WO2017050149A1 - 信息搜索方法和装置 - Google Patents

信息搜索方法和装置 Download PDF

Info

Publication number
WO2017050149A1
WO2017050149A1 PCT/CN2016/098817 CN2016098817W WO2017050149A1 WO 2017050149 A1 WO2017050149 A1 WO 2017050149A1 CN 2016098817 W CN2016098817 W CN 2016098817W WO 2017050149 A1 WO2017050149 A1 WO 2017050149A1
Authority
WO
WIPO (PCT)
Prior art keywords
title
search
short
user
information
Prior art date
Application number
PCT/CN2016/098817
Other languages
English (en)
French (fr)
Inventor
曾安祥
欧开日
Original Assignee
阿里巴巴集团控股有限公司
曾安祥
欧开日
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 阿里巴巴集团控股有限公司, 曾安祥, 欧开日 filed Critical 阿里巴巴集团控股有限公司
Priority to EP16848031.7A priority Critical patent/EP3355204A4/en
Priority to JP2018515095A priority patent/JP2018533136A/ja
Publication of WO2017050149A1 publication Critical patent/WO2017050149A1/zh
Priority to US15/927,999 priority patent/US20180210961A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/248—Presentation of query results
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/25—Integrating or interfacing systems involving database management systems
    • G06F16/258—Data format conversion from or to a database
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/334—Query execution
    • G06F16/3344—Query execution using natural language analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0623—Item investigation

