IPTV (Internet Protocol Television) similar recommendation method based on media asset medium attributes and high-frequency weights

Abstract

The invention discloses an IPTV (Internet Protocol Television) similar recommendation method based on media asset medium attributes and high-frequency weights, which comprises the following steps: classifying hot media asset data according to a preset first attribute parameter to obtain classified data, the hot media asset data being obtained from an external data source, and the hot media asset data being obtained from the external data source; and performing weight calculation on the classified data according to the list data of the external data source and the behavior data of the user to obtain a data weight, extracting hot media asset data required to be recommended from the classified data according to the data weight to obtain target media asset data, and returning the target media asset data to a display area of the network television in a paging manner. According to the invention, media asset resources can be intelligently recommended, manpower resources are reduced, and operation cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet television, and in particular to an IPTV similarity recommendation method based on media attributes and high-frequency weights. Background Art

[0002] With the rapid development of online television, the number of media resources on online TV platforms has increased exponentially, encompassing a wide range of genres, including movies, TV series, documentaries, and children's programs. This rich content provides users with more choices, but it also creates the problem of information overload, making it difficult for users to quickly find content that suits their interests on online TV platforms and thus reducing the user experience.

[0003] However, online TV platforms lack a system for automatically recommending content, and the display of media resources often relies on manual recommendation by humans, which requires a large amount of human resources and increases operating costs. Summary of the Invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a method for recommending content for Internet television, which can intelligently recommend media resources, reduce human resources, and lower operating costs.

[0005] The present invention also provides a network television content recommendation device.

[0006] The present invention also provides a network television content recommendation device.

[0007] The present invention also provides a computer-readable storage medium.

[0008] In a first aspect, an embodiment of the present invention provides a method for recommending content on an Internet television, comprising:

[0009] Classifying the popular media asset data according to a preset first attribute parameter to obtain classified data; wherein the popular media asset data is obtained from an external data source;

[0010] Calculate the weight of the classification data based on the list data of the external data source and the user's behavior data to obtain the data weight;

[0011] extracting the classification data to be recommended from the classification data according to the data weight to obtain target media asset data;

[0012] The target media asset data is returned in pages to the display area of ​​the network television.

[0013] The network television content recommendation method of the embodiment of the present invention has at least the following beneficial effects: obtaining popular media videos, pictures, or other content from an external data source to obtain popular media data, classifying popular media data with the same first attribute parameter into the same category to obtain classified data of the same category, obtaining a popularity ranking corresponding to each classified data based on list data from the external data source, and setting a weight for the corresponding classified data based on the popularity ranking, obtaining behavior data by obtaining historical user operations on the classified data, and dynamically adjusting the weight of the classified data in real time based on the behavior data to obtain data weight, extracting classified data that meets the user's preferences from the classified data based on the data weight, obtaining target media data to be recommended, and transmitting the target media data to the display area of ​​the network television via paging return for display, thereby recommending corresponding media resources to the user. By setting weights for media resources based on popularity rankings and adjusting weights based on user operations, media resources that meet the user's preferences are screened and recommended based on the weights, and intelligently recommending media resources, reducing human resources and operating costs.

[0014] According to some other embodiments of the network television content recommendation method of the present invention, before classifying the popular media asset data according to the preset first attribute parameter to obtain the classified data, the method further includes:

[0015] Obtaining popular media asset data from the external data source to obtain initial media asset data;

[0016] Acquire the media resource data of the media resource management system of the network television to obtain internal media resource data;

[0017] The initial media asset data is compared with the internal media asset data, and identical media asset data is retained to obtain the popular media asset data.

[0018] According to other embodiments of the network television content recommendation method of the present invention, the first attribute parameter includes: data source platform or media asset type, and the classification of popular media asset data according to the preset first attribute parameter to obtain classified data includes:

[0019] Classifying the popular media asset data of the same data source platform into the same category to obtain the classified data;

[0020] Alternatively, the popular media asset data of the same media asset type are classified into the same category to obtain the classified data.

[0021] According to some other embodiments of the network television content recommendation method of the present invention, weight calculation of the classification data based on the list data of the external data source and the user's behavior data to obtain the data weight includes:

[0022] Allocating initial weights to the classification data according to the list data;

[0023] The initial weight is adjusted according to the behavior data to obtain a data weight.

