CN108536814B - Live broadcast room recommendation method, computer-readable storage medium and electronic device - Google Patents
Live broadcast room recommendation method, computer-readable storage medium and electronic deviceDownload PDFInfo
- Publication number
- CN108536814B CN108536814BCN201810304083.1ACN201810304083ACN108536814BCN 108536814 BCN108536814 BCN 108536814BCN 201810304083 ACN201810304083 ACN 201810304083ACN 108536814 BCN108536814 BCN 108536814B
- Authority
- CN
- China
- Prior art keywords
- live broadcast
- live
- room
- rooms
- broadcast room
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
- 238000000034methodMethods0.000titleclaimsabstractdescription21
- 230000006399behaviorEffects0.000description4
- 230000002238attenuated effectEffects0.000description2
- 238000010586diagramMethods0.000description2
- 230000000694effectsEffects0.000description2
- 238000005065miningMethods0.000description2
- 238000012986modificationMethods0.000description2
- 230000004048modificationEffects0.000description2
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
Translated fromChinese
Description
Translated fromChinese技术领域technical field
本发明涉及大数据推荐领域，尤其涉及一种基于观看路径的直播间推荐方法。The invention relates to the field of big data recommendation, in particular to a method for recommending a live broadcast room based on a viewing path.
背景技术Background technique
随着直播平台的发展，直播平台上的直播间越来越多，用户想从众多的直播间中选择一个自己喜欢的看的直播间变得更加困难，如何为用户推荐直播间成为了目前急需解决的问题。目前常用的向用户推荐直播间的方法是热播榜推荐，也就是向用户推荐一段时间内直播网站里按照受欢迎程度排序的主播的榜单。这种方法的缺点是没有考虑到用户的个性化需求，其对新用户具有一定的效果，但对于老用户不仅不能满足用户的需求，还会让用户觉得反感。With the development of live broadcast platforms, there are more and more live broadcast rooms on the live broadcast platform. It becomes more difficult for users to choose a live broadcast room they like to watch from among the many live broadcast rooms. How to recommend live broadcast rooms for users has become an urgent need. solved problem. At present, the commonly used method to recommend live broadcast rooms to users is to recommend the hot broadcast list, that is, to recommend to users the list of the anchors in the live broadcast website sorted by popularity within a period of time. The disadvantage of this method is that it does not take into account the individual needs of users, which has a certain effect on new users, but not only can not meet the needs of users for old users, but also makes users feel disgusted.
事实上，用户在直播平台上对直播间的观看行为是存在先后顺序的，每个用户都有一条属于自己的直播间观看路径，该路径表面上反映了用户观看直播间的时间顺序，但是从更深层次的角度来看，观看路径代表了用户的观看喜好，往往相似的直播间观看的时间间隔会很小，所以用户的观看路径是一个值得挖掘的信息。In fact, users' viewing behaviors of the live broadcast room on the live broadcast platform are sequential. Each user has a viewing path belonging to the live broadcast room. From a deeper perspective, the viewing path represents the user's viewing preferences, and the viewing time interval of similar live broadcast rooms is often very small, so the user's viewing path is a piece of information worthy of mining.
发明内容SUMMARY OF THE INVENTION
基于上述思路，为了克服上述问题的至少一个方面，本发明实施例提供一种直播间推荐方法，通过用户的观看路径来确定直播间之间的权重，进而确定直播间之间的相似度，再根据用户的观看记录对用户进行个性化的推荐。Based on the above ideas, in order to overcome at least one aspect of the above problems, an embodiment of the present invention provides a method for recommending a live room, determining the weight between the live rooms through the viewing path of the user, and then determining the similarity between the live rooms, and then determining the similarity between the live rooms. Personalized recommendations are made to users based on their viewing records.
根据本发明的一个方面，提供一种直播间推荐方法，包括如下步骤：According to one aspect of the present invention, a method for recommending a live broadcast room is provided, comprising the following steps:
步骤S1，根据观看记录，对直播平台上的每个用户在预设时间内观看的直播间按照时间顺序进行排序；Step S1, according to the viewing records, sort the live broadcast rooms watched by each user on the live broadcast platform in the preset time in chronological order;
步骤S2，获取直播平台中所有被观看过的直播间集合R，计算直播间集合R中的任意两个直播间之间的权重值；Step S2, obtain all the live broadcast room sets R that have been watched in the live broadcast platform, and calculate the weight value between any two live broadcast rooms in the live broadcast room set R;
步骤S3，根据任意两个直播间之间的权重值计算任意两个直播间之间的相似度值；Step S3, calculate the similarity value between any two live broadcast rooms according to the weight value between any two live broadcast rooms;
步骤S4，对于直播间集合R中的任一源直播间而言，将与任一源直播间相似的直播间按照相似度值由大到小的顺序排列在源直播间的推荐列表中；以及Step S4, for any source live broadcast room in the set R of live broadcast rooms, arrange the live broadcast rooms similar to any source live broadcast room in the recommendation list of the source live broadcast room according to the similarity value in descending order; And
步骤S5，获取用户最后观看的直播间作为上述源直播间，将源直播间的推荐列表中的处于开播状态的直播间依次推荐给用户。In step S5, the last live broadcast room watched by the user is obtained as the source live broadcast room, and the live broadcast rooms in the open state in the recommendation list of the source live broadcast room are sequentially recommended to the user.
根据一些实施例，在步骤S1之前还包括步骤：删除每个用户在预设时间内单次观看时间小于或等于预定时间的直播间的观看记录。According to some embodiments, before step S1, it further includes a step of: deleting the viewing records of each user in the live broadcast room whose single viewing time is less than or equal to the predetermined time within the preset time.
根据一些实施例，根据下式计算直播间集合R中的任意两个直播间之间的权重值：According to some embodiments, the weight value between any two live rooms in the set R of live rooms is calculated according to the following formula:
其中，wfb是直播间f到直播间b的权重值，M(f)是观看了直播间f的人数，M(f→b)是观看了直播间f后继续观看直播间b的人数。Among them, wfb is the weight value from live room f to live room b, M(f) is the number of people who watched live room f, and M(f→b) is the number of people who continue to watch live room b after watching live room f.
根据一些实施例，在步骤S2和步骤S3之间还包括以下步骤：获取直播间b的直接关联直播间集合N(b)，直接关联直播间集合N(b)指的是所有用户在观看直播间b之前所观看的紧邻的直播间的集合。According to some embodiments, the following steps are further included between step S2 and step S3: obtaining the set N(b) of directly related live broadcast rooms b, and the set N(b) of directly related live broadcast rooms refers to the fact that all users are watching the live broadcast The set of immediately adjacent live rooms watched before room b.
根据一些实施例，根据下式计算两个直播间之间的相似度值：According to some embodiments, the similarity value between the two live rooms is calculated according to the following formula:
其中，sim(a，b)是直播间a和b的相似度值；α是传导衰减因子，α的取值范围是0.8～0.9；k是迭代轮次，k是整数，取值范围为10～20；N(b)是直播间b的直接关联直播间集合；wib是直播间b的直接关联直播间i到直播间b的权重值；wjb是直播间b的直接关联直播间j到直播间b的权重值；sim(a，i)0＝wai，sim(a，a)0＝1。Among them, sim(a, b) is the similarity value between a and b in the live broadcast room; α is the conduction attenuation factor, and the value of α ranges from 0.8 to 0.9; k is the iteration round, k is an integer, and the value range is 10 ~20; N(b) is the set of directly related live rooms of live room b; wib is the weight value of live room i directly related to live room b to live room b; wjb is the directly related live room j of live room b The weight value to the live room b; sim(a, i)0 =wai , sim(a, a)0 =1.
根据本发明的另一个方面，提供一种计算机可读存储介质，其上存储有可执行指令，指令在由处理器执行时，可以实现根据上述实施例中的任一项的直播间推荐方法的步骤。According to another aspect of the present invention, there is provided a computer-readable storage medium on which executable instructions are stored, and when executed by a processor, the instructions can implement the method for recommending a live room according to any one of the foregoing embodiments. step.
根据本发明的又一个方面，提供一种电子设备，其包括：According to yet another aspect of the present invention, an electronic device is provided, comprising:
存储器，用于存储可执行指令；以及memory for storing executable instructions; and
处理器，用于执行存储器中存储的可执行指令，以实现根据上述实施例中的任一项的直播间推荐方法的步骤。The processor is configured to execute the executable instructions stored in the memory, so as to implement the steps of the method for recommending a live room according to any one of the foregoing embodiments.
与现有技术相比，本发明具有以下优点：通过用户的观看路径来确定直播间之间的权重，进而确定直播间之间的相似度，再根据用户的观看记录对用户进行个性化的推荐，提高了推荐的准确性，并且最大程度上保证推荐的直播间是用户喜欢观看的直播间。Compared with the prior art, the present invention has the following advantages: the weight between the live rooms is determined by the viewing path of the user, and then the similarity between the live rooms is determined, and then the user is recommended according to the user's viewing record. , which improves the accuracy of the recommendation and guarantees to the greatest extent that the recommended live room is the one that the user likes to watch.
附图说明Description of drawings
通过下文中参照附图对本发明所作的描述，本发明的其它目的和优点将显而易见，并可帮助对本发明有全面的理解。Other objects and advantages of the present invention will be apparent from the following description of the present invention with reference to the accompanying drawings, and may assist in a comprehensive understanding of the present invention.
图1是实施根据本发明实施例的直播间推荐方法的整体流程图；1 is an overall flow chart of implementing a method for recommending a live room according to an embodiment of the present invention;
图2是根据本发明实施例的计算机可读存储介质的结构示意图；2 is a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present invention;
图3是根据本发明实施例的电子设备的结构示意图。FIG. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
具体实施方式Detailed ways
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。In order to make the purposes, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments These are some embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
在本发明实施例中使用的术语是仅仅出于描述特定实施例的目的，而非旨在限制本发明。除非另外定义，本发明使用的技术术语或者科学术语应当为本发明所属领域内具有一般技能的人士所理解的通常意义。The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. Unless otherwise defined, technical or scientific terms used in the present invention should have the ordinary meaning as understood by one of ordinary skill in the art to which the present invention belongs.
本发明提供一种直播间推荐方法，根据图1所示，该方法包括以下步骤：The present invention provides a method for recommending a live broadcast room. As shown in FIG. 1 , the method includes the following steps:
S1，根据观看记录，对直播平台上的每个用户在预设时间内观看的直播间按照时间顺序进行排序。S1, according to the viewing records, sort the live broadcast rooms watched by each user on the live broadcast platform in a chronological order.
直播平台上的每个用户观看直播间都会产生记录，这些记录都保存在数据库中，将每个用户在预设时间内的观看记录从数据库中调取出来，这个预设时间是可以自定义的，例如，在本实施例中预设时间可以是7天。当然，在其他实施例中，也可以是其他时间长度，比如可以为更长的时间长度，例如30天，还可以是较短的时间长度，例如数小时。然后，将记录上的直播间按照时间顺序排序，时间越早的直播间可以排在越前面。Each user on the live broadcast platform will generate records when watching the live broadcast room. These records are stored in the database. The viewing records of each user within a preset time are retrieved from the database. This preset time can be customized. For example, in this embodiment, the preset time may be 7 days. Of course, in other embodiments, other time lengths are also possible, such as longer time lengths, such as 30 days, or shorter time lengths, such as several hours. Then, the recorded live broadcast rooms are sorted in chronological order, and the earlier live broadcast rooms can be arranged in the front.
在一些可能的实施例中，在进行上述步骤之前，还可以进行如下步骤：删除每个用户在预设时间内单次观看时间小于或等于预定时间的直播间的观看记录。用户观看时间小于或等于预定时间的观看行为可能只是不小心点到该直播间或者其他某些类似的行为，并不是真正观看了该直播间或者对该直播间有兴趣，这个步骤是为了保留有效的观看行为，减小数据的误差，从而最大化地保证数据的准确性。这个预定时间也是可以自定义的，为了减小误差，在本实施例中可以设定预定时间为1分钟。In some possible embodiments, before the above steps are performed, the following step may be performed: delete the viewing records of each user in the live broadcast room whose single viewing time is less than or equal to the predetermined time within the preset time. The viewing behavior of the user whose viewing time is less than or equal to the predetermined time may be just accidentally clicking on the live room or some other similar behavior, not actually watching the live room or interested in the live room, this step is to keep the effective The viewing behavior can reduce the error of the data, so as to maximize the accuracy of the data. The predetermined time can also be customized. In order to reduce errors, in this embodiment, the predetermined time can be set to 1 minute.
S2，获取直播平台中所有被观看过的直播间集合R，计算直播间集合R中的任意两个直播间之间的权重值。S2: Obtain all the watched live room sets R in the live broadcast platform, and calculate the weight value between any two live broadcast rooms in the live broadcast room set R.
在预设时间内，可能有些直播间没有被用户观看过，这些未被用户观看过的直播间将无法计算与其他直播间之间的相似度，为了减少计算量，需要排除这些未被观看过的直播间。从数据库中获取直播平台上所有被用户观看过的直播间，将这些直播组成一个集合R，计算直播间集合R中的任意两个直播间之间的权重值，例如，可以根据下式计算直播间集合R中的直播间f和直播间b之间的权重值：Within the preset time, there may be some live broadcast rooms that have not been watched by users. These live broadcast rooms that have not been watched by users will not be able to calculate the similarity with other live broadcast rooms. In order to reduce the amount of calculation, it is necessary to exclude these unwatched live rooms. 's live broadcast room. Obtain all the live broadcast rooms on the live broadcast platform that have been watched by the user from the database, group these live broadcasts into a set R, and calculate the weight value between any two live broadcast rooms in the live broadcast room set R. For example, the live broadcast can be calculated according to the following formula The weight value between the live room f and the live room b in the room set R:
其中，wfb是直播间f到直播间b的权重值，M(f)是观看了直播间f的人数，M(f→b)是观看了直播间f后直接继续观看直播间b的人数。权重值，可以是指用户观看了直播间f后接着观看直播间b的概率。权重值越大，说明概率越高，也就说明用户在观看了直播间f后接着观看直播间b的概率越高。这在一定程度上反映了直播间f和直播间b的关联性，概率越高，说明直播间f和直播间b的关联性越大。Among them, wfb is the weight value from live room f to live room b, M(f) is the number of people who watched live room f, and M(f→b) is the number of people who continue to watch live room b directly after watching live room f . The weight value may refer to the probability that the user watches the live room f and then watches the live room b. The larger the weight value, the higher the probability, which means that the user has a higher probability of watching the live room b after watching the live room f. This reflects the correlation between live room f and live room b to a certain extent. The higher the probability, the greater the correlation between live room f and live room b.
在一些可能的实施例中，在计算完集合R中任意两个直播间之间的权重值后还包括如下步骤：获取直播间b的直接关联直播间集合N(b)，直接关联直播间集合N(b)指的是所有用户在观看直播间b之前所观看的紧邻的直播间的集合。这里的“紧邻”是指用户观看完该直播间后直接观看直播间b，在观看该直播间和观看直播间b之间没有观看其他直播间。In some possible embodiments, after calculating the weight value between any two live rooms in the set R, the following steps are further included: obtaining the set N(b) of the directly related live rooms of the live room b, and directly related to the set of live rooms N(b) refers to the set of immediately adjacent live rooms watched by all users before viewing live room b. The "close proximity" here means that the user directly watches the live broadcast room b after watching the live broadcast room, and does not watch other live broadcast rooms between watching the live broadcast room and watching the live broadcast room b.
S3，根据任意两个直播间之间的权重值计算任意两个直播间之间的相似度值。S3, calculate the similarity value between any two live broadcast rooms according to the weight value between any two live broadcast rooms.
例如，可以根据下式计算直播间a和直播间b之间的相似度值：For example, the similarity value between live room a and live room b can be calculated according to the following formula:
其中，sim(a，b)是直播间a和b的相似度值；α是传导衰减因子，α的取值范围是0～1，通常可以取0.8-0.9之间的数值；k是迭代轮次，k是整数，通常取值范围为10～20；N(b)是直播间b的直接关联直播间集合；wib是直播间b的直接关联直播间i到直播间b的权重值；wib是直播间b的直接关联直播间j到直播间b的权重值；sim(a，i)0＝wai，sim(a，a)0＝1。Among them, sim(a, b) is the similarity value between a and b in the live broadcast room; α is the conduction attenuation factor, and the value range of α is 0 to 1, which can usually take a value between 0.8 and 0.9; k is the iteration round times, k is an integer, usually in the range of 10 to 20; N(b) is the set of directly related live rooms of live room b; wib is the weight value of live room i to live room b directly related to live room b; wib is the weight value of the live room j directly related to the live room b to the live room b; sim(a, i)0 =wai , sim(a, a)0 =1.
S4，对于直播间集合R中的任一源直播间而言，将与任一源直播间相似的直播间按照相似度值由大到小的顺序排列在源直播间的推荐列表中。S4 , for any source live broadcast room in the set R of live broadcast rooms, arrange the live broadcast rooms similar to any source live broadcast room in the recommendation list of the source live broadcast rooms in descending order of similarity value.
举个例子说明一下源直播间的含义：直播间a和直播间b的相似度值为0.3，直播间a和直播间c的相似度值为0.2，直播间a和直播间d的相似度值为0.1，那么这里的源直播间就是直播间a，也即是说，源直播间是指作为基础直播间，与其他多个直播间具有相似关系的直播间。在这个例子里，按照相似度值由大到小的顺序进行排列，排列顺序如下：b、c、d。Take an example to illustrate the meaning of the source live room: the similarity value of live room a and live room b is 0.3, the similarity value of live room a and live room c is 0.2, and the similarity value of live room a and live room d. is 0.1, then the source live room here is the live room a, that is to say, the source live room refers to the basic live room that has a similar relationship with other live broadcast rooms. In this example, the similarity values are arranged in descending order, and the order is as follows: b, c, d.
S5，获取用户最后观看的直播间作为上述源直播间，将源直播间的推荐列表中的处于开播状态的直播间依次推荐给用户。S5 , acquiring the live broadcast room last viewed by the user as the source live broadcast room, and recommending the live broadcast rooms in the open state in the recommendation list of the source live broadcast room to the user in sequence.
根据用户的观看记录，找到用户最后观看的直播间，在将该直播间的推荐列表中的直播间推荐给用户之前，还需要判断这些直播间是否处于开播状态，如果没有开播，则不向用户推荐这些直播间，在确定了直播间的开播状态后，将处于开播状态的直播间按照推荐列表中的排序依次推荐给用户。例如，接着上面的例子，用户最后观看的直播间是a，直播间c没有开播，那么就按照b、d的顺序依次向用户推荐。According to the user's viewing record, find the live broadcast room last watched by the user, and before recommending the live broadcast room in the recommended list of the live broadcast room to the user, it is also necessary to judge whether these live broadcast rooms are in the open state. These live broadcast rooms are recommended. After the live broadcast state of the live broadcast room is determined, the live broadcast rooms in the open broadcast state are recommended to the user in order according to the order in the recommendation list. For example, following the above example, the last live broadcast room watched by the user is a, and the live broadcast room c is not on the air, so it is recommended to the user in the order of b and d.
下面列举一个实际例子具体说明本发明是如何计算两个直播间的相似度值的。An actual example is given below to specifically illustrate how the present invention calculates the similarity value between two live broadcasts.
假设有四条观看路径：a→c，a→d，c→b，d→b。观看直播间a的人数是1000，观看了直播间a后继续观看直播间c的人数是200，观看了直播间a后继续观看直播间d的人数是600，观看直播间c的人数是300，观看了直播间c后继续观看直播间b的人数是150，观看直播间d的人数是800，观看了直播间d后继续观看直播间b的人数是240。Suppose there are four viewing paths: a→c, a→d, c→b, d→b. The number of people watching live room a is 1000, the number of people watching live room c after watching live room a is 200, the number of people watching live room d after watching live room a is 600, and the number of people watching live room c is 300, After watching live room c, the number of people who continue to watch live room b is 150, the number of people watching live room d is 800, and the number of people who continue to watch live room b after watching live room d is 240.
首先计算权重值，计算结果如下：First calculate the weight value, the calculation results are as follows:
因为sim(a，i)0＝wai，所以sim(a，c)0＝wac，sim(a，d)0＝wad。Since sim(a, i)0 = wai , sim(a, c)0 = wac and sim(a, d)0 = wad .
α取0.8，第一轮迭代，a和b之间的相似度值如下：α is taken as 0.8, the first round of iteration, the similarity value between a and b is as follows:
同理可得，sim(a，c)1＝0.16，sim(a，d)1＝0.48。In the same way, sim(a, c)1 =0.16, sim(a, d)1 =0.48.
第二轮迭代，a和b之间的相似度值如下：In the second iteration, the similarity value between a and b is as follows:
……...
第十轮迭代，a和b之间的相似度值如下：In the tenth iteration, the similarity value between a and b is as follows:
在这个例子里，为了方便描述，并没有加入直播间c和直播间d的其他直接关联直播间，所以直播间a到直播间c和直播间a到直播间d的权重都是1，这就导致sim(a，c)k+1＝αsim(a，c)k，sim(a，d)k+1＝αsim(a，d)k，从而使得直播间a和直播间b之间的相似度值有所衰减。上述例子考虑的情景较为简单，在实际操作中，直播间c和直播间d还存在着其他关联直播间，真实的相似度值不会像上述示例一样不断衰减。In this example, for the convenience of description, there are no other directly related live rooms added to live room c and live room d, so the weights of live room a to live room c and live room a to live room d are all 1, which is leads to sim(a, c)k+1 = αsim(a, c)k , sim(a, d)k+1 = αsim(a, d)k , thus making the similarity between live room a and live room b The degree value is attenuated. The scenario considered in the above example is relatively simple. In actual operation, there are other related live rooms in live room c and live room d, and the real similarity value will not be attenuated like the above example.
由于用户观看直播间的路径代表了用户的喜好，路径可以形成一定的共现关系，本实施例中通过挖掘路径的深层含义，找到直播间之间的相似关系，从而对用户进行个性化的直播间推荐，极大地增强了推荐的效果，并提高了推荐的准确性。Since the path of the user watching the live broadcast room represents the user's preference, the path can form a certain co-occurrence relationship. In this embodiment, by mining the deep meaning of the path, the similar relationship between the live broadcast rooms is found, so as to carry out personalized live broadcast for the user. It can greatly enhance the effect of recommendation and improve the accuracy of recommendation.
基于同一发明构思，参考图2所示，本发明还提供一种计算机可读存储介质201，其上存储有可执行指令202，可执行指令202在由处理器执行时，可以实现根据上述实施例中的任一项所述的直播间推荐方法的步骤。Based on the same inventive concept, with reference to FIG. 2 , the present invention further provides a computer-
基于同一发明构思，参考图3所示，本发明还提供一种电子设备301，该电子设备301包括：Based on the same inventive concept, referring to FIG. 3 , the present invention further provides an
存储器310，其用于存储可执行指令311；以及
处理器320，其用于执行存储器310中存储的可执行指令311，以实现如上述实施例中任一项所述的直播间推荐方法的步骤。The
最后应说明的是：以上实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的精神和范围。Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand: it can still be Modifications are made to the technical solutions described in the foregoing embodiments, or some technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (6)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810304083.1ACN108536814B (en) | 2018-04-04 | 2018-04-04 | Live broadcast room recommendation method, computer-readable storage medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810304083.1ACN108536814B (en) | 2018-04-04 | 2018-04-04 | Live broadcast room recommendation method, computer-readable storage medium and electronic device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108536814A CN108536814A (en) | 2018-09-14 |
| CN108536814Btrue CN108536814B (en) | 2022-06-21 |
Family
ID=63482782
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810304083.1AActiveCN108536814B (en) | 2018-04-04 | 2018-04-04 | Live broadcast room recommendation method, computer-readable storage medium and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108536814B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111083503B (en)* | 2018-10-22 | 2022-02-22 | 武汉斗鱼网络科技有限公司 | Method, device, equipment and storage medium for calculating similarity of live broadcast rooms |
| CN109977264B (en)* | 2019-02-19 | 2022-09-09 | 武汉斗鱼鱼乐网络科技有限公司 | A user recommendation method, system, server and storage medium based on meta-path similarity |
| CN112770126A (en)* | 2020-12-29 | 2021-05-07 | 北京达佳互联信息技术有限公司 | Live broadcast room pushing method and device, server and storage medium |
| CN113592543B (en)* | 2021-07-27 | 2024-08-02 | 北京达佳互联信息技术有限公司 | Live broadcast evaluation method and device |
| CN113766263B (en)* | 2021-09-08 | 2022-07-19 | 北京快来文化传播集团有限公司 | Live broadcast room recommendation method and device |
| CN113938700B (en)* | 2021-10-27 | 2024-03-12 | 广州方硅信息技术有限公司 | Live broadcast room switching method and device and computer equipment |
| CN114969514B (en)* | 2022-05-06 | 2024-10-15 | 北京百度网讯科技有限公司 | Live broadcast recommendation method and device and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105338408A (en)* | 2015-12-02 | 2016-02-17 | 南京理工大学 | Video recommending method based on time factor |
| CN105847984A (en)* | 2016-03-25 | 2016-08-10 | 乐视控股（北京）有限公司 | Video recommending method and apparatus |
| CN106658083A (en)* | 2015-10-30 | 2017-05-10 | 北京国双科技有限公司 | Watching channel path counting method and watching channel path counting device |
| CN107835441A (en)* | 2017-10-10 | 2018-03-23 | 武汉斗鱼网络科技有限公司 | Live recommendation method, storage medium, equipment and system based on path prediction |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8117281B2 (en)* | 2006-11-02 | 2012-02-14 | Addnclick, Inc. | Using internet content as a means to establish live social networks by linking internet users to each other who are simultaneously engaged in the same and/or similar content |
- 2018
- 2018-04-04CNCN201810304083.1Apatent/CN108536814B/enactiveActive
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106658083A (en)* | 2015-10-30 | 2017-05-10 | 北京国双科技有限公司 | Watching channel path counting method and watching channel path counting device |
| CN105338408A (en)* | 2015-12-02 | 2016-02-17 | 南京理工大学 | Video recommending method based on time factor |
| CN105847984A (en)* | 2016-03-25 | 2016-08-10 | 乐视控股（北京）有限公司 | Video recommending method and apparatus |
| CN107835441A (en)* | 2017-10-10 | 2018-03-23 | 武汉斗鱼网络科技有限公司 | Live recommendation method, storage medium, equipment and system based on path prediction |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108536814A (en) | 2018-09-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108536814B (en) | Live broadcast room recommendation method, computer-readable storage medium and electronic device | |
| US11263240B2 (en) | Organizing survey text responses | |
| JP6685541B2 (en) | Method and apparatus for optimizing user credit score | |
| US10997257B2 (en) | Aggregating news events on online social networks | |
| CN105706083B (en) | Methods, systems, and media for providing answers to user-specific queries | |
| JP4650541B2 (en) | RECOMMENDATION DEVICE AND METHOD, PROGRAM, AND RECORDING MEDIUM | |
| US8555173B2 (en) | Recommendation engine | |
| CN104156392B (en) | Good friend and application personalized recommendation method and system | |
| US9098551B1 (en) | Method and system for ranking content by click count and other web popularity signals | |
| US9467744B2 (en) | Comment-based media classification | |
| JP6689515B2 (en) | Method and apparatus for identifying the type of user geographic location | |
| CN110209827B (en) | Search method, search device, computer-readable storage medium, and computer device | |
| US9679018B1 (en) | Document ranking based on entity frequency | |
| US9009298B2 (en) | Methods and apparatus to determine audience engagement indices associated with media presentations | |
| US20150332373A1 (en) | Method and system for pushing mobile application | |
| US20130297581A1 (en) | Systems and methods for customized filtering and analysis of social media content collected over social networks | |
| US8949228B2 (en) | Identification of new sources for topics | |
| US10248645B2 (en) | Measuring phrase association on online social networks | |
| CN107734062A (en) | Information push method and device | |
| CN106454536B (en) | Method and device for determining information recommendation degree | |
| CN111344730B (en) | Content management system and method of operation thereof | |
| US8954451B2 (en) | Selecting microblog entries based on web pages, via path similarity within hierarchy of categories | |
| US20130290340A1 (en) | Providing Control Over a Personalized Category of Information | |
| CN110175264A (en) | Construction method, server and the computer readable storage medium of video user portrait | |
| CN109587527B (en) | Personalized video recommendation method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | Effective date of registration:20250121 Address after:1208, 12th Floor, Building 2, 186A Litang Road, Changping District, Beijing 100000 Patentee after:Mingshida (Beijing) Sports Technology Co.,Ltd. Country or region after:China Address before:430000 Wuhan Donghu Development Zone, Wuhan, Hubei Province, No. 1 Software Park East Road 4.1 Phase B1 Building 11 Building Patentee before:WUHAN DOUYU NETWORK TECHNOLOGY Co.,Ltd. Country or region before:China | |
| TR01 | Transfer of patent right |