WO2016173185A1 - 信息推送方法和装置 - Google Patents

信息推送方法和装置 Download PDF

Info

Publication number
WO2016173185A1
WO2016173185A1 PCT/CN2015/090068 CN2015090068W WO2016173185A1 WO 2016173185 A1 WO2016173185 A1 WO 2016173185A1 CN 2015090068 W CN2015090068 W CN 2015090068W WO 2016173185 A1 WO2016173185 A1 WO 2016173185A1
Authority
WO
WIPO (PCT)
Prior art keywords
search
feature
site
keyword
user
Prior art date
Application number
PCT/CN2015/090068
Other languages
English (en)
French (fr)
Inventor
徐云峰
卢嘉龙
赵继承
Original Assignee
百度在线网络技术(北京)有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 百度在线网络技术(北京)有限公司 filed Critical 百度在线网络技术(北京)有限公司
Publication of WO2016173185A1 publication Critical patent/WO2016173185A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/3331Query processing
    • G06F16/3332Query translation
    • G06F16/3338Query expansion
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/335Filtering based on additional data, e.g. user or group profiles
    • G06F16/337Profile generation, learning or modification
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9535Search customisation based on user profiles and personalisation

Definitions

  • the present application relates to the field of computer technologies, and in particular, to the field of Internet technologies, and in particular, to an information push method and apparatus.
  • Information Push also known as “webcasting” is a technology that reduces information overload on the Internet by periodically transmitting information needed by users through certain technical standards or protocols. Information push technology can reduce the time it takes for users to search on the network by actively pushing information to users.
  • the existing information push strategy is usually based on the user's behavior in a network site (especially the click behavior), but fails to take advantage of the user's behavior on other network sites. Therefore, there is insufficient use of user behavior related data, and information push is difficult to individualize. Problem.
  • the purpose of the present application is to propose an improved information push method and apparatus to solve the technical problems mentioned in the background section above.
  • the present application provides an information push method, the method comprising: acquiring a search behavior feature of a user at a first site, wherein the search behavior feature includes a search keyword feature and/or a click feature; and acquiring the user a search behavior feature at a second site different from the first site; generating a push keyword based on the search behavior feature of the first site and the search behavior feature of the second site; based on the push keyword In the office Searching for information within the first site and/or the second site and pushing search results to the user.
  • the search keyword feature comprises at least one of: a search term entered by the user, a synonym of the search term, a synonym of the search term.
  • the generating a keyword for pushing based on a search behavior feature of the first site and a search behavior feature of the second site including: generating a feature based on a search behavior feature of the first site a push keyword; generating a second push keyword based on the search behavior feature of the second site; and generating a push keyword based on the first push keyword and the second push keyword.
  • the generating the first push keyword based on the search behavior feature of the first site comprises: parsing a search keyword feature in the search behavior feature of the first site, generating and Searching for a keyword-related search word set; parsing a click feature in the search behavior feature of the first site to generate a search word set related to the click feature; and based on the search word set related to the search keyword feature And the set of search words related to the click feature to generate a first push keyword.
  • the parsing the click feature in the search behavior feature of the first site to generate a search term set related to the click feature comprises: acquiring the click object of the user based on the click feature
  • the click object includes at least one of the following: a picture, a video, a text, a URL link; parsing the click object to generate a search word set related to the click feature.
  • the generating a second push keyword based on the search behavior feature of the second site comprises: parsing a search keyword feature in the search behavior feature of the second site, generating and Searching for a keyword-related search term set; parsing a click feature in the search behavior feature of the second site to generate a search word set related to the click feature; and based on the search word set related to the search keyword feature And the set of search words related to the click feature, and generating a second push keyword.
  • the performing information search and pushing the search result to the user in the first site and/or the second site based on the keyword for pushing includes: acquiring a search for a user group to which the user belongs a behavior characteristic; generating a keyword for user group push based on a search behavior characteristic of the user group; and pushing based on the push keyword and the user group Using keywords, information searches are performed within the first site and/or second site and search results are pushed to the user.
  • the present application provides an information pushing apparatus, where the apparatus includes: a first acquiring unit configured to acquire a search behavior feature of a user at a first site, wherein the search behavior feature includes a search keyword feature and/or Or a click feature; a second obtaining unit configured to acquire a search behavior feature of the user at a second site different from the first site; a generating unit configured to perform a search behavior feature based on the first site and the a search behavior feature of the second site, generating a keyword for pushing; a retrieval unit configured to perform information search and push to the user in the first site and/or the second site based on the keyword for pushing search results.
  • the search keyword feature comprises at least one of: a search term entered by the user, a synonym of the search term, a synonym of the search term.
  • the generating unit includes: a first generating module configured to generate a first push keyword based on a search behavior feature of the first site; and a second generating module configured to be configured based on the The search behavior feature of the second site generates a second push keyword; and the summary module is configured to generate a push keyword based on the first push keyword and the second push keyword.
  • the first generating module includes: a search keyword feature parsing sub-module configured to parse search keyword features in the search behavior feature of the first site, generate and search keyword features a related search word set; a click feature analysis sub-module configured to parse the click feature in the search behavior feature of the first site, generate a search word set related to the click feature; generate a sub-module configured to be based on The set of search words related to the search keyword feature and the set of search words related to the click feature generate a first push keyword.
  • a search keyword feature parsing sub-module configured to parse search keyword features in the search behavior feature of the first site, generate and search keyword features a related search word set
  • a click feature analysis sub-module configured to parse the click feature in the search behavior feature of the first site, generate a search word set related to the click feature
  • generate a sub-module configured to be based on The set of search words related to the search keyword feature and the set of search words related to the click feature generate a first
  • the click feature parsing sub-module is further configured to: obtain a click object of the user based on the click feature, wherein the click object includes at least one of the following: an image, a video, a text, a URL Linking; parsing the click object to generate a set of search terms related to the click feature.
  • the second generating module includes: a search keyword feature parsing sub-module configured to search for a keyword in the search behavior feature of the second site Querying, generating a set of search words related to the search keyword feature; and clicking the feature analysis sub-module configured to parse the click feature in the search behavior feature of the second site to generate a search term related to the click feature And a generating submodule configured to generate a second push keyword based on the search word set related to the search keyword feature and the search word set related to the click feature.
  • the retrieving unit further includes: an obtaining module configured to acquire a search behavior feature of the user group to which the user belongs; a user group push keyword generating module configured to perform a search behavior feature based on the user group Generating a user group push keyword; the search module is configured to perform information search and the information in the first site and/or the second site based on the push keyword and the user group push keyword The user pushes the search results.