[0024] According to some other embodiments of the network television content recommendation method of the present invention, extracting the classification data to be recommended from the classification data according to the data weight to obtain target media asset data includes:

[0025] Randomly draw several times within the preset weight range to obtain random weights;

[0026] The target media asset data is selected from the classified data according to the random weight and the data weight.

[0027] According to some other embodiments of the network television content recommendation method of the present invention, after extracting the classification data to be recommended from the classification data according to the data weight to obtain target media asset data, the method further includes:

[0028] Filtering the first media asset data that does not meet the rules according to the preset recommendation rules;

[0029] Filtering second media data that is not within the scope of the user's authority level;

[0030] The third media asset data with the same content is filtered according to the historically recommended target media asset data.

[0031] According to some other embodiments of the network television content recommendation method of the present invention, filtering third media asset data of the same content based on the historically recommended target media asset data includes:

[0032] Calculating the similarity of the target media asset data according to a preset second attribute parameter to obtain the media asset similarity;

[0033] The third media asset data is determined and filtered according to the media asset similarity.

[0034] In a second aspect, an embodiment of the present invention provides an apparatus for recommending content on an Internet television, comprising:

[0035] A media asset classification module, configured to classify popular media asset data according to a preset first attribute parameter to obtain classified data; wherein the popular media asset data is obtained from an external data source;

[0036] A weight calculation module, configured to perform weight calculation on the classification data based on the list data from the external data source and the user's behavior data to obtain data weight;

[0037] A media resource recommendation module is configured to extract the hot media resource data to be recommended from the classified data according to the data weights to obtain target media resource data;

[0038] The media resource display module is used to return the target media resource data in pages to the display area of ​​the network television.

[0039] In a third aspect, an embodiment of the present invention provides an Internet TV content recommendation device, comprising:

[0040] at least one processor, and

[0041] a memory communicatively connected to the at least one processor; wherein,

[0042] The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to perform the network TV content recommendation method as described in the first aspect.

[0043] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer-executable instructions for causing a computer to execute the method for recommending network TV content as described in the first aspect.

[0044] Other features and advantages of the present application will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present application. The purpose and other advantages of the present application can be realized and obtained through the structures particularly pointed out in the description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is a flow chart of a specific embodiment of the method for recommending content on Internet television according to an embodiment of the present invention;

[0046] Figure 2 This is a flow chart of another specific embodiment of the method for recommending content on Internet television according to an embodiment of the present invention;

[0047] Figure 3 yes Figure 1 A flow chart of a specific embodiment of step 101;

[0048] Figure 4 yes Figure 1 A flow chart of a specific embodiment of step 102;

[0049] Figure 5 yes Figure 1 A flow chart of a specific embodiment of step 103;

[0050] Figure 6This is a flow chart of another specific embodiment of the method for recommending content on Internet television according to an embodiment of the present invention;

[0051] Figure 7 yes Figure 6 A flow chart of a specific embodiment of step 603;

[0052] Figure 8 This is a module block diagram of a specific embodiment of the network TV content recommendation device in an embodiment of the present invention;

[0053] Figure 9 This is a bottom logic diagram of a specific embodiment of the method for recommending content on Internet TV according to an embodiment of the present invention;

[0054] Figure 10 This is a flow chart of a specific embodiment of the method for recommending content on Internet television according to an embodiment of the present invention.

[0055] Description of reference numerals:

[0056] Media asset classification module 801 , weight calculation module 802 , media asset recommendation module 803 , and media asset display module 804 . DETAILED DESCRIPTION

[0057] The following will clearly and completely describe the concept and technical effects of the present invention in conjunction with the embodiments to fully understand the purpose, features and effects of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, other embodiments obtained by those skilled in the art without creative work are all within the scope of protection of the present invention.

[0058] In the description of the present invention, if any directional description is involved, such as "upper," "lower," "front," "back," "left," "right," etc., indicating directions or positional relationships, these are based on the directions or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or component referred to must have a specific orientation, be constructed or operate in a specific orientation. Therefore, they should not be understood as limiting the present invention. If a feature is referred to as being "disposed," "fixed," "connected," or "mounted" on another feature, it may be directly disposed, fixed, or connected to the other feature, or indirectly disposed, fixed, connected, or mounted on the other feature.

