技术领域technical field
本申请涉及计算机技术领域，具体涉及互联网技术领域，尤其涉及基于人工智能的信息推送方法和装置。The present application relates to the field of computer technology, specifically to the field of Internet technology, and in particular to an information push method and device based on artificial intelligence.
背景技术Background technique
信息推送，又称为“网络广播”，是通过一定的技术标准或协议，在互联网上通过推送用户需要的信息来减少信息过载的一项技术。信息推送技术通过主动推送信息给用户，可以减少用户在网络上搜索所花的时间。现有的信息推送过程中，一些实现中统一推送热点给用户，其中热点可以表示网民关注的事件，另一种实现中根据用户历史搜索浏览记录个性化推送相应信息给用户。其中，统一推送热点的针对性较低，个性化推送对热点的推送效率较低。因此，这些信息推送方法，存在推送方式单一，信息推送的有效性较低的问题。Information push, also known as "network broadcasting", is a technology that reduces information overload by pushing the information that users need on the Internet through certain technical standards or protocols. Information push technology can reduce the time spent by users searching on the Internet by proactively pushing information to users. In the existing information push process, some implementations uniformly push hotspots to users, where hotspots can represent events concerned by netizens, and another implementation pushes corresponding information to users personalizedly according to users' historical search and browsing records. Among them, the unified push of hotspots is less pertinent, and the personalized push is less efficient in pushing hotspots. Therefore, these information push methods have the problems of single push method and low effectiveness of information push.
人工智能(Artificial Intelligence，英文缩写为AI)，是研究、开发用于模拟、延伸和扩展人的智能的理论、方法、技术及应用系统的技术科学。人工智能是计算机科学的一个分支，它企图了解智能的实质，并生产出一种新的能以人类智能相似的方式做出反应的智能机器，该领域的研究包括机器人、语言识别、图像识别、自然语言处理和专家系统等。因此，可以将人工智能应用于信息推送，提高信息推送的有效性。Artificial Intelligence (AI) is a technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. Artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a manner similar to human intelligence. Research in this field includes robotics, language recognition, image recognition, natural language processing and expert systems, etc. Therefore, artificial intelligence can be applied to information push to improve the effectiveness of information push.
发明内容Contents of the invention
本申请的目的在于提出一种基于人工智能的信息推送方法和装置，来解决以上背景技术部分提到的技术问题。The purpose of this application is to propose an information push method and device based on artificial intelligence to solve the technical problems mentioned in the background technology section above.
第一方面，本申请提供了一种基于人工智能的信息推送方法，该方法包括：获取各条待推送信息的热度值；根据热度值从待推送信息In the first aspect, the present application provides an information push method based on artificial intelligence, which includes: obtaining the popularity value of each piece of information to be pushed;
在一些实施例中，根据热度值从待推送信息中选取第一待推送信息、第二待推送信息包括：选取热度值大于第一预设阈值的待推送信息作为第一待推送信息，选取热度值大于第二预设阈值且小于第一预设阈值的待推送信息作为第二待推送信息；或者，将待推送信息按照热度值由大到小排列，选取前第一预设个数的待推送信息作为第一待推送信息，从第一待推送信息之后选取第二预设个数的待推送信息作为第二待推送信息。In some embodiments, selecting the first information to be pushed and the second information to be pushed from the information to be pushed according to the popularity value includes: selecting the information to be pushed whose popularity value is greater than the first preset threshold as the first information to be pushed, and selecting the popularity The information to be pushed whose value is greater than the second preset threshold and smaller than the first preset threshold is used as the second information to be pushed; The push information is used as the first information to be pushed, and a second preset number of information to be pushed is selected from the first information to be pushed as the second information to be pushed.
在一些实施例中，针对各条待推送信息，热度值通过以下方法计算得到：获取所有用户对与待推送信息相关联的搜索关键词的输入次数和对与待推送信息相关联的链接的点击次数；通过上述输入次数和点击次数根据预设的输入权重和点击权重计算热度值。In some embodiments, for each piece of information to be pushed, the popularity value is calculated by the following method: Obtain the number of times all users input search keywords associated with the information to be pushed and clicks on links associated with the information to be pushed Number of times; the heat value is calculated according to the preset input weight and click weight through the above input times and click times.
在一些实施例中，第一待推送信息和/或第二待推送信息通过交互页面进行推送；以及，上述方法还包括：检测用户在交互页面的第一预设操作、第二预设操作，其中，第一预设操作包括对待推送信息的选择操作，第二预设操作包括以下至少一种：对待推送信息的拒绝操作、对待推送信息的切换操作；根据第一预设操作，更新相应待推送信息的热度值；响应于用户的第二预设操作，推送下一条相应待推送信息。In some embodiments, the first information to be pushed and/or the second information to be pushed are pushed through the interactive page; and, the above method further includes: detecting the first preset operation and the second preset operation of the user on the interactive page, Wherein, the first preset operation includes a selection operation of the information to be pushed, and the second preset operation includes at least one of the following: a rejection operation of the information to be pushed, a switching operation of the information to be pushed; according to the first preset operation, update the corresponding The popularity value of the push information; in response to the user's second preset operation, push the next corresponding message to be pushed.
在一些实施例中，响应于第二推送条件被满足，根据用户的个性化信息选取出至少一条第二待推送信息进行推送包括：获取用户的个性化信息，该个性化信息包括以下至少一项：历史搜索信息、历史点击信息；根据该个性化信息提取用户的兴趣标签；基于上述兴趣标签与第二待推送信息的匹配确定上述兴趣标签与第二待推送信息的关联度；基于该关联度选择至少一条第二待推送信息进行推送。In some embodiments, in response to the second pushing condition being satisfied, selecting at least one piece of second information to be pushed according to the user's personalized information to push includes: obtaining the user's personalized information, and the personalized information includes at least one of the following : historical search information, historical click information; extract the user's interest tag according to the personalized information; determine the degree of association between the above interest tag and the second information to be pushed based on the matching of the above interest tag and the second information to be pushed; based on the degree of association Select at least one piece of second information to be pushed to push.
在一些实施例中，该关联度通过以下方法计算：In some embodiments, the degree of association is calculated by the following method:
P(C)＝F(A)×SIM(A,C)；P(C)=F(A)×SIM(A,C);
其中，P(C)表示兴趣标签A、待推送信息C的关联度，F(A)表示用户对兴趣标签A的兴趣度，SIM(A，C)表示兴趣标签A与待推送信息C的文本相似度。Among them, P(C) represents the degree of association between the interest tag A and the information C to be pushed, F(A) represents the user’s interest in the interest tag A, and SIM(A, C) represents the text of the interest tag A and the information C to be pushed similarity.
第二方面，本申请还提供了一种基于人工智能的信息推送装置，该装置包括：获取模块，配置用于获取各条待推送信息的热度值；选取模块，配置用于根据热度值从待推送信息中选取第一待推送信息、第二待推送信息；第一推送模块，配置用于响应于第一推送条件被满足，获取至少一条第一待推送信息进行推送；第一推送模块，配置用于响应于第二推送条件被满足，根据用户的个性化信息选取出至少一条第二待推送信息进行推送。In a second aspect, the present application also provides an artificial intelligence-based information push device, which includes: an acquisition module configured to acquire the popularity value of each piece of information to be pushed; a selection module configured to select from the information to be pushed according to the popularity value Select the first information to be pushed and the second information to be pushed from the push information; the first push module is configured to obtain at least one piece of first information to be pushed to push in response to the first push condition being met; the first push module is configured to It is used for selecting at least one piece of second information to be pushed according to the personalized information of the user and pushing it in response to the second pushing condition being satisfied.
在一些实施例中，选取模块进一步配置用于：选取热度值大于第一预设阈值的待推送信息作为第一待推送信息，选取热度值大于第二预设阈值且小于第一预设阈值的待推送信息作为第二待推送信息；或者，将待推送信息按照热度值由大到小排列，选取前第一预设个数的待推送信息作为第一待推送信息，从第一待推送信息之后选取第二预设个数的待推送信息作为第二待推送信息。In some embodiments, the selection module is further configured to: select the information to be pushed whose popularity value is greater than the first preset threshold as the first information to be pushed, and select the information whose popularity value is greater than the second preset threshold and smaller than the first preset threshold The information to be pushed is used as the second information to be pushed; or, the information to be pushed is arranged in descending order according to the popularity value, and the first preset number of information to be pushed is selected as the first information to be pushed, and the information to be pushed is selected from the first information to be pushed Then select a second preset number of information to be pushed as the second information to be pushed.
在一些实施例中，上述装置还包括热度值计算模块，配置用于针对各条待推送信息，通过以下方法计算得到热度值：获取所有用户对与待推送信息相关联的搜索关键词的输入次数和对与待推送信息相关联的链接的点击次数；通过上述输入次数和点击次数根据预设的输入权重和点击权重计算热度值。In some embodiments, the above-mentioned device further includes a popularity value calculation module configured to calculate the popularity value for each piece of information to be pushed by the following method: Obtain the number of times all users input the search keywords associated with the information to be pushed and the number of clicks on the link associated with the information to be pushed; the popularity value is calculated according to the preset input weight and click weight through the above input times and click times.
在一些实施例中，第一待推送信息和/或第二待推送信息通过交互页面进行推送；以及，上述装置还包括：检测模块，配置用于检测用户在交互页面的第一预设操作、第二预设操作，其中，第一预设操作包括对待推送信息的选择操作，第二预设操作包括以下至少一种：对待推送信息的拒绝操作、对待推送信息的切换操作；热度值更新模块，配置用于根据第一预设操作，更新相应待推送信息的热度值；第一推送模块、第二推送模块还分别配置用于响应于用户的第二预设操作，推送下一条相应待推送信息。In some embodiments, the first information to be pushed and/or the second information to be pushed are pushed through the interactive page; and, the above device further includes: a detection module configured to detect the first preset operation of the user on the interactive page, The second preset operation, wherein the first preset operation includes a selection operation of the information to be pushed, and the second preset operation includes at least one of the following: a rejection operation of the information to be pushed, a switching operation of the information to be pushed; a popularity value update module , configured to update the popularity value of the corresponding information to be pushed according to the first preset operation; the first push module and the second push module are also respectively configured to push the next piece of information to be pushed in response to the second preset operation of the user information.