  • the information pushing method and apparatus provided by the present application generates a push keyword based on the search behavior characteristics of the user at the first site and the second site different from the first site, and finally generates a push keyword based on the search behavior features, and finally based on the push key Words, searching for information in the first site and/or the second site and pushing the search results to the user, more fully utilizing the user behavior information, thereby realizing personalized information push and saving retrieval time .
  • FIG. 1 is an exemplary system architecture diagram to which the present application can be applied;
  • FIG. 2 is a flow chart of one embodiment of an information push method according to the present application.
  • FIG. 3 is a schematic diagram of an application scenario of an information pushing method according to the present application.
  • FIG. 5 is a schematic diagram of another application scenario of an information pushing method according to the present application.
  • FIG. 6 is a schematic structural diagram of an embodiment of an information pushing apparatus according to the present application.
  • FIG. 1 illustrates an exemplary system architecture 100 in which embodiments of the present application may be applied.
  • system architecture 100 can include terminal devices 101, 102, 103, network 104, and server 105.
  • the network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105.
  • Network 104 may include various types of connections, such as wired, wireless communication links, fiber optic cables, and the like.
  • the user can interact with the server 105 over the network 104 using the terminal devices 101, 102, 103 to receive or transmit messages and the like.
  • Various communication client applications such as a shopping application, a search application, an instant communication tool, a mailbox client, a social platform software, and the like, may be installed on the terminal devices 101, 102, and 103.
  • the terminal devices 101, 102, 103 may be various electronic devices, including but not limited to smart phones, tablets, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, motion picture expert compression standard audio layer 3) MP4 (Moving Picture Experts Group Audio Layer IV) player, laptop portable computer and desktop computer, etc.
  • MP3 players Moving Picture Experts Group Audio Layer III, motion picture expert compression standard audio layer 3
  • MP4 Moving Picture Experts Group Audio Layer IV
  • the server 105 may be a server that provides various services, such as a background server that provides support for shopping applications, search applications, and the like on the terminal devices 101, 102, 103.
  • the server can store, analyze, and the like the received data, and feed back the processing result to the terminal device.
  • the information pushing method provided by the embodiment of the present application may be performed by the terminal device 101, 102, and 103, or may be performed by the server 105.
  • the information pushing device may be disposed in the terminal device 101, 102, and 103, or may be configured. It is set in the server 105.
  • terminal devices, networks, and servers in Figure 1 is merely illustrative. Depending on the implementation needs, there can be any number of terminal devices, networks, and servers.
  • the information pushing method includes the following steps:
  • Step 201 Acquire a search behavior feature of the user at the first site.
  • the electronic device used by the user can acquire the search behavior feature of the user at the first site (for example, a search website) locally or remotely.
  • the first site for example, a search website
  • the electronic device is a background server supporting the first site
  • the foregoing search behavior feature may be directly obtained from the local device; and when the electronic device is a terminal device, the electronic device may be connected by a wired connection or a wireless connection.
  • the method acquires the user's search behavior characteristics from a back-end server that supports the first site.
  • the above wireless connection methods include, but are not limited to, 3G/4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods now known or developed in the future.
  • the above search behavior features may include search keyword features and/or click features.
  • the search keyword feature may include a search term used by the user in searching and a derivative word of the search term.
  • the derivative word of the search term may include at least one of the following: a synonym of the search term, for example, the search term "child” may have the synonym "child”; the synonym of the search term, for example, the search term "Chinese medicine” may There is a synonym "herbal”; an expanded word of the search term, for example, the search term "cold” may have an expansion word such as "fever” or "flu”.
  • the above click feature may include description or characterization of the user's click location or click object.
  • the above-mentioned click object may be each information item displayed directly on the website page or displayed as a search result, which may include, for example, but not limited to, a picture, a video, a text, a web link, and the like.
  • Step 202 Acquire a search behavior feature of the user at a second site different from the first site.
  • the electronic device used by the user may continue to acquire the second site (eg, shopping) different from the first site.
  • Website search behavior characteristics can include a search keyword feature and/or a click feature.
  • Step 203 Generate a push keyword based on the search behavior feature of the first site and the search behavior feature of the second site.
  • the electronic device used by the user may perform a summary analysis on the search behavior feature of the user at the first site and the search behavior feature at the second site to generate a push keyword, and the push keyword will be used. In the subsequent push for the information of the above users.
  • the search behavior feature may include a search keyword feature and/or a click feature
  • the search keyword feature and the click feature may be separately analyzed to obtain a push keyword.
  • the search term "child” included in the search keyword feature and the synonym "child” can be directly used as a keyword for pushing.
  • Clicking on the description of the user's click object included in the feature, such as "Building Block Toys” can also be used as a keyword for pushing.
  • the aggregated push keywords may include: “children”, “children” and "building blocks toys”.
  • Step 204 Perform information search in the first site and/or the second site based on the push keyword and push the search result to the user.
  • the push keyword generated in step 203 can be used as a search term to perform information search in the first site and/or the second site, and then the searched information is pushed to the user. For example, based on the above-mentioned push keywords "child”, “child” and "building block toy", a search is performed in a second site (for example, a shopping site), and a search result is returned to the user.
  • the step 203 of generating a push keyword may be performed as follows: first, generating a first push keyword based on a search behavior feature of the first site; and second, based on the second site The search behavior feature generates a second push keyword; finally, a push keyword is generated based on the first push keyword and the second push keyword.
  • the first or second push keyword may be generated as follows: First, the search keyword feature in the search behavior feature of the first or second site is analyzed to generate a search term related to the search keyword feature. a collection; secondly, parsing a click feature in the search behavior feature of the first or second site to generate a search term set related to the click feature; and finally, based on the search term set related to the search keyword feature and the foregoing Click the feature-related search word set to summarize the first or second push keywords.
  • the parsing of the click feature may be performed as follows:
  • the above-mentioned click object is each item of information displayed on the site page, such as an image, a video, a text, a URL link, and the like.
  • the click object is parsed to generate a search term set related to the click feature. For example, if the click object includes an image or video, the search term can be obtained based on the name of the image or video; if the click object includes a URL link, the search term can be obtained based on the relevant characters in the URL link.
  • FIG. 3 is a schematic diagram of an application scenario of the information pushing method according to the embodiment.
  • the user first logs in to the search engine website and enters the search term "child”.
  • the user enters the shopping site where the search term "cold medicine” is entered and the "thermometer” picture appearing on the search result page is clicked.
  • the keyword "child”, “child”, “cold medicine”, and “thermometer” for pushing can be obtained, as indicated by reference numeral 303.
  • the above-mentioned push keyword can be used as a search term, and the background information search can be continued in the shopping website, and the search result information can be obtained and pushed to the user.