[0059] In the description of the embodiments of the present invention, if the word "several" is mentioned, it means more than one; if the word "plurality" is mentioned, it means more than two; if the word "greater than," "less than," or "exceeds," it should be understood as excluding the number itself; if the word "above," "below," or "within" is mentioned, it should be understood as including the number itself. If the word "first" or "second" is mentioned, it should be understood as distinguishing technical features and should not be understood as indicating or implying relative importance, implicitly specifying the number of the indicated technical features, or implicitly specifying the order of the indicated technical features.

[0060] With the rapid development of online TV services, the number of media resources on these platforms has grown exponentially, encompassing a wide range of genres, including movies, TV series, documentaries, and children's programs. While this rich content offers users more choices, it also creates information overload, making it difficult for users to quickly find content that matches their interests, thus reducing the user experience. Therefore, recommendation systems have become a crucial tool for improving user content acquisition efficiency. However, online TV service platforms previously lacked automated recommendation systems, and the display of all media resources relied on manual intervention. Currently, processing online TV media resources presents the following challenges: high labor costs, as manual intervention requires significant human resources and increases operational costs; high subjectivity, making the display of media resources susceptible to human bias and making it difficult to ensure the fairness and diversity of recommended content; and low efficiency, which prevents real-time response to user needs, resulting in a poor user experience.

[0061] To address one of the above problems, the present invention proposes a method for recommending Internet TV content, which can intelligently recommend media resources, reduce human resources, and lower operating costs.

[0062] Reference Figure 1 , Figure 1 The flowchart of the method for recommending content of Internet TV in an embodiment of the present invention is shown. In some embodiments, the method for recommending content of Internet TV may include but is not limited to steps 101 to 104:

[0063] Step 101 : Classify popular media asset data according to a preset first attribute parameter to obtain classified data; wherein the popular media asset data is obtained from an external data source.

[0064] In step 101, the external data source represents the data source of media resources. External data sources include data sources such as iQiyi, Tencent Video, and Youku Video. This application does not specifically limit external data sources. In addition, popular media data represents popular media resources. Media resources include videos, images, and text, etc. This application does not specifically limit media resources.

[0065] Step 102 : weight the classified data based on the list data from the external data source and the user's behavior data to obtain the data weight.

[0066] In step 102, the list data represents the ranking list of media resources in the corresponding data source, and the user's behavior data represents the user's operations after viewing the current media resource. The behavior data includes the number of clicks, viewing history or ratings, etc. This application does not specifically limit the behavior data.

[0067] Step 103 : extracting the classification data to be recommended from the classification data according to the data weight to obtain target media asset data.

[0068] Step 104: Return the target media asset data in pages to the display area of ​​the network television.

[0069] In step 104, it is ensured that among the returned recommended target media data, different types of target media data, such as movies, documentaries, etc., are evenly distributed according to the weight ratio.

[0070] In steps 101 to 104 of the embodiment of the present application, popular media videos or pictures are obtained from an external data source to obtain popular media data, popular media data with the same first attribute parameter are classified into the same category to obtain classified data of the same category, the popularity ranking corresponding to each classified data is obtained based on the list data of the external data source, and weights are set for the corresponding classified data based on the popularity ranking. Behavior data is obtained by obtaining the user's historical operations on the classified data, and the weights of the classified data are dynamically adjusted in real time based on the behavior data to obtain data weights. The classified data is extracted based on the data weights to extract classified data that meets the user's preferences to obtain target media data to be recommended, and the target media data is transmitted to the display area of ​​the network TV through paging return for display, thereby recommending corresponding media resources to the user. By setting weights for media resources based on popularity rankings and adjusting weights based on user operations, media resources that meet the user's preferences are screened and recommended based on weights, media resources can be intelligently recommended, reducing human resources and operating costs.

[0071] Reference Figure 2 , Figure 2 A flowchart of a method for recommending online TV content in accordance with an embodiment of the present invention is shown. In some embodiments, before classifying popular media asset data according to a preset first attribute parameter to obtain classified data, the method for recommending online TV content further includes, but is not limited to, steps 201 to 203:

[0072] Step 201: Obtain popular media asset data from an external data source to obtain initial media asset data.

