WO2018023682A1 - 一种根据收听习惯推荐内容的方法和推荐系统 - Google Patents

一种根据收听习惯推荐内容的方法和推荐系统 Download PDF

Info

Publication number
WO2018023682A1
WO2018023682A1 PCT/CN2016/093479 CN2016093479W WO2018023682A1 WO 2018023682 A1 WO2018023682 A1 WO 2018023682A1 CN 2016093479 W CN2016093479 W CN 2016093479W WO 2018023682 A1 WO2018023682 A1 WO 2018023682A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
listening
unit
content
label
Prior art date
Application number
PCT/CN2016/093479
Other languages
English (en)
French (fr)
Inventor
吴晓敏
Original Assignee
吴晓敏
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 吴晓敏 filed Critical 吴晓敏
Priority to PCT/CN2016/093479 priority Critical patent/WO2018023682A1/zh
Publication of WO2018023682A1 publication Critical patent/WO2018023682A1/zh

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor

Definitions

  • the invention belongs to the field of Internet, and in particular relates to a method for recommending content according to listening habits and a recommendation system.
  • Internet Radio or Internet FM contains a lot of content, such as historical humanities, social sciences, novels, radio dramas, storytelling, music, cross talk, foreign languages, talk shows and so on.
  • users have the habit of listening to specific styles during certain time periods, such as listening to more relaxed songs such as Maria Teng and Tsai Chin in the evening, to relax themselves, listening to more inspirational and popular songs at work, and encouraging and refreshing themselves.
  • users search for their favorite listening content according to their listening habits in a complex content and a specific time, the user operation is cumbersome, and there is no target, it takes a long time, and the user experience is not very it is good.
  • An embodiment of the present invention provides a method for recommending content according to a listening habit, and the purpose is to provide a situation in which a user experience cannot be searched for a user's user experience in a specific time.
  • a method of pushing a listening content according to a user's listening habit is provided.
  • the present invention is implemented in such a manner that a method of recommending content according to listening habits includes the following steps:
  • the user listens to the radio during the specific time period, the user is pushed with the same content as the most frequently occurring tag, and the user has not listened to the content.
  • the embodiment of the invention further provides a recommendation system, including:
  • a recording unit for recording a preset label related to the played content
  • a statistical unit wherein the input end is respectively connected to the output end of the recording unit and the output end of the checking unit, and is used for counting a label corresponding to the played content in the user listening record;
  • a finishing unit whose input end is connected with the output end of the statistical unit, and is used for sorting the number of occurrences of related tags
  • a pushing unit whose input end is connected to the output end of the sorting unit, and is used for pushing the user to have the same label as the most frequently appearing label when the user listens to the radio during the specific time period, and the user has not listened to the content.
  • the invention actively pushes the listening content with the same label to the user according to the listening habit of the user, combined with the listening time of the user, thereby improving the listening experience of the user.
  • FIG. 1 is a schematic flowchart of a method for recommending content according to a listening habit according to an embodiment of the present invention
  • FIG. 2 is a schematic structural diagram of a recommendation system according to an embodiment of the present invention.
  • FIG. 1 is a schematic flowchart of a method for recommending content according to a listening habit according to an embodiment of the present invention. For convenience of description, only parts related to the embodiment of the present invention are shown.
  • step S101 a preset tag related to the played content is recorded.
  • the user listens to the "Tomb Notes" novel and “Luo Ji thinking” as an example, sets the label of 'Tomb Tomb' on “Tomb Notes”, and sets the label of 'Talk Show' on 'Luo Ji thinking' .
  • step S102 the user's listening record for a specific period of time is checked.
  • step S103 the tag corresponding to the played content in the user's listening record is counted.
  • step S104 the number of occurrences of the related tags is organized.
  • step S105 When the user listens to the radio during the specific time period, the process proceeds to step S105, and the user is pushed with the same content as the most frequently occurring tag, and the user has not listened to the content.
  • the system will recommend different contents with the same 'Tomb' label, such as "Ghost Blowing Light” with "Tomb” tag, "Tombstone Search” ⁇ , etc., for the user to choose; when the user listens to the content from 5 pm to 6 pm, the system will recommend different content with the same 'talk show' tag, such as the 'talk show' tag.
  • Xiaosongqi talks about ', 'dudu', 'old beam story sink', etc., for users to choose.
  • the invention actively pushes the listening content with the same label to the user according to the listening habit of the user, combined with the listening time of the user, thereby improving the listening experience of the user.
  • FIG. 2 is a schematic structural diagram of a recommendation system according to an embodiment of the present invention, where the recommendation system includes:
  • a recording unit 21 configured to record a preset label related to the played content
  • the checking unit 22 is configured to check a listening record of the user during a specific time period
  • the statistics unit 23 is connected to the output end of the recording unit 21 and the output end of the checking unit 22, and is used for counting the label corresponding to the playing content in the user listening record;
  • a sorting unit 24 whose input end is connected with the output end of the statistical unit 23, and is used for sorting the number of occurrences of related tags;
  • the pushing unit 25 has an input end connected to the output end of the sorting unit 24 for pushing the user to have the same label as the most frequently appeared when the user listens to the radio during the specific time period, and the user has not listened to Content.
  • the working principle is: the recording unit 21 records the preset label related to the playing content; the checking unit 22 checks the listening record of the user in a specific time period; the statistics unit 23 counts the label corresponding to the playing content in the user listening record; Unit 24 organizes the number of occurrences of the associated tag; when the user listens to the radio during the particular time period, push unit 25 pushes the user with the same tag as the most frequently occurring tag and the user has not listened to.
  • the invention actively pushes the listening content with the same label to the user according to the listening habit of the user, combined with the listening time of the user, thereby improving the listening experience of the user.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