在一些实施例中，第二推送模块包括：获取单元，配置用于获取 用户的个性化信息，该个性化信息包括以下至少一项：历史搜索信息、历史点击信息；提取单元，配置用于根据该个性化信息提取用户的兴趣标签；确定单元，配置用于基于上述兴趣标签与第二待推送信息的匹配确定上述兴趣标签与第二待推送信息的关联度；推送单元，配置用于基于该关联度选择至少一条第二待推送信息进行推送。In some embodiments, the second push module includes: an acquisition unit configured to acquire personalized information of the user, the personalized information including at least one of the following: historical search information, historical click information; an extraction unit configured to The personalized information extracts the user's interest tag; the determining unit is configured to determine the degree of association between the above interest tag and the second information to be pushed based on the matching of the above interest tag and the second information to be pushed; the push unit is configured to be based on the matching The degree of relevance selects at least one piece of second information to be pushed to be pushed.
在一些实施例中，该关联度通过以下方法计算：In some embodiments, the degree of association is calculated by the following method:
P(C)＝F(A)×SIM(A,C)；P(C)=F(A)×SIM(A,C);
其中，P(C)表示兴趣标签A、待推送信息C的关联度，F(A)表示用户对兴趣标签A的兴趣度，SIM(A，C)表示兴趣标签A与待推送信息C的文本相似度。Among them, P(C) represents the degree of association between the interest tag A and the information C to be pushed, F(A) represents the user’s interest in the interest tag A, and SIM(A, C) represents the text of the interest tag A and the information C to be pushed similarity.
第三方面，本申请还提供了一种计算设备，包括：一个或多个处理器；存储装置，用于存储一个或多个程序；当该一个或多个程序被所述一个或多个处理器执行，使得该一个或多个处理器实现上述的方法。In a third aspect, the present application also provides a computing device, including: one or more processors; a storage device for storing one or more programs; when the one or more programs are processed by the one or more The processor is executed, so that the one or more processors implement the above method.
本申请提供的基于人工智能的信息推送方法和装置，通过获取各条待推送信息的热度值，接着根据热度值从待推送信息中选取第一待推送信息、第二待推送信息，然后，响应于第一推送条件被满足，获取至少一条第一待推送信息进行推送，响应于第二推送条件被满足，根据用户的个性化信息选取出至少一条第二待推送信息进行推送。由于针对不同的待推送信息，通过不同的推送方式进行推送，从而可以提高信息推送的有效性。The information push method and device based on artificial intelligence provided by this application obtains the heat value of each piece of information to be pushed, and then selects the first information to be pushed and the second information to be pushed from the information to be pushed according to the heat value, and then responds When the first pushing condition is satisfied, at least one piece of first information to be pushed is obtained and pushed, and in response to the second pushing condition is satisfied, at least one piece of second information to be pushed is selected and pushed according to the personalized information of the user. Since different push methods are used to push different information to be pushed, the effectiveness of information push can be improved.
附图说明Description of drawings
通过阅读参照以下附图所作的对非限制性实施例所作的详细描述，本申请的其它特征、目的和优点将会变得更明显：Other characteristics, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:
图1是本申请可以应用于其中的示例性系统架构图；FIG. 1 is an exemplary system architecture diagram to which the present application can be applied;
图2是根据本申请的基于人工智能的信息推送方法的一个实施例的流程图；Fig. 2 is a flow chart of an embodiment of an information push method based on artificial intelligence according to the present application;
图3a、图3b是根据本申请的基于人工智能的信息推送方法的实施例的应用场景示意图；3a and 3b are schematic diagrams of application scenarios according to an embodiment of an artificial intelligence-based information push method according to the present application;
图4是根据本申请的基于人工智能的信息推送方法的另一个实施例的流程图；FIG. 4 is a flow chart of another embodiment of the method for pushing information based on artificial intelligence according to the present application;
图5是根据本申请的基于人工智能的信息推送装置的一个实施例的结构示意图；Fig. 5 is a schematic structural diagram of an embodiment of an information push device based on artificial intelligence according to the present application;
图6是适于用来实现本申请实施例的终端设备或服务器的计算机系统的结构示意图。Fig. 6 is a schematic structural diagram of a computer system suitable for implementing a terminal device or a server according to an embodiment of the present application.
具体实施方式detailed description
下面结合附图和实施例对本申请作进一步的详细说明。可以理解的是，此处所描述的具体实施例仅仅用于解释相关发明，而非对该发明的限定。另外还需要说明的是，为了便于描述，附图中仅示出了与有关发明相关的部分。The application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain related inventions, rather than to limit the invention. It should also be noted that, for the convenience of description, only the parts related to the related invention are shown in the drawings.
需要说明的是，在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互组合。下面将参考附图并结合实施例来详细说明本申请。It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and embodiments.
图1示出了可以应用本申请的基于人工智能的信息推送方法或信息推送装置的实施例的示例性系统架构100。FIG. 1 shows an exemplary system architecture 100 to which an embodiment of the artificial intelligence-based information pushing method or information pushing apparatus of the present application can be applied.
如图1所示，系统架构100可以包括终端设备101、102、103，网络104和服务器105。网络104用以在终端设备101、102、103和服务器105之间提供通信链路的介质。网络104可以包括各种连接类型，例如有线、无线通信链路或者光纤电缆等等。As shown in FIG. 1 , a system architecture 100 may include terminal devices 101 , 102 , 103 , a network 104 and a server 105 . The network 104 is used as a medium for providing communication links between the terminal devices 101 , 102 , 103 and the server 105 . Network 104 may include various connection types, such as wires, wireless communication links, or fiber optic cables, among others.
用户可以使用终端设备101、102、103通过网络104与服务器105交互，以接收或发送消息等。终端设备101、102、103上可以安装有各种通讯客户端应用，例如信息推送应用、新闻资讯类应用、网页浏览器应用、购物类应用、搜索类应用、即时通信工具、邮箱客户端、社交平台软件等。Users can use terminal devices 101 , 102 , 103 to interact with server 105 via network 104 to receive or send messages and the like. Various communication client applications can be installed on the terminal devices 101, 102, 103, such as information push applications, news applications, web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.
终端设备101、102、103可以是具有显示屏并且支持语音或符号输入的各种电子设备，包括但不限于智能手机、平板电脑、电子书阅读器、MP3播放器(Moving PictureExperts Group Audio Layer III，动态影像专家压缩标准音频层面3)、MP4(MovingPicture Experts Group Audio Layer IV，动态影像专家压缩标准音频层面4)播放器、膝上型便携计算机和台式计算机等等。Terminal devices 101, 102, 103 can be various electronic devices with display screens and support voice or symbol input, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, Moving Picture Experts Compression Standard Audio Layer 3), MP4 (MovingPicture Experts Group Audio Layer IV, Moving Picture Experts Compression Standard Audio Layer 4) Players, Laptop Portable Computers and Desktop Computers, etc.
服务器105可以是提供各种服务的服务器，例如对终端设备101、102、103上运行的信息推送应用、新闻资讯类应用提供支持的后台服务器等。服务器105可以对接收到的信息请求等数据进行分析等处理，并将处理结果(例如推送的新闻)反馈给终端设备。The server 105 may be a server that provides various services, such as a background server that provides support for information push applications and news information applications running on the terminal devices 101 , 102 , and 103 . The server 105 can analyze and process the received data such as information requests, and feed back the processing results (for example, pushed news) to the terminal device.
需要说明的是，本申请所提供的基于人工智能的信息推送方法一般由服务器105执行。相应地，基于人工智能的信息推送装置一般设置在服务器105中。It should be noted that the artificial intelligence-based information push method provided in this application is generally executed by the server 105 . Correspondingly, the information pushing device based on artificial intelligence is generally set in the server 105 .
应该理解，图1中的终端设备、网络和服务器的数目仅仅是示意性的。根据实现需要，可以具有任意数目的终端设备、网络和服务器。It should be understood that the numbers of terminal devices, networks and servers in Fig. 1 are only illustrative. According to the implementation needs, there can be any number of terminal devices, networks and servers.
继续参考图2，示出了根据本申请的基于人工智能的信息推送方法的一个实施例的流程200。该基于人工智能的信息推送方法，包括以下步骤：Continuing to refer to FIG. 2 , a flow 200 of an embodiment of the method for pushing information based on artificial intelligence according to the present application is shown. The artificial intelligence-based information push method includes the following steps:
步骤201，获取各条待推送信息的热度值。Step 201, acquiring the popularity value of each piece of information to be pushed.
在本实施例中，基于人工智能的信息推送方法运行于其上的电子设备(例如图1所示的服务器105)可以首先针对各条待推送信息，从本地或远程地获取其热度值。这里的待推送信息可以是存储在上述电子设备上或者上述电子设备可以从其他设备获取的文字、图像、视频、音频等等信息(例如新闻)，其可以由上述电子设备以文档或页面等形式推送给用户。In this embodiment, the electronic device (for example, the server 105 shown in FIG. 1 ) on which the artificial intelligence-based information push method runs may first acquire the popularity value of each piece of information to be pushed locally or remotely. The information to be pushed here may be text, image, video, audio and other information (such as news) stored on the above-mentioned electronic device or obtained by the above-mentioned electronic device from other devices, which may be sent by the above-mentioned electronic device in the form of a document or a page, etc. push to the user.
