TWI658726B - Method for promoting videos based on public opinions and apparatus using the same - Google Patents

Method for promoting videos based on public opinions and apparatus using the same Download PDF

Info

Publication number
TWI658726B
TWI658726B TW107100262A TW107100262A TWI658726B TW I658726 B TWI658726 B TW I658726B TW 107100262 A TW107100262 A TW 107100262A TW 107100262 A TW107100262 A TW 107100262A TW I658726 B TWI658726 B TW I658726B
Authority
TW
Taiwan
Prior art keywords
post
movie
keywords
posts
videos
Prior art date
Application number
TW107100262A
Other languages
Chinese (zh)
Other versions
TW201931867A (en
Inventor
李如珍
張致和
申曉玉
曾朝尉
黃敏純
陳偉修
Original Assignee
中華電信股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中華電信股份有限公司 filed Critical 中華電信股份有限公司
Priority to TW107100262A priority Critical patent/TWI658726B/en
Application granted granted Critical
Publication of TWI658726B publication Critical patent/TWI658726B/en
Publication of TW201931867A publication Critical patent/TW201931867A/en

Links

Abstract

本發明提供一種基於時事推廣影片的方法及其裝置。前述方法包括:取得一影片資料庫中多個影片的多個詮釋資料;取得一社群網站中多個貼文的多個互動參數以及前述貼文中的多個關鍵字;基於前述互動參數估計各貼文的一受注目程度;基於各貼文的受注目程度從前述貼文中取出一第一貼文;基於第一貼文的多個第一關鍵字從前述影片中找出一第一影片,其中第一影片的前述詮釋資料的其中之一對應於前述第一關鍵字的其中之一;以及推廣第一影片。The invention provides a method and a device for promoting a movie based on current events. The foregoing method includes: obtaining multiple interpretation data of multiple videos in a video database; obtaining multiple interactive parameters of multiple posts in a social networking site and multiple keywords in the aforementioned posts; estimating each based on the interactive parameters A degree of attention of a post; extracting a first post from the foregoing post based on the degree of attention of each post; finding a first video from the foregoing video based on a plurality of first keywords of the first post, One of the aforementioned interpretation data of the first video corresponds to one of the aforementioned first keywords; and promotion of the first video.

Description

基於時事推廣影片的方法及其裝置Method and device for promoting movies based on current events

本發明是有關於一種推廣影片的方法及其裝置,且特別是有關於一種基於時事推廣影片的方法及其裝置。The present invention relates to a method and a device for promoting a movie, and more particularly, to a method and a device for promoting a movie based on current events.

隨著隨選視訊服務(Video on Demand,VoD)不斷地擴展,片庫系統內的影片持續大量增加。在此情況下,如何預測出影片的熱門程度,並據以派送予使用者觀看已成為一項非常重要的議題。絕大多數的使用者會觀看相同的少數熱門影片,因此,若能準確預測出熱門影片的話,便能透過優先派送、廣告推薦等方式來提供使用者更友善的操作體驗。並且,還可將片庫內熱門的影片預先派至近端伺服器讓影片在各個近端伺服器而得到有效率地配置。更甚者,可將目前仍在合約授權期限內的未上架影片自動上架。With the continuous expansion of Video on Demand (VoD), the number of videos in the library system continues to increase. In this case, how to predict the popularity of the video and send it to users for viewing has become a very important issue. The vast majority of users watch the same few popular videos, so if you can accurately predict popular videos, you can provide users with a more user-friendly operating experience through priority delivery, ad recommendation, and other methods. In addition, the popular videos in the library can be sent to the near-end server in advance, so that the videos can be efficiently configured on each near-end server. What's more, unlisted videos that are still within the contract authorization period can be automatically listed.

然而,目前存在的預測影片熱門程度的方法多是在取得影片的詮釋資料後,依據相似度高的影片的歷史點閱資料來預測新進影片的熱門程度,因而無法反應出影片隨著外部時事議題發酵而導致的變化。另外,即便可讓使用者在另行設置的評估系統上對影片進行評分或討論等互動再據以預測未來的熱門影片,但此方法除了需在VOD系統之外另建置提供使用者網路社交互動的評估平台之後,還需要培養使用者在此評估系統內進行大量的網路社交互動,實作上有一定的難度。However, most of the existing methods for predicting the popularity of a video are to obtain the interpretation data of the video and predict the popularity of the new video based on the historical click-through data of the highly similar videos, so it cannot reflect the issue of the video following external current events Changes caused by fermentation. In addition, even if users can interact with ratings or discussions on a separate evaluation system and then predict future popular videos based on this method, this method needs to be set up in addition to the VOD system to provide users with social networking After the interactive evaluation platform, it is necessary to train users to conduct a large number of online social interactions in this evaluation system, which is difficult to implement.