  • the method provided in the above embodiment of the present application achieves targeted information push by summarizing the search behavior characteristics of the user at different sites and extracting the push keywords, and then using the push keywords to retrieve the push information, thereby saving the targeted information. User's retrieval time.
  • the flow 400 of the information pushing method includes the following steps:
  • Step 401 Acquire a search behavior feature of the user at the first site.
  • the electronic device used by the user can acquire the search behavior feature of the user at the first site (for example, a search website) locally or remotely.
  • the above search behavior features may include search keyword features and/or click features.
  • the search keyword feature may include a search term used by the user in searching and a derivative word of the search term.
  • the above click feature can be packaged A description or characterization of the user's click location or click object.
  • Step 402 Acquire a search behavior feature of the user at a second site different from the first site.
  • the electronic device used by the user may continue to acquire the second site (eg, shopping) different from the first site.
  • Website search behavior characteristics For example, a search site
  • Step 403 Generate a keyword for pushing based on the search behavior feature of the first site and the search behavior feature of the second site.
  • the electronic device used by the user may perform a summary analysis on the search behavior feature of the user at the first site and the search behavior feature at the second site to generate a push keyword, and the push keyword will be used. In the subsequent push for the information of the above users.
  • Step 404 Obtain a search behavior feature of the user group to which the user belongs.
  • the user group to which the user belongs may include at least one of the following: a user group formed by the user's telephone contact, and the user group may be obtained through a telephone address book in the user's mobile terminal; a user group formed by a friend in a user's instant messaging tool (eg, QQ, WeChat, etc.), which can be obtained through the contact record of the instant messaging tool; a user group formed by the user using the same search term, for example, using Multiple users of the same search term "cold medicine" can form a user group.
  • a user group formed by the user's telephone contact and the user group may be obtained through a telephone address book in the user's mobile terminal
  • a user group formed by a friend in a user's instant messaging tool eg, QQ, WeChat, etc.
  • a user group formed by the user using the same search term for example, using Multiple users of the same search term "cold medicine" can form a user group.
  • the search behavior characteristics of each user in the user group may be acquired correspondingly, and then the summary analysis is performed to obtain the search behavior characteristics of the entire user group.
  • the search behavior feature of a specific user refer to the description of step 201 above, which is not described here.
  • Step 405 Generate a keyword for user group push based on the search behavior feature of the user group.
  • the search keyword features included in the search behavior feature of the user group may be parsed to generate a search term set related to the search keyword feature; and then, the click feature in the search behavior feature is parsed, Generating a set of search words related to the click feature; finally, generating a user group push keyword based on the search word set related to the search keyword feature and the search word set related to the click feature.
  • Step 406 based on the push keyword and the user group push keyword, perform information search in the first site and/or the second site and push the search result to the user.
  • the push keyword and the user group push keyword can be used as search terms, information search can be performed in the first site and/or the second site, and the searched information can be pushed to the user.
  • the step 401, the step 402, the step 403, and the step 406 in the foregoing implementation process are substantially the same as the step 201, the step 202, the step 203, and the step 204 in the foregoing embodiment, and details are not described herein again.
  • the flow 400 of the information pushing method in the embodiment is more than the step 404 of acquiring the search behavior feature of the user group to which the user belongs and the user group based.
  • FIG. 5 is a schematic diagram of an application scenario of the information pushing method according to the embodiment.
  • the user A first logs in to the search engine site and inputs the search term "child”.
  • the user A enters the shopping site where the search term "cold medicine” is entered and the "thermometer” picture appearing on the search result page is clicked.
  • the keywords "child”, “child”, “cold medicine”, and "thermometer” for the user A can be obtained, as indicated by reference numeral 503.
  • the present application provides an embodiment of an information pushing apparatus, and the apparatus embodiment and the method shown in FIG.
  • the device can be specifically applied to various electronic devices.
  • the information pushing apparatus 600 described in this embodiment includes a first acquiring unit 601, a second acquiring unit 602, a generating unit 603, and a retrieving unit 604.
  • the first obtaining unit 601 is configured to acquire a search behavior feature of the user at the first site, where the search behavior feature includes a search keyword feature and/or a click feature; and the second obtaining unit 602 is configured to acquire the user is different.
  • the generating unit 603 is configured to generate a push keyword based on the search behavior feature of the first site and the search behavior feature of the second site;
  • the retrieval unit 604 is configured to Based on the above-mentioned push keyword, information search is performed in the first site and/or the second site, and the search result is pushed to the user.
  • the first obtaining unit 601 of the information pushing device 600 can acquire the search behavior feature of the user at the first site (for example, a search website) locally or remotely. Specifically, when the information pushing device 600 is located on the background server supporting the first site, the first obtaining unit 601 may directly acquire the search behavior feature from the server; and when the information pushing device 600 is located at the terminal used by the user. When the device is on the device, the first obtaining unit 601 may acquire the search behavior feature of the user from a background server that supports the first site by using a wired connection manner or a wireless connection manner.
  • the above search behavior features may include search keyword features and/or click features.
  • the second obtaining unit 602 may continue to acquire the second site of the user different from the first site (for example, Search behavior characteristics of shopping sites).
  • the generating unit 603 of the information pushing device 600 may perform a summary analysis on the search behavior feature acquired by the first obtaining unit 601 and the search behavior feature acquired by the second obtaining unit 602, and generate a push keyword for the push.
  • the keywords will be used in the subsequent push of information for the above users.
  • the retrieval unit 604 of the information pushing device 600 may use the push keyword generated by the generating unit 603 as a search term to perform information search in the first site and/or the second site, and then obtain the search result.
  • the information is pushed to the above users.
  • the retrieving unit 604 of the information pushing apparatus 600 further includes: an obtaining module (not shown) configured to acquire a user belonging to a search behavior feature of the user group; a user group push keyword generating module (not shown) configured to generate a user group push keyword based on the search behavior feature of the user group; a search module (not shown), configured The information search is performed in the first site and/or the second site based on the push keyword and the user group push keyword, and the search result is pushed to the user.
  • information push device 600 also includes other well-known structures, such as processors, memories, etc., which are not shown in FIG. 6 in order to unnecessarily obscure the embodiments of the present disclosure.
  • the unit or module involved in the embodiment of the present application may be implemented by software or by hardware.
  • the described unit or module may also be provided in the processor, for example, as a processor including a first acquisition unit, a second acquisition unit, a generation unit, and a retrieval unit.
  • the names of these units do not constitute a limitation on the unit itself in some cases.
  • the first obtaining unit may also be described as “a unit configured to acquire a search behavior feature of the user at the first site”.
  • the present application further provides a computer readable storage medium, which may be a computer readable storage medium included in the apparatus described in the foregoing embodiment, or may exist separately, not A computer readable storage medium that is assembled into a terminal.
  • the computer readable storage medium stores one or more programs that are used by one or more processors to perform the information push method described in this application.

