WO2016127568A1 - 搜索推荐方法和装置 - Google Patents

搜索推荐方法和装置 Download PDF

Info

Publication number
WO2016127568A1
WO2016127568A1 PCT/CN2015/084036 CN2015084036W WO2016127568A1 WO 2016127568 A1 WO2016127568 A1 WO 2016127568A1 CN 2015084036 W CN2015084036 W CN 2015084036W WO 2016127568 A1 WO2016127568 A1 WO 2016127568A1
Authority
WO
WIPO (PCT)
Prior art keywords
recommended content
title
search term
feature information
search
Prior art date
Application number
PCT/CN2015/084036
Other languages
English (en)
French (fr)
Inventor
黄际洲
王海峰
李莹
万璐
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
Priority to KR1020167034096A priority Critical patent/KR101937430B1/ko
Priority to EP15881729.6A priority patent/EP3142022A4/en
Priority to JP2017502985A priority patent/JP6400178B2/ja
Priority to US15/322,523 priority patent/US20170132322A1/en
Publication of WO2016127568A1 publication Critical patent/WO2016127568A1/zh

Links

Images

Classifications

    • 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
    • G06F16/332Query formulation
    • G06F16/3322Query formulation using system suggestions
    • 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
    • G06F16/951Indexing; Web crawling techniques
    • 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 invention relates to the field of Internet technologies, and in particular, to a search recommendation method and apparatus.
  • the title of the right recommendation content is fixed mode or fixed.
  • the fixed mode includes: “related animals”, “related plants”, “related characters”, etc., fixed titles For example, “other people also search.”
  • the present invention aims to solve at least one of the technical problems in the related art to some extent.
  • Another object of the present invention is to provide a search recommendation device.
  • the search recommendation method includes: receiving a search term, and acquiring recommended content according to the search term; generating a title of the recommended content according to the search term and the recommended content.
  • the title includes association information with the search term and association information with the recommended content; and displaying the recommended content and the title of the recommended content.
  • the search recommendation method can generate a title of the recommended content according to the search term and the recommended content, thereby realizing dynamic generation of the title of the recommended content, avoiding the fixed mode, and
  • the title of the content includes the associated information with the search term, which can enable the user to understand the reason for recommending the content and satisfy the user's needs, so that the user can better understand the recommended content and the search term or his own search intention.
  • the search recommendation apparatus includes: an acquisition module, Receiving a search term, and obtaining recommended content according to the search term; a generating module, configured to generate a title of the recommended content according to the search term and the recommended content, where the title includes association information with the search term And information related to the recommended content; a display module, configured to display the recommended content and a title of the recommended content.
  • the search recommendation apparatus can generate a title of the recommended content according to the search term and the recommended content, thereby realizing dynamic generation of the title of the recommended content, avoiding the fixed mode, and
  • the title of the content includes the associated information with the search term, which can enable the user to understand the reason for recommending the content and satisfy the user's needs, so that the user can better understand the recommended content and the search term or his own search intention.
  • An embodiment of the present invention further provides an electronic device, including: one or more processors; a memory; one or more programs, wherein the one or more programs are stored in the memory when the one or more
  • the processor performs the following operations: receiving a search term, and acquiring recommended content according to the search term; generating a title of the recommended content according to the search term and the recommended content, where the title includes the search term Association information and association information with the recommended content; displaying the recommended content and a title of the recommended content.
  • An embodiment of the present invention further provides a non-volatile computer storage medium, where the computer storage medium stores one or more modules, and when the one or more modules are executed, performing the following operations: receiving a search term, and according to The search term acquires recommended content; and generates a title of the recommended content according to the search term and the recommended content, where the title includes association information with the search term and association information with the recommended content; The recommended content and the title of the recommended content.
  • FIG. 1 is a schematic flow chart of a search recommendation method according to an embodiment of the present invention.
  • FIG. 2 is a schematic flow chart of a manner of generating a title of recommended content in an embodiment of the present invention
  • Figure 3a is a schematic diagram of a title corresponding to a recommended content in the prior art of a search term
  • FIG. 3b is a schematic diagram of a title corresponding to a search content generated in an embodiment of the present invention.
  • 4a is a schematic diagram of a title of a recommended content in the prior art corresponding to another search term
  • 4b is a schematic diagram of a title of a recommended content generated in an embodiment of the present invention corresponding to another search term;
  • Figure 5a is a schematic diagram of a title corresponding to recommended content in another prior art search term
  • FIG. 5b is a schematic diagram of a title of a recommended content generated in an embodiment of the present invention corresponding to another search term;
  • FIG. 6 is a schematic flow chart showing another manner of generating a title of a recommended content in an embodiment of the present invention.
  • FIG. 7 is a schematic flow chart showing another manner of generating a title of recommended content in an embodiment of the present invention.
  • FIG. 8 is a schematic structural diagram of a search recommendation apparatus according to another embodiment of the present invention.
  • FIG. 9 is a schematic structural diagram of a search recommendation apparatus according to another embodiment of the present invention.
  • FIG. 10 is a schematic structural diagram of a search recommendation apparatus according to another embodiment of the present invention.
  • FIG. 1 is a schematic flowchart of a search recommendation method according to an embodiment of the present invention, where the method includes:
  • S11 Receive a search term, and obtain recommended content according to the search term.
  • the search engine can receive a search term (query) input by the user in the search bar, and the search term can also be called a query word or a search term.
  • search term search term
  • the search engine After the search engine receives the search term, the search result can be obtained according to the search term, and the related recommended content can be obtained according to the search term.
  • the recommended content for example, the content in the database is scored according to a preset algorithm, and the recommended content is obtained from the plurality of data according to the score result.
  • S12 Generate, according to the search term and the recommended content, a title of the recommended content, where the title includes association information with the search term and association information with the recommended content.
  • the title of the recommended content is generated according to the search term and the recommended content, and since the search term and/or the recommended content may be changed, the title of the recommended content is also variable. Therefore, dynamic generation of recommended content can be achieved. Even if the recommended content is the same, if the search terms are different, the title of the different recommended content can be generated.
  • the association information with the search term is feature information of the search term
  • the association information with the recommended content is shared feature information of the recommended content.
  • the The search term and the recommended content generate a title of the recommended content, including:
  • S21 Acquire feature information of the search term, where the feature information includes: a core word in the search term, or a word indicating a search intention of the search term.
  • S23 Include the feature information of the search term and the common feature information of the recommended content in the target of the recommended content In the title.
  • FIG. 3a is a display effect diagram of the recommended content in the prior art.
  • the title of the recommended content is only “related mammals", and “others also search”. This type of fixed title.
  • the title of the recommended content is dynamically generated according to the search term and the recommended content.
  • the title 31 of the recommended content may specifically include: "the petite pets like Junjie” and "the star celebrities who are well-known”.
  • “Jiao Jie is as cute and cute as Jun Jie” will include the search term “Jun Jie” and “Meng Chong” and “Pet Petite” are the common features of the recommended content.
  • FIG. 4a it is a display effect diagram of the recommended content in the prior art. As shown in FIG. 4a, the title of the recommended content is only “related plants”. "Others also search" such fixed titles.
  • the title 41 of the recommended content is dynamically generated according to the search term and the recommended content.
  • the search term is “thin queen”, referring to FIG. 5a, it is a display effect diagram of the recommended content in the prior art. As shown in FIG. 5a, the title of the recommended content is only “related characters”, “others also search. "This type of fixed title.
  • the title 51 of the recommended content is dynamically generated according to the search term and the recommended content.
  • the character information of the search term and the common feature information of the recommended content are included in a title of the recommended content, including:
