed, failing to elicit new user needs or cultivate new interests.

[0005] Therefore, the relevant technologies have at least the following problems: the data configuration efficiency is low and the type of user interest data obtained is relatively single, resulting in the inability to better perform accurate and real-time content information recommendations, thereby reducing the user experience. Summary of the Invention

[0006] The present invention aims to at least partially address one of the technical problems in the related art. To this end, the present invention provides a method, apparatus, electronic device, and medium for pushing television content, which can improve configuration efficiency and the speed of hotspot updates, and can push content in real time based on user interests, thereby enhancing the user experience.

[0007] In one aspect, an embodiment of the present invention provides a method for pushing television broadcast content, comprising:

[0008] Obtaining recommendation data for the TV viewport exposure recommendation position and performing data feature extraction processing to obtain playback content feature data, the playback content feature data including TV viewport recommendation position exposure data, TV viewport recommendation position focus data, and user behavior data, the user behavior data including the number of clicks on the TV playback content, the TV playback content viewing time data, and the number of TV playback content subscriptions;

[0009] Weighting the feature data of the broadcast content to construct the contribution value of the reported TV broadcast content and the contribution value of the TV broadcast content viewing;

[0010] Collect user viewing behavior data and determine the user dynamic operation recommendation coefficient;

[0011] Perform weighted calculations on the reported contribution value of TV content, the contribution value of TV content viewing, and the user dynamic operation recommendation coefficient, and update the recommendation data of the TV viewport exposure recommendation position based on the calculation results.

[0012] Optionally, obtaining recommendation data of the TV viewport exposure recommendation position and performing data feature extraction processing to obtain playback content feature data includes:

[0013] Collect recommendation data for TV viewport exposure recommendation positions;

[0014] Cleaning and deduplicating the recommended data of the TV viewport exposure recommendation position to obtain pre-processed recommended data of the TV viewport exposure recommendation position;

[0015] Feature extraction processing is performed based on the pre-processed recommendation data of the TV viewport exposure recommendation position to obtain playback content feature data.

[0016] Optionally, weighting is performed on the content feature data to construct a TV content reporting contribution value and a TV content viewing contribution value, including:

[0017] Determine the percentage of the playback content feature data within a preset period frequency based on the playback content feature data;

[0018] Determine the weights corresponding to the playback content feature data, where the weights of the playback content feature data include the weights of the exposure data of the TV viewport recommendation position, the weights of the out-of-focus data of the TV viewport recommendation position, and the weights of the user behavior data;

[0019] By combining the weight of the broadcast content feature data and the proportion of the broadcast content feature data, the contribution value of TV broadcast content reporting and the contribution value of TV broadcast content viewing are constructed.

[0020] Optionally, the calculation expression for the contribution value of the TV broadcast content report is: E a =(Age1*P1+Age2*P2+Age3*P3)*t

[0021] In the above formula, E a It represents the contribution value of TV content reporting, Age1 represents the exposure data ratio of TV viewport recommendation position, Age2 represents the out-of-focus data ratio of TV viewport recommendation position, Age3 represents the number of clicks on TV content, P1 represents the exposure data weight of TV viewport recommendation position, P2 represents the out-of-focus data weight of TV viewport recommendation position, P3 represents the click weight of TV content, and t represents the preset cycle frequency.

[0022] Optionally, the calculation expression of the TV broadcast content viewing contribution value is: E b =(Age4+Age5)*P4*t

[0023] In the above formula, E b It represents the contribution value of TV content viewing, Age4 represents the proportion of TV content viewing time data, Age5 represents the proportion of TV content subscription times, P4 represents the weight of TV content viewing time data and the weight of TV content subscription times, and t represents the preset cycle frequency.

[0024] Optionally, collecting user content viewing behavior data and determining the user dynamic operation recommendation coefficient includes:

[0025] Collecting user viewing behavior data, including TV content classification data, cast and crew data, and business type data;

[0026] Performing data cleaning and deduplication processing on the user's content viewing behavior data to obtain pre-processed user content viewing behavior data;

[0027] Determine the proportion of user content viewing behavior data within a preset period frequency based on the pre-processed user content viewing behavior data;

[0028] Determine the corresponding user content viewing behavior data coefficient based on the user content viewing behavior data ratio;

[0029] The user dynamic operation recommendation coefficient is determined based on the user content viewing behavior data coefficient and the user content viewing behavior data proportion.

[0030] Optionally, a weighted calculation is performed on the reported contribution value of the TV broadcast content, the TV broadcast content viewing contribution value, and the user dynamic operation recommendation coefficient, and the recommendation data of the TV viewport exposure recommendation position is updated according to the calculation result, including:

[0031] Performing weighted calculations on the reported contribution value of TV content, the TV content viewing contribution value, and the user dynamic operation recommendation coefficient to obtain a calculation result;

[0032] Constructing preset exposure factor thresholds;

[0033] Select the TV broadcast content corresponding to the calculated result being greater than the preset exposure coefficient threshold, and update the recommended data of the TV viewport exposure recommendation position.

[0034] On the other hand, an embodiment of the present invention provides a device for pushing television broadcast content, including:

[0035] The first module is used to obtain recommendation data of the TV viewport exposure recommendation position and perform data feature extraction processing to obtain playback content feature data. The playback content feature data includes TV viewport recommendation position exposure data, TV viewport recommendation position focus data, and user behavior data. The user behavior data includes the number of clicks on the TV playback content, the viewing time of the TV playback content, and the number of subscriptions to the TV playback content.

