WO2016101716A1 - 基于用户搜索意图的搜索方法及装置 - Google Patents

基于用户搜索意图的搜索方法及装置 Download PDF

Info

Publication number
WO2016101716A1
WO2016101716A1 PCT/CN2015/094150 CN2015094150W WO2016101716A1 WO 2016101716 A1 WO2016101716 A1 WO 2016101716A1 CN 2015094150 W CN2015094150 W CN 2015094150W WO 2016101716 A1 WO2016101716 A1 WO 2016101716A1
Authority
WO
WIPO (PCT)
Prior art keywords
search
search result
user
modifier
result item
Prior art date
Legal status (The legal status 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 status listed.)
Ceased
Application number
PCT/CN2015/094150
Other languages
English (en)
French (fr)
Inventor
王雁南
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Qihoo Technology Co Ltd
Qizhi Software Beijing Co Ltd
Original Assignee
Beijing Qihoo Technology Co Ltd
Qizhi Software Beijing Co Ltd
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 Beijing Qihoo Technology Co Ltd, Qizhi Software Beijing Co Ltd filed Critical Beijing Qihoo Technology Co Ltd
Publication of WO2016101716A1 publication Critical patent/WO2016101716A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; 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 search, and in particular, to a search method and apparatus based on user search intention.
  • the existing search method is based on the search term, and the search words are matched, and the webpage containing the search words is presented as a search result.
  • the search result required by the user is a valid search result, and if the effective ratio of the provided search result is low, the search itself is inefficient.
  • the present invention has been made in order to provide a user search intent based search method and corresponding apparatus that overcomes the above problems or at least partially solves or alleviates the above problems.
  • a search method based on a user's search intention including:
  • the search result page is drawn according to the adjusted search result.
  • a search apparatus based on a user search intent including:
  • the determining module is adapted to determine whether the search term input by the user includes a specific modifier that reflects the user's search intention
  • the adjusting module is adapted to: if the determination result of the determining module is yes, adjust the ranking of the search results according to the search intent corresponding to the specific modifier;
  • a drawing module is adapted to draw a search result page according to the adjusted search result.
  • a computer program comprising computer readable code, when the computer readable code is run on a computing device, causing the computing device to perform execution based on any of the above The search method for the user to search for intent.
  • a computer readable medium storing a computer program as described above is provided.
  • the search result ranking in the embodiment of the present invention is not a simple search result, but the search intention is accurately understood by a specific modifier, and the normal search intent is a premise that the search engine gives a satisfactory result to the user.
  • the user may explicitly indicate the type of intent in a specific modifier, and the present invention can make the search engine correctly understand the user's needs according to the specific modifier, thereby giving priority to giving the user the most satisfactory result, optimizing the ranking of the result, and improving the search. effectiveness.
  • FIG. 1 shows a process flow diagram of a search method based on a user's search intent, in accordance with one embodiment of the present invention
  • FIG. 2 illustrates a particular modifier reflecting a particular vertical search in accordance with one embodiment of the present invention.
  • FIG. 3 is a block diagram showing a structure of a search device based on a user's search intention according to an embodiment of the present invention
  • FIG. 4 shows a block diagram of a computing device for performing a user search intent based search method in accordance with the present invention
  • Figure 5 illustrates a storage unit for maintaining or carrying program code that implements a user search intent based search method in accordance with the present invention.
  • FIG. 1 illustrates a process flow diagram of a search method based on user search intent, in accordance with one embodiment of the present invention.
  • the search method based on the user search intention includes at least steps S102 to S106:
  • Step S102 determining whether the search term input by the user includes a specific modifier that reflects the user's search intention, and if so, executing step S104 and step S106, and if not, executing step S108;
  • Step S104 Adjust the search result ranking according to the search intent corresponding to the specific modifier.
  • Step S106 Sorting the search result page according to the adjusted search result
  • Step S108 Sort the search result page according to the search result obtained by the input search word.
  • the search result ranking in the embodiment of the present invention is not a simple search result, but the search intention is accurately understood by a specific modifier, and the normal search intent is a premise that the search engine gives a satisfactory result to the user.
  • the user may explicitly indicate the intent type in a specific modifier, and the present invention can give the user the most priority by giving the search engine a correct understanding of the user's needs according to the specific modifier. Satisfactory results, sorting the optimization results, and improving search efficiency.
  • the "map" in the search term "robot up to map” is a specific modifier that reflects the user's search intent.
  • the search engine can determine that the user's search intent is to search for an apple's picture; the search term “machine cat online viewing” "Online viewing” is a specific modifier that reflects the user's search intent.
  • the search engine can determine that the user's search intent is to search for "machine cat” video; the "500 words” in the search word "a happy little thing 500 words” is the embodiment.
  • the user searches for a specific modifier of the intent, and the search engine can determine that the user's search intent is a essay related to "a happy little thing.” It can be seen from the above embodiment that by analyzing some specific modifiers (such as graphs, online viewing, 500 words, etc.) included in the search term, it is possible to know whether a search engine has a specific search intention, thereby giving the most suitable user. Satisfactory result of intention.
  • some specific modifiers such as graphs, online viewing, 500 words, etc.
  • the particular modifier is further used to embody the user's search intent with a particular vertical search field.
  • the vertical search engine is a professional search engine for a certain industry. It is a subdivision and extension of the search engine. It is to integrate a certain type of information in the web library, and to map the fields to extract the required data for processing. Some form is returned to the user.
  • Vertical search is a new search engine service model proposed by a relatively large amount of information, inaccurate query, and insufficient depth of a general search engine. It has certain value for a specific domain, a specific group of people or a specific demand. Information and related services. Its characteristics are "specialized, refined, deep", and has an industry color, compared with the massive information disorder of the general search engine, the vertical search engine is more focused, specific and in-depth.
  • a specific vertical search field represented by a specific modifier may be determined by matching a specific modifier with a preset correspondence table, wherein the correspondence table stores a specific modifier and a vertical Search for correspondence between domains. Then, according to the matching result, a specific vertical search field represented by a specific modifier is determined.
  • the correspondence table is generated by data mining and/or manual labeling.
  • step S104 at least one search result item corresponding to the search intent is searched according to the specific modifier obtained in step S102. Subsequently, the position of the found at least one search result item in the ranking of the search results will be adjusted. In order to efficiently improve the search efficiency of the user, it is preferable to advance the position of the found at least one search result item in the search result ranking.
  • the specific modifier is further used to reflect the search intent of the user having a specific vertical search field
  • the at least one search result item is at least one search result item in the specific vertical search field. More accurate by analyzing specific modifiers by search terms Grasp the user's intentions and adjust the order of the results so that the results that best meet the user's needs are ranked as possible, thus improving the user experience.