  • the feature information of the search term and the shared feature information of the recommended content are included in the title of the recommended content in the form of a web buzzword.
  • the title of the recommended content is expressed in the form of a network buzzword.
  • the method when generating the title of the recommended content, the method further includes:
  • the method may further include:
  • the title of the recommended content and the recommended content may be displayed correspondingly.
  • the displaying the recommended content and the title of the recommended content including:
  • the recommended content sorted according to the title is displayed.
  • the number of recommended content per display is very small. For example, corresponding to a title, usually only 4 recommended content at a time, then the sorting order may be prioritized according to the sort order of the obtained recommended content. Previous recommendations.
  • the recommended content when the recommended content is sorted, the title content is combined, the ranking with the degree related to the title is ranked first, and the recommended content is optimized.
  • the recommended content is displayed in the form of a card, the card-level global optimization is realized. Way to sort cards.
  • the recommended content of the related person may be acquired. After the recommended content is obtained, the recommended content having the shared characteristic information may be selected therefrom, and the title is generated according to the shared feature information, and then the title may be preferentially displayed corresponding to the title. Recommended content with a common feature.
  • the corresponding recommended content is the queen, which is the optimized content of the relevant person in Fig. 5a.
  • FIG. 8 is a schematic structural diagram of a search recommendation apparatus according to another embodiment of the present invention.
  • the apparatus 80 includes an acquisition module 81, a generation module 82, and a presentation module 83.
  • the obtaining module 81 is configured to receive a search term, and obtain recommended content according to the search term;
  • the search engine can receive a search term (query) input by the user in the search bar, and the search term can also be called a query word or a search term.
  • search term search term
  • the search engine After the search engine receives the search term, the search result can be obtained according to the search term, and the related recommended content can be obtained according to the search term.
  • the recommended content for example, the content in the database is scored according to a preset algorithm, and the recommended content is obtained from the plurality of data according to the score result.
  • a generating module 82 configured to generate, according to the search term and the recommended content, a title of the recommended content, where the title includes association information with the search term and association information with the recommended content;
  • the title of the recommended content is generated according to the search term and the recommended content, and since the search term and/or the recommended content may be changed, the title of the recommended content is also variable, thereby Dynamic generation of recommended content can be achieved. Even if the recommended content is the same, if the search terms are different, the title of the different recommended content can be generated.
  • the association information with the search term is feature information of the search term
  • the association information with the recommended content is shared feature information of the recommended content
  • the generating Module 82 includes:
  • a first unit 821 configured to acquire feature information of the search term, where the feature information includes: a core word in the search term, or a word indicating a search intention of the search term;
  • a second unit 822 configured to acquire common feature information of the recommended content
  • the third unit 823 is configured to include the feature information of the search term and the shared feature information of the recommended content in the title of the recommended content.
  • FIG. 3a is a display effect diagram of the recommended content in the prior art.
  • the title of the recommended content is only “related mammals", and “others also search”. This type of fixed title.
  • the title of the recommended content is dynamically generated according to the search term and the recommended content.
  • the title 31 of the recommended content may specifically include: "the petite pets like Junjie” and "the star celebrities who are well-known”.
  • “Jiao Jie is as cute and cute as Jun Jie” will include the search term “Jun Jie” and “Meng Chong” and “Pet Petite” are the common features of the recommended content.
  • FIG. 4a it is a display effect diagram of the recommended content in the prior art. As shown in FIG. 4a, the title of the recommended content is only “related plants”. "Others also search" such fixed titles.
  • the title 41 of the recommended content is dynamically generated according to the search term and the recommended content.
  • the search term is “thin queen”, referring to FIG. 5a, it is a display effect diagram of the recommended content in the prior art. As shown in FIG. 5a, the title of the recommended content is only “related characters”, “others also search. "This type of fixed title.
  • the title 51 of the recommended content is dynamically generated according to the search term and the recommended content.
  • the third unit 823 is specifically configured to:
  • the feature information of the search term and the shared feature information of the recommended content are included in the title of the recommended content in the form of a web buzzword.
  • the title of the recommended content is expressed in the form of a network buzzword.
  • the generating module 82 further includes:
  • the fourth unit 824 is configured to generate a title of the recommended content of the preset content if the title of the recommended content including the feature information of the search term and the shared feature information of the recommended content cannot be obtained.
  • the generating module 82 further includes:
  • the update module 825 is configured to update the title of the recommended content.
  • the title of the recommended content is periodically updated by a preset period, or a preset trigger event is set, and when the trigger event occurs, the title of the recommended content is updated.
  • the display module 83 is configured to display the recommended content and the title of the recommended content.
  • the title of the recommended content and the recommended content may be displayed correspondingly.
  • the display module 83 is specifically configured to:
  • the recommended content sorted according to the title is displayed.
  • the number of recommended content per display is very small. For example, corresponding to a title, usually only 4 recommended content at a time, then the sorting order may be prioritized according to the sort order of the obtained recommended content. Previous recommendations.
  • the recommended content when the recommended content is sorted, the title content is combined, the ranking with the degree related to the title is ranked first, and the recommended content is optimized.
  • the recommended content is displayed in the form of a card, the card-level global optimization is realized. Way to sort cards.
  • the recommended content of the related person may be acquired. After the recommended content is obtained, the recommended content having the shared characteristic information may be selected therefrom, and the title is generated according to the shared feature information, and then the title may be preferentially displayed corresponding to the title. Recommended content with a common feature.
  • the corresponding recommended content is the queen, which is the optimized content of the relevant person in Fig. 5a.
  • An embodiment of the present invention further provides an electronic device, including: one or more processors; a memory; one or more programs, wherein the one or more programs are stored in the memory when the one or more
  • the processor performs the following operations: receiving a search term, and acquiring recommended content according to the search term; generating a title of the recommended content according to the search term and the recommended content, where the title includes the search term Association information and association information with the recommended content; displaying the recommended content and a title of the recommended content.
  • An embodiment of the present invention further provides a non-volatile computer storage medium, where the computer storage medium stores one or more modules, and when the one or more modules are executed, performing the following operations: receiving a search term, and according to The search term acquires recommended content; and generates a title of the recommended content according to the search term and the recommended content, where the title includes association information with the search term and association information with the recommended content; The recommended content and the title of the recommended content.
  • portions of the invention may be implemented in hardware, software, firmware or a combination thereof.
  • multiple steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system.
  • a suitable instruction execution system For example, if implemented in hardware, as in another embodiment, it can be implemented by any one or combination of the following techniques well known in the art: having logic gates for implementing logic functions on data signals. Discrete logic circuits, application specific integrated circuits with suitable combinational logic gates, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.
  • each functional unit in each embodiment of the present invention may be integrated into one processing module, or each unit may exist physically separately, or two or more units may be integrated into one module.
  • the above integrated modules can be implemented in the form of hardware or in the form of software functional modules.
  • the integrated modules, if implemented in the form of software functional modules and sold or used as stand-alone products, may also be stored in a computer readable storage medium.
  • the above mentioned storage medium may be a read only memory, a magnetic disk or an optical disk or the like.