[0036] The second module is used to assign weights to the feature data of the broadcast content and construct the contribution value of the reported TV broadcast content and the contribution value of the TV broadcast content viewing;

[0037] The third module is used to collect user viewing behavior data and determine the user dynamic operation recommendation coefficient;

[0038] The fourth module is used to perform weighted calculation processing on the contribution value reported by TV broadcast content, the contribution value of TV broadcast content viewing and the user dynamic operation recommendation coefficient, and update the recommendation data of the TV viewport exposure recommendation position according to the calculation results.

[0039] Optionally, the first module is specifically configured to:

[0040] Collect recommendation data for TV viewport exposure recommendation positions;

[0041] Cleaning and deduplicating the recommended data of the TV viewport exposure recommendation position to obtain pre-processed recommended data of the TV viewport exposure recommendation position;

[0042] Feature extraction processing is performed based on the pre-processed recommendation data of the TV viewport exposure recommendation position to obtain playback content feature data.

[0043] Optionally, the second module is specifically configured to:

[0044] Determine the percentage of the playback content feature data within a preset period frequency based on the playback content feature data;

[0045] Determine the weights corresponding to the playback content feature data, where the weights of the playback content feature data include the weights of the exposure data of the TV viewport recommendation position, the weights of the out-of-focus data of the TV viewport recommendation position, and the weights of the user behavior data;

[0046] Combining the weight of the broadcast content feature data and the proportion of the broadcast content feature data, construct the TV broadcast content reporting contribution value and the TV broadcast content viewing contribution value;

[0047] The calculation expression of the contribution value of TV broadcast content reporting is: E a =(Age1*P1+Age2*P2+Age3*P3)*t

[0048] In the above formula, E a Indicates the contribution value of TV content reported, Age1 indicates the exposure data ratio of TV viewport recommendation position, Age2 indicates the focus data ratio of TV viewport recommendation position, Age3 indicates the number of clicks on TV content, P1 indicates the exposure data weight of TV viewport recommendation position, P2 indicates the focus data weight of TV viewport recommendation position, P3 indicates the number of clicks on TV content, and t indicates the preset cycle frequency;

[0049] The calculation expression of the TV broadcast content ratings contribution value is: E b =(Age4+Age5)*P4*t

[0050] In the above formula, E b It represents the contribution value of TV content viewing, Age4 represents the proportion of TV content viewing time data, Age5 represents the proportion of TV content subscription times, P4 represents the weight of TV content viewing time data and the weight of TV content subscription times, and t represents the preset cycle frequency.

[0051] Optionally, the third module is specifically configured to:

[0052] Collecting user viewing behavior data, including TV content classification data, cast and crew data, and business type data;

[0053] Performing data cleaning and deduplication processing on the user's content viewing behavior data to obtain pre-processed user content viewing behavior data;

[0054] Determine the proportion of user content viewing behavior data within a preset period frequency based on the pre-processed user content viewing behavior data;

[0055] Determine the corresponding user content viewing behavior data coefficient based on the user content viewing behavior data ratio;

[0056] The user dynamic operation recommendation coefficient is determined based on the user content viewing behavior data coefficient and the user content viewing behavior data proportion.

[0057] Optionally, the fourth module is specifically configured to:

[0058] Performing weighted calculations on the reported contribution value of TV content, the TV content viewing contribution value, and the user dynamic operation recommendation coefficient to obtain a calculation result;

[0059] Constructing preset exposure factor thresholds;

[0060] Select the TV broadcast content corresponding to the calculated result being greater than the preset exposure coefficient threshold, and update the recommended data of the TV viewport exposure recommendation position.

[0061] On the other hand, an embodiment of the present invention provides an electronic device, including: a processor and a memory; the memory is used to store programs; the processor executes the program to implement the above-mentioned method for pushing television playback content.

[0062] On the other hand, an embodiment of the present invention provides a computer storage medium storing a program executable by a processor. The program executable by the processor is used to implement the above-mentioned method for pushing television playback content when executed by the processor.

[0063] The beneficial effects of the method, device, electronic device and medium of the present invention are as follows: first, by obtaining the recommendation data of the TV viewport exposure recommendation position and performing data feature extraction processing, the playback content feature data is obtained, wherein the playback content feature data includes the TV viewport recommendation position exposure data, the TV viewport recommendation position focus data and the user behavior data. The embodiment of the present invention changes the existing point reporting to surface reporting, expands the user behavior data surface, and then obtains the interest type and non-interest type of the current user, perceives and predicts the behavior data of three types of users, thereby improving the user's perception, further performs weighting processing on the playback content feature data, constructs the TV playback content reporting contribution value and the TV playback content viewing contribution value, and determines the user dynamic operation recommendation coefficient. The embodiment of the present invention is through By weighting the number of times the recommendation position of the page that users browse is exposed and the number of times the user is focused on the content of the recommendation position on the page, the user's new content demand direction is predicted, and the data stream display of new content is pushed based on this, which improves the configuration efficiency and the speed of hot spot updates and expands the recommended content. It can also push content in real time according to the changes in user interests, that is, make more accurate content recommendations by enriching the type of user interest data. Finally, a weighted calculation is performed on the contribution value reported for TV broadcast content, the contribution value for TV broadcast content ratings and the user dynamic operation recommendation coefficient, and the recommendation data of the TV viewport exposure recommendation position is updated according to the calculation results. The content is presented by combining the recommendation flow with the dynamic board layout, which improves the timeliness of content recommendations and enhances the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] The accompanying drawings are used to provide a further understanding of the technical solution of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the technical solution of the present invention and do not constitute a limitation to the technical solution of the present invention.