Definitions

  • the present application relates to the field of Internet technologies, and in particular, to an information search method and apparatus.
  • the input method can be used to input the search term to trigger the search.
  • the user searches within the application on the mobile terminal, if the input method is used, since the size of the mobile terminal is relatively small, it is not convenient for the user to input the search word by using the input method.
  • a search term selectable by the user may be displayed in the drop-down area of the input box and the navigation area of the page.
  • the present application aims to solve at least one of the technical problems in the related art to some extent.
  • an object of the present application is to provide an information search method, which can facilitate a user to initiate a search, and the number of search words available for selection by the user is large.
  • Another object of the present application is to propose an information search device.
  • the information search method of the first aspect of the present application includes: receiving a search term input by a user; acquiring a search result according to the search term; acquiring description information of the search result; and describing the information from the description Extracting one or more word segments; combining the one or more word segments to generate a title of the search result, at least one word segment respectively carrying a hyperlink tag; and returning the title of the word segment combination carrying the hyperlink tag to the client end display.
  • the information search method proposed by the embodiment of the first aspect of the present application can initiate a new search based on the search result by extracting one or more word segments from the description information of the search result and carrying the hyperlink tag in at least one participle.
  • the user initiates the search, and since the combined word segmentation is used as the title, theoretically, an infinite segmentation can be displayed, thereby expanding the number of new search terms and better satisfying the user's needs.
  • the information search device of the second aspect of the present application includes: a receiving module, configured to receive a search term input by a user; a first obtaining module, configured to obtain a search result according to the search term; An obtaining module, configured to obtain description information of the search result; and extracting a module, For extracting one or more word segments from the description information; a generating module, configured to combine the one or more word segments to generate a title of the search result, at least one word segment respectively carrying a hyperlink tag; a sending module, The title used to combine the word segmentation carrying the hyperlink tag is returned to the client for display.
  • the information search system proposed by the embodiment of the second aspect of the present application can initiate a new search based on the search result by extracting one or more word segments from the description information of the search result and carrying the hyperlink tag in at least one word segment.
  • the user initiates the search, and since the combined word segmentation is used as the title, theoretically, an infinite segmentation can be displayed, thereby expanding the number of new search terms and better satisfying the user's needs.
  • FIG. 1a is a schematic flowchart of an information search method according to an embodiment of the present application.
  • FIG. 1b is a schematic flowchart of an information search method according to an embodiment of the present application.
  • FIG. 2 is a schematic flowchart of an information searching method according to another embodiment of the present application.
  • FIG. 3 is a schematic diagram of search results displayed in an embodiment of the present application.
  • FIG. 4 is a schematic structural diagram of an information search apparatus according to another embodiment of the present application.
  • FIG. 5 is a schematic structural diagram of an information search apparatus according to another embodiment of the present application.
  • FIG. 1 is a schematic flowchart of an information search method according to an embodiment of the present application, where the method includes:
  • S11 Receive a search term input by the user.
  • the user may input a search term on the client, and after receiving the search term input by the user, the client may send the search term to the server.
  • search words input by the user to the client are not limited to input by the input method, but may also be input after clicking the selected search word in the navigation, drop-down box, etc., or may be a search term of voice input, of course, understandable If the voice input is used, the server can perform voice recognition to convert the text after receiving the voice data, and then search for the corresponding search result in the database.
  • the server After receiving the search term, the server can search in the database to find the search result corresponding to the search term.
  • the server can obtain information of the product corresponding to the "down jacket", and the information of the product includes, for example, the original title of the product, the picture of the product, the product details, and the like.
  • the description information may be a title or a detailed description of the search result or the like.
  • the server may segment and identify the title of the search result, extract one or more word segments from it, or extract the word segmentation from the remaining description information other than the title.
  • the title of the article includes, for example, an original title, or a short title obtained by reducing the original title.
  • an original title For example, when the user searches for "down jacket”, the original title of a search result (product) is "Antarctic new middle-aged men's thick fur collar down jacket men's jacket", then keywords can be extracted from this original title. or,
  • the original title can be converted first to get a short title, and the short title is to retain the key information in the original title to reduce the length of the original title.
  • the short title candidate set may be pre-configured, and the short title candidate set includes a plurality of short titles, and then the short title belonging to the short title candidate set is extracted from the original title.
  • the short title candidate set includes: “thickening fur collar down jacket", "vibrant fleshy”, etc., since the original title includes a "thick hairy down jacket" belonging to the short title candidate set, the extracted short title is "Thick hair fur collar down jacket.”
  • the keyword can also be extracted from the short title.
  • the data other than the product title includes, for example, feature data of the product or feature data of the store to which the product belongs.
  • the feature data is, for example, a selling point, and the selling point refers to information that can be attracted to the user, describes the non-physical attribute of the product or the store, and is obtained through statistics.
  • the feature data of the product includes, for example, "super high praise rate”, “college student favorite”, “fat mm gospel”, and the like
  • the feature data of the store includes, for example, "gold medal seller", "6 year old shop”, and the like. After that, keywords can be extracted from data other than these titles.
  • S15 Combine the one or more word segments to generate a title of the search result, at least A participle carries a hyperlink label.
  • the search results include the original title, such as the original title is "Antarctic men's new middle-aged men's thick fur collar down jacket men's jacket”, in which you can extract the "thickness”, “hair collar”, “down jacket” these parts, Assuming that the participle with the hyperlink label is "thickened”, the title of the search result is "thick plush down jacket”, and the "thickness” refers to the participle after the hyperlink is added.
  • Hyperlinks are HTML elements that are used more frequently in websites. By setting HTML elements, you can add hyperlinks to keywords to complete jumps between pages.
  • the server sends the combined title to the client, and the client displays the processed title on the search result page, such as "thickening plush down jacket” on the display position of the product title.
  • the method may further include:
  • S17 Receive selection information of a user's participle carrying a hyperlink label, and determine a word segment selected by the user;
  • the new search term is "thickness + down jacket.”
  • search for the search result corresponding to "thickness + down jacket” and return it to the client for display.
  • a new search based on the search result may be initiated, which is convenient for the user to initiate the search, and
  • the word segmentation is used as a title, in theory, it can display unlimited word segmentation, which can expand the number of new search words and better meet user needs.
  • FIG. 2 is a schematic flowchart of an information search method according to another embodiment of the present application. This embodiment takes a commodity search as an example. The method includes:
  • the user may input a search term on the client, and after receiving the search term input by the user, the client may send the search term to the server.