  • the adjustment of the search result item faces a problem of how to adjust.
  • the following algorithm is defined in the embodiment of the present invention, and is suitable for the adjustment of the search result item. Specifically, at least one search result item is weighted according to a preset rule to obtain a weighted value of each search result item. Then, according to the weighting value, the position of each search result item in the ranking of the search results is adjusted.
  • the weighting process can be various.
  • the search result item is a graph
  • the color of the graph is weighted, the color weight value is high, the black and white weight value is low, and in the color picture, the one-step weighting value is performed according to the color type
  • the weighting values of the above colors are higher than the weighting values of the three or less colors, and so on.
  • the search term is “Robot Gundam Graph”.
  • the weight of the four-color up graph is 10
  • the weight of the three-color up graph is 5
  • the weight of the black-and-white graph is 1, so the adjusted search In the result item, the four colors are as high as the top, followed by the three colors up to the map, followed by the black and white map.
  • the setting of the weighting rules makes the sorting of the search result items more orderly and orderly, further improving the search efficiency.
  • At least one search result item corresponding to the search search intention may also be marked to adjust the position of each marked search result item in the search result ranking. Marking can distinguish different search result items, which is simple and convenient. It is more accurate and easy to use the mark to adjust the sorting.
  • FIG. 2 illustrates a flow diagram of a search method based on user search intent when a particular modifier embodies a particular vertical search domain, in accordance with one embodiment of the present invention.
  • the method includes steps S202 to S212:
  • Step S202 The user initiates a search
  • Step S204 analyzing whether there is a specific modifier in the search term
  • step S206 After the user initiates the search, it is determined by text semantic analysis whether the search term contains a specific modifier. If yes, go to step S206 to step S210; if no, go to step S212;
  • Step S206 Find and search for a search result item that meets a vertical search field
  • the corresponding relationship table may be used to determine whether the user has a search intention of a certain vertical search domain, that is, whether the specific modifier can reflect the search intention of a vertical search domain, wherein the corresponding relationship table stores a specific modifier and Correspondence with a vertical search field. And, the correspondence table is prepared in advance by data mining or manual setting.
  • Step S208 performing weighting processing on the marked search result item, and adjusting the ranking in the search result by using the new weighting value
  • Step S210 Display a search result page drawn according to the adjusted search result
  • Step S212 displaying a natural search result obtained by searching according to the search term.
  • an embodiment of the present invention further provides a search device based on a user search intention, which is used to support a search method based on a user search intention illustrated by any one of the above embodiments or a combination thereof.
  • FIG. 3 shows a schematic structural diagram of a search device based on a user's search intention according to an embodiment of the present invention. Referring to FIG. 3, the device at least includes:
  • the determining module 310 is adapted to determine whether the search term input by the user includes a specific modifier that reflects the user's search intention;
  • the adjustment module 320 is coupled to the determination module 310, and is adapted to adjust the search result ranking according to the search intention corresponding to the specific modifier if the determination result of the determination module 310 is YES;
  • the drawing module 330 is coupled to the adjustment module 320 and is adapted to draw the search result page according to the adjusted search result.
  • the adjustment module 320 can also be adapted to:
  • the adjustment module 320 can also be adapted to:
  • the position of each search result item in the sorting of search results is adjusted according to the weighting value.
  • the adjustment module 320 can also be adapted to:
  • the specific modifier is further used to reflect whether the user has a search intent for a particular vertical search field.
  • the adjustment module 320 can also be adapted to:
  • the position of at least one search result item in a particular vertical search field in the ranking of the search results is adjusted forward.
  • the adjustment module 320 can determine a particular vertical search field embodied by a particular modifier as follows:
  • the correspondence table stores the correspondence between the specific modifier and the vertical search domain
  • a specific vertical search field in which a particular modifier is embodied is determined based on the matching result.
  • the drawing module 330 is further adapted to: if the determination result of the determining module is negative, the search result page is sorted according to the search result obtained by the input search word.
  • the search result ranking in the embodiment of the present invention is not a simple search result, but the search intention is accurately understood by a specific modifier, and the normal search intent is a premise that the search engine gives a satisfactory result to the user.
  • the user may explicitly indicate the type of intent in a specific modifier, and the present invention can make the search engine correctly understand the user's needs according to the specific modifier, thereby giving priority to giving the user the most satisfactory result, optimizing the ranking of the result, and improving the search. effectiveness.
  • modules in the devices of the embodiments can be adaptively changed and placed in one or more devices different from the embodiment.
  • Modules or units or components in an embodiment may be combined into one module or unit Or components, and in addition, they can be divided into multiple sub-modules or sub-units or sub-components.
  • any combination of the features disclosed in the specification, including the accompanying claims, the abstract and the drawings, and any methods so disclosed, or All processes or units of the device are combined.
  • the various component embodiments of the present invention may be implemented in hardware, or in a software module running on one or more processors, or in a combination thereof.
  • a microprocessor or digital signal processor may be used in practice to implement some or all of the functionality of some or all of the components of the search intent based user search in accordance with embodiments of the present invention.
  • the invention can also be implemented as a device or device program (e.g., a computer program and a computer program product) for performing some or all of the methods described herein.
  • a program implementing the invention may be stored on a computer readable medium or may be in the form of one or more signals. Such signals may be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.
  • FIG. 4 illustrates a computing device that can implement a search method based on user search intent in accordance with the present invention.
  • the computing device conventionally includes a processor 410 and a computer program product or computer readable medium in the form of a memory 420.
  • the memory 420 may be an electronic memory such as a flash memory, an EEPROM (Electrically Erasable Programmable Read Only Memory), an EPROM, a hard disk, or a ROM.
  • Memory 420 has a memory space 430 for program code 431 for performing any of the method steps described above.
  • storage space 430 for program code may include various program code 431 for implementing various steps in the above methods, respectively.
  • the program code can be read from or written to one or more computer program products.
  • These computer program products include program code carriers such as hard disks, compact disks (CDs), memory cards or floppy disks. Such computer program products are typically portable or fixed storage units as described with reference to FIG.
  • the storage unit may have storage segments, storage spaces, and the like that are similarly arranged to memory 420 in the computing device of FIG.
  • the program code can be compressed, for example, in an appropriate form.
  • the storage unit includes computer readable code 431', ie, code readable by a processor, such as 410, that when executed by a computing device causes the computing device to perform each of the methods described above step.