[0073] In step 201, media resource data represents data generated after information is recorded by the media resource, that is, a representation method of the media resource in the electronic field.

[0074] Step 202: Acquire the media asset data of the media asset management system of the network television to obtain internal media asset data.

[0075] In step 202, the IPTV uses a media asset management system to store internal media asset data in the cloud. A media asset management system is a software system used to manage and organize content, primarily used for media asset management within IPTV. By breaking content down into reusable components, such as paragraphs, images, and tables, the media asset management system makes content creation, editing, publishing, and maintenance more efficient and flexible.

[0076] Step 203 : Compare the initial media asset data with the internal media asset data, retain the same media asset data, and obtain popular media asset data.

[0077] Steps 201 to 203 shown in the embodiment of the present application obtain media data within a certain popular ranking in a popular list of an external data source to obtain initial media data, obtain media data stored in the cloud by the media pipeline system of the network TV to obtain internal media data, compare the initial media data with the internal media data one by one, and compare the initial media data and the internal media data for similarity. If the current initial media data is the same as any internal media data, retain the current initial media data to obtain popular media data.

[0078] Reference Figure 3 , Figure 3 A flowchart of a method for recommending online TV content in an embodiment of the present invention is shown. In some embodiments, the first attribute parameter includes: a data source platform or a media asset type. Classifying popular media asset data according to the preset first attribute parameter to obtain classified data specifically includes but is not limited to steps 301 to 302:

[0079] Step 301: Classify popular media asset data from the same data source platform into the same category to obtain classified data.

[0080] In step 301, if the popular media asset data belongs to the same data source platform, the popular media asset data belonging to the same data source platform are classified into the same category to obtain classified data. The data source platform includes external data sources, such as iQiyi, Tencent Video, and Youku Video.

[0081] Step 302 , alternatively, classify popular media asset data of the same media asset type into the same category to obtain classified data.

[0082] In step 302, if the popular media asset data belong to the same media asset type, the popular media asset data belonging to the same media asset type are classified into the same category to obtain classified data. The media asset types include children's categories, documentary categories, movie categories, etc., which are not specifically limited in this application.

[0083] Reference Figure 4 , Figure 4 The flowchart of the method for recommending online TV content in an embodiment of the present invention is shown. In some embodiments, weights are calculated for the classified data based on the list data from the external data source and the user's behavior data, and the data weights obtained specifically include but are not limited to steps 401 to 402:

[0084] Step 401: assign initial weights to the categorized data based on the list data.

[0085] In step 401, weights are assigned based on the popularity ranking of the different external data sources and the category data within the list data to obtain initial weights. The initial weights are ranked from 1 to 10, with higher initial weights associated with more popular external data sources and higher initial weights associated with higher ranking category data within the external data source.

[0086] Step 402: Adjust the initial weight according to the behavior data to obtain the data weight.

[0087] In step 402, if the user has a record of watching the video content corresponding to the current classification data multiple times, the initial weight is increased to obtain an updated data weight; if the user does not have a record of watching the video content corresponding to the current classification data multiple times, the initial weight is decreased to obtain an updated data weight. If the user has clicked on the video content corresponding to the current classification data multiple times, the initial weight is increased to obtain an updated data weight; if the user has not clicked on the video content corresponding to the current classification data multiple times, the initial weight is decreased to obtain an updated data weight. If the user gives a high rating to the video content corresponding to the current classification data, the initial weight is increased to obtain an updated data weight; if the user gives a low rating to the video content corresponding to the current classification data, the initial weight is decreased to obtain an updated data weight.

[0088] It should be noted that the level of the initial weight is increased or decreased according to the number of views, the level of the initial weight is increased or decreased according to the number of clicks, and the level of the initial weight is increased or decreased according to the level of the score.

[0089] In steps 401 to 402 shown in the embodiment of the present application, weights are set based on the external data source of the corresponding usage popularity of the classification data and the popularity ranking of the classification data in the external data source, an initial weight is set for the current classification data, and the operations performed by the user on the current classification data, that is, the behavior data, are obtained in real time. The value of the initial weight is adjusted in real time based on the user's behavior data to obtain the data weight, which can solve the cold start problem, avoid the deviation of the recommendation results dominated by popular content, and improve the accuracy and personalization of content recommendations of network TV.