有鑑於此,本發明提供一種基於時事推廣影片的方法及其裝置,其可藉由追蹤社群網站的方式來得知目前較為熱門的議題,並據以從影片資料庫中找出與熱門議題相關的影片再加以推廣。藉此,可讓使用者較輕易地接觸到與時事相關的影片,從而改善使用者體驗。In view of this, the present invention provides a method and a device for promoting a movie based on current events, which can learn the current hot topics by tracking social networking sites, and find out from the video database related to hot topics Promoted videos. In this way, users can more easily access videos related to current events, thereby improving the user experience.

本發明提供一種基於時事推廣影片的方法,包括:取得一影片資料庫中多個影片的多個詮釋資料;取得一社群網站中多個貼文的多個互動參數以及前述貼文中的多個關鍵字;基於前述互動參數估計各貼文的一受注目程度;基於各貼文的受注目程度從前述貼文中取出一第一貼文;基於第一貼文的多個第一關鍵字從前述影片中找出一第一影片,其中第一影片的前述詮釋資料的其中之一對應於前述第一關鍵字的其中之一;以及推廣第一影片。The present invention provides a method for promoting a movie based on current events, including: obtaining multiple interpretation data of multiple videos in a movie database; obtaining multiple interactive parameters of multiple posts in a social networking site and multiple of the aforementioned posts Keywords; estimating a degree of attention of each post based on the aforementioned interaction parameters; extracting a first post from the foregoing post based on the degree of attention of each post; multiple first keywords based on the first post from the foregoing A first video is found in the video, wherein one of the foregoing interpretation data of the first video corresponds to one of the first keywords; and promoting the first video.

本發明提供一種影片推廣裝置,包括儲存電路及處理器。儲存電路儲存多個模組。處理器連接儲存電路,並存取前述模組以執行下列步驟:取得一影片資料庫中多個影片的多個詮釋資料;取得一社群網站中多個貼文的多個互動參數以及前述貼文中的多個關鍵字;基於前述互動參數估計各貼文的一受注目程度;基於各貼文的受注目程度從前述貼文中取出一第一貼文;基於第一貼文的多個第一關鍵字從前述影片中找出一第一影片,其中第一影片的前述詮釋資料的其中之一對應於前述第一關鍵字的其中之一;以及推廣第一影片。The invention provides a film promotion device, which includes a storage circuit and a processor. The storage circuit stores multiple modules. The processor is connected to the storage circuit and accesses the aforementioned module to perform the following steps: obtaining multiple interpretation data of multiple videos in a movie database; obtaining multiple interactive parameters of multiple posts in a social website and the aforementioned postings Multiple keywords in the text; estimating a degree of attention of each post based on the aforementioned interaction parameters; extracting a first post from the foregoing post based on the degree of attention of each post; multiple first based on the first post The keyword finds a first video from the aforementioned videos, wherein one of the aforementioned interpretation data of the first video corresponds to one of the aforementioned first keywords; and promoting the first video.

基於上述,本發明提供一種基於時事推廣影片的方法及其裝置,其可在所關注的社群網站的貼文中依據互動參數找出具有較高受注目度的貼文,並從此貼文中取得相關的關鍵字。之後,可判斷影片資料庫中是否存在具有相應詮釋資料的影片,若有則將其推廣,以讓使用者能夠優先看到與時事相關的影片,從而改善使用者體驗。Based on the above, the present invention provides a method and device for promoting a movie based on current events, which can find posts with a high degree of attention based on the interaction parameters in the posts of the social website concerned, and obtain relevant information from the posts. Keywords. Then, it can be determined whether there are videos with corresponding interpretation data in the video database, and if so, promote them so that users can preferentially see videos related to current events, thereby improving the user experience.

為讓本發明的上述特徵和優點能更明顯易懂,下文特舉實施例,並配合所附圖式作詳細說明如下。In order to make the above features and advantages of the present invention more comprehensible, embodiments are hereinafter described in detail with reference to the accompanying drawings.

請參照圖1,其是依據本發明之一實施例繪示的影片推廣裝置及影音串流終端設備的示意圖。在本實施例中,影片推廣裝置100包括儲存電路110及處理器120。影片推廣裝置100例如可設置於電信服務業者維護的多媒體內容傳輸平台上,並可用於決定多個影音串流終端設備20的派片策略,其中各影音串流終端設備20例如是佈建於多個使用者家中或類似場所中的多媒體隨選視訊(Multimedia on Demand,MOD)機上盒、網路協定電視(Internet Protocol Television,IPTV)裝置、OTT(over-the-top)裝置及/或前述的近端伺服器,但本發明可不限於此。Please refer to FIG. 1, which is a schematic diagram of a movie promotion device and a video streaming terminal device according to an embodiment of the present invention. In this embodiment, the film promotion device 100 includes a storage circuit 110 and a processor 120. The movie promotion device 100 may be set on a multimedia content transmission platform maintained by a telecommunications service provider, and may be used to determine a distribution policy for multiple video streaming terminal devices 20, where each video streaming terminal device 20 is deployed in multiple Multimedia on demand (MOD) set-top boxes, Internet Protocol Television (IPTV) devices, OTT (over-the-top) devices and / or the foregoing in a user's home or a similar place The near-end server, but the present invention may not be limited to this.