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)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

本发明公开了一种基于用户搜索意图的搜索方法及装置。基于用户搜索意图的搜索方法,包括:判断用户输入的搜索词中是否包含体现所述用户搜索意图的特定修饰词;若是,根据所述特定修饰词对应的搜索意图,调整搜索结果排序;根据所述调整后的搜索结果排序绘制搜索结果页。采用本发明能够优化结果排序,提高搜索效率。

Description

基于用户搜索意图的搜索方法及装置 技术领域
本发明涉及互联网搜索领域,尤其涉及一种基于用户搜索意图的搜索方法及装置。
背景技术
随着互联网技术越来越普及,用户对于互联网搜索也越来越依赖。现在用户想要搜索未知的事情时,通常的选择都是:打开浏览器,在浏览器的搜索框中输入搜索词以及搜索指令,由浏览器发起搜索,得到搜索结果。
现有的搜索方式是以搜索词为依据,对搜索词进行匹配,将包含了搜索词的网页作为搜索结果对外呈现。
但是,由于互联网数据的宽泛性和大数据性,包含搜索词的网页可能成千上万甚至更多。用户需要在如此大量的数据中查找到自己想要的搜索结果,工作量大,并会耗费大量时间,降低用户的感受体验。
对于搜索引擎而言,用户所需要的搜索结果才是有效的搜索结果,若提供的搜索结果有效比率较低,使得搜索本身效率偏低。
发明内容
鉴于上述问题,提出了本发明以便提供一种克服上述问题或者至少部分地解决或者减缓上述问题的基于用户搜索意图的搜索方法和相应的装置。
根据本发明的一个方面,提供了一种基于用户搜索意图的搜索方法,包括:
判断用户输入的搜索词中是否包含体现所述用户搜索意图的特定修饰词;
若是,根据所述特定修饰词对应的搜索意图,调整搜索结果排序;
根据所述调整后的搜索结果排序绘制搜索结果页。
根据本发明的另一个方面,提供了一种基于用户搜索意图的搜索装置,包括:
判断模块,适于判断用户输入的搜索词中是否包含体现所述用户搜索意图的特定修饰词;
调整模块,适于若所述判断模块的判断结果为是,根据所述特定修饰词对应的搜索意图,调整搜索结果排序;
绘制模块,适于根据所述调整后的搜索结果排序绘制搜索结果页。
根据本发明的又一个方面,提供了一种计算机程序,其包括计算机可读代码,当所述计算机可读代码在计算设备上运行时,导致所述计算设备执行根据上述中的任一种基于用户搜索意图的搜索方法。
根据本发明的再一个方面,提供了一种计算机可读介质,其中存储了如上所述的计算机程序。
本发明的有益效果为:
在本发明实施例中,接收到用户输入的搜索词后,判断其中是否包含体现用户搜索意图的特定修饰词,若是,则根据特定修饰词对应的搜索意图调整搜索结果排序。由此可见,本发明实施例中的搜索结果排序并非是简单的搜索结果,而是通过特定修饰词准确地理解搜索意图,正常的搜索意图是搜索引擎给出用户满意结果的前提。用户可能在特定修饰词中明确指明了意图类型,本发明即可通过根据特定修饰词,使得搜索引擎正确理解用户需求,从而尽可能优先给出用户最满意的结果,优化结果排序,提高了搜索效率。
上述说明仅是本发明技术方案的概述,为了能够更清楚了解本发明的技术手段,而可依照说明书的内容予以实施,并且为了让本发明的上述和其它目的、特征和优点能够更明显易懂,以下特举本发明的具体实施方式。
附图说明
通过阅读下文优选实施方式的详细描述,各种其他的优点和益处对于本领域普通技术人员将变得清楚明了。附图仅用于示出优选实施方式的目的,而并不认为是对本发明的限制。而且在整个附图中,用相同的参考符号表示相同的部件。在附图中:
图1示出了根据本发明一个实施例的基于用户搜索意图的搜索方法的处理流程图;
图2示出了根据本发明一个实施例的特定修饰词体现特定垂直搜 索领域时的基于用户搜索意图的搜索方法的流程图;
图3示出了根据本发明一个实施例的基于用户搜索意图的搜索装置的结构示意图;
图4示出了用于执行根据本发明的基于用户搜索意图的搜索方法的计算设备的框图;以及
图5示出了用于保持或者携带实现根据本发明的基于用户搜索意图的搜索方法的程序代码的存储单元。
具体实施方式
下面结合附图和具体的实施方式对本发明作进一步的描述。虽然附图中显示了本公开的示例性实施例,然而应当理解,可以以各种形式实现本公开而不应被这里阐述的实施例所限制。相反,提供这些实施例是为了能够更透彻地理解本公开,并且能够将本公开的范围完整的传达给本领域的技术人员。
为解决上述技术问题,本发明实施例提供了一种基于用户搜索意图的搜索方法。图1示出了根据本发明一个实施例的基于用户搜索意图的搜索方法的处理流程图。参见图1,基于用户搜索意图的搜索方法至少包括步骤S102至步骤S106:
步骤S102、判断用户输入的搜索词中是否包含体现用户搜索意图的特定修饰词,若是,执行步骤S104及步骤S106,若否,执行步骤S108;
步骤S104、根据特定修饰词对应的搜索意图,调整搜索结果排序;
步骤S106、根据调整后的搜索结果排序绘制搜索结果页;
步骤S108、根据输入的搜索词得到的搜索结果排序绘制搜索结果页。
在本发明实施例中,接收到用户输入的搜索词后,判断其中是否包含体现用户搜索意图的特定修饰词,若是,则根据特定修饰词对应的搜索意图调整搜索结果排序。由此可见,本发明实施例中的搜索结果排序并非是简单的搜索结果,而是通过特定修饰词准确地理解搜索意图,正常的搜索意图是搜索引擎给出用户满意结果的前提。用户可能在特定修饰词中明确指明了意图类型,本发明即可通过根据特定修饰词,使得搜索引擎正确理解用户需求,从而尽可能优先给出用户最 满意的结果,优化结果排序,提高了搜索效率。
例如,搜索词“机器人高达图”中的“图”即为体现用户搜索意图的特定修饰词,搜索引擎可以确定用户的搜索意图是搜索苹果的图片;搜索词“机器猫在线观看”中的“在线观看”即为体现用户搜索意图的特定修饰词,搜索引擎可以确定用户的搜索意图是搜索“机器猫”视频;搜索词“一件幸福的小事500字”中的“500字”即为体现用户搜索意图的特定修饰词,搜索引擎可以确定用户的搜索意图是与“一件幸福的小事”相关的范文。通过上述实施例可以看出,通过分析搜索词中包含的一些特定修饰词(如,图、在线观看、500字等),可以了解一个搜索引擎是否具有特定的搜索意图,从而给出最符合用户意图的满意结果。
优选地,特定修饰词进一步用于体现用户具有特定垂直搜索领域的搜索意图。垂直搜索引擎是针对某一个行业的专业搜索引擎,是搜索引擎的细分和延伸,是对网页库中的某类专门的信息进行一次整合,定向分字段抽取出需要的数据进行处理后再以某种形式返回给用户。垂直搜索是相对通用搜索引擎的信息量大、查询不准确、深度不够等提出来的新的搜索引擎服务模式,通过针对某一特定领域、某一特定人群或某一特定需求提供的有一定价值的信息和相关服务。其特点就是“专、精、深”,且具有行业色彩,相比较通用搜索引擎的海量信息无序化,垂直搜索引擎则显得更加专注、具体和深入。
在本发明的一个实施例中,可以通过如下方式确定特定修饰词体现的特定垂直搜索领域:将特定修饰词与预设的对应关系表进行匹配,其中,对应关系表存储有特定修饰词与垂直搜索领域间的对应关系。进而根据匹配结果确定特定修饰词体现的特定垂直搜索领域。其中,对应关系表通过数据挖掘和/或人工标注生成。
步骤S104在实施时,根据步骤S102中判断得到的特定修饰词,查找搜索意图对应的至少一个搜索结果项。随后,将调整查找到的至少一个搜索结果项在搜索结果排序中的位置。为了高效率地提高用户的搜索效率,优选地,将查找到的至少一个搜索结果项的位置在搜索结果排序中前移。其中,当特定修饰词进一步用于体现用户具有特定垂直搜索领域的搜索意图时,至少一个搜索结果项则是特定垂直搜索领域中的至少一个搜索结果项。通过搜索词分析特定修饰词,更准确 地把握用户意图,并对结果排序进行调整,使得最满足用户需求的结果尽可能的排在前面,从而改善用户体验。
由于根据特定修饰词查找到的搜索结果项数量为至少一个,当搜索结果项为两个以上时,搜索结果项的调整面临如何调整的问题。本发明实施例中定义了如下算法,适于搜索结果项的调整。具体地,根据预设规则对至少一个搜索结果项进行加权处理,得到每个搜索结果项的加权值。进而根据加权值调整每个搜索结果项在搜索结果排序中的位置。加权处理的规则可以为多种,例如,搜索结果项为图时,以图的颜色为加权项,彩色加权值高,黑白加权值低,彩色图片中,按颜色种类进行一步限定加权值,三种以上颜色的加权值相对三种以下颜色的加权值要高,等等。例如,搜索词为“机器人高达图”,搜索结果中,四色高达图的加权值为10,三色高达图的加权值为5,黑白高达图的加权值为1,因此,调整后的搜索结果项中,四色高达图最靠前,其次是三色高达图,再其次为黑白高达图。加权规则的设置,使得搜索结果项的排序更为整齐有序,进一步提高了搜索效率。
在一个优选的实施例中,还可以对查找搜索意图对应的至少一个搜索结果项进行标记,进而调整每个被标记的搜索结果项在搜索结果排序中的位置。标记能够区别不同的搜索结果项,简单、方便,利用标记调整排序的方式更为准确易行。
图2示出了根据本发明一个实施例的特定修饰词体现特定垂直搜索领域时的基于用户搜索意图的搜索方法的流程图。参见图2,该方法包括步骤S202至步骤S212:
步骤S202、用户发起搜索;
步骤S204、分析搜索词中是否存在特定修饰词;
当用户发起搜索后,通过文本语义分析,判断该搜索词是否含有特定修饰词。若是,执行步骤S206至步骤S210;若否,执行步骤S212;
步骤S206、查找出符合某垂直搜索领域的搜索结果项并标记;
其中,根据对应关系表可以辅助判断用户是否具有某个垂直搜索领域的搜索意图,即特定修饰词是否能够体现某个垂直搜索领域的搜索意图,其中,对应关系表中存储有特定修饰词及其与某垂直搜索领域的对应关系。并且,该对应关系表通过数据挖掘或人工设置提前准备好。
步骤S208、针对有标记的搜索结果项进行加权处理,并利用新的加权值调整其在搜索结果中的排序;
步骤S210、显示根据调整后的搜索结果绘制的搜索结果页;
步骤S212、展现根据搜索词搜索得到的自然搜索结果。
基于同一发明构思,本发明实施例还提供了一种基于用户搜索意图的搜索装置,用于支持上述任一个实施例或其组合所示意的基于用户搜索意图的搜索方法。图3示出了根据本发明一个实施例的基于用户搜索意图的搜索装置的结构示意图。参见图3,该装置至少包括:
判断模块310,适于判断用户输入的搜索词中是否包含体现用户搜索意图的特定修饰词;
调整模块320,与判断模块310耦合,适于若判断模块310的判断结果为是,根据特定修饰词对应的搜索意图,调整搜索结果排序;
绘制模块330,与调整模块320耦合,适于根据调整后的搜索结果排序绘制搜索结果页。
在一个优选的实施例中,调整模块320还可以适于:
根据特定修饰词,查找搜索意图对应的至少一个搜索结果项;
调整查找到的至少一个搜索结果项在搜索结果排序中的位置。
在一个优选的实施例中,调整模块320还可以适于:
根据预设规则对至少一个搜索结果项进行加权处理,得到每个搜索结果项的加权值;
根据加权值调整每个搜索结果项在搜索结果排序中的位置。
在一个优选的实施例中,调整模块320还可以适于:
对至少一个搜索结果项进行标记;
调整每个被标记的搜索结果项在搜索结果排序中的位置。
在一个优选的实施例中,特定修饰词进一步用于体现用户是否具有特定垂直搜索领域的搜索意图。
在一个优选的实施例中,调整模块320还可以适于:
查找特定垂直搜索领域中的至少一个搜索结果项;
将特定垂直搜索领域中的至少一个搜索结果项在搜索结果排序中的位置向前调整。
在一个优选的实施例中,调整模块320可以通过如下方式确定特定修饰词体现的特定垂直搜索领域:
将特定修饰词与预设的对应关系表进行匹配,其中,对应关系表存储有特定修饰词与垂直搜索领域间的对应关系;
根据匹配结果确定特定修饰词体现的特定垂直搜索领域。
在一个优选的实施例中,绘制模块330还可以适于:若判断模块的判断结果为否,根据输入的搜索词得到的搜索结果排序绘制搜索结果页。
根据本发明实施例提供的基于用户搜索意图的搜索方法及装置能够达到如下有益效果:
在本发明实施例中,接收到用户输入的搜索词后,判断其中是否包含体现用户搜索意图的特定修饰词,若是,则根据特定修饰词对应的搜索意图调整搜索结果排序。由此可见,本发明实施例中的搜索结果排序并非是简单的搜索结果,而是通过特定修饰词准确地理解搜索意图,正常的搜索意图是搜索引擎给出用户满意结果的前提。用户可能在特定修饰词中明确指明了意图类型,本发明即可通过根据特定修饰词,使得搜索引擎正确理解用户需求,从而尽可能优先给出用户最满意的结果,优化结果排序,提高了搜索效率。
在此处所提供的说明书中,说明了大量具体细节。然而,能够理解,本发明的实施例可以在没有这些具体细节的情况下实践。在一些实例中,并未详细示出公知的方法、结构和技术,以便不模糊对本说明书的理解。
类似地,应当理解,为了精简本公开并帮助理解各个发明方面中的一个或多个,在上面对本发明的示例性实施例的描述中,本发明的各个特征有时被一起分组到单个实施例、图、或者对其的描述中。然而,并不应将该公开的方法解释成反映如下意图:即所要求保护的本发明要求比在每个权利要求中所明确记载的特征更多的特征。更确切地说,如下面的权利要求书所反映的那样,发明方面在于少于前面公开的单个实施例的所有特征。因此,遵循具体实施方式的权利要求书由此明确地并入该具体实施方式,其中每个权利要求本身都作为本发明的单独实施例。
本领域那些技术人员可以理解,可以对实施例中的设备中的模块进行自适应性地改变并且把它们设置在与该实施例不同的一个或多个设备中。可以把实施例中的模块或单元或组件组合成一个模块或单元 或组件,以及此外可以把它们分成多个子模块或子单元或子组件。除了这样的特征和/或过程或者单元中的至少一些是相互排斥之外,可以采用任何组合对本说明书(包括伴随的权利要求、摘要和附图)中公开的所有特征以及如此公开的任何方法或者设备的所有过程或单元进行组合。除非另外明确陈述,本说明书(包括伴随的权利要求、摘要和附图)中公开的每个特征可以由提供相同、等同或相似目的的替代特征来代替。
此外,本领域的技术人员能够理解,尽管在此所述的一些实施例包括其它实施例中所包括的某些特征而不是其它特征,但是不同实施例的特征的组合意味着处于本发明的范围之内并且形成不同的实施例。例如,在下面的权利要求书中,所要求保护的实施例的任意之一都可以以任意的组合方式来使用。
本发明的各个部件实施例可以以硬件实现,或者以在一个或者多个处理器上运行的软件模块实现,或者以它们的组合实现。本领域的技术人员应当理解,可以在实践中使用微处理器或者数字信号处理器(DSP)来实现根据本发明实施例的基于用户搜索意图的搜索装置中的一些或者全部部件的一些或者全部功能。本发明还可以实现为用于执行这里所描述的方法的一部分或者全部的设备或者装置程序(例如,计算机程序和计算机程序产品)。这样的实现本发明的程序可以存储在计算机可读介质上,或者可以具有一个或者多个信号的形式。这样的信号可以从因特网网站上下载得到,或者在载体信号上提供,或者以任何其他形式提供。
例如,图4示出了可以实现根据本发明的基于用户搜索意图的搜索方法的计算设备。该计算设备传统上包括处理器410和以存储器420形式的计算机程序产品或者计算机可读介质。存储器420可以是诸如闪存、EEPROM(电可擦除可编程只读存储器)、EPROM、硬盘或者ROM之类的电子存储器。存储器420具有用于执行上述方法中的任何方法步骤的程序代码431的存储空间430。例如,用于程序代码的存储空间430可以包括分别用于实现上面的方法中的各种步骤的各个程序代码431。这些程序代码可以从一个或者多个计算机程序产品中读出或者写入到这一个或者多个计算机程序产品中。这些计算机程序产品包括诸如硬盘,紧致盘(CD)、存储卡或者软盘之类的程序代码载体。 这样的计算机程序产品通常为如参考图5所述的便携式或者固定存储单元。该存储单元可以具有与图4的计算设备中的存储器420类似布置的存储段、存储空间等。程序代码可以例如以适当形式进行压缩。通常,存储单元包括计算机可读代码431’,即可以由例如诸如410之类的处理器读取的代码,这些代码当由计算设备运行时,导致该计算设备执行上面所描述的方法中的各个步骤。
本文中所称的“一个实施例”、“实施例”或者“一个或者多个实施例”意味着,结合实施例描述的特定特征、结构或者特性包括在本发明的至少一个实施例中。此外,请注意,这里“在一个实施例中”的词语例子不一定全指同一个实施例。
应该注意的是上述实施例对本发明进行说明而不是对本发明进行限制,并且本领域技术人员在不脱离所附权利要求的范围的情况下可设计出替换实施例。在权利要求中,不应将位于括号之间的任何参考符号构造成对权利要求的限制。单词“包含”不排除存在未列在权利要求中的元件或步骤。位于元件之前的单词“一”或“一个”不排除存在多个这样的元件。本发明可以借助于包括有若干不同元件的硬件以及借助于适当编程的计算机来实现。在列举了若干装置的单元权利要求中,这些装置中的若干个可以是通过同一个硬件项来具体体现。单词第一、第二、以及第三等的使用不表示任何顺序。可将这些单词解释为名称。
此外,还应当注意,本说明书中使用的语言主要是为了可读性和教导的目的而选择的,而不是为了解释或者限定本发明的主题而选择的。因此,在不偏离所附权利要求书的范围和精神的情况下,对于本技术领域的普通技术人员来说许多修改和变更都是显而易见的。对于本发明的范围,对本发明所做的公开是说明性的,而非限制性的,本发明的范围由所附权利要求书限定。

Claims (19)

  1. 一种基于用户搜索意图的搜索方法,包括:
    判断用户输入的搜索词中是否包含体现所述用户搜索意图的特定修饰词;
    若是,根据所述特定修饰词对应的搜索意图,调整搜索结果排序;
    根据所述调整后的搜索结果排序绘制搜索结果页。
  2. 根据权利要求1所述的方法,其中,根据所述特定修饰词对应的搜索意图,调整搜索结果排序,包括:
    根据所述特定修饰词,查找所述搜索意图对应的至少一个搜索结果项;
    调整查找到的所述至少一个搜索结果项在搜索结果排序中的位置。
  3. 根据权利要求1-2任一项所述的方法,其中,所述调整查找到的所述至少一个搜索结果项在搜索结果排序中的位置,包括:
    根据预设规则对所述至少一个搜索结果项进行加权处理,得到每个搜索结果项的加权值;
    根据所述加权值调整每个搜索结果项在搜索结果排序中的位置。
  4. 根据权利要求1-3任一项所述的方法,其中,调整查找到的所述至少一个搜索结果项在搜索结果排序中的位置,还包括:
    对所述至少一个搜索结果项进行标记;
    调整每个被标记的搜索结果项在搜索结果排序中的位置。
  5. 根据权利要求1至4任一项所述的方法,其中,所述特定修饰词进一步用于体现所述用户具有特定垂直搜索领域的搜索意图。
  6. 根据权利要求1-5任一项所述的方法,其中,根据所述特定修饰词对应的搜索意图,调整搜索结果排序,包括:
    查找所述特定垂直搜索领域中的至少一个搜索结果项;
    将所述特定垂直搜索领域中的至少一个搜索结果项在搜索结果排序中的位置向前调整。
  7. 根据权利要求1-6任一项所述的方法,其中,通过如下方式确定所述特定修饰词体现的特定垂直搜索领域:
    将所述特定修饰词与预设的对应关系表进行匹配,其中,所述对 应关系表存储有特定修饰词与垂直搜索领域间的对应关系;
    根据匹配结果确定所述特定修饰词体现的特定垂直搜索领域。
  8. 根据权利要求1-7任一项所述的方法,其中,所述对应关系表通过数据挖掘和/或人工标注生成。
  9. 根据权利要求1至8任一项所述的方法,其中,还包括:
    若否,根据输入的搜索词得到的搜索结果排序绘制搜索结果页。
  10. 一种基于用户搜索意图的搜索装置,包括:
    判断模块,适于判断用户输入的搜索词中是否包含体现所述用户搜索意图的特定修饰词;
    调整模块,适于若所述判断模块的判断结果为是,根据所述特定修饰词对应的搜索意图,调整搜索结果排序;
    绘制模块,适于根据所述调整后的搜索结果排序绘制搜索结果页。
  11. 根据权利要求10所述的装置,其中,所述调整模块还适于:
    根据所述特定修饰词,查找所述搜索意图对应的至少一个搜索结果项;
    调整查找到的所述至少一个搜索结果项在搜索结果排序中的位置。
  12. 根据权利要求10-11任一项所述的装置,其中,所述调整模块还适于:
    根据预设规则对所述至少一个搜索结果项进行加权处理,得到每个搜索结果项的加权值;
    根据所述加权值调整每个搜索结果项在搜索结果排序中的位置。
  13. 根据权利要求10-12任一项所述的装置,其中,所述调整模块还适于:
    对所述至少一个搜索结果项进行标记;
    调整每个被标记的搜索结果项在搜索结果排序中的位置。
  14. 根据权利要求10-13任一项所述的装置,其中,所述特定修饰词进一步用于体现所述用户是否具有特定垂直搜索领域的搜索意图。
  15. 根据权利要求10-14任一项所述的装置,其中,所述调整模块还适于:
    查找所述特定垂直搜索领域中的至少一个搜索结果项;
    将所述特定垂直搜索领域中的至少一个搜索结果项在搜索结果排 序中的位置向前调整。
  16. 根据权利要求10-15任一项所述的装置,其中,所述调整模块通过如下方式确定所述特定修饰词体现的特定垂直搜索领域:
    将所述特定修饰词与预设的对应关系表进行匹配,其中,所述对应关系表存储有特定修饰词与垂直搜索领域间的对应关系;
    根据匹配结果确定所述特定修饰词体现的特定垂直搜索领域。
  17. 根据权利要求10-16任一项所述的装置,其中,
    所述绘制模块还适于:若所述判断模块的判断结果为否,根据输入的搜索词得到的搜索结果排序绘制搜索结果页。
  18. 一种计算机程序,包括计算机可读代码,当所述计算机可读代码在计算设备上运行时,导致所述计算设备执行根据权利要求1-9中的任一种用户搜索意图的搜索方法。
  19. 一种计算机可读介质,其中存储了如权利要求18所述的计算机程序。
PCT/CN2015/094150 2014-12-22 2015-11-09 基于用户搜索意图的搜索方法及装置 Ceased WO2016101716A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201410806485.3 2014-12-22
CN201410806485.3A CN104462510B (zh) 2014-12-22 2014-12-22 基于用户搜索意图的搜索方法及装置

Publications (1)

Publication Number Publication Date
WO2016101716A1 true WO2016101716A1 (zh) 2016-06-30

Family

ID=52908545

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/094150 Ceased WO2016101716A1 (zh) 2014-12-22 2015-11-09 基于用户搜索意图的搜索方法及装置

Country Status (2)

Country Link
CN (1) CN104462510B (zh)
WO (1) WO2016101716A1 (zh)

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104462510B (zh) * 2014-12-22 2018-09-11 北京奇虎科技有限公司 基于用户搜索意图的搜索方法及装置
CN104715066B (zh) * 2015-03-31 2017-04-12 北京奇付通科技有限公司 一种搜索优化方法、装置和系统
EP3079083A1 (en) * 2015-04-09 2016-10-12 Google, Inc. Providing app store search results
CN104881451A (zh) * 2015-05-18 2015-09-02 百度在线网络技术(北京)有限公司 图片搜索方法及装置
CN106708887A (zh) * 2015-11-17 2017-05-24 镇江诺尼基智能技术有限公司 一种意图驱动的产品搜索系统和方法
CN106462645A (zh) * 2016-01-07 2017-02-22 马岩 网络信息的搜索方法及系统
CN106250530A (zh) * 2016-08-06 2016-12-21 马岩 大数据中关键字分类搜索方法及系统
WO2018027341A1 (zh) * 2016-08-06 2018-02-15 马岩 大数据中关键字分类搜索方法及系统
CN107256242A (zh) * 2017-05-27 2017-10-17 北京小米移动软件有限公司 搜索结果显示方法及装置、终端、服务器及存储介质
CN110363605B (zh) * 2018-04-10 2024-07-26 北京京东尚科信息技术有限公司 信息搜索方法和装置及计算机可读存储介质
CN110737840B (zh) * 2019-10-22 2023-07-28 海信视像科技股份有限公司 语音控制方法及显示设备

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101216825A (zh) * 2007-12-29 2008-07-09 朱廷劭 标引关键词提取/预测方法、在线广告推荐方法和装置
CN103927328A (zh) * 2014-03-18 2014-07-16 清华大学 查询意图挖掘的方法和系统
CN104462510A (zh) * 2014-12-22 2015-03-25 北京奇虎科技有限公司 基于用户搜索意图的搜索方法及装置

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8341157B2 (en) * 2009-07-31 2012-12-25 Yahoo! Inc. System and method for intent-driven search result presentation
CN102456054B (zh) * 2010-10-28 2016-05-18 深圳市世纪光速信息技术有限公司 一种搜索方法及系统
CN102043833B (zh) * 2010-11-25 2013-12-25 北京搜狗科技发展有限公司 一种基于查询词进行搜索的方法和搜索装置
CN102722503A (zh) * 2011-03-31 2012-10-10 北京百度网讯科技有限公司 一种对检索结果进行排序的方法及装置
CN102163228B (zh) * 2011-04-13 2014-10-08 北京百度网讯科技有限公司 用于确定资源候选项的排序结果的方法、装置及设备
CN102890683B (zh) * 2011-07-21 2016-01-20 阿里巴巴集团控股有限公司 信息提供方法及装置
US20130166543A1 (en) * 2011-12-22 2013-06-27 Microsoft Corporation Client-based search over local and remote data sources for intent analysis, ranking, and relevance
CN103593373B (zh) * 2012-08-16 2018-09-07 北京百度网讯科技有限公司 一种用于搜索结果排序的方法与设备

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101216825A (zh) * 2007-12-29 2008-07-09 朱廷劭 标引关键词提取/预测方法、在线广告推荐方法和装置
CN103927328A (zh) * 2014-03-18 2014-07-16 清华大学 查询意图挖掘的方法和系统
CN104462510A (zh) * 2014-12-22 2015-03-25 北京奇虎科技有限公司 基于用户搜索意图的搜索方法及装置

Also Published As

Publication number Publication date
CN104462510B (zh) 2018-09-11
CN104462510A (zh) 2015-03-25

Similar Documents

Publication Publication Date Title
CN104462510B (zh) 基于用户搜索意图的搜索方法及装置
US12038977B2 (en) Visual recognition using user tap locations
US9984310B2 (en) Systems and methods for identifying semantically and visually related content
CN106202124B (zh) 网页分类方法及装置
US10289700B2 (en) Method for dynamically matching images with content items based on keywords in response to search queries
US9280561B2 (en) Automatic learning of logos for visual recognition
US20170351709A1 (en) Method and system for dynamically rankings images to be matched with content in response to a search query
WO2015070673A1 (zh) 浏览器侧进行网络搜索的方法与浏览器
WO2016000555A1 (zh) 基于社交网络的内容、新闻推荐方法和系统
CN104050286B (zh) 一种提供搜索结果整合的方法和装置
JP2017535860A (ja) マルチメディア内容の提供方法および装置
US10235387B2 (en) Method for selecting images for matching with content based on metadata of images and content in real-time in response to search queries
US10275472B2 (en) Method for categorizing images to be associated with content items based on keywords of search queries
CN102750347B (zh) 一种用于图像或视频搜索重排序的方法
CN102521321A (zh) 基于检索词歧义性和用户偏好的视频搜索方法
CN108170293A (zh) 输入联想的个性化推荐方法及装置
WO2016107125A1 (zh) 信息搜索方法及装置
CN107679186A (zh) 基于实体库进行实体搜索的方法及装置
CN119415762A (zh) 基于网页搜索和知识图谱的检索方法、系统、设备及介质
CN104615621B (zh) 搜索中的相关性处理方法和系统
WO2016101727A1 (zh) 基于问答的搜索结果调整方法和装置
WO2022241987A1 (zh) 图像检索方法及装置
CN108228802A (zh) 一种输入联想的推荐方法及装置
CN104317903B (zh) 章节式文本的章节完整性的识别方法和装置
CN104077555A (zh) 一种识别图片搜索中坏例的方法和装置

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: 15871787

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: 15871787

Country of ref document: EP

Kind code of ref document: A1