[0090] Reference Figure 5 , Figure 5 The flowchart of the method for recommending online TV content in an embodiment of the present invention is shown. In some embodiments, the classification data to be recommended is extracted from the classification data according to the data weight, and the target media asset data is obtained, specifically including but not limited to steps 501 to 502:

[0091] Step 501: randomly draw several times within a preset weight range to obtain a random weight.

[0092] Step 502: Select target media asset data from the classified data according to the random weight and the data weight.

[0093] In steps 501 and 502, as shown in the embodiment of this application, random sampling is performed several times within a weight range of 1 to 10 to obtain random weights of corresponding levels. The levels of the random weights are compared with the levels of the data weights, and classified data with the same weight levels are selected to obtain the target media asset data. By combining random sampling with weights, the recommendation system avoids over-reliance on popular content and ensures the diversity of recommended content.

[0094] Reference Figure 6 , Figure 6 A flowchart of a method for recommending online TV content according to an embodiment of the present invention is shown. In some embodiments, after extracting the classification data to be recommended from the classification data according to the data weights to obtain the target media asset data, the method for recommending online TV content further includes, but is not limited to, steps 601 to 603:

[0095] Step 601: Filter first media asset data that does not meet the rules according to a preset recommendation rule.

[0096] In step 601, target media data that does not meet the recommendation rules, i.e., the first media data, is filtered from the extracted target media data according to the preset recommendation rules. The recommendation rules may include social recommendations, personalized location recommendations, and search recommendations, etc., and the present application does not specifically limit the recommendation rules.

[0097] Step 602: Filter the second media asset data that is not within the scope of the user's authority according to the user's authority level.

[0098] In step 602, target media data not within the user's permission range, i.e., the second media data, is filtered from the extracted target media data based on the user's permission level. The target media data is filtered based on the user's permission level. User permission levels include VIP, SVIP, and non-VIP levels, and this application does not specifically limit permission levels.

[0099] Step 603: Filter third media asset data with the same content according to the historically recommended target media asset data.

[0100] In step 603, target media asset data with the same content, ie, third media asset data, is filtered from the extracted target media asset data according to the historically recommended target media asset data.

[0101] Reference Figure 7 , Figure 7 The flowchart of the method for recommending content of network TV in an embodiment of the present invention is shown. In some embodiments, filtering the third media asset data of the same content according to the target media asset data recommended in history specifically includes but is not limited to steps 701 to 702:

[0102] Step 701 : Calculate the similarity of target media asset data according to a preset second attribute parameter to obtain the media asset similarity.

[0103] In step 701, the second attribute parameter includes type, label, and rating, etc. The present application does not specifically limit the media asset attributes.

[0104] Step 702: Determine and filter the third media asset data based on the media asset similarity.

[0105] In steps 701 to 702 shown in the embodiment of the present application, the similarity between the two target media asset data is calculated based on parameters such as the type, label, and score of the target media asset data to obtain media asset similarity. The media asset similarity is compared with a preset similarity threshold. If the comparison result indicates that the media asset similarity is greater than the similarity threshold, the two target media asset data are the same, that is, the current target media asset data is the third media asset data. If the media asset similarity is less than the similarity threshold, the two target media asset data are similar.

[0106] It should be noted that the content similarity between target media asset data is calculated in combination with media asset attributes, target media asset data similar to the user's historical preferences are recommended first, and target media asset data with too similar content are filtered out.

[0107] In some embodiments, the target media data returned with each request is removed from the cache to ensure that the same target media data will not be returned in a certain number of subsequent requests. For example, if the target media data repository contains 500 pieces of target media data and the user requests 20 pieces of target media data each time, the same target media data will not be returned in the next 25 requests. Furthermore, the caching mechanism includes: after the recommended target media data is generated, the recommended target media data is removed from the cache. If the cache is insufficient, the target media data is reloaded from the target media data repository.

[0108] In addition, the embodiment of the present application also discloses an Internet TV content recommendation device, please refer to Figure 8 , Figure 8 This is a block diagram of a network television content recommendation device disclosed in one embodiment of the present invention. The network television content recommendation device can implement the aforementioned network television content recommendation method. The network television content recommendation device includes: a media asset classification module 801, a weight calculation module 802, a media asset recommendation module 803, and a media asset display module 804. The media asset classification module 801, the weight calculation module 802, the media asset recommendation module 803, and the media asset display module 804 are all communicatively connected.