儲存電路110例如是記憶體、硬碟或是其他任何可用於儲存資料的元件,而可用以記錄多個程式碼或模組。處理器120耦接儲存電路110。處理器120例如是一般用途處理器、特殊用途處理器、傳統的處理器、數位訊號處理器、多個微處理器(microprocessor)、一個或多個結合數位訊號處理器核心的微處理器、控制器、微控制器、特殊應用集成電路(Application Specific Integrated Circuit,ASIC)、場可程式閘陣列電路(Field Programmable Gate Array,FPGA)、任何其他種類的積體電路、狀態機、基於進階精簡指令集機器(Advanced RISC Machine,ARM)的處理器以及類似品。The storage circuit 110 is, for example, a memory, a hard disk, or any other component that can be used to store data, and can be used to record multiple codes or modules. The processor 120 is coupled to the storage circuit 110. The processor 120 is, for example, a general-purpose processor, a special-purpose processor, a conventional processor, a digital signal processor, a plurality of microprocessors, one or more microprocessors combined with a digital signal processor core, and a control unit. Controller, microcontroller, Application Specific Integrated Circuit (ASIC), Field Programmable Gate Array (FPGA), any other kind of integrated circuit, state machine, based on advanced reduced instructions Processors of Advanced RISC Machine (ARM) and the like.

請參照圖2,其是依據本發明之一實施例繪示的基於時事推廣影片的方法流程圖。在本實施例中,圖2的方法可由圖1的影片推廣裝置100執行,以下即搭配圖1所示的各個元件來說明圖2所示方法的各個步驟。Please refer to FIG. 2, which is a flowchart of a method for promoting a movie based on current events according to an embodiment of the present invention. In this embodiment, the method in FIG. 2 may be executed by the film promotion device 100 in FIG. 1. The following describes the steps of the method in FIG. 2 with each element shown in FIG. 1.

首先,在步驟210中,處理器120取得影片資料庫中影片的詮釋資料(metadata)。在一實施例中,前述影片資料庫例如是由多媒體內容傳輸平台(例如MOD、IPTV及OTT等)的業者所維護的資料庫,其中可包含在授權期間內的各式影片,而各影片的詮釋資料例如包括片名、演員、導演、類型及影片內容供應商輸入的標籤(Tag)、行銷亮點(Comment)等,但本發明可不限於此。First, in step 210, the processor 120 obtains metadata of movies in a movie database. In an embodiment, the aforementioned movie database is, for example, a database maintained by a provider of multimedia content transmission platforms (such as MOD, IPTV, OTT, etc.), which may include various types of movies during the license period, and The interpretation data includes, for example, a title, an actor, a director, a genre, and a tag, a comment, etc. input by a movie content provider, but the present invention is not limited thereto.

接著,在步驟220中,處理器120取得社群網站中多個貼文的多個互動參數以及前述貼文中的多個關鍵字。前述社群網站例如是Facebook、Youtube、Twitter或其他類似的網站。在一實施例中,處理器120可依管理人員的設定而追蹤社群網站中的特定內容(例如粉絲專頁或是由社群網站所自動產生的熱門影片列表),再從這些特定內容中取得貼文。舉例而言,處理器120例如可追蹤Facebook上的數個主流新聞粉絲專頁,並從這些新聞粉絲專頁取得貼文。舉另一例而言,處理器120還可依管理人員的設定而追蹤Youtube所產生的發燒影片列表,並將此發燒影片列表中所列的各個影片及其相關描述視為步驟220中所考慮的貼文,但本發明可不限於此。Next, in step 220, the processor 120 obtains a plurality of interaction parameters of a plurality of posts in the social networking site and a plurality of keywords in the aforementioned posts. The aforementioned social networking site is, for example, Facebook, Youtube, Twitter, or other similar websites. In one embodiment, the processor 120 may track specific content (such as a fan page or a list of popular videos automatically generated by the social network site) on a social network site according to the settings of the management staff, and then select from the specific content. Get posts. For example, the processor 120 may, for example, track several mainstream news fan pages on Facebook and obtain posts from these news fan pages. For another example, the processor 120 may also track the list of feverish videos generated by Youtube according to the settings of the management personnel, and consider each movie listed in this feverish movie list and its related description as considered in step 220 Posts, but the invention is not limited to this.