其中，热度可以用于表示网民对某个事物(如热点事件)的关注程度，热度值可以是该关注程度的量值。可以理解，对同一个事物，可能有多种表达，因此，可以通过对所获取的信息通过语义分析、关键词提取和匹配等等中的一个或多个方法进行关联，从而将表达同一个事物的信息与该事物关联。实践中，可以先对所获取的信息提取关键词，然后根据两条信息的关键词及其同义词、近义词的匹配计算两条信息的关联度，再根据预设的关联度阈值确定两条信息是否相关联。可选地，两条信息的关联度可以通过Jaccard系数之类的方法计算，如：两条信息的关联度＝两条信息的关键词相匹配的词数/两条信息的关键 词的总个数。两个关键词相匹配，可以是他们本身相匹配，也可以是其近义词、同义词相匹配。举例而言，信息A的关键词包括“感冒、发烧”，信息B的关键词包括“伤风、流鼻涕”，由于感冒和伤风是近义词，因此这两个关键词相匹配，则信息A和信息B的关联度＝信息A和信息B的关键词相匹配的词数2/信息A和信息B的关键词的总个数4＝0.5。Wherein, popularity can be used to indicate the degree of attention of netizens to a certain thing (such as a hot event), and the popularity value can be a magnitude of the degree of attention. It can be understood that there may be multiple expressions for the same thing. Therefore, the acquired information can be associated with one or more methods of semantic analysis, keyword extraction and matching, etc., so as to express the same thing information associated with the thing. In practice, you can first extract keywords from the acquired information, then calculate the degree of relevance of the two pieces of information based on the keywords of the two pieces of information and their synonyms, and match the synonyms, and then determine whether the two pieces of information are based on the preset threshold of relevance. Associated. Optionally, the degree of relevance of the two pieces of information can be calculated by methods such as the Jaccard coefficient, such as: the degree of relevance of the two pieces of information=the number of words that match the keywords of the two pieces of information/the total number of keywords in the two pieces of information number. The matching of two keywords can be their own matching, or their synonyms and synonyms. For example, the keywords of information A include "cold, fever", and the keywords of information B include "cold, runny nose". Since cold and cold are synonyms, these two keywords match, then information A and information The degree of relevance of B=the number of words matching the keywords of information A and information B 2/the total number of keywords of information A and information B 4=0.5.
每条待推送信息的热度值可以直接获取，也可以由上述电子设备计算获得。例如，在一些实现中，上述电子设备可以获取某个待推送信息相关页面(如前述的与待推送信息关联的页面)的浏览量，作为热度值。The popularity value of each piece of information to be pushed can be obtained directly, or calculated by the above-mentioned electronic device. For example, in some implementations, the above-mentioned electronic device may obtain, as the popularity value, the number of views of a page related to information to be pushed (such as the aforementioned page associated with the information to be pushed).
在本实施例的一些可选实现方式中，上述电子设备可以获取所有用户对与待推送信息相关联的搜索关键词的输入次数，以及对与待推送信息相关联的链接(如关键词链接)的点击次数(或点击率)，然后根据预设的输入权重和点击权重计算热度值。如，待推送信息的热度值＝所有用户对与待推送信息相关联的搜索关键词的输入次数×输入权重+所有用户对与待推送信息相关联的链接的点击次数(或点击率)×点击权重。其中，输入权重和点击权重可以人为预设，也可以通过对一定数量的样本集进行机器学习获取。以机器学习为例，将样本中各条样本信息的上述输入次数和点击次数作为已知量，将相关网页浏览量或与网页浏览量正相关的数据作为上述“输入次数×输入权重+上述点击次数×点击权重”的结果，通过机器学习求解输入权重和点击权重。可以理解，对于诸如新闻之类的信息而言，时间越近可能意义越大，因此，在一些实现中，上述电子设备计算的待推送信息的热度值还可以与信息发布时间到当前时间的距离负相关。例如，待推送信息的热度值＝(上述输入次数×输入权重+上述点击次数×点击权重)×时间衰减系数，该时间衰减系数可以与信息发布时间到当前时间的距离负相关。另外，从不同站点(例如需要用户认证的科技网站和任意用户可以进入的八卦网站等)获取的信息，信息质量(如可信度、真实性等)也不一样，因此，在另一些实现中，上述电子设备还可以根据信息来源预设有站点权重，所计算的待推送信息的热度值还可以 对各个站点中的站点热度值求加权和。例如：待推送信息A的热度值＝(待推送信息A在站点1的上述输入次数×输入权重+待推送信息A在站点1的上述点击次数×点击权重)×站点1的站点权重+(待推送信息A在站点2的上述输入次数×输入权重+待推送信息A在站点2的上述点击次数×点击权重)×站点2的站点权重+……。In some optional implementations of this embodiment, the above-mentioned electronic device can acquire the number of times all users input search keywords associated with the information to be pushed, and the links (such as keyword links) associated with the information to be pushed The number of clicks (or click-through rate), and then calculate the popularity value according to the preset input weight and click weight. For example, the popularity value of the information to be pushed = the number of times all users input the search keywords associated with the information to be pushed × input weight + the number of clicks (or click rate) of all users on the links associated with the information to be pushed × clicks Weights. Wherein, the input weight and the click weight can be artificially preset, or can be acquired by machine learning on a certain number of sample sets. Taking machine learning as an example, the above-mentioned number of inputs and clicks of each piece of sample information in the sample is taken as a known quantity, and the relevant page views or data positively related to the page views are taken as the above-mentioned "number of inputs × input weight + the above-mentioned clicks" Number of clicks × click weight”, and solve the input weight and click weight through machine learning. It can be understood that for information such as news, the closer the time may be, the more meaningful it may be. Therefore, in some implementations, the popularity value of the information to be pushed calculated by the above-mentioned electronic device may also be related to the distance from the information publishing time to the current time. negative correlation. For example, the popularity value of the information to be pushed = (the above-mentioned input times×input weight+the above-mentioned number of clicks×click weight)×time decay coefficient, and the time decay coefficient may be negatively correlated with the distance from the information publishing time to the current time. In addition, the information quality (such as credibility, authenticity, etc.) of information obtained from different sites (such as technology websites that require user authentication and gossip websites that any user can enter, etc.) is also different. Therefore, in other implementations The above-mentioned electronic device may also be preset with site weights according to information sources, and the calculated popularity value of the information to be pushed may also be a weighted sum of the site popularity values in each site. For example: the popularity value of information A to be pushed = (the above-mentioned input times of information A to be pushed on site 1 × input weight + the above-mentioned number of clicks of information A to be pushed on site 1 × click weight) × site weight of site 1 + (to be pushed The above-mentioned input times of push information A on site 2 × input weight + the above-mentioned click times of information A to be pushed on site 2 × click weight) × site weight of site 2 + . . .
步骤202，根据热度值从待推送信息中选取第一待推送信息、第二待推送信息。Step 202: Select the first information to be pushed and the second information to be pushed from the information to be pushed according to the popularity value.
在本实施例中，基于人工智能的信息推送方法运行于其上的电子设备(例如图1所示的服务器105)上可以根据热度值对待推送信息进行区分，并选取出不同热度的第一待推送信息和第二待推送信息。可以理解，第一待推送信息和第二待推送信息分别可以与网民关注度不同的事物相关联。例如，当待推送信息是新闻时，第一待推送信息可以是热度较高的新闻，第二待推送信息可以是热度低于第一待推送信息的新闻中热度较高的新闻。In this embodiment, the electronic device (such as the server 105 shown in FIG. 1 ) on which the artificial intelligence-based information push method runs can distinguish the information to be pushed according to the popularity value, and select the first waiting information with different popularity. Push information and second to-be-pushed information. It can be understood that the first information to be pushed and the second information to be pushed may be respectively associated with things with different attention levels of netizens. For example, when the information to be pushed is news, the first information to be pushed may be news with higher popularity, and the second information to be pushed may be news with higher popularity among news with lower popularity than the first information to be pushed.
在本实施例的一些可选实现方式中，上述电子设备可以通过对待推送信息的热度值满足的条件进行判断来选取第一待推送信息和第二待推送信息。具体地，上述电子设备可以选取热度值大于第一预设阈值(如0.8)的待推送信息作为第一待推送信息，选取热度值大于第二预设阈值(如0.6)且小于第一预设阈值(如0.8)的待推送信息作为第二待推送信息；或者，将待推送信息按照热度值由大到小排列，选取前第一预设个数(如5)的待推送信息作为第一待推送信息，从第一待推送信息之后选取第二预设个数(如2000)的待推送信息作为第二待推送信息。In some optional implementation manners of this embodiment, the electronic device may select the first information to be pushed and the second information to be pushed by judging a condition that the popularity value of the information to be pushed satisfies. Specifically, the above-mentioned electronic device may select information to be pushed with a heat value greater than a first preset threshold (such as 0.8) as the first information to be pushed, and select a heat value that is greater than a second preset threshold (such as 0.6) and less than the first preset The information to be pushed with a threshold value (such as 0.8) is used as the second information to be pushed; or, the information to be pushed is arranged in descending order according to the popularity value, and the information to be pushed with the first preset number (such as 5) is selected as the first For the information to be pushed, a second preset number (such as 2000) of information to be pushed is selected from the first information to be pushed as the second information to be pushed.
步骤203，响应于第一推送条件被满足，获取至少一条第一待推送信息进行推送。Step 203, in response to the first pushing condition being satisfied, at least one piece of first information to be pushed is obtained and pushed.
在本实施例中，对于第一推送信息，基于人工智能的信息推送方法运行于其上的电子设备(例如图1所示的服务器105)在检测到第一推送条件被满足时，可以获取至少一条第一待推送信息推送给用户。In this embodiment, for the first push information, the electronic device on which the artificial intelligence-based information push method runs (such as the server 105 shown in FIG. 1 ) can obtain at least A first piece of information to be pushed is pushed to the user.
这里，第一推送条件可以是预先设定的、存储在上述电子设备上的，该第一推送条件例如可以是时间条件、网络连接状态条件、收到 信息推送请求等等。例如，当本申请的基于人工智能的信息推送方法应用于为新闻推送类应用提供支持的后台服务器时，上述时间条件可以是预先设定的推送时间，如每间隔预设时间段(如5分钟等)的时间点，也可以是第一推送信息被选取出的时间点等等；网络连接状态条件例如可以是与上述电子设备建立连接(如登录客户端)或网络信号强度大于预设阈值等等；信息推送请求例如可以是客户端通过用户的预定按钮(如“换一条”按钮)的操作触发的信息推送请求等等。Here, the first push condition may be preset and stored on the above-mentioned electronic device, and the first push condition may be, for example, time condition, network connection status condition, receipt of an information push request, and the like. For example, when the artificial intelligence-based information push method of the present application is applied to a background server that provides support for news push applications, the above-mentioned time condition can be a preset push time, such as every preset time period (such as 5 minutes) etc.), it can also be the time point when the first push information is selected, etc.; the network connection status condition can be, for example, establishing a connection with the above-mentioned electronic device (such as logging in to the client) or the network signal strength is greater than a preset threshold, etc. etc.; the information push request may be, for example, an information push request triggered by the client through an operation of a user's predetermined button (such as a "replacement" button).