Landscapes

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

Abstract

一种搜索推荐方法和装置,该搜索推荐方法包括接收搜索词,并根据所述搜索词获取推荐内容(S11);根据所述搜索词和所述推荐内容,生成推荐内容的标题,所述标题中包含与所述搜索词的关联信息以及与所述推荐内容的关联信息(S12);展示所述推荐内容和所述推荐内容的标题(S13)。该方法能够更好的满足用户需求。

Description

搜索推荐方法和装置
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02月13日提交的、发明名称为“搜索推荐方法和装置”的、中国专利申请号“201510079816.2”的优先权。
技术领域
本发明涉及互联网技术领域,尤其涉及一种搜索推荐方法和装置。
背景技术
用户在搜索时,可以在右侧推荐内容。现有技术中,右侧推荐内容的标题(title)是固定模式或者固定不变的,例如,固定模式包括:“相关动物”,“相关植物”,“相关人物”等,固定不变的标题例如是“其他人还搜”。
用户在获得推荐内容时,有为什么推荐这些内容的需求,但是,现有技术不能满足用户这种需求。
发明内容
本发明旨在至少在一定程度上解决相关技术中的技术问题之一。
为此,本发明的一个目的在于提出一种搜索推荐方法,该方法可以更好的满足用户需求。
本发明的另一个目的在于提出一种搜索推荐装置。
为达到上述目的,本发明第一方面实施例提出的搜索推荐方法,包括:接收搜索词,并根据所述搜索词获取推荐内容;根据所述搜索词和所述推荐内容,生成推荐内容的标题,所述标题中包含与所述搜索词的关联信息以及与所述推荐内容的关联信息;展示所述推荐内容和所述推荐内容的标题。
本发明第一方面实施例提出的搜索推荐方法,通过根据所述搜索词和所述推荐内容,生成推荐内容的标题,可以实现推荐内容的标题的动态生成,避免固定模式,并且,通过在推荐内容的标题中包含与所述搜索词的关联信息,可以使得用户了解推荐这些内容的原因,满足用户需求,从而使用户能够更好地了解到推荐内容与自己输入的搜索词或自己的搜索意图之间的关系。
为达到上述目的,本发明第二方面实施例提出的搜索推荐装置,包括:获取模块,用 于接收搜索词,并根据所述搜索词获取推荐内容;生成模块,用于根据所述搜索词和所述推荐内容,生成推荐内容的标题,所述标题中包含与所述搜索词的关联信息以及与所述推荐内容的关联信息;展示模块,用于展示所述推荐内容和所述推荐内容的标题。
本发明第二方面实施例提出的搜索推荐装置,通过根据所述搜索词和所述推荐内容,生成推荐内容的标题,可以实现推荐内容的标题的动态生成,避免固定模式,并且,通过在推荐内容的标题中包含与所述搜索词的关联信息,可以使得用户了解推荐这些内容的原因,满足用户需求,从而使用户能够更好地了解到推荐内容与自己输入的搜索词或自己的搜索意图之间的关系。
本发明实施例还提供一种电子设备,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,当被所述一个或者多个处理器执行时进行如下操作:接收搜索词,并根据所述搜索词获取推荐内容;根据所述搜索词和所述推荐内容,生成推荐内容的标题,所述标题中包含与所述搜索词的关联信息以及与所述推荐内容的关联信息;展示所述推荐内容和所述推荐内容的标题。
本发明实施例还提供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者多个模块,当所述一个或者多个模块被执行时进行如下操作:接收搜索词,并根据所述搜索词获取推荐内容;根据所述搜索词和所述推荐内容,生成推荐内容的标题,所述标题中包含与所述搜索词的关联信息以及与所述推荐内容的关联信息;展示所述推荐内容和所述推荐内容的标题。
本发明附加的方面和优点将在下面的描述中部分给出,部分将从下面的描述中变得明显,或通过本发明的实践了解到。
附图说明
本发明上述的和/或附加的方面和优点从下面结合附图对实施例的描述中将变得明显和容易理解,其中:
图1是本发明一实施例提出的搜索推荐方法的流程示意图;
图2是本发明实施例中生成推荐内容的标题的一种方式的流程示意图;
图3a是对应一种搜索词现有技术中的推荐内容的标题的示意图;
图3b是对应一种搜索词本发明实施例中生成的推荐内容的标题的示意图;
图4a是对应另一种搜索词现有技术中的推荐内容的标题的示意图;
图4b是对应另一种搜索词本发明实施例中生成的推荐内容的标题的示意图;
图5a是对应另一种搜索词现有技术中的推荐内容的标题的示意图;
图5b是对应另一种搜索词本发明实施例中生成的推荐内容的标题的示意图;
图6是本发明实施例中生成推荐内容的标题的另一种方式的流程示意图;
图7是本发明实施例中生成推荐内容的标题的另一种方式的流程示意图;
图8是本发明另一实施例提出的搜索推荐装置的结构示意图;
图9是本发明另一实施例提出的搜索推荐装置的结构示意图;
图10是本发明另一实施例提出的搜索推荐装置的结构示意图。
具体实施方式
下面详细描述本发明的实施例,所述实施例的示例在附图中示出,其中自始至终相同或类似的标号表示相同或类似的模块或具有相同或类似功能的模块。下面通过参考附图描述的实施例是示例性的,仅用于解释本发明,而不能理解为对本发明的限制。相反,本发明的实施例包括落入所附加权利要求书的精神和内涵范围内的所有变化、修改和等同物。
图1是本发明一实施例提出的搜索推荐方法的流程示意图,该方法包括:
S11:接收搜索词,并根据所述搜索词获取推荐内容。
搜索引擎可以接收用户在搜索栏中输入的搜索词(query),搜索词也可以称为查询词或者检索词等。
搜索引擎接收到搜索词后,可以根据搜索词获取相应的搜索结果,还可以根据搜索词获取相关的推荐内容。
在获取推荐内容时,例如,根据预设的算法对数据库中内容进行评分,根据评分结果从众多的数据中获取推荐内容。
S12:根据所述搜索词和所述推荐内容,生成推荐内容的标题,所述标题中包含与所述搜索词的关联信息以及与所述推荐内容的关联信息。
不同于现有技术,本实施例中,推荐内容的标题(title)是根据搜索词和推荐内容生成的,由于搜索词和/或推荐内容可以是变化的,因此,推荐内容的标题也是可变的,从而可以实现推荐内容的动态生成。即使推荐内容相同,如果搜索词不同,则可以生成不同的推荐内容的标题。
可选的,所述与所述搜索词的关联信息是所述搜索词的特征信息,所述与所述推荐内容的关联信息是所述推荐内容的共有特征信息,参见图2,所述根据所述搜索词和所述推荐内容,生成推荐内容的标题,包括:
S21:获取所述搜索词的特征信息,所述特征信息包括:所述搜索词中的核心词,或者,表明所述搜索词的检索意图的词。
S22:获取所述推荐内容的共有特征信息。
S23:将所述搜索词的特征信息以及所述推荐内容的共有特征信息包含在推荐内容的标 题中。
例如,当搜索词是“俊介”时,参见图3a,为现有技术中推荐内容的展示效果图,如图3a所示,推荐内容的标题只是“相关哺乳动物”,“其他人还搜”这类固定的标题。
而本实施例中,推荐内容的标题是根据搜索词和推荐内容动态生成的。
例如,参见图3b,推荐内容的标题31可以具体包括:“与俊介一样娇小可爱的萌宠”,以及“那些家喻户晓的明星宠物”。
其中,“与俊介一样娇小可爱的萌宠”中会包括搜索词“俊介”以及“萌宠”和“娇小可爱”是推荐内容的共有特征。
另外,系统理解了“俊介”是一个网络上爆红的萌宠的名字,可以反映用户想要网络上火爆的萌宠的检索意图,因此,标题“那些家喻户晓的明星宠物”可以包含用户的检索意图“家喻户晓”,以及共有特征信息“宠物”。
又例如,当搜索词是“新装修客厅里面放什么植物”时,参见图4a,为现有技术中推荐内容的展示效果图,如图4a所示,推荐内容的标题只是“相关植物”,“其他人还搜”这类固定的标题。
而本实施例中,参见图4b,推荐内容的标题41是根据搜索词和推荐内容动态生成的。
又例如,当搜索词是“薄皇后”时,参见图5a,为现有技术中推荐内容的展示效果图,如图5a所示,推荐内容的标题只是“相关人物”,“其他人还搜”这类固定的标题。
而本实施例中,参见图5b,推荐内容的标题51是根据搜索词和推荐内容动态生成的。
可选的,在上述各种搜索时,所述将所述搜索词的特征信息以及所述推荐内容的共有特征信息包含在推荐内容的标题中,包括:
采用网络流行语的形式,将所述搜索词的特征信息以及所述推荐内容的共有特征信息包含在推荐内容的标题中。
例如,参见图5b,推荐内容的标题包括“汉朝后宫的那些女人们”是采用网络流行语形式进行表述的。
可选的,参见图6,在生成推荐内容的标题时,还可以包括:
S24:如果不能得到包含所述搜索词的特征信息以及所述推荐内容的共有特征信息的推荐内容的标题,则生成预设内容的推荐内容的标题。
例如,以图3b的搜索为例,如果得不到如图3b所示的标题时,可以生成“更好的推荐”等标题。
可选的,参见图7,在生成推荐内容的标题后,还可以包括:
S25:更新所述推荐内容的标题。
例如,采用预设的周期,定期更新推荐内容的标题,或者,预设设置触发事件,当触 发事件发生时,更新推荐内容的标题。
S13:展示所述推荐内容和所述推荐内容的标题。
在生成推荐内容的标题后,可以对应展示推荐内容和推荐内容的标题。
可选的,所述展示所述推荐内容和所述推荐内容的标题,包括:
根据所述推荐内容的标题,对所述推荐内容进行排序;
对应所述推荐内容的标题,展示根据所述标题排序后的推荐内容。
例如,受限于展示空间,每次展示的推荐内容的个数很少,例如,对应一个标题,通常每次只能4个推荐内容,那么可以按照获取的推荐内容的排序顺序,优先展示排序在前的推荐内容。
本实施例中,在对推荐内容进行排序时会结合标题内容,将与标题相关程度大的排序在前,实现推荐内容的优化,当推荐内容是以卡片形式展示时,实现卡片级全局最优的方式排序卡片。
具体的,例如在人物搜索时,可以获取相关人物的推荐内容,在获取推荐内容后,可以从中选择具有共有特性信息的推荐内容,并根据共有特征信息生成标题,之后可以对应该标题优先展示这些具有共有特征的推荐内容。
例如,参见图5b,当标题是“历史上富有传奇色彩的皇后”,相应的推荐内容是皇后,是对图5a的相关人物进行优化后的内容。
本实施例中,通过根据所述搜索词和所述推荐内容,生成推荐内容的标题,可以实现推荐内容的标题的动态生成,避免固定模式,并且,通过在推荐内容的标题中包含与所述搜索词的关联信息,可以使得用户了解推荐这些内容的原因,满足用户需求,从而使用户能够更好地了解到推荐内容与自己输入的搜索词或自己的搜索意图之间的关系。另外,通过标题优化推荐内容,可以推荐更合适的内容;通过分析搜索词和推荐内容得到标题,可以避免分类错误,例如避免将动物分为植物,提升用户体验;通过更新标题,降低枯燥乏味,避免形成感知疲劳,提高对用户的吸引力;通过将推荐内容划分到相应的标题下,相对于“其他人还搜”内包罗万象的内容,可以避免内容混乱。
图8是本发明另一实施例提出的搜索推荐装置的结构示意图,该装置80包括获取模块81,生成模块82和展示模块83。
获取模块81,用于接收搜索词,并根据所述搜索词获取推荐内容;
搜索引擎可以接收用户在搜索栏中输入的搜索词(query),搜索词也可以称为查询词或者检索词等。
搜索引擎接收到搜索词后,可以根据搜索词获取相应的搜索结果,还可以根据搜索词获取相关的推荐内容。
在获取推荐内容时,例如,根据预设的算法对数据库中内容进行评分,根据评分结果从众多的数据中获取推荐内容。
生成模块82,用于根据所述搜索词和所述推荐内容,生成推荐内容的标题,所述标题中包含与所述搜索词的关联信息以及与所述推荐内容的关联信息;
不同于现有技术,本实施例中,推荐内容的标题是根据搜索词和推荐内容生成的,由于搜索词和/或推荐内容可以是变化的,因此,推荐内容的标题也是可变的,从而可以实现推荐内容的动态生成。即使推荐内容相同,如果搜索词不同,则可以生成不同的推荐内容的标题。
可选的,参见图9,所述与所述搜索词的关联信息是所述搜索词的特征信息,所述与所述推荐内容的关联信息是所述推荐内容的共有特征信息,所述生成模块82包括:
第一单元821,用于获取所述搜索词的特征信息,所述特征信息包括:所述搜索词中的核心词,或者,表明所述搜索词的检索意图的词;
第二单元822,用于获取所述推荐内容的共有特征信息;
第三单元823,用于将所述搜索词的特征信息以及所述推荐内容的共有特征信息包含在推荐内容的标题中。
例如,当搜索词是“俊介”时,参见图3a,为现有技术中推荐内容的展示效果图,如图3a所示,推荐内容的标题只是“相关哺乳动物”,“其他人还搜”这类固定的标题。
而本实施例中,推荐内容的标题是根据搜索词和推荐内容动态生成的。
例如,参见图3b,推荐内容的标题31可以具体包括:“与俊介一样娇小可爱的萌宠”,以及“那些家喻户晓的明星宠物”。
其中,“与俊介一样娇小可爱的萌宠”中会包括搜索词“俊介”以及“萌宠”和“娇小可爱”是推荐内容的共有特征。
另外,系统理解了“俊介”是一个网络上爆红的萌宠的名字,可以反映用户想要网络上火爆的萌宠的检索意图,因此,标题“那些家喻户晓的明星宠物”可以包含用户的检索意图“家喻户晓”,以及共有特征信息“宠物”。