[0065] FIG1 is a schematic diagram of an implementation environment for pushing television broadcast content provided by an embodiment of the present invention;

[0066] 2 is a schematic flow chart of a method for pushing television broadcast content according to an embodiment of the present invention;

[0067] 3 is a schematic diagram of a flow chart of combined weight determination of a television content push strategy according to an embodiment of the present invention;

[0068] FIG4 is a schematic diagram of a process for performing data feature extraction processing according to an embodiment of the present invention;

[0069] FIG5 is a schematic diagram of a flow chart of a weight assignment process according to an embodiment of the present invention;

[0070] FIG6 is a schematic diagram of a process for determining a user dynamic operation recommendation coefficient according to an embodiment of the present invention;

[0071] FIG7 is a schematic diagram of a flow chart of weighted calculation processing according to an embodiment of the present invention;

[0072] FIG8 is a schematic structural diagram of a device for pushing television broadcast content provided by an embodiment of the present invention;

[0073] FIG9 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention;

[0074] FIG10 is a block diagram of a computer system structure of an electronic device suitable for implementing an embodiment of the present invention, provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0075] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0076] It should be noted that although the system diagrams illustrate functional module divisions and the flowcharts illustrate a logical sequence, in certain circumstances, the steps shown or described may be performed in a sequence that differs from the module divisions in the system or the sequence in the flowcharts. The terms "first / S100," "second / S200," and the like in the specification, claims, and drawings are used to distinguish similar objects and are not necessarily intended to describe a specific sequence or precedence.

[0077] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0078] It is understandable that the push method for television broadcast content provided in the embodiment of the present invention can be applied to any computer device with data processing and computing capabilities, and this computer device can be various terminals or servers. When the computer device in the embodiment is a server, the server is an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. Optionally, the terminal is a smart phone, tablet computer, laptop computer, desktop computer, etc., but is not limited to this.

[0079] FIG1 is a schematic diagram of an implementation environment provided by an embodiment of the present invention. Referring to FIG1 , the implementation environment includes at least one terminal 102 and a server 101. The terminal 102 and the server 101 can be connected to a network wirelessly or wired to complete data transmission and exchange.

[0080] Server 101 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), as well as big data and artificial intelligence platforms.

[0081] In addition, server 101 can also be a node server in a blockchain network. Blockchain is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, and encryption algorithm.

[0082] The terminal 102 may be a smart phone, tablet computer, laptop computer, desktop computer, smart speaker, smart watch, etc., but is not limited thereto. The terminal 102 and the server 101 may be connected directly or indirectly via wired or wireless communication, which is not limited in this embodiment of the present invention.

[0083] Exemplarily based on the implementation environment shown in Figure 1, an embodiment of the present invention provides a method for pushing television broadcast content. The following is explained using the example of the method for pushing television broadcast content applied to the server 101. It can be understood that the method for pushing television broadcast content can also be applied to the terminal 102.

[0084] Referring to FIG2 , FIG2 is a flowchart of a method for pushing television broadcast content applied to a server according to an embodiment of the present invention. The execution subject of the method for pushing television broadcast content can be any of the aforementioned computer devices. Referring to FIG2 , the method includes the following steps:

[0085] S100: Obtain recommendation data for the TV viewport exposure recommendation position and perform data feature extraction processing to obtain playback content feature data, wherein the playback content feature data includes TV viewport recommendation position exposure data, TV viewport recommendation position focus data, and user behavior data. The user behavior data includes the number of clicks on the TV playback content, the viewing time of the TV playback content, and the number of subscriptions to the TV playback content.

[0086] It should be noted that, in some embodiments, as shown in FIG4 , step S100 may include: S101, collecting recommendation data of the TV viewport exposure recommendation position; S102, cleaning and deduplicating the recommendation data of the TV viewport exposure recommendation position to obtain pre-processed recommendation data of the TV viewport exposure recommendation position; S103, performing feature extraction processing based on the pre-processed recommendation data of the TV viewport exposure recommendation position to obtain playback content feature data.

[0087] In some specific embodiments, the recommended data of the TV viewport exposure recommendation position can be collected by an acquisition device, wherein the acquisition device can be composed of a PCMCIA interface and a data transmission module interconnected with the set-top box and the CAM. The PCMCIA interface in the embodiment of the present invention is connected to the PCMCIA mother slot of the digital TV device, and the PCMCIA interface of the CAM card is connected to the PCMCIA interface in the embodiment of the present invention to achieve interconnection and intercommunication between the three. The collected data is reported to the control end by the data transmission module (such as USB, network card) to obtain the recommended data of the TV viewport exposure recommendation position.

[0088] In some specific embodiments, first, the recommendation data of the TV viewport exposure recommendation position is read, which can be done using appropriate programming languages ​​and libraries, such as using Python's pandas library to read CSV files or SQL databases. Further data cleaning is performed. Before performing data deduplication processing, data cleaning is required. The embodiments of the present invention include processing missing values, deleting duplicate values, checking abnormal values, etc. Then, data deduplication processing is performed. After data cleaning, deduplication processing can be started. For the recommendation data of the TV viewport exposure recommendation position, there may be duplicate recommendation items. For example, the same program or advertisement is recommended multiple times in the same time period. The deduplication function in the programming language or the deduplication operation in the database can be used to delete these duplicate items. Finally, the deduplication processing is completed, and the cleaned and deduplicated data is stored in a file or database. You can also choose to visualize the results to better understand the data and discover patterns.