在本实施例中，上述电子设备可以将第一待推送信息的以下至少一项推送给用户：标题、关键词、链接。In this embodiment, the electronic device may push at least one of the following items of the first information to be pushed to the user: title, keyword, and link.
步骤204，响应于第二推送条件被满足，根据用户的个性化信息选取出至少一条第二待推送信息推送给用户。Step 204, in response to the second push condition being met, select at least one piece of second information to be pushed according to the personalized information of the user and push it to the user.
在本实施例中，对于第二待推送信息，上述电子设备可以响应于第二推送条件被满足，根据用户的个性化信息从第二待推送信息中选取出至少一条第二待推送信息推送给用户。In this embodiment, for the second information to be pushed, the above-mentioned electronic device may select at least one piece of second information to be pushed from the second information to be pushed according to the user's personalized information and push it to user.
这里，第二推送条件可以是预先设定的、存储在上述电子设备上的，该第二推送条件例如可以是时间条件、网络连接状态条件、收到信息推送请求等等。第二推送条件可以和第一推送条件一致，此时，上述电子设备可以将第一待推送信息和第二待推送信息一起推送给用户；第二推送条件也可以与第一推送条件不一致，此时，上述电子设备可以将第一待推送信息和第二待推送信息分别推送给用户。Here, the second push condition may be preset and stored on the electronic device, and the second push condition may be, for example, a time condition, a network connection status condition, an information push request received, and the like. The second push condition may be consistent with the first push condition. At this time, the electronic device may push the first information to be pushed and the second information to be pushed to the user together; the second push condition may also be inconsistent with the first push condition. , the electronic device may push the first information to be pushed and the second information to be pushed to the user respectively.
其中，用户的个性化信息可以是体现用户的个体特性的信息，例如性别、年龄、职业、爱好、历史行为等等。电子设备可以根据用户的个性化信息选取第二待推送信息，例如，可以根据职业“演员”选取与娱乐类的第二待推送信息、根据年龄“65岁”选择老年人养生类的第二待推送信息等等。上述电子设备上可以预先存储至少一个用户的个性化信息，也可以在进行信息推送时再获取相应用户的个性化信息，本申请对此不做限定。实践中，电子设备可以根据用户的客户端设置信息、用户历史行为信息中的至少一项来获取用户的个性化信息。Wherein, the user's personalized information may be information that reflects the user's individual characteristics, such as gender, age, occupation, hobbies, historical behavior, and so on. The electronic device can select the second information to be pushed according to the user's personalized information. For example, it can select the second information to be pushed in the entertainment category according to the occupation "actor", and select the second information to be pushed in the health care category for the elderly according to the age "65 years old". Push information and so on. Personalized information of at least one user may be pre-stored on the above-mentioned electronic device, and the personalized information of the corresponding user may be acquired again when information is pushed, which is not limited in this application. In practice, the electronic device may obtain the user's personalized information according to at least one item of the user's client setting information and the user's historical behavior information.
在本实施例的一些可选实现方式中，上述电子设备首先可以获取用户的个性化信息，该个性化信息可以包括但不限于以下至少一项： 历史搜索信息、历史点击信息等等。历史搜索信息例如可以是搜索关键词等，历史点击信息例如可以是用户点击的关键词或链接对应页面的关键词等。接着，上述电子设备可以根据用户的个性化信息提取相应用户的兴趣标签。兴趣标签可以是用于表示用户感兴趣信息的关键词、语句等。例如，用户的历史搜索信息包括大量娱乐类信息相关的搜索关键词(如影视明星的名字等)，则可以提取用户的兴趣标签“娱乐”或“八卦”等。电子设备也可以将用户的历史搜索信息和/或历史点击信息通过语义进行聚类，每个类对应用户关注的一个事物(如热点事件)，并将该热点事件的关键词提取为用户的兴趣标签。然后，针对某个用户，上述电子设备可以将所提取的兴趣标签与第二待推送信息进行匹配，并根据匹配结果确定用户的兴趣标签与第二待推送信息的关联度。这里，上述电子设备可以提取第二待推送信息的关键词与用户的兴趣标签进行匹配，并利用Jaccard系数之类的文本相似度计算方法计算第二待推送信息的关键词与用户的兴趣标签的文本相似度作为用户的兴趣标签与第二待推送信息的关联度，在此不再赘述。接着，上述电子设备可以基于关联度选择第二待推送信息推送给用户，例如选择关联度大于预设关联度阈值的第二待推送信息，或者关联度较大的前N(N为正整数)个第二待推送信息推送给用户。可选地，用户的兴趣标签可以有多个，每个兴趣标签还可以具有兴趣度。其中，兴趣度可以表示用户对兴趣标签的感兴趣程度，其可以与用户搜索或点击关键词的次数成正比。此时，上述关联度可以通过以下方法计算：In some optional implementation manners of this embodiment, the above-mentioned electronic device may first obtain personalized information of the user, and the personalized information may include but not limited to at least one of the following: historical search information, historical click information, and the like. The historical search information may be, for example, a search keyword, and the historical click information may be, for example, a keyword clicked by a user or a keyword linked to a corresponding page. Next, the above-mentioned electronic device may extract interest tags of the corresponding user according to the personalized information of the user. Interest tags may be keywords, sentences, etc. used to represent information of interest to the user. For example, if the user's historical search information includes a large number of search keywords related to entertainment information (such as names of film and television stars, etc.), then the user's interest tags "entertainment" or "gossip" can be extracted. The electronic device can also cluster the user's historical search information and/or historical click information through semantics, each class corresponds to a thing (such as a hot event) that the user is concerned about, and extract the keyword of the hot event as the user's interest Label. Then, for a certain user, the electronic device may match the extracted interest tag with the second information to be pushed, and determine the degree of relevance between the user's interest tag and the second information to be pushed according to the matching result. Here, the above-mentioned electronic device can extract the keywords of the second information to be pushed and match the user's interest tags, and use a text similarity calculation method such as Jaccard coefficient to calculate the relationship between the keywords of the second information to be pushed and the user's interest tags. The text similarity is used as the degree of association between the user's interest tag and the second information to be pushed, which will not be repeated here. Next, the above-mentioned electronic device may select the second information to be pushed based on the degree of association and push it to the user, for example, select the second information to be pushed with the degree of association greater than the preset threshold of association degree, or the top N with the degree of association (N is a positive integer) The second information to be pushed is pushed to the user. Optionally, there may be multiple interest tags of the user, and each interest tag may also have an interest degree. Wherein, the degree of interest may indicate the degree of interest of the user in the interest tag, which may be directly proportional to the number of times the user searches or clicks on the keyword. At this time, the above-mentioned correlation degree can be calculated by the following method:
P(C)＝F(A)×SIM(A,C)；P(C)=F(A)×SIM(A,C);
其中，P(C)表示兴趣标签A、待推送信息C的关联度，F(A)表示用户对兴趣标签A的兴趣度，SIM(A，C)表示兴趣标签A与待推送信息C的文本相似度。Among them, P(C) represents the degree of association between the interest tag A and the information C to be pushed, F(A) represents the user’s interest in the interest tag A, and SIM(A, C) represents the text of the interest tag A and the information C to be pushed similarity.
在本实施例的一些可选实现方式中，对于第一待推送信息，上述电子设备可以仅向用户推送标题或短摘要，并给出操作选项，以供用户选择是否需要详细了解该第一待推送信息。这里的操作选项例如可以是语音或字符输入接口、选择按钮、关联链接等等。对于第二待推送信息，上述电子设备可以向用户推送长摘要，同时给出操作选项， 以供用户选择是否根据关联关键词请求更多相关信息。In some optional implementations of this embodiment, for the first information to be pushed, the above-mentioned electronic device may only push the title or a short summary to the user, and provide operation options for the user to choose whether to learn more about the first information to be pushed. Push information. The operation options here may be, for example, voice or character input interfaces, selection buttons, associated links, and the like. For the second information to be pushed, the above-mentioned electronic device may push a long abstract to the user, and at the same time provide operation options for the user to choose whether to request more relevant information based on associated keywords.
作为一个应用场景，本申请提供的基于人工智能的信息推送方法可以应用于为新闻推送类应用提供支持的后台服务器，如图3a和3b所示，该新闻推送类应用301可以安装并运行于终端300上。As an application scenario, the artificial intelligence-based information push method provided by this application can be applied to a background server that provides support for news push applications, as shown in Figures 3a and 3b, the news push application 301 can be installed and run on a terminal 300 on.
在该应用场景中，后台服务器首先可以获取各条待推送信息(新闻)的热度值，然后根据热度值从待推送信息中选取第一待推送信息、第二待推送信息，在该应用场景中假设第一待推送信息是热度值由高到低的前5条新闻，第二待推送信息例如是热度值由高到低的第6-1005条新闻。In this application scenario, the background server can first obtain the popularity value of each piece of information to be pushed (news), and then select the first information to be pushed and the second information to be pushed from the information to be pushed according to the popularity value. In this application scenario Assume that the first information to be pushed is the first 5 news items with popularity value from high to low, and the second information to be pushed is, for example, news 6-1005 with popularity value from high to low.
接着，如图3a所示，假设用户打开终端300上运行的新闻推送类应用301，新闻推送类应用301客户端与后台建立连接，此时第一推送条件被满足，则后台服务器可以将第一待推送信息302推送给用户。在图3a给出的示意中，后台服务器向用户推送了第一待推送信息302的标题或短摘要“宇航员公布太空探索重大发现！”。Next, as shown in Figure 3a, assuming that the user opens the news push application 301 running on the terminal 300, the client of the news push application 301 establishes a connection with the background, and at this time the first push condition is satisfied, then the background server can send the first The information to be pushed 302 is pushed to the user. In the illustration shown in FIG. 3 a , the background server pushes the title or short summary of the first information to be pushed 302 "Astronaut announces major discovery of space exploration!" to the user.
或者，假设用户打开终端300上运行的新闻推送类应用301，新闻推送类应用301客户端与后台建立连接，此时第二推送条件被满足，则如图3b所示，后台服务器可以将第二待推送信息303推送给用户。在图3b给出的示意中，后台服务器向用户推送了第二待推送信息303的长摘要“12月11日消息，据人民铁道网报道，铁路2017年春运方案已经出台，今年铁路春运从1月13日起至2月21日止，共40天，近6成网络火车票购买不需要验证码”。Or, assuming that the user opens the news push application 301 running on the terminal 300, the client of the news push application 301 establishes a connection with the background, and the second push condition is satisfied at this time, then as shown in Figure 3b, the background server can send the second The information to be pushed 303 is pushed to the user. In the illustration given in Figure 3b, the background server pushes the long abstract of the second message to be pushed 303 to the user. "Dec. From February 13 to February 21, a total of 40 days, nearly 60% of online train ticket purchases do not require a verification code."