又例如,当搜索词是“新装修客厅里面放什么植物”时,参见图4a,为现有技术中推荐内容的展示效果图,如图4a所示,推荐内容的标题只是“相关植物”,“其他人还搜”这类固定的标题。
而本实施例中,参见图4b,推荐内容的标题41是根据搜索词和推荐内容动态生成的。
又例如,当搜索词是“薄皇后”时,参见图5a,为现有技术中推荐内容的展示效果图,如图5a所示,推荐内容的标题只是“相关人物”,“其他人还搜”这类固定的标题。
而本实施例中,参见图5b,推荐内容的标题51是根据搜索词和推荐内容动态生成的。
可选的,所述第三单元823具体用于:
采用网络流行语的形式,将所述搜索词的特征信息以及所述推荐内容的共有特征信息包含在推荐内容的标题中。
例如,参见图5b,推荐内容的标题包括“汉朝后宫的那些女人们”是采用网络流行语形式进行表述的。
可选的,参见图10,所述生成模块82还包括:
第四单元824,用于如果不能得到包含所述搜索词的特征信息以及所述推荐内容的共有特征信息的推荐内容的标题,则生成预设内容的推荐内容的标题。
例如,以图3b的搜索为例,如果得不到如图3b所示的标题时,可以生成“更好的推荐”等标题。
可选的,参见图9,所述生成模块82还包括:
更新模块825,用于更新所述推荐内容的标题。
例如,采用预设的周期,定期更新推荐内容的标题,或者,预设设置触发事件,当触发事件发生时,更新推荐内容的标题。
展示模块83,用于展示所述推荐内容和所述推荐内容的标题。
在生成推荐内容的标题后,可以对应展示推荐内容和推荐内容的标题。
可选的,所述展示模块83具体用于:
根据所述推荐内容的标题,对所述推荐内容进行排序;
对应所述推荐内容的标题,展示根据所述标题排序后的推荐内容。
例如,受限于展示空间,每次展示的推荐内容的个数很少,例如,对应一个标题,通常每次只能4个推荐内容,那么可以按照获取的推荐内容的排序顺序,优先展示排序在前的推荐内容。
本实施例中,在对推荐内容进行排序时会结合标题内容,将与标题相关程度大的排序在前,实现推荐内容的优化,当推荐内容是以卡片形式展示时,实现卡片级全局最优的方式排序卡片。
具体的,例如在人物搜索时,可以获取相关人物的推荐内容,在获取推荐内容后,可以从中选择具有共有特性信息的推荐内容,并根据共有特征信息生成标题,之后可以对应该标题优先展示这些具有共有特征的推荐内容。
例如,参见图5b,当标题是“历史上富有传奇色彩的皇后”,相应的推荐内容是皇后,是对图5a的相关人物进行优化后的内容。
本实施例中,通过根据所述搜索词和所述推荐内容,生成推荐内容的标题,可以实现推荐内容的标题的动态生成,避免固定模式,并且,通过在推荐内容的标题中包含与所述 搜索词的关联信息,可以使得用户了解推荐这些内容的原因,满足用户需求,从而使用户能够更好地了解到推荐内容与自己输入的搜索词或自己的搜索意图之间的关系。另外,通过标题优化推荐内容,可以推荐更合适的内容;通过分析搜索词和推荐内容得到标题,可以避免分类错误,例如避免将动物分为植物,提升用户体验;通过更新标题,降低枯燥乏味,避免形成感知疲劳,提高对用户的吸引力;通过将推荐内容划分到相应的标题下,相对于“其他人还搜”内包罗万象的内容,可以避免内容混乱。
本发明实施例还提供一种电子设备,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,当被所述一个或者多个处理器执行时进行如下操作:接收搜索词,并根据所述搜索词获取推荐内容;根据所述搜索词和所述推荐内容,生成推荐内容的标题,所述标题中包含与所述搜索词的关联信息以及与所述推荐内容的关联信息;展示所述推荐内容和所述推荐内容的标题。
本发明实施例还提供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者多个模块,当所述一个或者多个模块被执行时进行如下操作:接收搜索词,并根据所述搜索词获取推荐内容;根据所述搜索词和所述推荐内容,生成推荐内容的标题,所述标题中包含与所述搜索词的关联信息以及与所述推荐内容的关联信息;展示所述推荐内容和所述推荐内容的标题。
需要说明的是,在本发明的描述中,术语“第一”、“第二”等仅用于描述目的,而不能理解为指示或暗示相对重要性。此外,在本发明的描述中,除非另有说明,“多个”的含义是两个或两个以上。
流程图中或在此以其他方式描述的任何过程或方法描述可以被理解为,表示包括一个或更多个用于实现特定逻辑功能或过程的步骤的可执行指令的代码的模块、片段或部分,并且本发明的优选实施方式的范围包括另外的实现,其中可以不按所示出或讨论的顺序,包括根据所涉及的功能按基本同时的方式或按相反的顺序,来执行功能,这应被本发明的实施例所属技术领域的技术人员所理解。
应当理解,本发明的各部分可以用硬件、软件、固件或它们的组合来实现。在上述实施方式中,多个步骤或方法可以用存储在存储器中且由合适的指令执行系统执行的软件或固件来实现。例如,如果用硬件来实现,和在另一实施方式中一样,可用本领域公知的下列技术中的任一项或他们的组合来实现:具有用于对数据信号实现逻辑功能的逻辑门电路的离散逻辑电路,具有合适的组合逻辑门电路的专用集成电路,可编程门阵列(PGA),现场可编程门阵列(FPGA)等。
本技术领域的普通技术人员可以理解实现上述实施例方法携带的全部或部分步骤是可以通过程序来指令相关的硬件完成,所述的程序可以存储于一种计算机可读存储介质中, 该程序在执行时,包括方法实施例的步骤之一或其组合。
此外,在本发明各个实施例中的各功能单元可以集成在一个处理模块中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个模块中。上述集成的模块既可以采用硬件的形式实现,也可以采用软件功能模块的形式实现。所述集成的模块如果以软件功能模块的形式实现并作为独立的产品销售或使用时,也可以存储在一个计算机可读取存储介质中。
上述提到的存储介质可以是只读存储器,磁盘或光盘等。
在本说明书的描述中,参考术语“一个实施例”、“一些实施例”、“示例”、“具体示例”、或“一些示例”等的描述意指结合该实施例或示例描述的具体特征、结构、材料或者特点包含于本发明的至少一个实施例或示例中。在本说明书中,对上述术语的示意性表述不一定指的是相同的实施例或示例。而且,描述的具体特征、结构、材料或者特点可以在任何的一个或多个实施例或示例中以合适的方式结合。
尽管上面已经示出和描述了本发明的实施例,可以理解的是,上述实施例是示例性的,不能理解为对本发明的限制,本领域的普通技术人员在本发明的范围内可以对上述实施例进行变化、修改、替换和变型。