Landscapes

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

Abstract

本申请公开了信息推送方法和装置。所述方法的一具体实施方式包括:获取用户在第一站点的搜索行为特征,其中,搜索行为特征包括搜索关键词特征和/或点击特征;获取所述用户在不同于第一站点的第二站点的搜索行为特征;基于所述第一站点的搜索行为特征和所述第二站点的搜索行为特征,生成推送用关键词;基于所述推送用关键词,在所述第一站点和/或第二站点内进行信息搜索并向所述用户推送搜索结果。该实施方式实现了富于个性化的信息推送,节约了检索时间。

Description

信息推送方法和装置
相关申请的交叉引用
本申请要求百度在线网络技术(北京)有限公司于2015年4月27日提交的,发明名称为“信息推送方法和装置”的、中国专利申请号“201510204755.8”的优先权,其全部内容作为整体并入本申请中。
技术领域
本申请涉及计算机技术领域,具体涉及互联网技术领域,尤其涉及信息推送方法和装置。
背景技术
信息推送,又称为“网络广播”,是通过一定的技术标准或协议,在互联网上通过定期传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。
现有的信息推送策略通常基于用户在一个网络站点内的行为(尤其是点击行为),而未能利用用户在其他网络站点的行为,从而,存在着用户行为相关数据利用不足,信息推送难以个性化的问题。
发明内容
本申请的目的在于提出一种改进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。
第一方面,本申请提供了一种信息推送方法,所述方法包括:获取用户在第一站点的搜索行为特征,其中,搜索行为特征包括搜索关键词特征和/或点击特征;获取所述用户在不同于第一站点的第二站点的搜索行为特征;基于所述第一站点的搜索行为特征和所述第二站点的搜索行为特征,生成推送用关键词;基于所述推送用关键词,在所 述第一站点和/或第二站点内进行信息搜索并向所述用户推送搜索结果。
在一些实施例中,所述搜索关键词特征包括以下至少一项:所述用户输入的搜索词、所述搜索词的同义词、所述搜索词的近义词。
在一些实施例中,所述基于所述第一站点的搜索行为特征和所述第二站点的搜索行为特征,生成推送用关键词,包括:基于所述第一站点的搜索行为特征,生成第一推送用关键词;基于所述第二站点的搜索行为特征,生成第二推送用关键词;基于所述第一推送用关键词和第二推送用关键词,生成推送用关键词。
在一些实施例中,所述基于所述第一站点的搜索行为特征,生成第一推送用关键词,包括:对所述第一站点的搜索行为特征中的搜索关键词特征进行解析,生成与搜索关键词特征相关的搜索词集合;对所述第一站点的搜索行为特征中的点击特征进行解析,生成与点击特征相关的搜索词集合;基于所述与搜索关键词特征相关的搜索词集合以及所述与点击特征相关的搜索词集合,生成第一推送用关键词。
在一些实施例中,所述对所述第一站点的搜索行为特征中的点击特征进行解析,生成与点击特征相关的搜索词集合,包括:基于所述点击特征,获取所述用户的点击对象,其中所述点击对象包括以下至少一项:图片、视频、文字、网址链接;对所述点击对象进行解析,生成与点击特征相关的搜索词集合。
在一些实施例中,所述基于所述第二站点的搜索行为特征,生成第二推送用关键词,包括:对所述第二站点的搜索行为特征中的搜索关键词特征进行解析,生成与搜索关键词特征相关的搜索词集合;对所述第二站点的搜索行为特征中的点击特征进行解析,生成与点击特征相关的搜索词集合;基于所述与搜索关键词特征相关的搜索词集合以及所述与点击特征相关的搜索词集合,生成第二推送用关键词。
在一些实施例中,所述基于所述推送用关键词,在所述第一站点和/或第二站点内进行信息搜索并向所述用户推送搜索结果,包括:获取用户所属用户群的搜索行为特征;基于所述用户群的搜索行为特征,生成用户群推送用关键词;基于所述推送用关键词和所述用户群推送 用关键词,在所述第一站点和/或第二站点内进行信息搜索并向所述用户推送搜索结果。
第二方面,本申请提供了一种信息推送装置,所述装置包括:第一获取单元,配置用于获取用户在第一站点的搜索行为特征,其中,搜索行为特征包括搜索关键词特征和/或点击特征;第二获取单元,配置用于获取所述用户在不同于第一站点的第二站点的搜索行为特征;生成单元,配置用于基于所述第一站点的搜索行为特征和所述第二站点的搜索行为特征,生成推送用关键词;检索单元,配置用于基于所述推送用关键词,在所述第一站点和/或第二站点内进行信息搜索并向所述用户推送搜索结果。
在一些实施例中,所述搜索关键词特征包括以下至少一项:所述用户输入的搜索词、所述搜索词的同义词、所述搜索词的近义词。
在一些实施例中,所述生成单元包括:第一生成模块,配置用于基于所述第一站点的搜索行为特征,生成第一推送用关键词;第二生成模块,配置用于基于所述第二站点的搜索行为特征,生成第二推送用关键词;汇总模块,配置用于基于所述第一推送用关键词和第二推送用关键词,生成推送用关键词。
在一些实施例中,所述第一生成模块包括:搜索关键词特征解析子模块,配置用于对所述第一站点的搜索行为特征中的搜索关键词特征进行解析,生成与搜索关键词特征相关的搜索词集合;点击特征解析子模块,配置用于对所述第一站点的搜索行为特征中的点击特征进行解析,生成与点击特征相关的搜索词集合;生成子模块,配置用于基于所述与搜索关键词特征相关的搜索词集合以及所述与点击特征相关的搜索词集合,生成第一推送用关键词。
在一些实施例中,所述点击特征解析子模块进一步配置用于:基于所述点击特征,获取所述用户的点击对象,其中所述点击对象包括以下至少一项:图片、视频、文字、网址链接;对所述点击对象进行解析,生成与点击特征相关的搜索词集合。
在一些实施例中,所述第二生成模块包括:搜索关键词特征解析子模块,配置用于对所述第二站点的搜索行为特征中的搜索关键词特 征进行解析,生成与搜索关键词特征相关的搜索词集合;点击特征解析子模块,配置用于对所述第二站点的搜索行为特征中的点击特征进行解析,生成与点击特征相关的搜索词集合;生成子模块,配置用于基于所述与搜索关键词特征相关的搜索词集合以及所述与点击特征相关的搜索词集合,生成第二推送用关键词。
在一些实施例中,所述检索单元进一步包括:获取模块,配置用于获取用户所属用户群的搜索行为特征;用户群推送用关键词生成模块,配置用于基于所述用户群的搜索行为特征,生成用户群推送用关键词;检索模块,配置用于基于所述推送用关键词和所述用户群推送用关键词,在所述第一站点和/或第二站点内进行信息搜索并向所述用户推送搜索结果。
本申请提供的信息推送方法和装置,通过获取用户在第一站点以及不同于第一站点的第二站点的搜索行为特征,随后基于这些搜索行为特征来生成推送用关键词,最后基于推送用关键词,在第一站点和/或第二站点内进行信息搜索并向所述用户推送搜索结果,更充分地利用了用户行为信息,从而实现了富于个性化的信息推送,也节约了检索时间。
附图说明
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:
图1是本申请可以应用于其中的示例性系统架构图;
图2是根据本申请的信息推送方法的一个实施例的流程图;
图3是根据本申请的信息推送方法的一个应用场景的示意图;
图4是根据本申请的信息推送方法的又一个实施例的流程图;