可以理解，图3a、图3b的应用场景仅对为新闻推送类应用提供支持的后台服务器执行本实施例的基于人工智能的信息推送方法进行了示例性说明，本申请的基于人工智能的信息推送方法还有其他应用场景和实现可能，在此不再一一例举。It can be understood that the application scenarios in FIG. 3a and FIG. 3b only illustrate the implementation of the artificial intelligence-based information push method of this embodiment by the background server that provides support for news push applications. The artificial intelligence-based information push method of this application There are other application scenarios and implementation possibilities of the method, which will not be listed one by one here.
因此，本实施例的基于人工智能的信息推送方法，由于针对不同的待推送信息，通过不同的推送方式进行推送，从而可以提高信息推送的有效性。Therefore, the information push method based on artificial intelligence in this embodiment can improve the effectiveness of information push because different push methods are used to push different information to be pushed.
继续参考图4，示出了根据本申请的基于人工智能的信息推送方法的另一个实施例的流程400。图4示出的实施例中，基于人工智能 的信息推送方法运行于其上的电子设备(例如图1所示的服务器105)可以将第一待推送信息和/或第二待推送信息通过交互页面进行推送。该基于人工智能的信息推送流程400，包括以下步骤：Continuing to refer to FIG. 4 , a flow 400 of another embodiment of the method for pushing information based on artificial intelligence according to the present application is shown. In the embodiment shown in FIG. 4 , the electronic device (such as the server 105 shown in FIG. 1 ) on which the artificial intelligence-based information push method runs can send the first information to be pushed and/or the second information to be pushed through interactive The page is pushed. The artificial intelligence-based information push process 400 includes the following steps:
步骤401，获取各条待推送信息的热度值。Step 401, acquiring the popularity value of each piece of information to be pushed.
在本实施例中，基于人工智能的信息推送方法运行于其上的电子设备(例如图1所示的服务器105)可以首先针对各条待推送信息，从本地或远程地获取其热度值。这里的待推送信息可以是存储在上述电子设备上或者上述电子设备可以从其他设备获取的文字、图像、视频、音频等等信息(例如新闻)，其可以由上述电子设备以文档或页面等形式推送给用户。其中，热度可以用于表示网民对某个事物(如热点事件)的关注程度，热度值可以是该关注程度的量值。In this embodiment, the electronic device (for example, the server 105 shown in FIG. 1 ) on which the artificial intelligence-based information push method runs may first acquire the popularity value of each piece of information to be pushed locally or remotely. The information to be pushed here may be text, image, video, audio and other information (such as news) stored on the above-mentioned electronic device or obtained by the above-mentioned electronic device from other devices, which may be sent by the above-mentioned electronic device in the form of a document or a page, etc. push to the user. Wherein, popularity can be used to indicate the degree of attention of netizens to a certain thing (such as a hot event), and the popularity value can be a magnitude of the degree of attention.
步骤402，根据热度值从待推送信息中选取第一待推送信息、第二待推送信息。Step 402: Select the first information to be pushed and the second information to be pushed from the information to be pushed according to the popularity value.
在本实施例中，基于人工智能的信息推送方法运行于其上的电子设备(例如图1所示的服务器105)上可以根据热度值对待推送信息进行区分，并选取出不同热度的第一待推送信息和第二待推送信息。可以理解，第一待推送信息和第二待推送信息分别可以与网民关注度不同的事物相关联。例如，当待推送信息是新闻时，第二待推送信息可以是热度低于第一待推送信息的新闻中热度较高的新闻。In this embodiment, the electronic device (such as the server 105 shown in FIG. 1 ) on which the artificial intelligence-based information push method runs can distinguish the information to be pushed according to the popularity value, and select the first waiting information with different popularity. Push information and second to-be-pushed information. It can be understood that the first information to be pushed and the second information to be pushed may be respectively associated with things with different attention levels of netizens. For example, when the information to be pushed is news, the second information to be pushed may be news with a higher popularity than the first information to be pushed.
步骤403，响应于第一推送条件被满足，获取至少一条第一待推送信息进行推送。Step 403, in response to the first pushing condition being satisfied, at least one piece of first information to be pushed is obtained and pushed.
在本实施例中，对于第一推送信息，基于人工智能的信息推送方法运行于其上的电子设备(例如图1所示的服务器105)在检测到第一推送条件被满足时，可以获取至少一条第一待推送信息通过交互页面推送给用户。其中，交互页面可以是能够用于用户和电子设备的交互的页面，例如包括按钮控件、统一资源定位符(URL)链接、超链接、字符或语音输入接口等等交互元素的页面，。该交互页面可以接收用户的相应操作，例如用户对按钮控件、统一资源定位符链接、超链接的点击操作以及通过字符或语音输入接口进行的字符或语音输入操作等。In this embodiment, for the first push information, the electronic device on which the artificial intelligence-based information push method runs (such as the server 105 shown in FIG. 1 ) can obtain at least A first piece of information to be pushed is pushed to the user through the interactive page. Wherein, the interactive page may be a page that can be used for interaction between the user and the electronic device, for example, a page including interactive elements such as button controls, uniform resource locator (URL) links, hyperlinks, character or voice input interfaces, and the like. The interactive page can receive corresponding user operations, such as user click operations on button controls, uniform resource locator links, and hyperlinks, and character or voice input operations through character or voice input interfaces.
步骤404，响应于第二推送条件被满足，根据用户的个性化信息选取出至少一条第二待推送信息通过交互页面推送给用户。Step 404, in response to the second push condition being met, select at least one piece of second information to be pushed according to the personalized information of the user and push it to the user through the interactive page.
在本实施例中，对于第二待推送信息，上述电子设备可以响应于第二推送条件被满足，根据用户的个性化信息从第二待推送信息中选取出至少一条第二待推送信息推送给用户。这里，第二推送条件可以是预先设定的、存储在上述电子设备上的，该第二推送条件例如可以是时间条件、网络连接状态条件、收到信息推送请求等等。第二推送条件可以和第一推送条件一致，也可以与第一推送条件不一致。In this embodiment, for the second information to be pushed, the above-mentioned electronic device may select at least one piece of second information to be pushed from the second information to be pushed according to the user's personalized information and push it to user. Here, the second push condition may be preset and stored on the electronic device, and the second push condition may be, for example, a time condition, a network connection status condition, an information push request received, and the like. The second push condition may be consistent with the first push condition, or may be inconsistent with the first push condition.
步骤405，检测用户在交互页面的第一预设操作、第二预设操作。Step 405, detecting the first preset operation and the second preset operation performed by the user on the interactive page.
上述电子设备可以将用户在交互页面的操作根据操作所代表的用户对所推送的信息的意向(如是否感兴趣)预先分类。在本实施例中，上述电子设备还可以进一步检测用户在交互页面的第一预设操作、第二预设操作。其中，第一预设操作可以包括对待推送信息的选择操作，第二预设操作可以包括但不限于以下至少一种：对待推送信息的拒绝操作、对待推送信息的切换操作等等。The above-mentioned electronic device may pre-classify the user's operation on the interactive page according to the user's intention (such as whether or not he is interested in) of the pushed information represented by the operation. In this embodiment, the electronic device may further detect a first preset operation and a second preset operation performed by the user on the interactive page. Wherein, the first preset operation may include a selection operation of the information to be pushed, and the second preset operation may include but not limited to at least one of the following: a rejection operation of the information to be pushed, a switching operation of the information to be pushed, and the like.
作为示例，请参考图3a和图3b示出的应用场景。图3a中示出的推送第一待推送信息302的交互页面给出了操作选项3021和3022，以及输入法选项3023。其中，操作选项3021“什么情况？说来听听！”可供用户选择详细了解该第一待推送信息及其关联信息，操作选项3022“不感兴趣，换一条”可供用户选择从后台服务器请求另一条第一待推送信息，输入法选项3023可供用户选择切换至输入框输入搜索词或语句(query)以搜索相应的待推送信息。在图3a中，用户对操作选项3021对应按钮的点击操作可以作为第一预设操作，用户对操作选项3022、输入法选项3023对应按钮的点击操作可以作为第二预设操作。假设用户对操作选项3022对应的按钮进行了点击操作，则后台服务器可以根据该操作向用户推送新的待推送信息。同样，在图3b中，所示出的推送第二待推送信息303的交互页面给出了操作选项3031、3032和3033，以及输入法选项3034。其中，操作选项3031“大年三十火车票12月29开抢！”可供链接到相关联的新闻页面或者火车票购买页面，操作选项3032“这事没那么简单”可供链接到相关联 的新闻或事件背景页面，操作选项3033“讲点别的”可供从后台服务器请求另一条待推送信息，输入法选项3034的作用同输入法选项3023，在此不再赘述。这里，用户对操作选项3031、3032对应按钮的点击操作可以作为第一预设操作，用户对操作选项3033、输入法选项3034对应按钮的点击操作可以作为第二预设操作。As an example, please refer to the application scenarios shown in Fig. 3a and Fig. 3b. The interactive page for pushing the first information to be pushed 302 shown in FIG. 3 a provides operation options 3021 and 3022 and an input method option 3023 . Among them, the operation option 3021 "What's the situation? Let's hear it!" is available for the user to choose to learn more about the first information to be pushed and its associated information, and the operation option 3022 "Not interested, change another" is available for the user to choose to request from the background server Another first piece of information to be pushed, the input method option 3023 can be selected by the user to switch to the input box to input a search term or sentence (query) to search for the corresponding information to be pushed. In FIG. 3a, the user's click operation on the button corresponding to the operation option 3021 can be used as the first preset operation, and the user's click operation on the buttons corresponding to the operation option 3022 and the input method option 3023 can be used as the second preset operation. Assuming that the user clicks the button corresponding to the operation option 3022, the background server may push new information to be pushed to the user according to the operation. Similarly, in FIG. 3 b , the shown interactive page for pushing the second information to be pushed 303 provides operation options 3031 , 3032 and 3033 , and an input method option 3034 . Among them, the operation option 3031 "New Year's Eve train tickets will be sold on December 29!" can be linked to the associated news page or train ticket purchase page, and the operation option 3032 "It's not that simple" can be linked to the associated news page. On the news or event background page, the operation option 3033 "Tell me something else" can be used to request another piece of information to be pushed from the background server. Here, the user's click operation on the buttons corresponding to the operation options 3031 and 3032 can be used as the first preset operation, and the user's click operations on the buttons corresponding to the operation option 3033 and the input method option 3034 can be used as the second preset operation.
可以理解，用户的第一预设操作、第二预设操作，也是代表用户个体意愿的。因此，在一些实现中，上述电子设备可以将每个用户进行的第一预设操作、第二预设操作作为用户个性化信息的一部分，在针对相应用户的下次信息推送过程中，步骤404中用户的个性化信息可以包括上述电子设备所采集到的相应用户第一预设操作、第二预设操作在内的个性化信息。It can be understood that the user's first preset operation and second preset operation also represent the user's individual wishes. Therefore, in some implementations, the above-mentioned electronic device may use the first preset operation and the second preset operation performed by each user as part of the user's personalized information, and during the next information push process for the corresponding user, step 404 The personalized information of the user may include the personalized information collected by the electronic device, including the first preset operation and the second preset operation of the corresponding user.
步骤406，根据第一预设操作，更新相应待推送信息的热度值。Step 406, according to the first preset operation, update the popularity value of the corresponding information to be pushed.
在本实施例中，上述电子设备可以根据用户的第一预设操作，更新相应待推送信息的热度值。可以理解，当某一个或多个用户选择了所推送的待推送信息时，总体网民对相应待推送信息的关注度增加，相应待推送信息的热度值也增加。上述电子设备可以在检测到用户对某个待推送信息第一预设操作时实时更新相应待推送信息的热度值，也可以根据一定的时间间隔(如5分钟)采集包括第一预设操作在内的数据计算待推送信息的热度值。In this embodiment, the electronic device may update the popularity value of the corresponding information to be pushed according to the first preset operation of the user. It can be understood that when one or more users select the information to be pushed, the overall netizens' attention to the corresponding information to be pushed increases, and the popularity value of the corresponding information to be pushed also increases. The above-mentioned electronic device can update the popularity value of the corresponding information to be pushed in real time when it detects that the user performs the first preset operation on the information to be pushed, or can collect information including the first preset operation according to a certain time interval (such as 5 minutes). Calculate the popularity value of the information to be pushed based on the data in it.
相应待推送信息的热度值被更新后，上述电子设备在一次执行本实施例的基于人工智能的信息推送方法时，在步骤401中可以获取更新后的热度值。After the popularity value of the information to be pushed is updated, the electronic device may obtain the updated popularity value in step 401 when executing the artificial intelligence-based information pushing method of this embodiment.
步骤407，响应于用户的第二预设操作，推送下一条相应待推送信息。Step 407, in response to the user's second preset operation, push the next corresponding message to be pushed.
在本实施例中，响应于用户的第二预设操作(如对待推送信息的拒绝操作、对待推送信息的切换操作等等)，上述电子设备可以向用户推送下一条相应待推送信息，例如，响应于用户对第一待推送信息的第二预设操作，上述电子设备可以向用户推送下一条第一待推送信息，响应于用户对第二待推送信息的第二预设操作，上述电子设备可以向用户推送下一条第二待推送信息。在一些实现中，第一待推送信息和 第二待推送信息可以混合推送，即响应于用户对第一待推送信息的第二预设操作，上述电子设备可以向用户推送下一条第二待推送信息，反之亦然，本申请对此不做限定。在图3a、3b给出的应用场景中，如图3b所示，通过用户对图3a中的操作选项3022对应的按钮进行的点击操作，后台服务器接收到用户表达的对第一待推送信息302“没兴趣，讲点别的”的意图，进一步向用户推送第二待推送信息303。In this embodiment, in response to the user's second preset operation (such as the rejection operation of the information to be pushed, the switching operation of the information to be pushed, etc.), the above-mentioned electronic device can push the next corresponding piece of information to be pushed to the user, for example, In response to the user's second preset operation on the first information to be pushed, the electronic device may push the next first piece of information to be pushed to the user, and in response to the user's second preset operation on the second information to be pushed, the above electronic device may The next second piece of information to be pushed can be pushed to the user. In some implementations, the first information to be pushed and the second information to be pushed can be mixed and pushed, that is, in response to the user’s second preset operation on the first information to be pushed, the electronic device can push the next second piece of information to be pushed to the user. Information, and vice versa, this application does not limit it. In the application scenarios shown in Figures 3a and 3b, as shown in Figure 3b, through the user's click operation on the button corresponding to the operation option 3022 in Figure 3a, the background server receives the first information to be pushed 302 expressed by the user The intention of "not interested, let's talk about something else" further pushes the second to-be-pushed message 303 to the user.
从图4中可以看出，与图2对应的实施例相比，本实施例中的基于人工智能的信息推送方法的流程400通过交互页面推送待推送信息，并增加根据用户在交互页面的操作进行相应处理的步骤406和407。由此，本实施例描述的方案可以供用户根据自身需求选择自己需要的信息，从而实现对所推送信息的个性化选择。It can be seen from FIG. 4 that, compared with the embodiment corresponding to FIG. 2 , the flow 400 of the method for pushing information based on artificial intelligence in this embodiment pushes the information to be pushed through the interactive page, and adds information according to the user's operation on the interactive page. Steps 406 and 407 of corresponding processing are performed. Therefore, the solution described in this embodiment can allow users to select the information they need according to their own needs, so as to realize personalized selection of the pushed information.
进一步参考图5，作为对上述基于人工智能的信息推送方法的实现，本申请提供了一种基于人工智能的信息推送装置的一个实施例，该装置实施例与图2所示的方法实施例相对应。Further referring to FIG. 5 , as an implementation of the above-mentioned artificial intelligence-based information push method, the present application provides an embodiment of an artificial intelligence-based information push device, which is similar to the method embodiment shown in FIG. 2 correspond.
如图5所示，本实施例的基于人工智能的信息推送装置500包括：获取模块501、选取模块502、第一推送模块503和第二推送模块504。其中，获取模块501可以配置用于获取各条待推送信息的热度值；选取模块502可以配置用于根据热度值从待推送信息中选取第一待推送信息、第二待推送信息；第一推送模块503可以配置用于响应于第一推送条件被满足，获取至少一条第一待推送信息进行推送；第一推送模块504可以配置用于响应于第二推送条件被满足，根据用户的个性化信息选取出至少一条第二待推送信息进行推送。As shown in FIG. 5 , the artificial intelligence-based information push device 500 of this embodiment includes: an acquisition module 501 , a selection module 502 , a first push module 503 and a second push module 504 . Among them, the acquisition module 501 can be configured to acquire the popularity value of each piece of information to be pushed; the selection module 502 can be configured to select the first information to be pushed and the second information to be pushed from the information to be pushed according to the popularity value; The module 503 may be configured to acquire at least one piece of first information to be pushed to push in response to the first push condition being satisfied; the first push module 504 may be configured to, in response to the second push condition being satisfied, obtain at least one piece of information to be pushed according to the user's personalized information At least one piece of second information to be pushed is selected and pushed.
在本实施例的一些可选实现方式中，选取模块502可以进一步配置用于：选取热度值大于第一预设阈值的待推送信息作为第一待推送信息，选取热度值大于第二预设阈值且小于第一预设阈值的待推送信息作为第二待推送信息；或者，将待推送信息按照热度值由大到小排列，选取前第一预设个数的待推送信息作为第一待推送信息，从第一待推送信息之后选取第二预设个数的待推送信息作为第二待推送信息。In some optional implementations of this embodiment, the selection module 502 may be further configured to: select information to be pushed with a popularity value greater than a first preset threshold as the first information to be pushed, and select a popularity value greater than a second preset threshold And the information to be pushed that is less than the first preset threshold is used as the second information to be pushed; or, the information to be pushed is arranged in descending order according to the popularity value, and the first preset number of information to be pushed is selected as the first information to be pushed information, selecting a second preset number of information to be pushed after the first information to be pushed as the second information to be pushed.
在本实施例的一些可选实现方式中，上述装置500还包括热度值计算模块(未示出)，配置用于针对各条待推送信息，通过以下方法计 算得到热度值：获取所有用户对与待推送信息相关联的搜索关键词的输入次数和对与待推送信息相关联的链接的点击次数；通过上述输入次数和点击次数根据预设的输入权重和点击权重计算热度值。In some optional implementations of this embodiment, the above-mentioned device 500 also includes a popularity value calculation module (not shown), configured to calculate the popularity value for each piece of information to be pushed by the following method: obtain all user pairs and The input times of search keywords associated with the information to be pushed and the number of clicks on the links associated with the information to be pushed; through the above input times and click times, the popularity value is calculated according to the preset input weight and click weight.
在本实施例的一些可选实现方式中，第一待推送信息和/或第二待推送信息通过交互页面进行推送；以及，上述装置500还可以包括：检测模块(未示出)，可以配置用于检测用户在交互页面的第一预设操作、第二预设操作，其中，第一预设操作可以包括对待推送信息的选择操作，第二预设操作可以包括但不限于以下至少一种：对待推送信息的拒绝操作、对待推送信息的切换操作等等；热度值更新模块(未示出)，可以配置用于根据第一预设操作，更新相应待推送信息的热度值；第一推送模块、第二推送模块还分别可以配置用于响应于用户的第二预设操作，推送下一条相应待推送信息。In some optional implementations of this embodiment, the first information to be pushed and/or the second information to be pushed is pushed through an interactive page; and, the above device 500 may further include: a detection module (not shown), which may be configured It is used to detect the first preset operation and the second preset operation of the user on the interactive page, wherein the first preset operation may include the selection operation of the information to be pushed, and the second preset operation may include but not limited to at least one of the following : the rejection operation of the information to be pushed, the switching operation of the information to be pushed, etc.; the popularity value update module (not shown), which can be configured to update the popularity value of the corresponding information to be pushed according to the first preset operation; the first push The module and the second push module can also be configured to push the next corresponding message to be pushed in response to the second preset operation of the user.
在本实施例的一些可选实现方式中，第二推送模块504可以包括：获取单元(未示出)，可以配置用于获取用户的个性化信息，该个性化信息包括以下至少一项：历史搜索信息、历史点击信息；提取单元(未示出)，可以配置用于根据该个性化信息提取用户的兴趣标签；确定单元(未示出)，可以配置用于基于上述兴趣标签与第二待推送信息的匹配确定上述兴趣标签与第二待推送信息的关联度；推送单元(未示出)，可以配置用于基于该关联度选择至少一条第二待推送信息进行推送。In some optional implementations of this embodiment, the second push module 504 may include: an acquisition unit (not shown), which may be configured to acquire personalized information of the user, and the personalized information includes at least one of the following: history Search information, historical click information; an extraction unit (not shown), which can be configured to extract the user's interest tag according to the personalized information; a determination unit (not shown), which can be configured to be based on the above-mentioned interest tag and the second target The matching of the push information determines the degree of association between the interest tag and the second information to be pushed; the push unit (not shown) may be configured to select at least one piece of second information to be pushed based on the degree of association to push.
在本实施例的一些可选实现方式中，上述关联度通过以下方法计算：In some optional implementations of this embodiment, the above-mentioned degree of association is calculated by the following method:
P(C)＝F(A)×SIM(A,C)；P(C)=F(A)×SIM(A,C);
其中，P(C)表示兴趣标签A、待推送信息C的关联度，F(A)表示用户对兴趣标签A的兴趣度，SIM(A，C)表示兴趣标签A与待推送信息C的文本相似度。Among them, P(C) represents the degree of association between the interest tag A and the information C to be pushed, F(A) represents the user’s interest in the interest tag A, and SIM(A, C) represents the text of the interest tag A and the information C to be pushed similarity.
值得说明的是，基于人工智能的信息推送装置500中记载的诸模块与参考图2描述的方法中的各个步骤相对应。由此，上文针对方法描述的操作和特征同样适用于装置500及其中包含的模块或单元，在此不再赘述。It is worth noting that the modules recorded in the artificial intelligence-based information push device 500 correspond to each step in the method described with reference to FIG. 2 . Therefore, the operations and features described above for the method are also applicable to the device 500 and the modules or units included therein, and will not be repeated here.
本领域技术人员可以理解，上述基于人工智能的信息推送装置500还包括一些其他公知结构，例如处理器、存储器等，为了不必要地模糊本公开的实施例，这些公知的结构在图5中未示出。Those skilled in the art can understand that the above-mentioned artificial intelligence-based information push device 500 also includes some other known structures, such as processors, memories, etc. In order to unnecessarily obscure the embodiments of the present disclosure, these known structures are not shown in FIG. show.
下面参考图6，其示出了适于用来实现本申请实施例的终端设备/服务器的计算机系统600的结构示意图。图6示出的终端设备/服务器仅仅是一个示例，不应对本申请实施例的功能和使用范围带来任何限制。Referring now to FIG. 6 , it shows a schematic structural diagram of a computer system 600 suitable for implementing a terminal device/server according to an embodiment of the present application. The terminal device/server shown in FIG. 6 is only an example, and should not limit the functions and scope of use of this embodiment of the present application.
如图6所示，计算机系统600包括中央处理单元(CPU)601，其可以根据存储在只读存储器(ROM)602中的程序或者从存储部分608加载到随机访问存储器(RAM)603中的程序而执行各种适当的动作和处理。在RAM 603中，还存储有系统600操作所需的各种程序和数据。CPU601、ROM 602以及RAM603通过总线604彼此相连。输入/输出(I/O)接口605也连接至总线604。As shown in FIG. 6 , a computer system 600 includes a central processing unit (CPU) 601 that can be programmed according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage section 608 into a random-access memory (RAM) 603 Instead, various appropriate actions and processes are performed. In the RAM 603, various programs and data necessary for the operation of the system 600 are also stored. The CPU 601 , ROM 602 , and RAM 603 are connected to each other via a bus 604 . An input/output (I/O) interface 605 is also connected to the bus 604 .
以下部件连接至I/O接口605：包括键盘或触摸屏等的输入部分606；包括诸如阴极射线管(CRT)、液晶显示器(LCD)等的输出部分607；包括硬盘等的存储部分608；以及包括诸如LAN卡、调制解调器等的网络接口卡的通信部分609。通信部分609经由诸如因特网的网络执行通信处理。驱动器610也根据需要连接至I/O接口605。可拆卸介质611，诸如磁盘、光盘、磁光盘、半导体存储器等等，根据需要安装在驱动器610上，以便于从其上读出的计算机程序根据需要被安装入存储部分608。The following components are connected to the I/O interface 605: an input section 606 including a keyboard or a touch screen, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc.; a storage section 608 including a hard disk, etc.; A communication section 609 of a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, optical disk, magneto-optical disk, semiconductor memory, etc. is mounted on the drive 610 as necessary so that a computer program read therefrom is installed into the storage section 608 as necessary.
特别地，根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信部分609从网络上被下载和安装，和/或从可拆卸介质611被安装。在该计算机程序被中央处理单元(CPU)601执行时，执行本申请的方法中限定的上述功能。需要说明的是，本申请所述的非易失性计算机可读介质可以是非易失性计算机可读信号介质或者非易失性计算机可读存储介质或者是上述两者的任意组合。非易失性计算机可读存储介质例如可以是——但不限于——电、磁、光、 电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。非易失性计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本申请中，非易失性计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本申请中，计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读的信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：无线、电线、光缆、RF等等，或者上述的任意合适的组合。In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, where the computer program includes program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via communication portion 609 and/or installed from removable media 611 . When the computer program is executed by the central processing unit (CPU) 601, the above-mentioned functions defined in the method of the present application are performed. It should be noted that the non-volatile computer-readable medium described in the present application may be a non-volatile computer-readable signal medium or a non-volatile computer-readable storage medium or any combination of the above two. A non-volatile computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples of non-volatile computer readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), Erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. In the present application, a non-transitory computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, in which computer-readable program codes are carried. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. . Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
附图中的流程图和框图，图示了按照本申请各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in a flowchart or block diagram may represent a module, program segment, or portion of code that contains one or more logical functions for implementing specified executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved. It should also be noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented by a dedicated hardware-based system that performs the specified functions or operations , or may be implemented by a combination of dedicated hardware and computer instructions.
描述于本申请实施例中所涉及到的模块可以通过软件的方式实现，也可以通过硬件的方式来实现。所描述的模块也可以设置在处理器中， 例如，可以描述为：一种处理器包括获取模块、选取模块、第一推送模块和第二推送模块。其中，这些模块的名称在某种情况下并不构成对该单元本身的限定，例如，获取模块还可以被描述为“配置用于获取各条待推送信息的热度值的模块”。The modules involved in the embodiments described in the present application may be implemented by means of software or hardware. The described modules may also be set in a processor, for example, it may be described as: a processor includes an acquisition module, a selection module, a first push module, and a second push module. Wherein, the names of these modules do not limit the unit itself under certain circumstances, for example, the obtaining module can also be described as "a module configured to obtain the popularity value of each piece of information to be pushed".
作为另一方面，本申请还提供了一种计算机可读介质，该计算机可读介质可以是上述实施例中描述的装置中所包含的；也可以是单独存在，而未装配入该装置中。上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该装置执行时，使得该装置：获取各条待推送信息的热度值；根据热度值从待推送信息中选取第一待推送信息、第二待推送信息；响应于第一推送条件被满足，获取至少一条第一待推送信息进行推送；响应于第二推送条件被满足，根据用户的个性化信息选取出至少一条第二待推送信息进行推送。As another aspect, the present application also provides a computer-readable medium. The computer-readable medium may be included in the device described in the above embodiments, or it may exist independently without being assembled into the device. The above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the device, the device: obtains the heat value of each piece of information to be pushed; selects the first piece of information from the information to be pushed according to the heat value One information to be pushed, the second information to be pushed; in response to the first push condition being satisfied, at least one piece of the first information to be pushed is obtained and pushed; in response to the second push condition being satisfied, at least one piece of information is selected according to the user's personalized information The second information to be pushed is pushed.
以上描述仅为本申请的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本申请中所涉及的发明范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述发明构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本申请中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。The above description is only a preferred embodiment of the present application and an illustration of the applied technical principles. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to the technical solution formed by the specific combination of the above-mentioned technical features, and should also cover the technical solutions formed by the above-mentioned technical features or without departing from the above-mentioned inventive concept. Other technical solutions formed by any combination of equivalent features. For example, a technical solution formed by replacing the above-mentioned features with technical features with similar functions disclosed in (but not limited to) this application.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710175451.2ACN106993030A (en) | 2017-03-22 | 2017-03-22 | Information-pushing method and device based on artificial intelligence |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710175451.2ACN106993030A (en) | 2017-03-22 | 2017-03-22 | Information-pushing method and device based on artificial intelligence |
| Publication Number | Publication Date |
|---|---|
| CN106993030Atrue CN106993030A (en) | 2017-07-28 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710175451.2APendingCN106993030A (en) | 2017-03-22 | 2017-03-22 | Information-pushing method and device based on artificial intelligence |
| Country | Link |
|---|---|
| CN (1) | CN106993030A (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107426328A (en)* | 2017-08-08 | 2017-12-01 | 百度在线网络技术（北京）有限公司 | Information-pushing method and device |
| CN107612966A (en)* | 2017-08-11 | 2018-01-19 | 百度在线网络技术（北京）有限公司 | Feed information feedback processing methods and system |
| CN107679943A (en)* | 2017-09-27 | 2018-02-09 | 广州市万表科技股份有限公司 | Intelligent recommendation method and system |
| CN107886373A (en)* | 2017-12-11 | 2018-04-06 | 广东欧珀移动通信有限公司 | Advertisement sending method based on keyword, advertisement pushing device and electric terminal |
| CN108090131A (en)* | 2017-11-23 | 2018-05-29 | 北京洪泰同创信息技术有限公司 | It teaches the method for pushing of auxiliary resource data and teaches the pusher of auxiliary resource data |
| TWI648979B (en)* | 2017-08-02 | 2019-01-21 | 中華電信股份有限公司 | Authentication method and system thereof |
| CN109993583A (en)* | 2019-04-02 | 2019-07-09 | 深圳市腾讯信息技术有限公司 | Information-pushing method and device, storage medium and electronic device |
| CN110309189A (en)* | 2018-03-13 | 2019-10-08 | 深圳市腾讯计算机系统有限公司 | The temperature acquisition methods and device of entity word |
| CN110413895A (en)* | 2019-07-31 | 2019-11-05 | 腾讯科技（深圳）有限公司 | A method for pushing information and a related device |
| CN110737828A (en)* | 2019-09-16 | 2020-01-31 | 平安科技（深圳）有限公司 | An information push method and related device |
| CN111125526A (en)* | 2019-12-24 | 2020-05-08 | 腾讯科技（深圳）有限公司 | Content pushing method and device based on artificial intelligence and electronic equipment |
| CN112464079A (en)* | 2019-09-09 | 2021-03-09 | 北京奇虎科技有限公司 | Push information display method, device and system |
| CN112507211A (en)* | 2020-11-18 | 2021-03-16 | 青岛海尔科技有限公司 | Message pushing method and device, storage medium and electronic device |
| CN112818210A (en)* | 2019-11-15 | 2021-05-18 | 上海连尚网络科技有限公司 | Method and device for pushing information |
| CN113360550A (en)* | 2021-08-10 | 2021-09-07 | 深圳市爱云信息科技有限公司 | Accurate content distribution platform based on big data |
| CN113781246A (en)* | 2021-09-14 | 2021-12-10 | 平安科技（深圳）有限公司 | Policy generation method and device based on preset label and storage medium |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102750334A (en)* | 2012-06-01 | 2012-10-24 | 北京市农林科学院农业科技信息研究所 | Agricultural information accurate propelling method based on data mining (DM) |
| US20130091129A1 (en)* | 2011-10-10 | 2013-04-11 | Samsung Electronics Co., Ltd. | Search method and system using keyword |
| CN103164804A (en)* | 2011-12-16 | 2013-06-19 | 阿里巴巴集团控股有限公司 | Personalized method and personalized device of information push |
| CN103501340A (en)* | 2013-10-08 | 2014-01-08 | 北京金山网络科技有限公司 | Message push method, message push device and client |
| CN104573054A (en)* | 2015-01-21 | 2015-04-29 | 杭州朗和科技有限公司 | Information pushing method and equipment |
| CN105095431A (en)* | 2015-07-22 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Method and device for pushing videos based on behavior information of user |
| CN105139237A (en)* | 2015-09-25 | 2015-12-09 | 百度在线网络技术（北京）有限公司 | Information push method and apparatus |
| CN105302904A (en)* | 2015-10-29 | 2016-02-03 | 努比亚技术有限公司 | Information pushing method and apparatus |
| CN105893443A (en)* | 2015-12-15 | 2016-08-24 | 乐视网信息技术（北京）股份有限公司 | Video recommendation method and apparatus, and server |
| CN106161627A (en)* | 2016-07-12 | 2016-11-23 | 百度在线网络技术（北京）有限公司 | Method and device for pushed information |
| CN106407425A (en)* | 2016-09-27 | 2017-02-15 | 北京百度网讯科技有限公司 | A method and a device for information push based on artificial intelligence |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130091129A1 (en)* | 2011-10-10 | 2013-04-11 | Samsung Electronics Co., Ltd. | Search method and system using keyword |
| CN103164804A (en)* | 2011-12-16 | 2013-06-19 | 阿里巴巴集团控股有限公司 | Personalized method and personalized device of information push |
| CN102750334A (en)* | 2012-06-01 | 2012-10-24 | 北京市农林科学院农业科技信息研究所 | Agricultural information accurate propelling method based on data mining (DM) |
| CN103501340A (en)* | 2013-10-08 | 2014-01-08 | 北京金山网络科技有限公司 | Message push method, message push device and client |
| CN104573054A (en)* | 2015-01-21 | 2015-04-29 | 杭州朗和科技有限公司 | Information pushing method and equipment |
| CN105095431A (en)* | 2015-07-22 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Method and device for pushing videos based on behavior information of user |
| CN105139237A (en)* | 2015-09-25 | 2015-12-09 | 百度在线网络技术（北京）有限公司 | Information push method and apparatus |
| CN105302904A (en)* | 2015-10-29 | 2016-02-03 | 努比亚技术有限公司 | Information pushing method and apparatus |
| CN105893443A (en)* | 2015-12-15 | 2016-08-24 | 乐视网信息技术（北京）股份有限公司 | Video recommendation method and apparatus, and server |
| CN106161627A (en)* | 2016-07-12 | 2016-11-23 | 百度在线网络技术（北京）有限公司 | Method and device for pushed information |
| CN106407425A (en)* | 2016-09-27 | 2017-02-15 | 北京百度网讯科技有限公司 | A method and a device for information push based on artificial intelligence |
| Title |
|---|
| 缪平: ""基于微博用户兴趣模型的信息推送技术的研究"", 《中国优秀硕士学位论文全文数据库信息科技辑》* |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI648979B (en)* | 2017-08-02 | 2019-01-21 | 中華電信股份有限公司 | Authentication method and system thereof |
| CN107426328A (en)* | 2017-08-08 | 2017-12-01 | 百度在线网络技术（北京）有限公司 | Information-pushing method and device |
| CN107612966B (en)* | 2017-08-11 | 2021-01-26 | 百度在线网络技术（北京）有限公司 | Feed information feedback processing method and system |
| CN107612966A (en)* | 2017-08-11 | 2018-01-19 | 百度在线网络技术（北京）有限公司 | Feed information feedback processing methods and system |
| CN107679943A (en)* | 2017-09-27 | 2018-02-09 | 广州市万表科技股份有限公司 | Intelligent recommendation method and system |
| CN108090131A (en)* | 2017-11-23 | 2018-05-29 | 北京洪泰同创信息技术有限公司 | It teaches the method for pushing of auxiliary resource data and teaches the pusher of auxiliary resource data |
| CN107886373A (en)* | 2017-12-11 | 2018-04-06 | 广东欧珀移动通信有限公司 | Advertisement sending method based on keyword, advertisement pushing device and electric terminal |
| CN107886373B (en)* | 2017-12-11 | 2021-09-21 | Oppo广东移动通信有限公司 | Advertisement pushing method and device based on keywords and electronic terminal |
| CN110309189B (en)* | 2018-03-13 | 2023-04-18 | 深圳市腾讯计算机系统有限公司 | Method and device for acquiring heat of entity words |
| CN110309189A (en)* | 2018-03-13 | 2019-10-08 | 深圳市腾讯计算机系统有限公司 | The temperature acquisition methods and device of entity word |
| CN109993583B (en)* | 2019-04-02 | 2021-07-27 | 深圳市腾讯信息技术有限公司 | Information pushing method and device, storage medium and electronic device |
| CN109993583A (en)* | 2019-04-02 | 2019-07-09 | 深圳市腾讯信息技术有限公司 | Information-pushing method and device, storage medium and electronic device |
| CN110413895A (en)* | 2019-07-31 | 2019-11-05 | 腾讯科技（深圳）有限公司 | A method for pushing information and a related device |
| CN112464079A (en)* | 2019-09-09 | 2021-03-09 | 北京奇虎科技有限公司 | Push information display method, device and system |
| CN110737828A (en)* | 2019-09-16 | 2020-01-31 | 平安科技（深圳）有限公司 | An information push method and related device |
| CN112818210A (en)* | 2019-11-15 | 2021-05-18 | 上海连尚网络科技有限公司 | Method and device for pushing information |
| CN112818210B (en)* | 2019-11-15 | 2024-06-21 | 上海连尚网络科技有限公司 | Method and device for pushing information |
| CN111125526A (en)* | 2019-12-24 | 2020-05-08 | 腾讯科技（深圳）有限公司 | Content pushing method and device based on artificial intelligence and electronic equipment |
| CN112507211A (en)* | 2020-11-18 | 2021-03-16 | 青岛海尔科技有限公司 | Message pushing method and device, storage medium and electronic device |
| CN113360550A (en)* | 2021-08-10 | 2021-09-07 | 深圳市爱云信息科技有限公司 | Accurate content distribution platform based on big data |
| CN113781246A (en)* | 2021-09-14 | 2021-12-10 | 平安科技（深圳）有限公司 | Policy generation method and device based on preset label and storage medium |
| CN113781246B (en)* | 2021-09-14 | 2024-03-05 | 平安科技（深圳）有限公司 | Strategy generation method and device based on preset label and storage medium |
| Publication | Publication Date | Title |
|---|---|---|
| CN106993030A (en) | Information-pushing method and device based on artificial intelligence | |
| CN107172151B (en) | Method and device for pushing information | |
| US11172040B2 (en) | Method and apparatus for pushing information | |
| CN109522483B (en) | Method and device for pushing information | |
| CN109460514B (en) | Method and device for pushing information | |
| CN107463704B (en) | Search method and device based on artificial intelligence | |
| CN109145280B (en) | Information pushing method and device | |
| CN107220386B (en) | Information pushing method and device | |
| CN107241260B (en) | News pushing method and device based on artificial intelligence | |
| CN108804450B (en) | Information pushing method and device | |
| WO2018192491A1 (en) | Information pushing method and device | |
| CN106960030B (en) | Information pushing method and device based on artificial intelligence | |
| US10771424B2 (en) | Usability and resource efficiency using comment relevance | |
| CN107908789A (en) | Method and apparatus for generating information | |
| CN107526718B (en) | Method and apparatus for generating text | |
| CN107577807B (en) | Method and device for pushing information | |
| US20190171724A1 (en) | Method and apparatus for determining hot event | |
| CN108228906B (en) | Method and apparatus for generating information | |
| WO2018149115A1 (en) | Method and apparatus for providing search results | |
| WO2017000402A1 (en) | Page generation method and device | |
| CN106407361A (en) | Method and device for pushing information based on artificial intelligence | |
| US20140164296A1 (en) | Chatbot system and method with entity-relevant content from entity | |
| WO2017121076A1 (en) | Information-pushing method and device | |
| CN111274490B (en) | Method and device for processing consultation information | |
| CN103534699A (en) | Methods, apparatuses and computer program products for providing topic model with wording preferences |
| 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication | Application publication date:20170728 |