Claims (14)

  1. 一种搜索推荐方法,其特征在于,包括:
    接收搜索词,并根据所述搜索词获取推荐内容;
    根据所述搜索词和所述推荐内容,生成推荐内容的标题,所述标题中包含与所述搜索词的关联信息以及与所述推荐内容的关联信息;
    展示所述推荐内容和所述推荐内容的标题。
  2. 根据权利要求1所述的方法,其特征在于,所述与所述搜索词的关联信息是所述搜索词的特征信息,所述与所述推荐内容的关联信息是所述推荐内容的共有特征信息,所述根据所述搜索词和所述推荐内容,生成所述推荐内容的标题,包括:
    获取所述搜索词的特征信息,所述特征信息包括:所述搜索词中的核心词,或者,表明所述搜索词的检索意图的词;
    获取所述推荐内容的共有特征信息;
    将所述搜索词的特征信息以及所述推荐内容的共有特征信息包含在推荐内容的标题中。
  3. 根据权利要求2所述的方法,其特征在于,所述将所述搜索词的特征信息以及所述推荐内容的共有特征信息包含在推荐内容的标题中,包括:
    采用网络流行语的形式,将所述搜索词的特征信息以及所述推荐内容的共有特征信息包含在推荐内容的标题中。
  4. 根据权利要求2或3所述的方法,其特征在于,还包括:
    如果不能得到包含所述搜索词的特征信息以及所述推荐内容的共有特征信息的推荐内容的标题,则生成预设内容的推荐内容的标题。
  5. 根据权利要求1-4任一项所述的方法,其特征在于,所述展示所述推荐内容和所述推荐内容的标题,包括:
    根据所述推荐内容的标题,对所述推荐内容进行排序;
    对应所述推荐内容的标题,展示根据所述标题排序后的推荐内容。
  6. 根据权利要求1-5任一项所述的方法,其特征在于,所述生成推荐内容的标题之后,所述方法还包括:
    更新所述推荐内容的标题。
  7. 一种搜索推荐装置,其特征在于,包括:
    获取模块,用于接收搜索词,并根据所述搜索词获取推荐内容;
    生成模块,用于根据所述搜索词和所述推荐内容,生成推荐内容的标题,所述标题中 包含与所述搜索词的关联信息以及与所述推荐内容的关联信息;
    展示模块,用于展示所述推荐内容和所述推荐内容的标题。
  8. 根据权利要求7所述的装置,其特征在于,所述与所述搜索词的关联信息是所述搜索词的特征信息,所述与所述推荐内容的关联信息是所述推荐内容的共有特征信息,所述生成模块包括:
    第一单元,用于获取所述搜索词的特征信息,所述特征信息包括:所述搜索词中的核心词,或者,表明所述搜索词的检索意图的词;
    第二单元,用于获取所述推荐内容的共有特征信息;
    第三单元,用于将所述搜索词的特征信息以及所述推荐内容的共有特征信息包含在推荐内容的标题中。
  9. 根据权利要求8所述的装置,其特征在于,所述第三单元具体用于:
    采用网络流行语的形式,将所述搜索词的特征信息以及所述推荐内容的共有特征信息包含在推荐内容的标题中。
  10. 根据权利要求8或9所述的装置,其特征在于,所述生成模块还包括:
    第四单元,用于如果不能得到包含所述搜索词的特征信息以及所述推荐内容的共有特征信息的推荐内容的标题,则生成预设内容的推荐内容的标题。
  11. 根据权利要求7-10任一项所述的装置,其特征在于,所述展示模块具体用于:
    根据所述推荐内容的标题,对所述推荐内容进行排序;
    对应所述推荐内容的标题,展示根据所述标题排序后的推荐内容。
  12. 根据权利要求7-11任一项所述的装置,其特征在于,还包括:
    更新模块,用于更新所述推荐内容的标题。
  13. 一种电子设备,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,当被所述一个或者多个处理器执行时:
    执行如权利要求1-6任一项所述的方法。
  14. 一种非易失性计算机存储介质,其特征在于,所述计算机存储介质存储有一个或者多个模块,当所述一个或者多个模块被执行时:
    执行如权利要求1-6任一项所述的方法。
PCT/CN2015/084036 2015-02-13 2015-07-15 搜索推荐方法和装置 WO2016127568A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
KR1020167034096A KR101937430B1 (ko) 2015-02-13 2015-07-15 검색 추천 방법 및 장치
EP15881729.6A EP3142022A4 (en) 2015-02-13 2015-07-15 Search recommendation method and device
JP2017502985A JP6400178B2 (ja) 2015-02-13 2015-07-15 検索推薦方法及び装置
US15/322,523 US20170132322A1 (en) 2015-02-13 2015-07-15 Search recommendation method and device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510079816.2A CN104679848B (zh) 2015-02-13 2015-02-13 搜索推荐方法和装置
CN201510079816.2 2015-02-13