本发明属于互联网领域,提供了一种根据收听习惯推荐内容的方法以及推荐系统,方法包括:记录预设的与播放内容有关的标签;检查用户在特定的时间段内的收听记录;统计用户收听记录中与播放内容对应的标签;整理相关标签的出现次数;当用户在所述特定时间段内收听收音机时,向用户推送具有与出现次数最多的标签相同,且用户没有收听过的内容。该发明通过根据用户的收听习惯,结合用户的收听时间,从而主动向用户推送具有相同标签的收听内容,从而提升用户收听体验。

Description

一种根据收听习惯推荐内容的方法和推荐系统 技术领域
本发明属于互联网领域,尤其是涉及一种根据收听习惯推荐内容的方法以及推荐系统。
背景技术
现在,手机的用途越来越广泛,已经从打电话和发短信的功能机时代发展到了今天可以进行人机交互的智能机时代,手机俨然已经成为了我们身体上的一种延伸,成为我们生活、工作和学习的重要工具。我们通过手机购物、理财、工作、了解资讯、社交等。
现今,很多用户通过手机上的网络收音机或是网络FM,如喜马拉雅、懒人听书等软件,利用自己闲暇或是零碎的时间,收听自己喜欢和感兴趣的内容,也成为了一种重要的学习和休息放松的方式。
但是,网络收音机或是网络FM里所收录的内容非常多,如,历史人文、社科、小说、广播剧、评书、音乐、相声、外语、脱口秀等各个方面。同时,用户有在特定时间段收听特定风格内容的习惯,比如在晚上收听邓丽君、蔡琴等比较舒缓的歌曲,用来给自己放松,在上班时收听比较励志、劲爆的歌曲,给自己鼓劲和提神。因此,用户在庞杂的内容中和特定的时间中,根据自己的收听习惯,寻找自己喜欢的收听内容时,用户操作会比较繁琐,而且没有目标性,耗时也较长,用户的体验不是很好。
综上,针对于当前用户不能在特定的时间中,快捷容易的查找到感兴趣的收听内容,用户体验不佳的情况,需要提供一种根据用户收听习惯推送收听内容的方法。
技术问题
本发明实施例提供了一种根据收听习惯推荐内容的方法,目的在于针对于针对于当前用户不能在特定的时间中,快捷容易的查找到感兴趣的收听内容,用户体验不佳的情况,需要提供一种根据用户收听习惯推送收听内容的方法。
技术解决方案
本发明是这样实现的:一种根据收听习惯推荐内容的方法,包括以下步骤:
记录预设的与播放内容有关的标签;
检查用户在特定的时间段内的收听记录;
统计用户收听记录中与播放内容对应的标签;
整理相关标签的出现次数;
当用户在所述特定时间段内收听收音机时,向用户推送具有与出现次数最多的标签相同,且用户没有收听过的内容。
本发明实施例还提供了一种推荐系统,包括:
记录单元,检查单元,统计单元,整理单元,推送单元,其中:
记录单元,用于记录预设的与播放内容有关的标签;
检查单元,用于检查用户在特定的时间段内的收听记录;
统计单元,其输入端分别与所述记录单元的输出端以及所述检查单元的输出端连接,用于统计用户收听记录中与播放内容对应的标签;
整理单元,其输入端与所述统计单元的输出端连接,用于整理相关标签的出现次数;
推送单元,其输入端与所述整理单元的输出端连接,用于当用户在所述特定时间段内收听收音机时,向用户推送具有与出现次数最多的标签相同,且用户没有收听过的内容。
有益效果
该发明通过根据用户的收听习惯,结合用户的收听时间,从而主动向用户推送具有相同标签的收听内容,从而提升用户收听体验。
附图说明
图1是本发明实施例提供的一种根据收听习惯推荐内容的方法的流程示意图;
图2是本发明实施例提供的推荐系统的结构示意图。
本发明的实施方式
为了使本发明的目的、技术方案及优点更加清楚明白,以下结合附图及实施例,对本发明进行进一步详细说明。应当理解,此处所描述的具体实施例仅仅用以解释本发明,并不用于限定本发明。
图1是发明实施例提供的一种根据收听习惯推荐内容的方法的流程示意图,为了便于说明,只示出了与本发明实施例相关的部分。
在步骤S101中,记录预设的与播放内容有关的标签。
在本实施例中,以用户听《盗墓笔记》小说和'罗辑思维'为例,在《盗墓笔记》上设置'盗墓'的标签,在'罗辑思维'上设置'脱口秀'的标签。
在步骤S102中,检查用户在特定的时间段内的收听记录。
如,检查用户在早上8点到9点和下午5点到6点这两个时间段内的收听记录,例如,检查到用户在早上8点到9点内都在听《盗墓笔记》小说,在下午5点到6点用户都在听'罗辑思维'。
在步骤S103中,统计用户收听记录中与播放内容对应的标签。
在步骤S104中,整理相关标签的出现次数。
当用户在所述特定时间段内收听收音机时,则进入步骤S105,向用户推送具有与出现次数最多的标签相同,且用户没有收听过的内容。
经过统计分析,用户收听的《盗墓笔记》小说和'罗辑思维'这两个内容,《盗墓笔记》所对应的标签是'盗墓','罗辑思维'对应的标签是'脱口秀',而且上述两个内容分别在早上8点到9点和下午5点到6点这两个时间段,几乎每天都在听,出现的次数最多。因此,当用户在早上8点到9点这个时间段收听内容时,系统会向用户推荐具有相同'盗墓'标签的不同内容,如,具有'盗墓'标签的《鬼吹灯》、《寻墓记》等,以供用户选择;当用户在下午5点到6点这个时间段收听内容时,系统会向用户推荐具有相同'脱口秀'标签的不同内容,如,具有'脱口秀'标签的'晓松奇谈'、'嘟嘟'、'老梁故事汇'等,以供用户选择。
该发明通过根据用户的收听习惯,结合用户的收听时间,从而主动向用户推送具有相同标签的收听内容,从而提升用户收听体验。
图2是本发明实施例提供的一种推荐系统的结构示意图,该推荐系统包括:
记录单元21,检查单元22,统计单元23,整理单元24,推送单元25,其中:
记录单元21,用于记录预设的与播放内容有关的标签;
检查单元22,用于检查用户在特定的时间段内的收听记录;
统计单元23,其输入端分别与所述记录单元21的输出端以及所述检查单元22的输出端连接,用于统计用户收听记录中与播放内容对应的标签;
整理单元24,其输入端与所述统计单元23的输出端连接,用于整理相关标签的出现次数;
推送单元25,其输入端与所述整理单元24的输出端连接,用于当用户在所述特定时间段内收听收音机时,向用户推送具有与出现次数最多的标签相同,且用户没有收听过的内容。
其工作原理是:记录单元21记录预设的与播放内容有关的标签;检查单元22检查用户在特定的时间段内的收听记录;统计单元23统计用户收听记录中与播放内容对应的标签;整理单元24整理相关标签的出现次数;当用户在所述特定时间段内收听收音机时,推送单元25向用户推送具有与出现次数最多的标签相同,且用户没有收听过的内容。
该发明通过根据用户的收听习惯,结合用户的收听时间,从而主动向用户推送具有相同标签的收听内容,从而提升用户收听体验。
以上仅为本发明的较佳实施例而已,并不用以限制本发明,凡在本发明的精神和原则之内所作的任何修改、等同替换和改进等,均应包含在本发明的保护范围之内。

Claims (2)

  1. 一种根据收听习惯推荐内容的方法,其特征在于,所述方法包括如下步骤:
    记录预设的与播放内容有关的标签;
    检查用户在特定的时间段内的收听记录;
    统计用户收听记录中与播放内容对应的标签;
    整理相关标签的出现次数;
    当用户在所述特定时间段内收听收音机时,向用户推送具有与出现次数最多的标签相同,且用户没有收听过的内容。
  2. 一种推荐系统,其特征在于,所述推荐系统包括:
    记录单元,检查单元,统计单元,整理单元,推送单元,其中:
    记录单元,用于记录预设的与播放内容有关的标签;
    检查单元,用于检查用户在特定的时间段内的收听记录;
    统计单元,其输入端分别与所述记录单元的输出端以及所述检查单元的输出端连接,用于统计用户收听记录中与播放内容对应的标签;
    整理单元,其输入端与所述统计单元的输出端连接,用于整理相关标签的出现次数;
    推送单元,其输入端与所述整理单元的输出端连接,用于当用户在所述特定时间段内收听收音机时,向用户推送具有与出现次数最多的标签相同,且用户没有收听过的内容。
PCT/CN2016/093479 2016-08-05 2016-08-05 一种根据收听习惯推荐内容的方法和推荐系统 WO2018023682A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2016/093479 WO2018023682A1 (zh) 2016-08-05 2016-08-05 一种根据收听习惯推荐内容的方法和推荐系统

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2016/093479 WO2018023682A1 (zh) 2016-08-05 2016-08-05 一种根据收听习惯推荐内容的方法和推荐系统

Publications (1)

Publication Number Publication Date
WO2018023682A1 true WO2018023682A1 (zh) 2018-02-08

Family

ID=61072474

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/093479 WO2018023682A1 (zh) 2016-08-05 2016-08-05 一种根据收听习惯推荐内容的方法和推荐系统

Country Status (1)

Country Link
WO (1) WO2018023682A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2008021906A2 (en) * 2006-08-08 2008-02-21 Google Inc. Interest targeting
CN103377200A (zh) * 2012-04-17 2013-10-30 腾讯科技(深圳)有限公司 用户偏好信息采集方法和装置
CN104899302A (zh) * 2015-06-10 2015-09-09 百度在线网络技术(北京)有限公司 向用户推荐音乐的方法和装置
CN105302890A (zh) * 2015-10-16 2016-02-03 海信集团有限公司 一种多媒体内容在线推荐的方法及其辅助方法和装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2008021906A2 (en) * 2006-08-08 2008-02-21 Google Inc. Interest targeting
CN103377200A (zh) * 2012-04-17 2013-10-30 腾讯科技(深圳)有限公司 用户偏好信息采集方法和装置
CN104899302A (zh) * 2015-06-10 2015-09-09 百度在线网络技术(北京)有限公司 向用户推荐音乐的方法和装置
CN105302890A (zh) * 2015-10-16 2016-02-03 海信集团有限公司 一种多媒体内容在线推荐的方法及其辅助方法和装置

Similar Documents

Publication Publication Date Title
WO2018023665A1 (zh) 视频推荐技术的数据采集方法和视频推荐系统
WO2017028093A1 (zh) 广告投放方法和广告投放系统
WO2018023688A1 (zh) 一种网络收音机内容推荐的方法和推荐系统
WO2018023682A1 (zh) 一种根据收听习惯推荐内容的方法和推荐系统
WO2018023676A1 (zh) 一种根据地点推荐收听内容的方法和推荐系统
Kerz et al. Language that captivates the audience: predicting affective ratings of ted talks in a multi-label classification task
WO2018023680A1 (zh) 根据时间推荐内容技术的数据采集方法和推荐系统
WO2018023681A1 (zh) 根据时间段推荐内容时的信息推送方法和推荐系统
WO2017028098A1 (zh) 推荐网站时显示技术信息的方法和网站推荐系统
WO2017028183A1 (zh) 根据主题展示新闻信息的方法和新闻展示系统
WO2018023637A1 (zh) 一种信息整理技术的使用情况采集方法和新闻推送系统
WO2018023687A1 (zh) 推荐收音机内容时的信息推送方法和推荐系统
WO2018023675A1 (zh) 根据地点推荐收听内容时的信息推送方法和推荐系统
WO2018023239A1 (zh) 音效插技术的数据采集方法和音乐播放器
WO2018023686A1 (zh) 内容推荐技术的数据采集方法和推荐系统
WO2018023236A1 (zh) 音效插入技术的数据采集方法和音乐播放器
WO2018018250A1 (zh) 一种根据年龄推荐节目的数据采集方法以及节目播放系统
WO2018023248A1 (zh) 听书方式的使用情况采集方法和阅读系统
WO2018023679A1 (zh) 一种根据时间识别用户兴趣的方法和识别系统
WO2017124263A1 (zh) 推荐书籍时的信息推送方法以及图书推荐系统
WO2017024500A1 (zh) 数据交流方法和数据交流系统
WO2018023678A1 (zh) 识别兴趣时的信息推送方法和识别系统
WO2017028182A1 (zh) 按关键词展示新闻时的信息提示方法和新闻展示系统
WO2018023251A1 (zh) 手机解锁技术的数据采集方法和解锁系统
WO2018018283A1 (zh) 歌曲信息识别技术的使用情况统计方法和识别系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16911278

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16911278

Country of ref document: EP

Kind code of ref document: A1