[0089] In some specific embodiments, a feature extraction method is selected, and the feature extraction method includes statistical methods, machine learning methods, deep learning, etc. According to the selected feature extraction method, different features are extracted from the recommendation data. For example, the ratings of the program, the age and gender distribution of the audience, the viewing time, etc. can be extracted as features. In addition, the extraction of time series features can also be considered, such as the time series pattern of recommendations, the viewing behavior of the audience, etc. In a specific embodiment of the present invention, the exposure data of the recommended position of the TV viewport, the focus data of the recommended position of the TV viewport, and the user behavior data are used as the extracted playback content feature data, wherein the user behavior data includes the number of clicks on the TV playback content, the viewing time data of the TV playback content, and the number of subscriptions to the TV playback content.

[0090] It should be noted that, in a specific embodiment of the present invention, the TV viewport recommendation position exposure data indicates the number of exposures triggered by the TV viewport to the content during the evaluation period, the TV viewport recommendation position focus data indicates the number of times the cursor is focused on the content triggered by the TV viewport during the evaluation period, the number of clicks on the TV content, that is, the number of times the user clicks on the recommendation position, indicates the number of clicks triggered on the content during the evaluation period, the TV content viewing time data indicates the total viewing time of the user for the content during the evaluation period, and the number of TV content subscriptions indicates the number of subscriptions to the content triggered by the content during the evaluation period.

[0091] Furthermore, it should be noted that the TV viewport recommendation position means that on the TV screen, the recommendation position is set to different exposure time and position for different audience groups and different time periods to achieve better recommendation effect. The TV viewport exposure recommendation position can be divided into the top recommendation position, which is located at the top of the TV screen and is generally used to recommend the most important programs or advertisements with a longer exposure time; the side recommendation position, which is located on the side of the TV screen and is generally used to recommend less important programs or advertisements with a shorter exposure time; the bottom recommendation position, which is located at the bottom of the TV screen and is generally used to recommend some minor programs or advertisements with a shorter exposure time. The recommendation position refers to the content units seen on TV, and each recommendation position can be configured with a content resource. The out-of-focus data refers to a state data of the cursor staying on each recommendation position.

[0092] S200: Weighting the content feature data to construct a TV content reporting contribution value and a TV content viewing contribution value;

[0093] It should be noted that, in some embodiments, as shown in Figure 5, step S200 may include: S201, determining the proportion of playback content feature data within a preset periodic frequency based on the playback content feature data; S202, determining the weight corresponding to the playback content feature data, the weight of the playback content feature data including the weight of the TV viewport recommended position exposure data, the weight of the TV viewport recommended position out-of-focus data and the weight of the user behavior data; S203, combining the weight of the playback content feature data and the proportion of the playback content feature data to construct a TV playback content reporting contribution value and a TV playback content viewing contribution value.

[0094] In some specific embodiments, the preset periodic frequency is determined to be a reasonable time span period, i.e., a week or a month, or a time point dimension, i.e., morning and evening peaks, etc. Further, within the preset periodic frequency, the total number of viewport exposures of all recommended content positions, the total number of focus defocuses of all recommended content positions, the total number of clicks on all recommended content positions, the total viewing time of all content, and the total number of subscriptions for all content are obtained within the entire periodic frequency, and the TV viewport recommended position exposure data, the TV viewport recommended position focus defocus data, the number of clicks on TV content, the TV content viewing time data, and the number of subscriptions for TV content are divided by the corresponding total number, respectively, to further obtain the proportion data on the content, specifically including the proportion of TV viewport recommended position exposure data, the proportion of TV viewport recommended position focus defocus data, the proportion of TV content clicks, the proportion of TV content viewing time data, and the proportion of TV content subscriptions;

[0095] The calculation expression for the exposure data ratio of TV viewport recommendation position is:

[0096] In the above formula, Age1 represents the proportion of exposure data of the recommended position in the TV viewport, ∑N1 represents the total number of exposures of all recommended position content in the viewport, and n1 represents the exposure data of the recommended position in the TV viewport.

[0097] The calculation expression for the proportion of out-of-focus data in the recommended TV viewport position is:

[0098] In the above formula, Age2 represents the proportion of out-of-focus data in the recommended position of the TV viewport, ∑N2 represents the total number of out-of-focus times of all recommended position content viewport exposures, and n2 represents the out-of-focus data of the recommended position of the TV viewport.

[0099] The calculation expression for the percentage of clicks on TV content is:

[0100] In the above formula, Age3 represents the percentage of clicks on TV content, ∑N3 represents the total number of clicks on all recommended content viewports, and n3 represents the number of clicks on TV content.

[0101] The calculation expression for the proportion of TV content viewing time data is:

[0102] In the above formula, Age4 represents the proportion of TV viewing time, ∑N4 represents the total viewing time of all content, and n4 represents the TV viewing time data.

[0103] The calculation expression for the proportion of TV content subscription times is:

[0104] In the above formula, Age5 represents the proportion of TV content subscriptions, ∑N5 represents the total number of all content subscriptions, and n5 represents the number of TV content subscriptions.

[0105] In some specific embodiments, the weight corresponding to the playback content feature data is determined. The weight data of the embodiments of the present invention can be dynamically configured and adjusted according to the user's interests. First, the user's interest level is measured based on the proportion of exposure data of the TV viewport recommendation position, the proportion of out-of-focus data of the TV viewport recommendation position, the proportion of clicks on the TV playback content, the proportion of TV playback content viewing time data and the proportion of TV playback content subscription times to obtain the user's interest level in different categories of TV playback content. According to the user's interest level, the corresponding weight is calculated for each playback content. The weight can be weighted averaged or assigned corresponding weights based on the user's interest level to reflect the user's attention to different parameters. According to the user's interest changes and real-time feedback, the parameter weights are dynamically adjusted. For example, if a user is more interested in a certain category of television content, the parameter weight of this category of products can be increased accordingly to better meet the needs of the user. The adjusted parameter weight can be applied to the algorithm and model to optimize the results of recommendation, search or other related tasks. This can be achieved by modifying the weight parameters in the algorithm or retraining the model, continuously monitoring the system performance and user feedback, and adjusting the parameter weight according to actual conditions. If the system performance is poor or the user is not satisfied with the recommendation results, it is necessary to review the setting of the parameter weight and adjust it accordingly. In this way, the feature data of the playback content is weighted. The weight results include the viewport exposure recommendation position share weight, which refers to the coefficient of the viewport exposure share of the content in the contribution degree; the viewport exposure recommendation position out-of-focus share weight, which refers to the coefficient of the viewport exposure recommendation position out-of-focus share of the content in the contribution degree; the user click content share weight, which refers to the coefficient of the content clicked by the user in the contribution degree; the content viewing time and subscription source share weight, which refers to the coefficient of the content viewing time and subscription source share in the contribution degree.

[0106] In some specific embodiments, the weight of the playback content feature data and the proportion data of the playback content feature data are combined to construct the TV playback content reporting contribution value and the TV playback content viewing contribution value. The TV playback content reporting contribution value is used to understand the user's preference for different programs, which helps to better grasp the user's needs, optimize program content and arrangement, and improve user satisfaction. The contribution value can be used as one of the indicators for program quality evaluation to help the system terminal understand the popularity and effect of the TV program type. The contribution value can be used as one of the reference indicators for predicting ratings. By analyzing historical contribution data, the viewing trend of future programs can be predicted to help better plan programs. The audience contribution value of TV broadcast content is used to understand the audience acceptance and popularity of a certain type of TV content. By analyzing the audience contribution of different programs, we can understand which programs have higher audience attention and ratings, so as to choose a more appropriate advertising strategy. By analyzing historical audience contribution data, we can predict the viewing trend of future programs, so as to better plan program scheduling and adjust broadcast strategies. By analyzing the audience contribution of different TV content, we can understand the audience's needs and preferences for different types of TV content, so as to better grasp audience needs and market trends, and improve TV content quality and user satisfaction.

[0107] The calculation expression of the contribution value of TV broadcast content reporting is: E a =(Age1*P1+Age2*P2+Age3*P3)*t

[0108] In the above formula, E a Indicates the contribution value of TV content reported, Age1 indicates the exposure data ratio of TV viewport recommendation position, Age2 indicates the focus data ratio of TV viewport recommendation position, Age3 indicates the number of clicks on TV content, P1 indicates the exposure data weight of TV viewport recommendation position, P2 indicates the focus data weight of TV viewport recommendation position, P3 indicates the number of clicks on TV content, and t indicates the preset cycle frequency;

[0109] The calculation expression of the TV broadcast content ratings contribution value is: E b =(Age4+Age s )*P4*t

[0110] In the above formula, E b It represents the contribution value of TV content viewing, Age4 represents the proportion of TV content viewing time data, Age5 represents the proportion of TV content subscription times, P4 represents the weight of TV content viewing time data and the weight of TV content subscription times, and t represents the preset cycle frequency.

[0111] It should be noted that, in the embodiment of the present invention, P1+P2+P3+P4=100%.

[0112] S300: Collecting user viewing behavior data and determining the user dynamic operation recommendation coefficient;

[0113] It should be noted that, in some embodiments, as shown in Figure 6, step S300 may include: S301, collecting user content viewing behavior data, the user content viewing behavior data includes TV content classification data, cast data and business type data; S302, performing data cleaning and deduplication processing on the user content viewing behavior data to obtain pre-processed user content viewing behavior data; S303, determining the proportion of user content viewing behavior data within a preset period frequency based on the pre-processed user content viewing behavior data; S304, determining the corresponding user content viewing behavior data coefficient based on the proportion of user content viewing behavior data; S305, determining the user dynamic operation recommendation coefficient based on the user content viewing behavior data coefficient and the proportion of user content viewing behavior data.

[0114] In some embodiments, user viewing behavior data is collected. Television content classification data is the result of classifying and labeling television programs, primarily to facilitate operations such as searching, browsing, and recommending television programs. This classification data typically includes aspects such as program type, theme, style, and audience, and can be generated through various methods, including manual classification and machine learning algorithms. Cast and crew data refers to data related to actors, guests, and hosts associated with a television program. This data may include information such as the actors' names, occupations, acting experience, and filmography, as well as guest background information and the hosts' hosting style and experience. This data helps television stations select appropriate actors and guests when producing programs, improving the quality and appeal of the programs. Service type data refers to data related to television services, including channel type, program production costs, advertising revenue, and ratings. This data can assist television stations in business decision-making and data analysis, such as developing program scheduling plans, adjusting advertising strategies, and evaluating program quality and revenue. By enriching user viewing behavior data, embodiments of the present invention can further and more accurately grasp the types of user interest types and understand changes in user interests in real time, facilitating weight adjustment in step S200.

[0115] In some embodiments, the collected data is preprocessed, including data cleaning, missing value processing, outlier processing, etc. This specific embodiment step is mainly to improve the quality and accuracy of the data; after data preprocessing, data deduplication processing is required. This specific embodiment step is mainly to remove duplicate data records to avoid interference with subsequent analysis; standardize the data and normalize different types of data to make different types of data comparable; after data standardization, data conversion can be performed to convert the data into a form suitable for machine learning algorithms to better analyze user behavior; by using machine learning algorithms to mine the deduplicated and converted data, the patterns and trends of users' viewing content are discovered to better understand users' behavior patterns; the mined results are analyzed to derive the characteristics and trends of users' viewing behavior to better understand users' interests and needs.

[0116] In some embodiments, the proportion of user content viewing behavior data within a preset period frequency is determined based on the pre-processed user content viewing behavior data, including the proportion of television content classification data, the proportion of cast and crew data, and the proportion of business type data.

[0117] In some embodiments, the corresponding user content viewing behavior data coefficient is determined based on the proportion of user content viewing behavior data, including the operation configuration content type recommendation coefficient, the operation configuration cast and crew recommendation coefficient, and the operation configuration business classification recommendation coefficient.

[0118] In some embodiments, a user dynamic operation recommendation coefficient is determined based on the coefficient of the user's content viewing behavior data and the proportion of the user's content viewing behavior data. The user dynamic operation recommendation coefficient can evaluate the user's acceptance and satisfaction with the recommended content, and predict the user's future behavior and needs. This coefficient can be calculated and analyzed based on the user's behavior data, preferences, feedback, and other relevant information to help operators better understand user needs and behavior patterns, optimize recommendation algorithms and strategies, and improve user satisfaction and activity. The calculation expression of the user dynamic operation recommendation coefficient is: E c =Age a *P a +Age b *P b +Age c *P c

[0119] In the above formula, E c Indicates the user dynamic operation recommendation coefficient, Age a Indicates the percentage of TV content classification data, Age b Indicates the proportion of cast and crew data, Age cIndicates the proportion of business type data, P a represents the recommendation coefficient of the operation configuration content type, P b represents the recommendation coefficient of the operational configuration cast and crew, P c Indicates the recommendation coefficient of the operation configuration business classification.

[0120] It should be noted that, in the embodiment of the present invention, P a +P b +P c =100%.

[0121] S400: Perform weighted calculation processing on the reported contribution value of the TV broadcast content, the TV broadcast content viewing contribution value, and the user dynamic operation recommendation coefficient, and update the recommended data of the TV viewport exposure recommendation position based on the calculation result;

[0122] It should be noted that, in some embodiments, as shown in FIG7 , step S400 may include: S401, performing weighted calculation processing on the reported contribution value of the TV broadcast content, the TV broadcast content viewing contribution value, and the user dynamic operation recommendation coefficient to obtain a calculation result; S402, constructing a preset exposure coefficient threshold; S403, selecting the TV broadcast content corresponding to the calculation result being greater than the preset exposure coefficient threshold, and updating the recommendation data of the TV viewport exposure recommendation position.

[0123] In some specific embodiments, a weighted calculation is performed on the reported contribution value of television content, the viewing contribution value of television content, and the user dynamic operation recommendation coefficient, and an exposure coefficient threshold is set. The exposure coefficient threshold represents the user's interest in the exposure of the content. A benchmark value can be set based on specific actual scenarios. If the corresponding television content exceeds the exposure coefficient threshold, the user is considered to be interested in the content. If the corresponding television content is below the exposure coefficient threshold, the user is considered not to be completely interested in the content. Further, the weights in step S200 are randomly adjusted based on this, achieving the recommendation of television content based on changes in user interest types and updating the recommendation data of the television viewport exposure recommendation position. For each television content, its exposure coefficient is calculated based on its relevant data and algorithm model. This coefficient can reflect the exposure rate and attention of the content in the television market. The television content that meets the conditions is screened, and based on the calculation results, the television content with an exposure coefficient greater than the preset exposure coefficient threshold is screened. These contents may have higher exposure value and attention, and are suitable for further recommendation and promotion. Update the recommendation data of the TV viewport exposure recommendation position. For eligible TV broadcast content, update its recommendation data to the TV viewport exposure recommendation position. This data can include relevant information such as program name, cast information, broadcast time, program introduction, etc., so that users can better understand and select content of interest. Continuous monitoring and adjustment: After updating the recommendation data, continue to monitor indicators such as the click-through rate and viewing rate of the TV viewport exposure recommendation position, and adjust and optimize the preset exposure coefficient threshold and recommendation data based on actual conditions.

[0124] It should be noted that when selecting television broadcast content whose calculation results are greater than a preset exposure coefficient threshold, the embodiment of the present invention will further comprehensively consider the accuracy and stability of the data to avoid being affected by outliers and noise. At the same time, the recommended data will be updated and adjusted according to actual conditions to maintain its accuracy and real-time performance.

[0125] In summary, in response to the related problems existing in the prior art, the embodiments of the present invention provide an implementation method that helps to improve the configuration efficiency and the speed of hotspot updates, as well as content pushed in real time according to changes in user interests, thereby enhancing the user experience. By obtaining the recommendation data of the TV viewport exposure recommendation position and performing data feature extraction processing, the playback content feature data is obtained, the existing point reporting is changed to surface reporting, the user behavior data surface is expanded, and then the current user's interest type and non-interest type are obtained, and the behavioral data of three types of users are perceived and predicted, thereby improving the user's perception, and further weighting the playback content feature data is processed, constructing the TV playback content reporting contribution value and the TV playback content viewing contribution value, and determining the user dynamic operation recommendation coefficient, and weighting the number of times the user browses the recommended position of the layout and the number of times the user loses focus on the content of the recommended position of the layout, from It predicts the direction of users' new content needs and uses this to push data stream displays of new content, improves configuration efficiency and the speed of hot spot updates, expands recommended content, and can push content in real time according to changes in users' interests, that is, makes more accurate content recommendations by enriching the types of users' interest data. Finally, it performs weighted calculations on the contribution value reported for TV content, the contribution value for TV content viewing, and the user's dynamic operation recommendation coefficient, and updates the recommendation data of the TV viewport exposure recommendation position based on the calculation results. It presents content by combining recommendation flow with dynamic board layout, improves the timeliness of content recommendations, and enhances user experience.

[0126] On the other hand, as shown in Figure 8, an embodiment of the present invention provides a push device 800 for television broadcast content, including: a first module 810, used to obtain recommendation data of the TV viewport exposure recommendation position and perform data feature extraction processing to obtain broadcast content feature data, the broadcast content feature data including TV viewport recommendation position exposure data, TV viewport recommendation position focus data and user behavior data, the user behavior data including the number of times the TV broadcast content is clicked, the TV broadcast content viewing time data and the number of times the TV broadcast content is subscribed; a second module 820, used to perform weighting processing on the broadcast content feature data, and construct a TV broadcast content reporting contribution value and a TV broadcast content viewing contribution value; a third module 830, used to collect user content viewing behavior data and determine the user dynamic operation recommendation coefficient; a fourth module 840, used to perform weighted calculation processing on the TV broadcast content reporting contribution value, the TV broadcast content viewing contribution value and the user dynamic operation recommendation coefficient, and update the recommendation data of the TV viewport exposure recommendation position according to the calculation result.

[0127] The contents of the method embodiments of the present invention are all applicable to the device embodiments. The functions specifically implemented by the device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0128] On the other hand, as shown in FIG9 , an embodiment of the present invention further provides an electronic device 900 , which includes at least one processor 910 and at least one memory 920 for storing at least one program; taking a processor 910 and a memory 920 as an example.

[0129] The processor 910 and the memory 920 may be connected via a bus or other means.

[0130] The memory 920 is a non-transient computer-readable storage medium that can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory 920 may include a high-speed random access memory and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory 920 may optionally include a memory remotely located relative to the processor, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0131] The electronic device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, i.e., they may be located in one location or distributed across multiple network units. Some or all of these modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0132] Specifically, FIG10 schematically shows a block diagram of a computer system structure of an electronic device for implementing an embodiment of the present invention.

[0133] It should be noted that the computer system 1000 of the electronic device shown in FIG10 is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0134] As shown in Figure 10, the computer system 1000 includes a central processing unit (CPU) 1001, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 1002 or the program loaded from the storage part 1008 into the random access memory (RAM) 1003. Various programs and data required for system operation are also stored in the random access memory 1003. The CPU 1001, the read-only memory 1002, and the random access memory 1003 are connected to each other via a bus 1004. An input / output interface 1005 (i.e., an I / O interface) is also connected to the bus 1004.

[0135] The following components are connected to the input / output interface 1005: an input section 1006 including a keyboard, a mouse, and the like; an output section 1007 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 1008 including a hard disk; and a communication section 1009 including a network interface card such as a local area network card or a modem. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the input / output interface 1005 as needed. Removable media 1011, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 1010 as needed, so that computer programs read therefrom can be installed into the storage section 1008 as needed.

[0136] In particular, according to embodiments of the present invention, the processes described in the various method flow charts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for executing the methods shown in the flow charts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1009 and / or installed from removable media 1011. When executed by central processing unit 1001, the computer program performs the various functions defined in the system of the present invention.

[0137] It should be noted that the computer-readable medium shown in the embodiments of the present invention may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a 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 thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present invention, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0138] The contents of the method embodiments of the present invention are all applicable to the system embodiments. The functions specifically implemented by the system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above methods.

[0139] Another aspect of an embodiment of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement the above method.

[0140] The contents of the method embodiments of the present invention are all applicable to the computer-readable storage medium embodiments. The functions specifically implemented by the computer-readable storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0141] The present invention also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium and execute the computer instructions, causing the computer device to perform the above method.

[0142] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the above-mentioned module, program segment, or a part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0143] It should be noted that although several modules of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more modules or units described above can be concretized in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0144] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present invention.

[0145] In some optional embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided in an exemplary manner for the purpose of providing a more comprehensive understanding of the technology. The disclosed method is not limited to the operation and logic flow presented herein. Optional embodiments are contemplated in which the order of the various operations is changed and the sub-operations described as a part of a larger operation are performed independently.

[0146] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in separate physical devices or software modules. It will also be understood that a detailed discussion of the actual implementation of each module is not necessary for understanding the present invention. More specifically, given the properties, functions, and internal relationships of the various functional modules in the devices disclosed herein, the actual implementation of the module will be understood within the ordinary skill of an engineer. Therefore, a person skilled in the art will be able to implement the present invention as set forth in the claims using ordinary skill without undue experimentation. It will also be understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0147] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.

[0148] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution apparatus, device, or apparatus (e.g., a computer-based apparatus, a device including a processor, or other apparatus that can fetch instructions from and execute instructions on an instruction execution apparatus, device, or apparatus). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution apparatus, device, or apparatus.

[0149] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0150] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution device. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0151] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0152] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the claims and their equivalents.

[0153] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the embodiments. Those skilled in the art can make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. A method for pushing television broadcast content, characterized in that: include: Acquire recommendation data of the TV viewport exposure recommendation position and perform data feature extraction processing to obtain playback content feature data, wherein the playback content feature data includes TV viewport recommendation position exposure data, TV viewport recommendation position focus data and user behavior data, wherein the user behavior data includes the number of times the TV playback content is clicked, the TV playback content viewing time data and the number of times the TV playback content is subscribed; Performing weighting processing on the feature data of the broadcast content to construct a contribution value of the reported TV broadcast content and a contribution value of the TV broadcast content viewing; Collect user viewing behavior data and determine the user dynamic operation recommendation coefficient; A weighted calculation is performed on the reported contribution value of the TV broadcast content, the TV broadcast content viewing contribution value and the user dynamic operation recommendation coefficient, and the recommendation data of the TV viewport exposure recommendation position is updated according to the calculation result.

2. The method for pushing television broadcast content according to claim 1, characterized in that: The acquisition of the recommended data of the TV viewport exposure recommendation position and the data feature extraction process to obtain the playback content feature data includes: Collect recommended data for TV viewport exposure recommendation positions; Cleaning and deduplicating the recommended data of the TV viewport exposure recommended position to obtain pre-processed recommended data of the TV viewport exposure recommended position; Feature extraction processing is performed based on the preprocessed recommendation data of the television viewport exposure recommendation position to obtain the playback content feature data.

3. The method for pushing television broadcast content according to claim 1, characterized in that: The step of performing weighting processing on the feature data of the broadcast content to construct a contribution value of the reported television broadcast content and a contribution value of the viewing television content includes: Determine, according to the playback content characteristic data, the proportion of the playback content characteristic data within a preset periodic frequency; Determine the weight corresponding to the playback content feature data, the weight of the playback content feature data includes the weight of the exposure data of the TV viewport recommendation position, the weight of the out-of-focus data of the TV viewport recommendation position, and the weight of the user behavior data; The weight of the broadcast content feature data and the proportion data of the broadcast content feature data are combined to construct the television broadcast content reporting contribution value and the television broadcast content viewing contribution value.

4. The method for pushing television broadcast content according to claim 3, characterized in that: The calculation expression of the contribution value reported by the TV broadcast content is: a =(Age1*P1+Age2*P2+Age3*P3)*t In the above formula, E a It represents the contribution value reported by TV content, Age1 represents the exposure data ratio of TV viewport recommendation position, Age2 represents the out-of-focus data ratio of TV viewport recommendation position, Age3 represents the number of clicks on TV content, P1 represents the exposure data weight of TV viewport recommendation position, P2 represents the out-of-focus data weight of TV viewport recommendation position, P3 represents the weight of clicks on TV content, and t represents the preset cycle frequency.

5. The method for pushing television broadcast content according to claim 3, characterized in that: The calculation expression of the TV broadcast content viewing contribution value is: b =(Age4+Age5)*P4*t In the above formula, E b It represents the contribution value of TV content viewing, Age4 represents the proportion of TV content viewing time data, Age5 represents the proportion of TV content subscription times, P4 represents the weight of TV content viewing time data and the weight of TV content subscription times, and t represents the preset cycle frequency.

6. The method for pushing television broadcast content according to claim 1, characterized in that: The collecting of user viewing behavior data and determining the user dynamic operation recommendation coefficient includes: Collecting user content viewing behavior data, wherein the user content viewing behavior data includes television content classification data, cast and crew data, and business type data; Performing data cleaning and deduplication processing on the user content viewing behavior data to obtain pre-processed user content viewing behavior data; Determining a proportion of the user content viewing behavior data within the preset periodic frequency according to the preprocessed user content viewing behavior data; Determine a corresponding user content viewing behavior data coefficient according to the user content viewing behavior data proportion; The user dynamic operation recommendation coefficient is determined according to the user content viewing behavior data coefficient and the user content viewing behavior data proportion.

7. The method for pushing television broadcast content according to claim 1, characterized in that: The step of performing weighted calculation processing on the reported contribution value of the TV broadcast content, the TV broadcast content viewing contribution value and the user dynamic operation recommendation coefficient, and updating the recommendation data of the TV viewport exposure recommendation position according to the calculation result, includes: Performing weighted calculation processing on the reported contribution value of the television broadcast content, the television broadcast content viewing contribution value and the user dynamic operation recommendation coefficient to obtain a calculation result; Constructing preset exposure factor thresholds; The television broadcast content corresponding to the calculated result being greater than the preset exposure coefficient threshold is selected, and the recommendation data of the television viewport exposure recommendation position is updated.

8. A device for pushing TV broadcast content, characterized in that: include: The first module is used to obtain the recommendation data of the TV viewport exposure recommendation position and perform data feature extraction processing to obtain the playback content feature data, wherein the playback content feature data includes the TV viewport recommendation position exposure data, the TV viewport recommendation position focus data and the user behavior data, wherein the user behavior data includes the number of times the TV playback content is clicked, the TV playback content viewing time data and the number of times the TV playback content is subscribed; The second module is used to perform weighting processing on the feature data of the broadcast content, and construct a contribution value of the reported TV broadcast content and a contribution value of the TV broadcast content viewing; The third module is used to collect user viewing behavior data and determine the user dynamic operation recommendation coefficient; The fourth module is used to perform weighted calculation processing on the reported contribution value of the TV content, the TV content viewing contribution value and the user dynamic operation recommendation coefficient, and update the recommendation data of the TV viewport exposure recommendation position according to the calculation result.

9. An electronic device, characterized in that: including a processor and a memory; The memory is used to store programs; The processor executes the program to implement the method according to any one of claims 1 to 7.

10. A computer storage medium storing a program executable by a processor, characterized in that: The program executable by the processor is used to implement the method according to any one of claims 1 to 7 when executed by the processor.

Images