图5是根据本申请的信息推送方法的另一个应用场景的示意图;
图6是根据本申请的信息推送装置的一个实施例的结构示意图。
具体实施方式
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。
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。
图1示出了可以应用本申请实施例的示例性系统架构100。
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。
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。
终端设备101、102、103可以是各种电子设备,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 Picture Experts Group Audio Layer III,动态影像专家压缩标准音频层面3)、MP4(Moving Picture 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。
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上的购物类应用、搜索类应用等提供支持的后台服务器。服务器可以对接收到的数据进行存储、分析等处理,并将处理结果反馈给终端设备。
需要说明的是,本申请实施例所提供的信息推送方法可以由终端设备101、102、103执行,也可以由服务器105执行,信息推送装置可以设置于终端设备101、102、103中,也可以设置于服务器105中。
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。
继续参考图2,示出了根据本申请的信息推送方法的一个实施例 的流程200。所述的信息推送方法,包括以下步骤:
步骤201,获取用户在第一站点的搜索行为特征。
在本实施例中,用户所使用的电子设备(例如图1所示的终端设备或服务器)可以从本地或者远程地获取用户在第一站点(例如搜索网站)的搜索行为特征。具体而言,当上述电子设备就是对第一站点进行支持的后台服务器时,其可以直接从本地获取上述搜索行为特征;而当上述电子设备是终端设备时,其可以通过有线连接方式或者无线连接方式从对第一站点进行支持的后台服务器获取用户的搜索行为特征。上述无线连接方式包括但不限于3G/4G连接、WiFi连接、蓝牙连接、WiMAX连接、Zigbee连接、UWB(ultra wideband)连接、以及其他现在已知或将来开发的无线连接方式。
在这里,上述搜索行为特征可以包括搜索关键词特征和/或点击特征。其中,上述搜索关键词特征可以包括用户在搜索时所使用的搜索词及该搜索词的衍生词。具体地,该搜索词的衍生词可以包括以下至少一项:该搜索词的同义词,例如,搜索词“孩子”可以具有同义词“儿童”;该搜索词的近义词,例如,搜索词“中药”可以具有近义词“草药”;该搜索词的扩充词,例如,搜索词“感冒”可以具有“发烧”或“流感”之类的扩充词。而上述点击特征可以包括对用户的点击位置或点击对象等进行的描述或表征。具体地,上述点击对象可以是站点页面上直接显示的或者作为搜索结果显示的各个信息项,其例如可以包括但不限于,图片、视频、文字、网址链接等。
步骤202,获取用户在不同于第一站点的第二站点的搜索行为特征。
在本实施例中,在用户所使用的电子设备获取用户在第一站点(例如搜索网站)的搜索行为特征之后,上述电子设备可以继续获取用户在不同于第一站点的第二站点(例如购物网站)的搜索行为特征。其中,如上文所述,搜索行为特征可以包括搜索关键词特征和/或点击特征。
步骤203,基于第一站点的搜索行为特征和第二站点的搜索行为特征,生成推送用关键词。
在本实施例中,用户所使用的电子设备可以对上述用户在第一站点的搜索行为特征以及在第二站点的搜索行为特征进行汇总分析,生成推送用关键词,该推送用关键词将用于后继针对上述用户的信息推送中。
作为示例,由于搜索行为特征可以包括搜索关键词特征和/或点击特征,则可以对上述搜索关键词特征和点击特征分别进行分析,得到推送用关键词。例如,搜索关键词特征中包括的搜索词“孩子”以及同义词“儿童”,可以直接作为推送用关键词。点击特征中包括的对用户的点击对象的描述,例如“积木玩具”,也可以作为推送用关键词。最终,汇总得到的推送用关键词可以包括:“孩子”,“儿童”和“积木玩具”。
步骤204,基于推送用关键词,在第一站点和/或第二站点内进行信息搜索并向所述用户推送搜索结果。
在本实施例中,可以把在步骤203中生成的推送用关键词作为搜索词,在第一站点和/或第二站点内进行信息搜索,再把搜索得到的信息推送给上述用户。例如,可以基于上述推送用关键词“孩子”,“儿童”和“积木玩具”,在第二站点(例如购物网站)内进行搜索,并向用户返回搜索结果。
在本实施例的一些可选的实现方式中,生成推送用关键词的步骤203可以如下进行:首先,基于第一站点的搜索行为特征,生成第一推送用关键词;其次,基于第二站点的搜索行为特征,生成第二推送用关键词;最后,基于上述第一推送用关键词和第二推送用关键词,生成推送用关键词。
具体而言,可以如下生成第一或第二推送用关键词:首先,对上述第一或第二站点的搜索行为特征中的搜索关键词特征进行解析,生成与搜索关键词特征相关的搜索词集合;其次,对上述第一或第二站点的搜索行为特征中的点击特征进行解析,生成与点击特征相关的搜索词集合;最后,基于上述与搜索关键词特征相关的搜索词集合以及上述与点击特征相关的搜索词集合,汇总生成第一或第二推送用关键词。
在本实施例的一些可选的实现方式中,点击特征的解析可以如下进行:
首先,基于点击特征,获取用户的点击对象。其中,上述点击对象是站点页面上显示的各个信息项,例如图片、视频、文字、网址链接等。
接着,对上述点击对象进行解析,生成与点击特征相关的搜索词集合。例如,如果点击对象包括图片或视频,则可以根据图片或视频的名称得到搜索词;如果点击对象包括网址链接,则可以根据网址链接中的相关字符得到搜索词。
继续参见图3,图3是根据本实施例的信息推送方法的应用场景的一个示意图。如图3中的标号301所示,用户首先登陆了搜索引擎网站,并输入了搜索词“儿童”。接着,如标号302所示,上述用户进入了购物网站,在该购物网站中输入了搜索词“感冒药”,并且点击了搜索结果页面中出现的“体温计”图片。这时,可以得到推送用关键词“儿童”、“孩子”、“感冒药”、“体温计”,如标号303所示。最后,如标号304所示,可以用上述推送用关键词作为搜索词,在上述购物网站内继续进行后台的信息搜索,得到检索结果信息并推送给上述用户。
本申请的上述实施例提供的方法通过汇总用户在不同站点的搜索行为特征并提取出推送用关键词,再用推送用关键词检索出推送信息,实现了有针对性的信息推送,也节约了用户的检索时间。
进一步参考图4,其示出了信息推送方法的又一个实施例的流程400。该信息推送方法的流程400,包括以下步骤:
步骤401,获取用户在第一站点的搜索行为特征。
在本实施例中,用户所使用的电子设备(例如图1所示的终端设备或服务器)可以从本地或者远程地获取用户在第一站点(例如搜索网站)的搜索行为特征。在这里,上述搜索行为特征可以包括搜索关键词特征和/或点击特征。其中,上述搜索关键词特征可以包括用户在搜索时所使用的搜索词及该搜索词的衍生词。而上述点击特征可以包 括对用户的点击位置或点击对象等进行的描述或表征。