在不同的實施例中,前述互動參數例如包括讚數、留言數、分享次數、觀看次數的至少其中之一。此外,處理器120可自各貼文的標題、內文及哈希標籤(hashtag)的至少其中之一來取得貼文中的關鍵字,但本發明可不限於此。In different embodiments, the aforementioned interaction parameters include, for example, at least one of the number of likes, the number of comments, the number of shares, and the number of views. In addition, the processor 120 may obtain keywords in a post from at least one of a title, a body, and a hashtag of each post, but the present invention is not limited thereto.

此外,為了保證處理器120所觀注的貼文內容足夠新穎,處理器120所考慮的各貼文的發文時間距離當下時間可不遠於預設時間區間(其例如是由管理人員依需求而設定的任意時間區間)。舉例而言,若前述預設時間區間為2天,則處理器120在步驟220所考慮的貼文將會是2天內發布的貼文,而若前述預設時間區間為1週,則處理器120在步驟220所考慮的貼文將會是1週內發布的貼文,以此類推。In addition, in order to ensure that the content of the posts observed by the processor 120 is sufficiently novel, the posting time of each post considered by the processor 120 may not be less than the preset time interval (which is set by the management staff according to requirements, for example) Any time interval). For example, if the aforementioned preset time interval is 2 days, the post considered by the processor 120 in step 220 will be a post published within 2 days, and if the aforementioned preset time interval is 1 week, then processing The post considered by the device 120 in step 220 will be a post published within 1 week, and so on.

之後,在步驟230中,處理器120基於前述互動參數估計各貼文的受注目程度。在一實施例中,前述互動參數個別可對應於加權分數,例如一個讚為1分,一則留言為2分,一次分享為4分,一個觀看次數為0.2分。在此情況下,處理器120可將各貼文的加權分數加總以計算各貼文的分數,而此分數可正比於貼文的受注目程度。After that, in step 230, the processor 120 estimates the attention degree of each post based on the aforementioned interaction parameters. In an embodiment, the foregoing interaction parameters may individually correspond to weighted scores, for example, one like is 1 point, one message is 2 points, one share is 4 points, and one view number is 0.2 points. In this case, the processor 120 may sum up the weighted scores of each post to calculate the score of each post, and this score may be proportional to the degree of attention of the post.

舉例而言,假設A貼文具有10個讚而B貼文具有10則留言,則A貼文的分數即為10分,B貼文的分數即為20分。由於B貼文的分數高於A貼文,因此處理器120可判定B貼文的受注目程度高於A貼文。舉另一例而言,假設C貼文具有1個讚及1次分享,而D貼文具有3則留言及5個觀看次數,則C貼文的分數即為5分,而D貼文的分數即為7分,因此處理器120可判定D貼文的受注目程度高於C貼文。基於上述教示,本領域具通常知識者應可對應推得具有其他互動參數組合之貼文所對應的受注目程度,在此不再贅述。For example, if A post has 10 likes and B post has 10 comments, the score of A post is 10 points, and the score of B post is 20 points. Since the score of the B post is higher than that of the A post, the processor 120 may determine that the attention level of the B post is higher than that of the A post. For another example, suppose that a C post has 1 like and 1 share, and a D post has 3 comments and 5 views. Then the score of the C post is 5 points, and the score of the D post is That is 7 points, so the processor 120 can determine that the attention level of the D post is higher than that of the C post. Based on the above teachings, those with ordinary knowledge in the art should be able to deduce the corresponding degree of attention corresponding to posts with other interaction parameter combinations, which will not be repeated here.

在步驟240中,處理器120基於各貼文的受注目程度從前述貼文中取出第一貼文。在一實施例中,處理器120可直接將分數高於一預設門限值(其例如是由管理人員自行依需求設定的值)的各個貼文定義為第一貼文。In step 240, the processor 120 extracts the first post from the aforementioned posts based on the degree of attention of each post. In an embodiment, the processor 120 may directly define each post whose score is higher than a preset threshold (for example, a value set by a management person according to requirements) as the first post.

在另一實施例中,處理器120可依據各貼文的分數將貼文降冪排序,再從排序後的貼文取出第一貼文,其中第一貼文的排名可位於預設名次數量內。舉例而言,若前述預設名次數量為10,則處理器120可將分數前10高的貼文定義為第一貼文,而若前述預設名次數量為15,則處理器120可將分數前15高的貼文定義為第一貼文,依此類推。In another embodiment, the processor 120 may sort the posts in descending order according to the score of each post, and then extract the first post from the sorted posts, where the ranking of the first post may be at a preset number of times Inside. For example, if the number of times of the preset name is 10, the processor 120 may define the first 10 posts with the highest score as the first post, and if the number of times of the preset name is 15, the processor 120 may assign the score The top 15 high posts are defined as the first post, and so on.