[0109] The media asset classification module 801 classifies popular media asset data based on a preset first attribute parameter to obtain classified data. The popular media asset data is obtained from an external data source. The weight calculation module 802 weights the classified data based on the external data source's ranking data and user behavior data to obtain data weights. The media asset recommendation module 803 extracts the desired recommended popular media asset data from the classified data based on the data weights to obtain target media asset data. The media asset display module 804 paginates the target media asset data and returns it to the display area of ​​the network television.

[0110] Popular media videos, images, and other content are obtained from an external data source to obtain popular media data. The media classification module 801 classifies popular media data with the same first attribute parameter into the same category to obtain classified data of the same category. The weight calculation module 802 obtains the popularity ranking corresponding to each classified data based on the list data of the external data source and assigns a weight to the corresponding classified data based on the popularity ranking. By obtaining the user's historical operations on the classified data, behavioral data is obtained, and the weight of the classified data is dynamically adjusted in real time based on the behavioral data to obtain the data weight. The media recommendation module 803 extracts the classified data from the classified data based on the data weight, extracts the classified data that meets the user's preferences, and obtains the target media data to be recommended. The media display module 804 transmits the target media data to the display area of ​​the network TV via paging return for display, thereby recommending the corresponding media resources to the user. By assigning weights to media resources based on the popularity ranking and adjusting the weights based on the user's operations, media resources that meet the user's preferences are screened and recommended based on the weights. This can intelligently recommend media resources, reduce human resources, and lower operating costs.

[0111] The operation process of the network TV content recommendation device of this embodiment is specifically described above. Figure 1 、 Figure 2 、 Figure 3 、 Figure 4 、 Figure 5 、 Figure 6 、 Figure 7 、 Figure 9 Steps S101 to S104, steps S201 to S203, steps S301 and S302, steps S401 and S402, steps S501 and S502, steps S601 to S603, and steps S701 and S702 of the network TV content recommendation method are not repeated here.

[0112] Please refer to Figure 9 , Figure 9 An embodiment of the present invention discloses the underlying logic diagram of a method for recommending content on an online TV. In some embodiments, the big data end sorts the popular media data and transmits it to the resource library of the recommendation system background. The operator performs initial content classification and configures weight filtering intervention, obtains detailed information from the resource library, and filters popular media data with the same content. After the user requests a recommendation on the online TV end, the online TV obtains the recommended popular media data through the system interface service, caches the recommended popular media data, randomly screens a corresponding number of popular media data, filters out popular media data that does not meet the conditions, and removes completely identical popular media data to obtain target media data. The target media data is paged and fed back to the display area of ​​the online TV, and the user's operation behavior is monitored in real time and reported.

[0113] Please refer to Figure 10 , Figure 10 The present invention discloses a flowchart of a method for recommending content on an online television. In some embodiments, after the online television sends a recommendation request, it determines whether the number of cached popular media data meets a condition. If the condition is met, the weight of the popular media data is directly calculated, the corresponding popular media data is filtered according to the weight, and additional attributes of the popular media data are added. Duplicate popular media data is removed based on the additional attributes, and the cached popular media data is updated to recommend the cached popular media data. If the condition is not met, the popular media data is obtained from the database and cached in the cache space. The weight of the popular media data is calculated after the cache quantity meets the condition.

[0114] Another embodiment of the present invention discloses a network television content recommendation device, comprising: at least one processor, and a memory in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the following steps: Figure 1 The control method steps S101 to S104, Figure 2 The control method steps S201 to S203, Figure 3 The control method steps S301 and S302, Figure 4 The control method steps S401 and S402, Figure 5 The control method steps S501 and S502, Figure 6 The control method steps S601 to S603 and Figure 7 The network TV content recommendation method of step S701 and step S702 in the control method.