步骤402,获取用户在不同于第一站点的第二站点的搜索行为特征。
在本实施例中,在用户所使用的电子设备获取用户在第一站点(例如搜索网站)的搜索行为特征之后,上述电子设备可以继续获取用户在不同于第一站点的第二站点(例如购物网站)的搜索行为特征。
步骤403,基于第一站点的搜索行为特征和第二站点的搜索行为特征,生成推送用关键词。
在本实施例中,用户所使用的电子设备可以对上述用户在第一站点的搜索行为特征以及在第二站点的搜索行为特征进行汇总分析,生成推送用关键词,该推送用关键词将用于后继针对上述用户的信息推送中。
步骤404,获取用户所属用户群的搜索行为特征。
在本实施例中,对于用户而言,其所属的用户群可以包括以下至少一项:用户的电话联系人形成的用户群,这个用户群可以通过上述用户的移动终端中的电话通信录获得;用户的即时通讯工具(例如QQ,微信等)中的好友形成的用户群,这个用户群可以通过即时通讯工具的联系人记录获取;使用了相同的搜索词的用户形成的用户群,例如,使用了相同的搜索词“感冒药”的多个用户可以形成用户群。
在获取了用户所属的用户群之后,可以相应的获取该用户群中的每一个用户的搜索行为特征,再进行汇总分析,得到整个用户群的搜索行为特征。获取某个具体用户的搜索行为特征的方式可以参见上文步骤201的描述,在此不再赘叙。
步骤405,基于用户群的搜索行为特征,生成用户群推送用关键词。
在本实施例中,可以对用户群的搜索行为特征中包括的搜索关键词特征进行解析,生成与搜索关键词特征相关的搜索词集合;接着,对上述搜索行为特征中的点击特征进行解析,生成与点击特征相关的搜索词集合;最后,基于上述与搜索关键词特征相关的搜索词集合以及上述与点击特征相关的搜索词集合,汇总生成用户群推送用关键词。
步骤406,基于推送用关键词和用户群推送用关键词,在第一站点和/或第二站点内进行信息搜索并向用户推送搜索结果。
在本实施例中,可以把推送用关键词和用户群推送用关键词作为搜索词,在第一站点和/或第二站点内进行信息搜索,再把搜索得到的信息推送给上述用户。
在本实施例中,上述实现流程中的步骤401、步骤402、步骤403和步骤406分别与前述实施例中的步骤201、步骤202、步骤203和步骤204基本相同,在此不再赘述。
从图4中可以看出,与图2对应的实施例不同的是,本实施例中的信息推送方法的流程400多出了获取用户所属用户群的搜索行为特征的步骤404和基于用户群的搜索行为特征生成用户群推送用关键词的步骤405。通过增加的步骤404和405,本实施例描述的方案可以引入更多的用户相关搜索数据,从而实现有针对性且更加丰富而全面的信息推送。
继续参见图5,图5是根据本实施例的信息推送方法的应用场景的一个示意图。如图5中的标号501所示,用户A首先登陆了搜索引擎站点,并输入了搜索词“儿童”。接着,如标号502所示,上述用户A进入了购物网站,在该购物网站中输入了搜索词“感冒药”,并且点击了搜索结果页面中出现的“体温计”图片。这时,可以得到针对用户A的推送用关键词“儿童”、“孩子”、“感冒药”、“体温计”,如标号503所示。同时,如标号504所示,由于用户B也在搜索引擎站点使用了搜索词“儿童”,因此,用户A和用户B被认为属于相同的用户群,而用户B还使用了搜索词“泡腾片”。接着,如标号505所示,汇总用户A的推送用关键词和用户群推送用关键词,可以得到如下搜索词:“儿童”、“孩子”、“感冒药”、“体温计”、“泡腾片”;最后,可以再利用上述搜索词在购物网站内继续进行后台的信息搜索,得到检索结果信息并推送给上述用户A。
进一步参考图6,作为对上述各图所示方法的实现,本申请提供了一种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,该装置具体可以应用于各种电子设备中。
如图6所示,本实施例所述的信息推送装置600包括:第一获取单元601,第二获取单元602、生成单元603和检索单元604。其中,第一获取单元601配置用于获取用户在第一站点的搜索行为特征,其中,搜索行为特征包括搜索关键词特征和/或点击特征;第二获取单元602配置用于获取上述用户在不同于第一站点的第二站点的搜索行为特征;生成单元603配置用于基于上述第一站点的搜索行为特征和上述第二站点的搜索行为特征,生成推送用关键词;检索单元604配置用于基于上述推送用关键词,在上述第一站点和/或第二站点内进行信息搜索并向上述用户推送搜索结果。
在本实施例中,信息推送装置600的第一获取单元601可以从本地或者远程地获取用户在第一站点(例如搜索网站)的搜索行为特征。具体而言,当上述信息推送装置600位于对第一站点进行支持的后台服务器上时,第一获取单元601可以直接从服务器本地获取上述搜索行为特征;而当信息推送装置600位于用户使用的终端设备上时,第一获取单元601可以通过有线连接方式或者无线连接方式从对第一站点进行支持的后台服务器获取用户的搜索行为特征。在这里,上述搜索行为特征可以包括搜索关键词特征和/或点击特征。
在本实施例中,在第一获取单元601获取用户在第一站点(例如搜索网站)的搜索行为特征之后,第二获取单元602可以继续获取用户在不同于第一站点的第二站点(例如购物网站)的搜索行为特征。
在本实施例中,信息推送装置600的生成单元603可以对第一获取单元601获取的搜索行为特征以及第二获取单元602获取的搜索行为特征进行汇总分析,生成推送用关键词,该推送用关键词将用于后继针对上述用户的信息推送中。
在本实施例中,信息推送装置600的检索单元604可以把上述生成单元603生成的推送用关键词作为搜索词,在第一站点和/或第二站点内进行信息搜索,再把搜索得到的信息推送给上述用户。
在本实施例的一个可选实施方式中,上述信息推送装置600的检索单元604进一步包括:获取模块(未示出),配置用于获取用户所属 用户群的搜索行为特征;用户群推送用关键词生成模块(未示出),配置用于基于上述用户群的搜索行为特征,生成用户群推送用关键词;检索模块(未示出),配置用于基于上述推送用关键词和上述用户群推送用关键词,在第一站点和/或第二站点内进行信息搜索并向上述用户推送搜索结果。
本领域技术人员可以理解,上述信息推送装置600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6中未示出。
本申请实施例中所涉及到的单元或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。所描述的单元或模块也可以设置在处理器中,例如,可以描述为:一种处理器包括第一获取单元,第二获取单元、生成单元和检索单元。其中,这些单元的名称在某种情况下并不构成对该单元本身的限定,例如,第一获取单元还可以被描述为“配置用于获取用户在第一站点的搜索行为特征的单元”。
作为另一方面,本申请还提供了一种计算机可读存储介质,该计算机可读存储介质可以是上述实施例中所述装置中所包含的计算机可读存储介质;也可以是单独存在,未装配入终端中的计算机可读存储介质。所述计算机可读存储介质存储有一个或者一个以上程序,所述程序被一个或者一个以上的处理器用来执行描述于本申请的信息推送方法。
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所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。