在步驟250中,處理器120基於第一貼文的多個第一關鍵字從前述影片中找出第一影片。在一實施例中,處理器120可將各第一貼文的第一關鍵字個別與各影片的詮釋資料比對。當影片的其中之一者(下稱特定影片)的詮釋資料的其中之一相同於第一關鍵字之一時,處理器120可定義特定影片為第一影片。舉例而言,假設某第一貼文的第一關鍵字包含「M片名」、「N導演」及「P演員」,則處理器120可在影片資料庫中搜尋是否存在以「M片名」、「N導演」及「P演員」的至少其中之一作為詮釋資料的影片,若有則將此影片定義為第一影片。In step 250, the processor 120 finds the first movie from the aforementioned movies based on the first keywords of the first post. In an embodiment, the processor 120 may individually compare the first keywords of each first post with the interpretation data of each movie. When one of the interpretation data of one of the movies (hereinafter referred to as a specific movie) is the same as one of the first keywords, the processor 120 may define the specific movie as the first movie. For example, assuming that the first keyword of a first post includes "M title", "N director" and "P actor", the processor 120 may search the movie database for the presence of "M title" ", At least one of" Director N "and" P Actor "as the interpretive data, if any, this movie is defined as the first movie.

在其他實施例中,處理器120亦可在特定影片的詮釋資料匹配於各第一貼文的第一關鍵字的一數量達到一預設數量時,再定義特定影片為第一影片。舉例而言,假設前述預設數量為3,則當某特定影片的詮釋資料中有3筆匹配於各第一貼文的第一關鍵字時,處理器120可定義此特定影片為第一影片。換言之,假設另一特定影片的詮釋資料中只有2筆匹配於各第一貼文的第一關鍵字,則處理器120可不定義此特定影片為第一影片。藉此,可令處理器120進一步將較不熱門的影片濾除,使得後續的派片策略可更貼近時事。In other embodiments, the processor 120 may further define the specific movie as the first movie when the interpretation data of the specific movie matches a preset number of the first keywords of each first post. For example, assuming that the preset number is 3, when there are 3 first keywords matching the first post in the interpretation data of a specific movie, the processor 120 may define the specific movie as the first movie . In other words, assuming that there are only 2 first keywords matching the first post in the interpretation data of another specific movie, the processor 120 may not define this specific movie as the first movie. In this way, the processor 120 can further filter the less popular videos, so that the subsequent distribution strategy can be closer to current events.

在依前述教示從影片中找出第一影片之後,在步驟260中,處理器120推廣第一影片。在一實施例中,處理器120可判斷第一影片是否為未上架影片,若是則將第一影片派送至影音串流終端設備20,若否則提高第一影片被派送至影音串流終端設備20的順位。前述未上架影片例如包括已有一段時間未被派送至影音串流終端設備20的影片資料庫中的影片。因此,當被判斷為對應於熱門時事的第一影片為未上架影片時,處理器120可相應地將第一影片派送至影音串流終端設備20,以供使用者觀看。另一方面,若前述第一影片為已上架影片,則處理器120可藉由提高第一影片被派送至影音串流終端設備20的順位來提升第一影片被使用者觀看到的機率。After finding the first movie from the movies according to the aforementioned teachings, in step 260, the processor 120 promotes the first movie. In one embodiment, the processor 120 may determine whether the first movie is an unlisted movie, and if so, send the first movie to the video streaming terminal device 20; otherwise, increase the first movie to the video streaming terminal device 20 The order. The aforementioned unlisted movies include, for example, movies that have not been delivered to the movie database of the video streaming terminal device 20 for some time. Therefore, when it is determined that the first movie corresponding to the popular current event is an unlisted movie, the processor 120 may correspondingly send the first movie to the video streaming terminal device 20 for the user to watch. On the other hand, if the first movie is an already-released movie, the processor 120 may increase the probability that the first movie is viewed by the user by increasing the order in which the first movie is sent to the video streaming terminal device 20.

在其他實施例中,當影片推廣裝置100所屬的多媒體內容傳輸平台上設置有一推荐影片專區(其例如可顯示於MOD、IPTV及OTT的主頁面中供使用者選取)時,處理器120亦可將前述第一影片放入此推荐影片專區,用以提升使用者注意到第一影片的機率。In other embodiments, when a recommended movie section is set on the multimedia content transmission platform to which the movie promotion device 100 belongs (for example, it can be displayed on the main pages of MOD, IPTV, and OTT for users to select), the processor 120 may also The aforementioned first video is put into this recommended video area, so as to increase the probability that a user notices the first video.