Publications (1)

Publication Number Publication Date
WO2016127568A1 true WO2016127568A1 (zh) 2016-08-18

Family

ID=53314890

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/084036 WO2016127568A1 (zh) 2015-02-13 2015-07-15 搜索推荐方法和装置

Country Status (6)

Country Link
US (1) US20170132322A1 (zh)
EP (1) EP3142022A4 (zh)
JP (1) JP6400178B2 (zh)
KR (1) KR101937430B1 (zh)
CN (1) CN104679848B (zh)
WO (1) WO2016127568A1 (zh)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103902670B (zh) * 2014-03-17 2016-04-13 百度在线网络技术(北京)有限公司 搜索推荐方法和装置
CN104679848B (zh) * 2015-02-13 2019-05-03 百度在线网络技术(北京)有限公司 搜索推荐方法和装置
CN104933125B (zh) * 2015-06-10 2019-05-03 百度在线网络技术(北京)有限公司 基于信任关系的推荐方法和装置
CN105069148A (zh) * 2015-08-21 2015-11-18 成都秋雷科技有限责任公司 一种相关网页检索的方法
CN106547794B (zh) * 2015-09-22 2020-04-14 阿里巴巴集团控股有限公司 信息搜索方法和装置
KR20180069813A (ko) * 2015-10-16 2018-06-25 알리바바 그룹 홀딩 리미티드 타이틀 표시 방법 및 장치
CN107463552A (zh) * 2017-07-20 2017-12-12 北京奇艺世纪科技有限公司 一种生成视频主题名称的方法和装置
CN113469298B (zh) * 2021-09-03 2022-01-21 北京达佳互联信息技术有限公司 模型训练方法及资源推荐方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101446959A (zh) * 2008-12-30 2009-06-03 深圳市迅雷网络技术有限公司 一种基于互联网的新闻推荐方法和系统
CN101499091A (zh) * 2009-03-17 2009-08-05 辽宁般若网络科技有限公司 网页代表词推荐方法
US20120239639A1 (en) * 2011-03-14 2012-09-20 Slangwho, Inc. Search Engine
CN103914553A (zh) * 2014-04-14 2014-07-09 百度在线网络技术(北京)有限公司 搜索方法和搜索引擎
CN104679848A (zh) * 2015-02-13 2015-06-03 百度在线网络技术(北京)有限公司 搜索推荐方法和装置