Claims (16)

  1. 一种信息推送方法,其特征在于,所述方法包括:
    获取用户在第一站点的搜索行为特征,其中,搜索行为特征包括搜索关键词特征和/或点击特征;
    获取所述用户在不同于第一站点的第二站点的搜索行为特征;
    基于所述第一站点的搜索行为特征和所述第二站点的搜索行为特征,生成推送用关键词;
    基于所述推送用关键词,在所述第一站点和/或第二站点内进行信息搜索并向所述用户推送搜索结果。
  2. 根据权利要求1所述的方法,其特征在于,所述搜索关键词特征包括以下至少一项:所述用户输入的搜索词、所述搜索词的同义词、所述搜索词的近义词。
  3. 根据权利要求1或2所述的方法,其特征在于,所述基于所述第一站点的搜索行为特征和所述第二站点的搜索行为特征,生成推送用关键词,包括:
    基于所述第一站点的搜索行为特征,生成第一推送用关键词;
    基于所述第二站点的搜索行为特征,生成第二推送用关键词;
    基于所述第一推送用关键词和第二推送用关键词,生成推送用关键词。
  4. 根据权利要求3所述的方法,其特征在于,所述基于所述第一站点的搜索行为特征,生成第一推送用关键词,包括:
    对所述第一站点的搜索行为特征中的搜索关键词特征进行解析,生成与搜索关键词特征相关的搜索词集合;
    对所述第一站点的搜索行为特征中的点击特征进行解析,生成与点击特征相关的搜索词集合;
    基于所述与搜索关键词特征相关的搜索词集合以及所述与点击特 征相关的搜索词集合,生成第一推送用关键词。
  5. 根据权利要求4所述的方法,其特征在于,所述对所述第一站点的搜索行为特征中的点击特征进行解析,生成与点击特征相关的搜索词集合,包括:
    基于所述点击特征,获取所述用户的点击对象,其中所述点击对象包括以下至少一项:图片、视频、文字、网址链接;
    对所述点击对象进行解析,生成与点击特征相关的搜索词集合。
  6. 根据权利要求3-5之一所述的方法,其特征在于,所述基于所述第二站点的搜索行为特征,生成第二推送用关键词,包括:
    对所述第二站点的搜索行为特征中的搜索关键词特征进行解析,生成与搜索关键词特征相关的搜索词集合;
    对所述第二站点的搜索行为特征中的点击特征进行解析,生成与点击特征相关的搜索词集合;
    基于所述与搜索关键词特征相关的搜索词集合以及所述与点击特征相关的搜索词集合,生成第二推送用关键词。
  7. 根据权利要求1-6之一所述的方法,其特征在于,所述基于所述推送用关键词,在所述第一站点和/或第二站点内进行信息搜索并向所述用户推送搜索结果,包括:
    获取用户所属用户群的搜索行为特征;
    基于所述用户群的搜索行为特征,生成用户群推送用关键词;
    基于所述推送用关键词和所述用户群推送用关键词,在所述第一站点和/或第二站点内进行信息搜索并向所述用户推送搜索结果。
  8. 一种信息推送装置,其特征在于,所述装置包括:
    第一获取单元,配置用于获取用户在第一站点的搜索行为特征,其中,搜索行为特征包括搜索关键词特征和/或点击特征;
    第二获取单元,配置用于获取所述用户在不同于第一站点的第二 站点的搜索行为特征;
    生成单元,配置用于基于所述第一站点的搜索行为特征和所述第二站点的搜索行为特征,生成推送用关键词;
    检索单元,配置用于基于所述推送用关键词,在所述第一站点和/或第二站点内进行信息搜索并向所述用户推送搜索结果。
  9. 根据权利要求8所述的信息推送装置,其特征在于,所述搜索关键词特征包括以下至少一项:所述用户输入的搜索词、所述搜索词的同义词、所述搜索词的近义词。
  10. 根据权利要求8或9所述的信息推送装置,其特征在于,所述生成单元包括:
    第一生成模块,配置用于基于所述第一站点的搜索行为特征,生成第一推送用关键词;
    第二生成模块,配置用于基于所述第二站点的搜索行为特征,生成第二推送用关键词;
    汇总模块,配置用于基于所述第一推送用关键词和第二推送用关键词,生成推送用关键词。
  11. 根据权利要求10所述的信息推送装置,其特征在于,所述第一生成模块包括:
    搜索关键词特征解析子模块,配置用于对所述第一站点的搜索行为特征中的搜索关键词特征进行解析,生成与搜索关键词特征相关的搜索词集合;
    点击特征解析子模块,配置用于对所述第一站点的搜索行为特征中的点击特征进行解析,生成与点击特征相关的搜索词集合;
    生成子模块,配置用于基于所述与搜索关键词特征相关的搜索词集合以及所述与点击特征相关的搜索词集合,生成第一推送用关键词。
  12. 根据权利要求11所述的信息推送装置,其特征在于,所述点 击特征解析子模块进一步配置用于:
    基于所述点击特征,获取所述用户的点击对象,其中所述点击对象包括以下至少一项:图片、视频、文字、网址链接;
    对所述点击对象进行解析,生成与点击特征相关的搜索词集合。
  13. 根据权利要求10-12之一所述的信息推送装置,其特征在于,所述第二生成模块包括:
    搜索关键词特征解析子模块,配置用于对所述第二站点的搜索行为特征中的搜索关键词特征进行解析,生成与搜索关键词特征相关的搜索词集合;
    点击特征解析子模块,配置用于对所述第二站点的搜索行为特征中的点击特征进行解析,生成与点击特征相关的搜索词集合;
    生成子模块,配置用于基于所述与搜索关键词特征相关的搜索词集合以及所述与点击特征相关的搜索词集合,生成第二推送用关键词。
  14. 根据权利要求8-13之一所述的信息推送装置,其特征在于,所述检索单元进一步包括:
    获取模块,配置用于获取用户所属用户群的搜索行为特征;
    用户群推送用关键词生成模块,配置用于基于所述用户群的搜索行为特征,生成用户群推送用关键词;
    检索模块,配置用于基于所述推送用关键词和所述用户群推送用关键词,在所述第一站点和/或第二站点内进行信息搜索并向所述用户推送搜索结果。
  15. 一种设备,其特征在于,包括:
    一个或者多个处理器;
    存储器;
    一个或者多个程序,所述一个或者多个程序存储在所述存储器中,当被所述一个或多个处理器执行时:
    获取用户在第一站点的搜索行为特征,其中,搜索行为特征包括 搜索关键词特征和/或点击特征;
    获取所述用户在不同于第一站点的第二站点的搜索行为特征;
    基于所述第一站点的搜索行为特征和所述第二站点的搜索行为特征,生成推送用关键词;
    基于所述推送用关键词,在所述第一站点和/或第二站点内进行信息搜索并向所述用户推送搜索结果。
  16. 一种非易失性计算机存储介质,所述计算机存储介质存储有一个或多个程序,当所述一个或者多个程序被一个设备执行时,使得所述设备:
    获取用户在第一站点的搜索行为特征,其中,搜索行为特征包括搜索关键词特征和/或点击特征;
    获取所述用户在不同于第一站点的第二站点的搜索行为特征;
    基于所述第一站点的搜索行为特征和所述第二站点的搜索行为特征,生成推送用关键词;
    基于所述推送用关键词,在所述第一站点和/或第二站点内进行信息搜索并向所述用户推送搜索结果。
PCT/CN2015/090068 2015-04-27 2015-09-21 信息推送方法和装置 WO2016173185A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510204755.8 2015-04-27
CN201510204755.8A CN104834698A (zh) 2015-04-27 2015-04-27 信息推送方法和装置

Publications (1)

Publication Number Publication Date
WO2016173185A1 true WO2016173185A1 (zh) 2016-11-03

Family

ID=53812585

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/090068 WO2016173185A1 (zh) 2015-04-27 2015-09-21 信息推送方法和装置

Country Status (2)

Country Link
CN (1) CN104834698A (zh)
WO (1) WO2016173185A1 (zh)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104834698A (zh) * 2015-04-27 2015-08-12 百度在线网络技术(北京)有限公司 信息推送方法和装置
CN105701216B (zh) 2016-01-13 2017-03-08 北京三快在线科技有限公司 一种信息推送方法及装置
CN108304422B (zh) * 2017-03-08 2021-12-17 腾讯科技(深圳)有限公司 一种媒体搜索词推送方法和装置
CN107291835B (zh) * 2017-05-31 2020-12-22 北京京东尚科信息技术有限公司 一种搜索词的推荐方法和装置
CN109948014A (zh) * 2017-08-24 2019-06-28 阿里巴巴集团控股有限公司 一种搜索方法和服务器
CN110809761B (zh) * 2017-08-31 2024-04-02 深圳市欢太科技有限公司 应用资源处理方法及相关产品
CN107798066A (zh) * 2017-09-25 2018-03-13 北京小度信息科技有限公司 一种搜索词推送方法、装置及终端

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102693267A (zh) * 2011-02-24 2012-09-26 微软公司 扩大搜索结果
CN102831170A (zh) * 2012-07-25 2012-12-19 东莞宇龙通信科技有限公司 活动信息的推送方法及装置
CN102929892A (zh) * 2011-08-12 2013-02-13 莫润刚 基于社交网络的信息精准推广系统及方法
CN104834698A (zh) * 2015-04-27 2015-08-12 百度在线网络技术(北京)有限公司 信息推送方法和装置

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102289447B (zh) * 2011-06-16 2013-04-10 北京亿赞普网络技术有限公司 一种基于通讯网络报文的网站网页评价系统
CN102831124B (zh) * 2011-06-16 2015-08-05 北京亿赞普网络技术有限公司 基于跨网通信网络报文的用户行为关联分析方法
CN102855309B (zh) * 2012-08-21 2016-02-10 亿赞普(北京)科技有限公司 一种基于用户行为关联分析的信息推荐方法及装置
CN103412881B (zh) * 2013-07-17 2016-09-28 北京奇虎科技有限公司 提供搜索结果的方法及系统
CN103955465A (zh) * 2014-03-28 2014-07-30 百度在线网络技术(北京)有限公司 一种用于生成推荐页面的方法和装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102693267A (zh) * 2011-02-24 2012-09-26 微软公司 扩大搜索结果
CN102929892A (zh) * 2011-08-12 2013-02-13 莫润刚 基于社交网络的信息精准推广系统及方法
CN102831170A (zh) * 2012-07-25 2012-12-19 东莞宇龙通信科技有限公司 活动信息的推送方法及装置
CN104834698A (zh) * 2015-04-27 2015-08-12 百度在线网络技术(北京)有限公司 信息推送方法和装置

Also Published As

Publication number Publication date
CN104834698A (zh) 2015-08-12

Similar Documents

Publication Publication Date Title
US11252245B2 (en) Information pushing method and device
WO2016173185A1 (zh) 信息推送方法和装置
KR101320216B1 (ko) 소셜 네트워크들에서 배포를 위한 커스터마이징가능한 콘텐츠
US8825749B2 (en) Method of tracking offline user interaction in a rendered document on a mobile device
US8788342B2 (en) Intelligent feature expansion of online text ads
WO2017000402A1 (zh) 网页生成方法和装置
US20140095611A1 (en) Personalization through dynamic social channels
US8732252B2 (en) Cooperating system, chat server, program, and cooperating method
CN105488205B (zh) 页面生成方法和装置
US20160098416A1 (en) Auto complete search box based on the user's context to reduce user's input
CN103617267B (zh) 社交化扩展搜索方法及装置、系统
US20170193037A1 (en) Computerized System And Method For Augmenting Search Terms For Increased Efficiency And Effectiveness In Identifying Content
US20140068399A1 (en) Information processing device and information processing method
US10990620B2 (en) Aiding composition of themed articles about popular and novel topics and offering users a navigable experience of associated content
WO2019100986A1 (zh) 一种信息发送方法及装置
CN108027820A (zh) 用于产生短语黑名单以响应于搜索查询来防止某些内容出现在搜索结果中的方法和系统
CN108334516B (zh) 信息推送方法和装置
US20160283591A1 (en) Method for providing social activity integration service
JP6147629B2 (ja) ページコンテンツについて注目箇所を直ぐに表示するページサイトサーバ、プログラム及び方法
US20150310058A1 (en) Opportunistically solving search use cases
US20150310491A1 (en) Dynamic text ads based on a page knowledge graph
JP2017500632A (ja) 補助情報へのアクセスを提供するための方法およびシステム
US20080033918A1 (en) Systems, methods and computer program products for supplemental data communication and utilization
WO2014029358A1 (en) Method and apparatus for switching search engine to repeat search
US8935725B1 (en) Visually browsing videos

Legal Events

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

Ref document number: 15890560

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 15890560

Country of ref document: EP

Kind code of ref document: A1