另外,處理器120亦可對管理人員發出關聯於第一影片的通知,藉以讓管理人員協助推廣第一影片,但本發明可不限於此。In addition, the processor 120 may also send a notification to the manager related to the first movie, so that the manager can help promote the first movie, but the present invention is not limited thereto.

綜上所述,本發明提供一種基於時事推廣影片的方法及其裝置,其可在所關注的社群網站的貼文中依據互動參數找出較對應於時事的貼文,並從貼文中取得相關的關鍵字。之後,可判斷影片資料庫中是否存在具有相應詮釋資料的第一影片,若有則將此第一影片進行推廣。舉例而言,本發明可依據第一影片是否為未上架影片來調整其派送情形,或是另行將第一影片置於所屬多媒體內容傳輸平台上的推荐影片專區中來提升第一影片的能見度。或者,本發明亦可通知相關人員來協助推廣第一影片。藉此,使用者能夠優先看到與時事相關的影片,從而改善使用者體驗。In summary, the present invention provides a method and a device for promoting a movie based on current events, which can find posts that correspond to current events based on interaction parameters in the posts of the social network concerned, and obtain relevant information from the posts. Keywords. After that, it can be determined whether there is a first movie with corresponding interpretation data in the movie database, and if so, the first movie is promoted. For example, the present invention can adjust the delivery situation of the first movie based on whether it is an unlisted movie, or separately place the first movie in a recommended movie area on the multimedia content transmission platform to improve the visibility of the first movie. Alternatively, the present invention may notify relevant persons to assist in promoting the first film. This allows users to prioritize videos related to current events, thereby improving the user experience.

雖然本發明已以實施例揭露如上,然其並非用以限定本發明,任何所屬技術領域中具有通常知識者,在不脫離本發明的精神和範圍內,當可作些許的更動與潤飾,故本發明的保護範圍當視後附的申請專利範圍所界定者為準。Although the present invention has been disclosed as above with the examples, it is not intended to limit the present invention. Any person with ordinary knowledge in the technical field can make some modifications and retouching without departing from the spirit and scope of the present invention. The protection scope of the present invention shall be determined by the scope of the attached patent application.

100‧‧‧影片推廣裝置100‧‧‧ video promotion device

110‧‧‧儲存電路110‧‧‧Storage Circuit

120‧‧‧處理器120‧‧‧ processor

20‧‧‧影音串流終端設備20‧‧‧Video streaming terminal equipment

210~260‧‧‧步驟210 ~ 260‧‧‧step

圖1是依據本發明之一實施例繪示的影片推廣裝置及影音串流終端設備的示意圖。 圖2是依據本發明之一實施例繪示的基於時事推廣影片的方法流程圖。FIG. 1 is a schematic diagram of a movie promotion device and a video streaming terminal device according to an embodiment of the present invention. FIG. 2 is a flowchart of a method for promoting a movie based on current events according to an embodiment of the present invention.

Claims (16)

一種基於時事推廣影片的方法,包括:取得一影片資料庫中多個影片的多個詮釋資料;取得一社群網站中多個貼文的多個互動參數以及該些貼文中的多個關鍵字,其中該些互動參數包括一讚數、一留言數、一分享次數、一觀看次數的至少其中之一;基於該些互動參數估計各該貼文的一受注目程度,其中該些互動參數個別對應於一加權分數,且基於該些互動參數估計各該貼文的該受注目程度的步驟包括:將各該貼文的該些加權分數加總以計算各該貼文的一分數,其中該分數正比於該受注目程度;基於各該貼文的該受注目程度從該些貼文中取出一第一貼文;基於該第一貼文的多個第一關鍵字從該些影片中找出一第一影片,其中該第一影片的該些詮釋資料的其中之一對應於該些第一關鍵字的其中之一;以及推廣該第一影片。A method for promoting videos based on current events includes: obtaining multiple interpretation data of multiple videos in a video database; obtaining multiple interactive parameters of multiple posts in a social networking site and multiple keywords in the posts , Where the interaction parameters include at least one of a number of likes, a number of comments, a number of shares, and a number of views; an estimated degree of attention of each post is estimated based on the interaction parameters, and the interaction parameters are individually The step corresponding to a weighted score and estimating the attention level of each post based on the interaction parameters includes: adding up the weighted scores of each post to calculate a score of each post, where the The score is proportional to the degree of attention; a first post is taken from the posts based on the degree of attention of each post; a plurality of first keywords based on the first post are found from the videos A first film, wherein one of the interpretation data of the first film corresponds to one of the first keywords; and promoting the first film. 如申請專利範圍第1項所述的方法,其中基於各該貼文的該受注目程度從該些貼文中取出該第一貼文的步驟包括:依據各該貼文的該分數將該些貼文降冪排序;以及從排序後的該些貼文取出該第一貼文,其中該第一貼文的一排名位於一預設名次數量內。The method according to item 1 of the scope of patent application, wherein the step of extracting the first post from the posts based on the degree of attention of each post includes: placing the posts according to the score of each post Sort the text in descending order; and extract the first post from the sorted posts, where a ranking of the first post is within a preset number of times. 如申請專利範圍第1項所述的方法,其中該第一貼文的該分數高於一預設門限值。The method according to item 1 of the scope of patent application, wherein the score of the first post is higher than a preset threshold. 如申請專利範圍第1項所述的方法,其中各該貼文的該些關鍵字取自於各該貼文的一標題、一內文及一哈希標籤(hashtag)的至少其中之一。The method according to item 1 of the scope of patent application, wherein the keywords of each post are obtained from at least one of a title, a body text, and a hashtag of each post. 如申請專利範圍第1項所述的方法,其中基於該第一貼文的該些第一關鍵字從該些影片中找出該第一影片的步驟包括:將該些第一關鍵字個別與各該影片的該些詮釋資料比對;以及當該些影片的其中之一者的該些詮釋資料的其中之一相同於該些第一關鍵字之一時,定義該些影片的其中該者為該第一影片。The method according to item 1 of the scope of patent application, wherein the step of finding the first movie from the videos based on the first keywords of the first post includes: individually matching the first keywords with Comparison of the interpretive data of each of the videos; and when one of the interpretive data of one of the videos is the same as one of the first keywords, defining the one of the videos as The first movie. 如申請專利範圍第1項所述的方法,其中各該貼文的一發文時間距離一當下時間不遠於一預設時間區間。The method according to item 1 of the scope of patent application, wherein a posting time of each post is not less than a preset time interval from a current time. 如申請專利範圍第1項所述的方法,其中各該影片皆在一授權期間內。The method according to item 1 of the scope of patent application, wherein each of the films is within a license period. 如申請專利範圍第7項所述的方法,其中推廣該第一影片的步驟包括:判斷該第一影片是否為一未上架影片,若是則將該第一影片派送至多個影音串流終端設備,若否則提高該第一影片被派送至該些影音串流終端設備的一順位。The method according to item 7 of the scope of patent application, wherein the step of promoting the first movie includes: determining whether the first movie is an unlisted movie, and if so, dispatching the first movie to a plurality of video streaming terminal devices, If not, the order of sending the first movie to the video streaming terminal devices is improved. 一種影片推廣裝置,包括:一儲存電路,儲存多個模組;以及一處理器,其連接該儲存電路,並存取該些模組以執行下列步驟:取得一影片資料庫中多個影片的多個詮釋資料;取得一社群網站中多個貼文的多個互動參數以及該些貼文中的多個關鍵字,其中該些互動參數包括一讚數、一留言數、一分享次數、一觀看次數的至少其中之一;基於該些互動參數估計各該貼文的一受注目程度,其中該些互動參數個別對應於一加權分數,且該處理器經配置以將各該貼文的該些加權分數加總以計算各該貼文的一分數,其中該分數正比於該受注目程度;基於各該貼文的該受注目程度從該些貼文中取出一第一貼文;基於該第一貼文的多個第一關鍵字從該些影片中找出一第一影片,其中該第一影片的該些詮釋資料的其中之一對應於該些第一關鍵字的其中之一;以及推廣該第一影片。A video promotion device includes: a storage circuit that stores a plurality of modules; and a processor that is connected to the storage circuit and accesses the modules to perform the following steps: obtaining a plurality of videos in a video database Multiple interpretation data; obtaining multiple interactive parameters of multiple posts in a social networking site and multiple keywords in the posts, wherein the interactive parameters include a number of likes, a number of comments, a number of shares, a At least one of views; estimating a degree of attention for each of the posts based on the interaction parameters, wherein the interaction parameters each correspond to a weighted score, and the processor is configured to assign the The weighted scores are added together to calculate a score for each post, where the score is proportional to the degree of attention; a first post is taken from the posts based on the degree of attention of each post; based on the first A plurality of first keywords of a post find a first movie from the videos, wherein one of the interpretation data of the first movie corresponds to one of the first keywords; and Push The first movie. 如申請專利範圍第9項所述的裝置,其中該處理器經配置以:依據各該貼文的該分數將該些貼文降冪排序;以及從排序後的該些貼文取出該第一貼文,其中該第一貼文的一排名位於一預設名次數量內。The device according to item 9 of the scope of patent application, wherein the processor is configured to: sort the posts in descending order according to the score of each post; and extract the first from the sorted posts Posts, where a ranking of the first post is within a preset number of times. 如申請專利範圍第9項所述的裝置,其中該第一貼文的該分數高於一預設門限值。The device according to item 9 of the scope of patent application, wherein the score of the first post is higher than a preset threshold. 如申請專利範圍第9項所述的裝置,其中各該貼文的該些關鍵字取自於各該貼文的一標題、一內文及一哈希標籤(hashtag)的至少其中之一。The device according to item 9 of the scope of patent application, wherein the keywords of each post are obtained from at least one of a title, a body text, and a hashtag of each post. 如申請專利範圍第9項所述的裝置,其中該處理器經配置以:將該些第一關鍵字個別與各該影片的該些詮釋資料比對;以及當該些影片的其中之一者的該些詮釋資料的其中之一相同於該些第一關鍵字之一時,定義該些影片的其中該者為該第一影片。The device according to item 9 of the scope of patent application, wherein the processor is configured to: individually compare the first keywords with the interpretation data of each of the videos; and when one of the videos When one of the interpretation data is the same as one of the first keywords, one of the videos is defined as the first movie. 如申請專利範圍第9項所述的裝置,其中各該貼文的一發文時間距離一當下時間不遠於一預設時間區間。The device according to item 9 of the scope of patent application, wherein a posting time of each post is not less than a preset time interval from a current time. 如申請專利範圍第9項所述的裝置,其中各該影片皆在一授權期間內。The device according to item 9 of the scope of patent application, wherein each of the films is within a license period. 如申請專利範圍第15項所述的裝置,其中該處理器經配置以判斷該第一影片是否為一未上架影片,若是則將該第一影片派送至多個影音串流終端設備,若否則提高該第一影片被派送至該些影音串流終端設備的一順位。The device according to item 15 of the scope of patent application, wherein the processor is configured to determine whether the first movie is an unlisted movie, and if so, dispatch the first movie to a plurality of video streaming terminal devices, and otherwise improve The first movie is sent to a sequence of the video streaming terminal devices.
TW107100262A 2018-01-04 2018-01-04 Method for promoting videos based on public opinions and apparatus using the same TWI658726B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
TW107100262A TWI658726B (en) 2018-01-04 2018-01-04 Method for promoting videos based on public opinions and apparatus using the same

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
TW107100262A TWI658726B (en) 2018-01-04 2018-01-04 Method for promoting videos based on public opinions and apparatus using the same

Publications (2)

Publication Number Publication Date
TWI658726B true TWI658726B (en) 2019-05-01
TW201931867A TW201931867A (en) 2019-08-01

Family

ID=67348105

Family Applications (1)

Application Number Title Priority Date Filing Date
TW107100262A TWI658726B (en) 2018-01-04 2018-01-04 Method for promoting videos based on public opinions and apparatus using the same

Country Status (1)

Country Link
TW (1) TWI658726B (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101923544A (en) * 2009-06-15 2010-12-22 北京百分通联传媒技术有限公司 Method for monitoring and displaying Internet hot spots
CN103748530A (en) * 2012-08-17 2014-04-23 弗莱克斯电子有限责任公司 Media center
CN106331778A (en) * 2015-07-06 2017-01-11 腾讯科技(深圳)有限公司 Video recommendation method and device

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101923544A (en) * 2009-06-15 2010-12-22 北京百分通联传媒技术有限公司 Method for monitoring and displaying Internet hot spots
CN103748530A (en) * 2012-08-17 2014-04-23 弗莱克斯电子有限责任公司 Media center
CN106331778A (en) * 2015-07-06 2017-01-11 腾讯科技(深圳)有限公司 Video recommendation method and device

Also Published As

Publication number Publication date
TW201931867A (en) 2019-08-01

Similar Documents

Publication Publication Date Title
JP6935523B2 (en) Methods and systems for displaying contextually relevant information about media assets
US9936243B2 (en) Aggregating likes to a main page
US8510770B1 (en) Predicting live programs
WO2018192437A1 (en) Media content recommendation method, server, client and storage medium
JP5981024B2 (en) Sharing TV and video programs via social networking
US8832277B2 (en) Community tagging of a multimedia stream and linking to related content
US8572647B2 (en) Online ad placement based on user metrics for hosted media
US20120158527A1 (en) Systems, Methods and/or Computer Readable Storage Media Facilitating Aggregation and/or Personalized Sequencing of News Video Content
US20190266199A1 (en) Managing access rights to content using social media
US11558480B2 (en) Tracking content use via social media
EP2870775A1 (en) Dynamic media segment pricing
US9542395B2 (en) Systems and methods for determining alternative names
WO2014149686A1 (en) Sharing of media content
US20220292616A1 (en) Social watchlist
US20160021051A1 (en) Providing Access To Content Via Social Media
US10877982B1 (en) Detection of popular content with narrow appeal
TWI658726B (en) Method for promoting videos based on public opinions and apparatus using the same
US20150332309A1 (en) Advertisement scoring system and method