[0115] Another embodiment of the present invention discloses a computer-readable storage medium, the storage medium comprising: the storage medium stores computer-executable instructions, the computer-executable instructions are used to enable a computer to execute Figure 1 The control method steps S101 to S104, Figure 2 The control method steps S201 to S203, Figure 3 The control method steps S301 and S302, Figure 4 The control method steps S401 and S402, Figure 5 The control method steps S501 and S502, Figure 6 The control method steps S601 to S603 and Figure 7 The network TV content recommendation method of step S701 and step S702 in the control method.

[0116] The 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 place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0117] Those skilled in the art will appreciate that all or some of the steps and systems in the method disclosed above can be implemented as software, firmware, hardware, and appropriate combinations thereof. Some physical components or all physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, and the computer-readable medium can include computer storage media (or non-transitory media) and communication media (or temporary media). As known to those skilled in the art, the term computer storage media is included in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data) and is volatile and non-volatile, removable, and non-removable. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory, or other memory technology, CD-ROM, digital versatile disks (DVD), or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage, or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, as is well known to those skilled in the art, communication media typically embodies computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0118] While the embodiments of the present invention have been described in detail above with reference to the accompanying drawings, the present invention is not limited to the embodiments described above. Various modifications may be made within the scope of knowledge possessed by a person skilled in the art without departing from the spirit of the present invention. Furthermore, the embodiments of the present invention and the features thereof may be combined with one another unless there is a conflict.

Claims

1. A method for recommending Internet TV content, characterized in that: include: Classifying the popular media asset data according to a preset first attribute parameter to obtain classified data; wherein the popular media asset data is obtained from an external data source; Calculate the weight of the classification data based on the list data of the external data source and the user's behavior data to obtain the data weight; extracting the classification data to be recommended from the classification data according to the data weight to obtain target media asset data; The target media asset data is returned in pages to the display area of ​​the network television.

2. The method according to claim 1, characterized in that Before classifying the popular media asset data according to the preset first attribute parameter to obtain the classified data, the method further includes: Obtaining popular media asset data from the external data source to obtain initial media asset data; Acquire the media resource data of the media resource management system of the network television to obtain internal media resource data; The initial media asset data is compared with the internal media asset data, and identical media asset data is retained to obtain the popular media asset data.

3. The method according to claim 1, characterized in that The first attribute parameter includes: data source platform or media asset type. The classification of popular media asset data according to the preset first attribute parameter to obtain classified data includes: Classifying the popular media asset data of the same data source platform into the same category to obtain the classified data; Alternatively, the popular media asset data of the same media asset type are classified into the same category to obtain the classified data.

4. The method according to claim 1, wherein The weight calculation of the classification data based on the list data of the external data source and the user's behavior data to obtain the data weight includes: Allocating initial weights to the classification data according to the list data; The initial weight is adjusted according to the behavior data to obtain a data weight.

5. The method according to claim 1, characterized in that The step of extracting the classification data to be recommended from the classification data according to the data weight to obtain target media asset data includes: Randomly draw several times within the preset weight range to obtain random weights; The target media asset data is selected from the classified data according to the random weight and the data weight.

6. The method according to claim 1, characterized in that After extracting the classification data to be recommended from the classification data according to the data weight to obtain target media asset data, the method further includes: Filtering the first media asset data that does not meet the rules according to the preset recommendation rules; Filtering second media data that is not within the scope of the user's authority level; The third media asset data with the same content is filtered according to the historically recommended target media asset data.

7. The method according to claim 6, characterized in that The filtering of third media asset data having the same content as the target media asset data recommended historically includes: Calculating the similarity of the target media asset data according to a preset second attribute parameter to obtain the media asset similarity; The third media asset data is determined and filtered according to the media asset similarity.

8. A network television content recommendation device, characterized in that: include: A media asset classification module, configured to classify popular media asset data according to a preset first attribute parameter to obtain classified data; wherein the popular media asset data is obtained from an external data source; A weight calculation module, configured to perform weight calculation on the classification data based on the list data from the external data source and the user's behavior data to obtain data weight; A media resource recommendation module is configured to extract the hot media resource data to be recommended from the classified data according to the data weights to obtain target media resource data; The media resource display module is used to return the target media resource data in pages to the display area of ​​the network television.

9. A network television content recommendation device, characterized in that: include: at least one processor, and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the network TV content recommendation method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the network television content recommendation method according to any one of claims 1 to 7.

Images