Family Cites Families (35)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005182280A (ja) * 2003-12-17 2005-07-07 Ibm Japan Ltd 情報検索システム、検索結果加工システム及び情報検索方法並びにプログラム
CN1609859A (zh) * 2004-11-26 2005-04-27 孙斌 搜索结果聚类的方法
US7373341B2 (en) * 2004-12-30 2008-05-13 Business Objects, S.A. Computer readable medium, method and apparatus for preserving filtering conditions to query multilingual data sources at various locales when regenerating a report
US7526476B2 (en) * 2005-03-14 2009-04-28 Microsoft Corporation System and method for generating attribute-based selectable search extension
US8527874B2 (en) * 2005-08-03 2013-09-03 Apple Inc. System and method of grouping search results using information representations
JP2007122513A (ja) * 2005-10-28 2007-05-17 Dainippon Printing Co Ltd コンテンツ検索方法、及び、コンテンツ検索サーバ
US8370334B2 (en) * 2006-09-15 2013-02-05 Emc Corporation Dynamic updating of display and ranking for search results
JP4398992B2 (ja) * 2007-03-29 2010-01-13 株式会社東芝 情報検索装置、情報検索方法及び情報検索プログラム
US9324082B2 (en) * 2007-07-06 2016-04-26 Ebay Inc. System and method for providing information tagging in a networked system
US20090241044A1 (en) * 2008-03-18 2009-09-24 Cuill, Inc. Apparatus and method for displaying search results using stacks
US20100042660A1 (en) * 2008-08-12 2010-02-18 Peter Rinearson Systems and methods for presenting alternative versions of user-submitted content
JP5238418B2 (ja) * 2008-09-09 2013-07-17 株式会社東芝 情報推薦装置および情報推薦方法
US20100169316A1 (en) * 2008-12-30 2010-07-01 Yahoo! Inc. Search query concept based recommendations
US10269021B2 (en) * 2009-04-20 2019-04-23 4-Tell, Inc. More improvements in recommendation systems
US8498974B1 (en) * 2009-08-31 2013-07-30 Google Inc. Refining search results
JP5346991B2 (ja) * 2011-06-16 2013-11-20 日本電信電話株式会社 コンテンツ出力方法、コンテンツ出力装置およびコンテンツ出力プログラム
US20130031450A1 (en) * 2011-07-28 2013-01-31 Demand Media, Inc. Systems and methods for psychographic titling
US9026519B2 (en) * 2011-08-09 2015-05-05 Microsoft Technology Licensing, Llc Clustering web pages on a search engine results page
US20140181088A1 (en) * 2011-08-23 2014-06-26 Pierre R. Schwob Activity contextualization
US8788477B1 (en) * 2011-09-19 2014-07-22 Google Inc. Identifying addresses and titles of authoritative web pages by analyzing search queries in query logs
US9251270B2 (en) * 2012-01-17 2016-02-02 International Business Machines Corporation Grouping search results into a profile page
US9461876B2 (en) * 2012-08-29 2016-10-04 Loci System and method for fuzzy concept mapping, voting ontology crowd sourcing, and technology prediction
US9460214B2 (en) * 2012-12-28 2016-10-04 Wal-Mart Stores, Inc. Ranking search results based on color
US20160012136A1 (en) * 2013-03-07 2016-01-14 Eyeducation A.Y. LTD Simultaneous Local and Cloud Searching System and Method
US9002837B2 (en) * 2013-03-15 2015-04-07 Ipar, Llc Systems and methods for providing expert thread search results
US9619450B2 (en) * 2013-06-27 2017-04-11 Google Inc. Automatic generation of headlines
US9002835B2 (en) * 2013-08-15 2015-04-07 Google Inc. Query response using media consumption history
US9569525B2 (en) * 2013-09-17 2017-02-14 International Business Machines Corporation Techniques for entity-level technology recommendation
US10176256B1 (en) * 2013-12-23 2019-01-08 BroadbandTV, Corp Title rating and improvement process and system
US20150186539A1 (en) * 2013-12-26 2015-07-02 Doat Media Ltd. System and methods thereof for generation of widgets based on entities
CN103902670B (zh) * 2014-03-17 2016-04-13 百度在线网络技术(北京)有限公司 搜索推荐方法和装置
CN103927354A (zh) * 2014-04-11 2014-07-16 百度在线网络技术(北京)有限公司 交互式搜索及推荐方法和装置
CN103914554A (zh) * 2014-04-14 2014-07-09 百度在线网络技术(北京)有限公司 搜索推荐方法和装置
US10127316B2 (en) * 2014-08-08 2018-11-13 Facebook, Inc. Identifying and processing recommendation requests
US9710468B2 (en) * 2014-09-04 2017-07-18 Salesforce.Com, Inc. Topic profile query creation

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101446959A (zh) * 2008-12-30 2009-06-03 深圳市迅雷网络技术有限公司 一种基于互联网的新闻推荐方法和系统
CN101499091A (zh) * 2009-03-17 2009-08-05 辽宁般若网络科技有限公司 网页代表词推荐方法
US20120239639A1 (en) * 2011-03-14 2012-09-20 Slangwho, Inc. Search Engine
CN103914553A (zh) * 2014-04-14 2014-07-09 百度在线网络技术(北京)有限公司 搜索方法和搜索引擎
CN104679848A (zh) * 2015-02-13 2015-06-03 百度在线网络技术(北京)有限公司 搜索推荐方法和装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3142022A4 *

Also Published As

Publication number Publication date
US20170132322A1 (en) 2017-05-11
CN104679848B (zh) 2019-05-03
EP3142022A4 (en) 2018-01-10
CN104679848A (zh) 2015-06-03
EP3142022A1 (en) 2017-03-15
KR101937430B1 (ko) 2019-01-10
JP2017525041A (ja) 2017-08-31
JP6400178B2 (ja) 2018-10-03
KR20160149289A (ko) 2016-12-27

Similar Documents

Publication Publication Date Title
WO2016127568A1 (zh) 搜索推荐方法和装置
US20200110785A1 (en) Personalized search filter and notification system
WO2016091044A1 (zh) 一种热词推荐方法、装置、系统、设备和计算机存储介质
RU2670494C2 (ru) Способ обработки поискового запроса, сервер и машиночитаемый носитель для его осуществления
US11294873B2 (en) Query-goal-mission structures
EP3252619A1 (en) Method and system for dynamically rankings images to be matched with content in response to a search query
JP6381775B2 (ja) 情報処理システム及び情報処理方法
JP2018533783A (ja) 通信に含めるオブジェクト識別子の提案
US20140317078A1 (en) Method and system for retrieving information
BRPI0808067A2 (pt) Método e aparelho de interrogação de serviços da rede
US11823244B2 (en) Expressions of users interest
JP2021192241A (ja) 検索/作成されたデジタルメディアファイルに基づく潜在的関連のあるトピックの予測
WO2015149506A1 (zh) 搜索展现方法和装置
WO2016062099A1 (zh) 搜索方法及搜索装置
US11423057B2 (en) Impression tagging system for locations
WO2021129122A1 (zh) 书籍查询页面的展示方法、电子设备及计算机存储介质
US11899700B1 (en) Categorical exploration facilitation responsive to broad search queries
WO2017050149A1 (zh) 信息搜索方法和装置
TW201508522A (zh) 社會片段強化
WO2015139457A1 (zh) 搜索推荐方法和装置
KR102150572B1 (ko) 무한 검색 결과 페이지
JP2020521246A (ja) ネットワークアクセス可能なコンテンツの自動化された分類
US20160055203A1 (en) Method for record selection to avoid negatively impacting latency
JP2011191980A (ja) レシピ提供システム及び方法
KR102387578B1 (ko) 검색 서비스 제공 방법 및 시스템

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: 15881729

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 20167034096

Country of ref document: KR

Kind code of ref document: A

REEP Request for entry into the european phase

Ref document number: 2015881729

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 2015881729

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 15322523

Country of ref document: US

ENP Entry into the national phase

Ref document number: 2017502985

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE