技术领域：Technical field:
本发明涉及智能手机资讯软件的资讯展示排序技术领域，特别地涉及一种互联网应用软件的内容排序的技术方法。The invention relates to the technical field of information display and sorting of smart phone information software, in particular to a technical method for content sorting of Internet application software.
背景技术：Background technique:
随着互联网技术的发展，每天在我们都生活在大量的信息中，新闻、广告、科技、销售等等。大多都不是用户想看的，也无法接受那么多的信息量，更加无法有效的找到自身感兴趣的内容。我们需要把资讯过滤，排序，最终展示给用户的是优质的内容，否则用户就会很难在海量的资讯里，找到自己感兴趣的、热点的内容。目前应用市场有很多适用于智能手机的资讯软件，但能根据用户喜好，社会热点、发布时间做综合排序的应用还未有先例。资讯过滤并智能排序的技术方法，解决了目前市场上无法进行海量资讯过滤和推荐的问题，效果明显，大大吸引了用户的阅读兴趣，给用户更好的体验。With the development of Internet technology, we live in a lot of information every day, such as news, advertisements, technology, sales and so on. Most of them are not what users want to see, and they cannot accept so much information, and they cannot effectively find the content they are interested in. We need to filter and sort the information, and finally show users high-quality content, otherwise it will be difficult for users to find interesting and hot content among the massive information. At present, there are many information software suitable for smartphones in the application market, but there is no precedent for an application that can be comprehensively sorted according to user preferences, social hotspots, and release time. The technical method of information filtering and intelligent sorting solves the problem that massive information cannot be filtered and recommended in the current market. The effect is obvious, which greatly attracts users' interest in reading and gives users a better experience.
发明内容：Invention content:
本发明的主要目的是提供一种综合的海量资讯过滤并智能排序的解决方法，以满足用户的阅读需求，提高用户阅读体验。The main purpose of the present invention is to provide a comprehensive solution for massive information filtering and intelligent sorting, so as to meet the reading needs of users and improve the reading experience of users.
为解决上述问题本发明提供如下技术方案：For solving the above problems the present invention provides the following technical solutions:
1、首先记录下用户已经读过的资讯列表，对于用户已经阅读过的资讯，不再展示给用户。1. First record the list of information that the user has read, and no longer display the information that the user has read.
2、用户喜好的初始化，在用户没有提供喜好的初始阶段，根据用户的机型、所在地区、设置各类资讯的默认权重。2. Initialization of user preferences. In the initial stage when the user does not provide preferences, the default weight of various information is set according to the user's model and region.
3、根据用户的点击，计算出用户偏好权重，再代入资讯的发布时间，所在地区，总点击量，计算资讯的得分，再根据得分进行排序。如果用户点击了非用户喜欢的内容，那么加大这个内容的权重，说明用户的喜好有变化。如果资讯的总点击量过高，需要归一化，避免点击教小的资讯没有机会被展示。如果资讯的发布时间已经超过一段时间，需要降低资讯的得分，减少展示机会。3. According to the user's click, calculate the user's preference weight, and then substitute the release time of the information, the region, the total number of clicks, calculate the score of the information, and then sort according to the score. If the user clicks on content that is not the user's favorite, then increase the weight of this content, indicating that the user's preferences have changed. If the total number of clicks on the information is too high, it needs to be normalized to prevent clicks and information that is too small to be displayed. If the information has been published for more than a period of time, it is necessary to reduce the score of the information and reduce the display opportunities.
附图说明：Description of drawings:
图1： 受资讯点击数影响的曲线图Figure 1: The graph of the impact of information clicks
图2：不同机型用户的点击习惯Figure 2: Clicking habits of users of different models
具体实施方式：Detailed ways:
一、记录用户已经读过的资讯列表并排序，记为U(id1,id2,id3,…,idn)，和系统的全局已排序资讯列表，记为T(id1,id2,id3,…,idn)，其中用户已经读过的列表需要永久保留，除非全局资讯T的id有删除，才能删除已读的列表。首先根据公式TU获取用户没有读过的列表N(id1,id2,id3,…,idn)。1. Record and sort the information list that the user has read, denoted as U(id1,id2,id3,...,idn), and the system's global sorted information list, denoted as T(id1,id2,id3,...,idn ), where the list that the user has read needs to be kept permanently, unless the id of the global information T is deleted, the read list can only be deleted. First according to the formula T U gets the list N(id1,id2,id3,...,idn) that the user has not read.
二、用户喜好的初始化，根据用户的机型、所在地区，和各分类资讯在各机型、地区的总权重计算,不同机型的用户获取用户喜好的近似值，A品牌手机的用户就关注娱乐和生活的多一些，B品牌手机的用户关注科技的多一些。如图22. Initialization of user preferences. According to the user's model, location, and the total weight of each category information in each model and region, users of different models obtain approximate values of user preferences. Users of brand A mobile phones focus on entertainment And life more, B brand mobile phone users pay more attention to technology. Figure 2
根据用户的点击发生变化，为了能反应出用户喜好的变化，用户点击了在有效期内没有点击的分类的时候，需要加大这个分类的权重。According to the change of the user's click, in order to reflect the change of the user's preference, when the user clicks on a category that has not been clicked within the validity period, the weight of this category needs to be increased.
用户分类喜好=用户分类点击/用户总点击。User category preferences = user category clicks / user total clicks.
用户分类喜好=(用户分类点击+分类平均点击)/用户总点击。User category preferences = (user category clicks + category average clicks)/user total clicks.
资讯的总点击量过大，会影响点击量小但是发布时间较近的资讯被展示的机会，所以需要做归一化处理，资讯的点击数X=log10(x)，如图1。If the total number of clicks on the information is too large, it will affect the chance of displaying the information with a small number of clicks but a relatively recent release time. Therefore, normalization processing is required. The number of clicks on the information X=log10(x), as shown in Figure 1.
三、随着时间的增加，原来得分比较高的资讯应该缓慢的降低曝光机会，相对应的，得分比较高的资讯，发布时间不是最新，也能有曝光的机会。3. With the increase of time, information with a relatively high score should slowly reduce the chance of exposure. Correspondingly, information with a relatively high score, which is not released at the latest, can still have a chance of exposure.
资讯发布时间T;Information release time T;
当前时间NOW;Current time NOW;
资讯已发布的时间间隔秒t=NOW-T;Information has been published interval seconds t=NOW-T;
资讯时间得分:Information Time Score:
86400是一天的秒数，随着时间的变化，新资讯的得分会慢慢的超过得分高的老资讯。对点击总数归一化则有利于缩小资讯的点击数范围。86400 is the number of seconds in a day. As time changes, the score of new information will gradually exceed that of old information with high scores. Normalizing the total number of clicks helps to narrow down the range of clicks on the information.
四、资讯的地区属性对于当地的用户有比较重要的权重，A地区的新闻应该优先推给A地区的用户，由于地区资讯的特殊性，我们给资讯附带了地区属性，如果用户所在地区等于资讯的地区属性，那么这条资讯的权重加大，否则降低权重，这样可以让用户也有能看到异地资讯的机会，如果用户点击了异地资讯，那么异地资讯加入到用户的喜好设置，异地属性考虑到其特殊性，有效期需要降低。4. The regional attribute of information has a relatively important weight for local users. News in region A should be pushed to users in region A first. Due to the particularity of regional information, we attach regional attributes to the information. If the user's region is equal to the information region attribute, then the weight of this piece of information will be increased, otherwise the weight will be lowered, so that users can also have the opportunity to see information from other places. To its specificity, the validity period needs to be lowered.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410382244.0ACN104133906B (en) | 2014-08-06 | 2014-08-06 | A kind of information filters the technical method of simultaneously intelligent sequencing |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410382244.0ACN104133906B (en) | 2014-08-06 | 2014-08-06 | A kind of information filters the technical method of simultaneously intelligent sequencing |
| Publication Number | Publication Date |
|---|---|
| CN104133906A CN104133906A (en) | 2014-11-05 |
| CN104133906Btrue CN104133906B (en) | 2018-07-31 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410382244.0AExpired - Fee RelatedCN104133906B (en) | 2014-08-06 | 2014-08-06 | A kind of information filters the technical method of simultaneously intelligent sequencing |
| Country | Link |
|---|---|
| CN (1) | CN104133906B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104809154B (en)* | 2015-03-19 | 2019-03-08 | 百度在线网络技术（北京）有限公司 | The method and device recommended for information |
| CN105574061A (en)* | 2015-05-24 | 2016-05-11 | 刘晓建 | Method for filtering user generated content by network information acquisition tool |
| CN106547922B (en)* | 2016-12-07 | 2020-08-25 | 阿里巴巴（中国）有限公司 | Application program sorting method and device and server |
| CN107193891B (en)* | 2017-05-02 | 2021-08-17 | 百度在线网络技术（北京）有限公司 | Content recommendation method and device |
| CN108628949A (en)* | 2018-03-30 | 2018-10-09 | 北京金堤科技有限公司 | A kind of processing method and processing device that information is shown |
| CN110399572B (en)* | 2018-04-23 | 2022-08-23 | 腾讯科技（深圳）有限公司 | Information application control method and device and information display system |
| CN108961097B (en)* | 2018-07-12 | 2021-01-15 | 北京猫眼文化传媒有限公司 | Information processing method and device |
| CN112131465A (en)* | 2020-09-14 | 2020-12-25 | 绿瘦健康产业集团有限公司 | Activity information matching method, device, medium and terminal equipment |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102611785A (en)* | 2011-01-20 | 2012-07-25 | 北京邮电大学 | Personalized active news recommending service system and method for mobile phone user |
| CN102779136A (en)* | 2011-05-13 | 2012-11-14 | 北京搜狗科技发展有限公司 | Method and device for information search |
| CN103218355A (en)* | 2012-01-18 | 2013-07-24 | 腾讯科技（深圳）有限公司 | Method and device for generating tags for user |
| CN103631823A (en)* | 2012-08-28 | 2014-03-12 | 腾讯科技（深圳）有限公司 | Method and device for recommending media content |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008529117A (en)* | 2005-01-21 | 2008-07-31 | コーニンクレッカ フィリップス エレクトロニクス エヌ ヴィ | Method and apparatus for obtaining degree of common interest of user groups |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102611785A (en)* | 2011-01-20 | 2012-07-25 | 北京邮电大学 | Personalized active news recommending service system and method for mobile phone user |
| CN102779136A (en)* | 2011-05-13 | 2012-11-14 | 北京搜狗科技发展有限公司 | Method and device for information search |
| CN103218355A (en)* | 2012-01-18 | 2013-07-24 | 腾讯科技（深圳）有限公司 | Method and device for generating tags for user |
| CN103631823A (en)* | 2012-08-28 | 2014-03-12 | 腾讯科技（深圳）有限公司 | Method and device for recommending media content |
| Publication number | Publication date |
|---|---|
| CN104133906A (en) | 2014-11-05 |
| Publication | Publication Date | Title |
|---|---|---|
| CN104133906B (en) | A kind of information filters the technical method of simultaneously intelligent sequencing | |
| CN104281622B (en) | Information recommendation method and device in a kind of social media | |
| US9172764B2 (en) | Generating a platform for social interaction | |
| US10375188B2 (en) | Sending notifications as a service | |
| Mohr | The impact of social media on the fashion industry | |
| CN104065672B (en) | Advertisement sending method, client and advertisement push system | |
| JP6392239B2 (en) | Targeting users to objects based on search results in online systems | |
| US20160225030A1 (en) | Social data collection and automated social replies | |
| US20170316517A1 (en) | System and method for managing interaction between commercial and social users | |
| EP4009651A1 (en) | Methods and systems of providing visual content editing functions | |
| TW200937332A (en) | System and method for real-time media object-specific communications | |
| CN104469430A (en) | Video recommending method and system based on context and group combination | |
| US20180108040A1 (en) | Media content provision | |
| WO2014155207A1 (en) | Detect and automatically hide spoiler information in a collaborative environment | |
| CN104580244A (en) | Method and device for defending against malicious click | |
| Yang et al. | Engaging social media in China: platforms, publics, and production | |
| CN108230050A (en) | Advertisement placement method and system | |
| US20150156227A1 (en) | Synchronize Tape Delay and Social Networking Experience | |
| Hosio et al. | Application discoverability on multipurpose public displays: popularity comes at a price | |
| CN106537437A (en) | Identifying media channels that have a high likelihood of multiple consumptions by one or more users | |
| Johnson et al. | COPPAcalypse? The Youtube Settlement's Impact on Kids Content | |
| WO2015110845A1 (en) | Autocreated campaigns for hashtag keywords | |
| CN105373531B (en) | A kind of short topic text recognition method and device based on social networks | |
| JP2017138880A (en) | Learning device, learning method, and learning program | |
| US20150248501A1 (en) | Content analytics |
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | Granted publication date:20180731 | |
| CF01 | Termination of patent right due to non-payment of annual fee |