  • the search words input by the user to the client are not limited to input by the input method, but may also be input after clicking the selected search word in the navigation, drop-down box, etc., or may be a search term of voice input, of course, it is understandable If the voice input is used, the server can perform voice recognition to convert the text after receiving the voice data, and then search for the corresponding search result in the database.
  • S22 Acquire a corresponding item according to the search term, and obtain an original title of the item.
  • the server After receiving the search term, the server can search in the database to find the search result corresponding to the search term.
  • the server can obtain information of the product corresponding to the "down jacket", and the information of the product includes, for example, the original title of the product, the picture of the product, the product details, and the like.
  • the original title is "Antarctic men's new middle-aged men's thick fur collar down jacket men's jacket.”
  • the short title candidate set may be preset on the server side, and the short title candidate set includes a plurality of short titles.
  • the short title candidate set includes: “thickening fur collar down jacket”, “vibrant fleshy”, and the like.
  • a short title belonging to the short title candidate set is extracted from the original title. For example, since the original title includes a "thick hairy down jacket" belonging to the short title candidate set, the extracted short title is "thickening fur collar down jacket".
  • the original title can also be segmented, part of speech, etc., thereby facilitating short title extraction.
  • the acquired word segmentation is extracted from the short title, such as dividing the short title into "thickness” and "down jacket”.
  • word segmentation can also be extracted from data other than the product title.
  • the data other than the product title includes, for example, feature data of the product or feature data of the store to which the product belongs.
  • the feature data is, for example, a selling point, and the selling point refers to information that can be attracted to the user, describes the non-physical attribute of the product or the store, and is obtained through statistics.
  • the feature data of the product includes, for example, "super high praise rate”, “college student favorite”, “fat mm gospel”, and the like
  • the feature data of the store includes, for example, "gold medal seller", "6 year old shop", and the like.
  • S26 Carrying a hyperlink label on at least one participle, and combining the word segment with the hyperlink label and other word segments to obtain the processed product title.
  • the processed title is "thickened plush down jacket", where "thickness” refers to the participle after the hyperlink label is added.
  • Hyperlinks are HTML elements that are used more frequently in websites. By setting HTML elements, you can add hyperlinks to keywords to complete jumps between pages.
  • the server sends the processed search result to the guest.
  • the client displays the processed title on the search results page at the placement of the product title. For example, referring to Fig. 3, the processed article title 31 is shown, and the processed title is "thick plush down jacket".
  • a new search based on the search result can be initiated, and since the keyword is displayed on the product title, theoretically, an infinite participle can be displayed. So that you can expand the number of new search terms to better meet user needs.
  • the keyword is added to the product title, which is convenient for the user to view.
  • a new search can be initiated by a user clicking on a word segment with a hyperlink tag to speed up the search. By extracting the word segmentation from the feature data of the product or the feature data of the store, the user can be guided to initiate a search for a search term that would not have been previously searched.
  • FIG. 4 is a schematic structural diagram of an information search apparatus according to another embodiment of the present application.
  • the system 40 includes:
  • the receiving module 41 is configured to receive a search term input by the user
  • the user may input a search term on the client, and after receiving the search term input by the user, the client may send the search term to the server.
  • search words input by the user to the client are not limited to input by the input method, but may also be input after clicking the selected search word in the navigation, drop-down box, etc., or may be a search term of voice input, of course, understandable If the voice input is used, the server can perform voice recognition to convert the text after receiving the voice data, and then search for the corresponding search result in the database.
  • the first obtaining module 42 is configured to obtain a search result according to the search term
  • the server After receiving the search term, the server can search in the database to find the search result corresponding to the search term.
  • the server can obtain information of the product corresponding to the "down jacket", and the information of the product includes, for example, the original title of the product, the picture of the product, the product details, and the like.
  • a second obtaining module 43 configured to acquire description information of the search result
  • the search result when used for the product search, includes: information of the commodity corresponding to the search term, and the description information of the search result includes one or more of the following items:
  • the feature data of the store to which the item belongs is the feature data of the store to which the item belongs.
  • An extracting module 44 configured to extract one or more word segments from the description information
  • the server may segment and identify the title of the search result, extract one or more word segments from it, or extract the word segmentation from the remaining description information other than the title.
  • the title of the article includes, for example, an original title, or a short title obtained by reducing the original title.
  • an original title For example, when the user searches for "down jacket”, the original title of a search result (product) is "Antarctic new middle-aged men's thick fur collar down jacket men's jacket", then keywords can be extracted from this original title. or,
  • the original title can be converted first to get a short title, and the short title is to retain the key information in the original title to reduce the length of the original title.
  • the short title candidate set may be pre-configured, and the short title candidate set includes a plurality of short titles, and then the short title belonging to the short title candidate set is extracted from the original title.
  • the short title candidate set includes: “thickening fur collar down jacket", "vibrant fleshy”, etc., since the original title includes a "thick hairy down jacket" belonging to the short title candidate set, the extracted short title is "Thick hair fur collar down jacket.”
  • the keyword can also be extracted from the short title.
  • the data other than the product title includes, for example, feature data of the product or feature data of the store to which the product belongs.
  • the feature data is, for example, a selling point, and the selling point refers to information that can be attracted to the user, describes the non-physical attribute of the product or the store, and is obtained through statistics.
  • the feature data of the product includes, for example, "super high praise rate”, “college student favorite”, “fat mm gospel”, and the like
  • the feature data of the store includes, for example, "gold medal seller", "6 year old shop”, and the like. After that, keywords can be extracted from data other than these titles.
  • the title of the product includes: an original title of the product, and the extracting module 43 is specifically configured to:
  • the short title is divided into one or more word segments.
  • the extracting module 44 is configured to reduce the length of the original title into a short title, including:
  • a short title belonging to the short title candidate set is extracted in the original title.
  • a generating module 45 configured to combine the one or more word segments to generate a title of the search result, where at least one word segment carries a hyperlink tag;
  • the search results include the original title, such as the original title is "Antarctic new middle-aged men plus Thick fur collar down jacket men's jacket, in which you can extract the wording "thickness”, “hair collar”, “down jacket”, assuming that the participle carrying the hyperlink label is "thickening”, you can get the title of the search result is “Thickening plush down jacket”, where “thickening” refers to the participle after adding a hyperlink.
  • Hyperlinks are HTML elements that are used more frequently in websites. By setting HTML elements, you can add hyperlinks to keywords to complete A jump between pages.
  • the sending module 46 is configured to return the title of the word segmentation carrying the hyperlink tag to the user terminal for display.
  • the server sends the combined title to the client, and the client displays the processed title on the search result page, such as "thickening plush down jacket” on the display position of the product title.
  • the apparatus 40 further includes:
  • a determining module 47 configured to receive selection information of a user's participle carrying a hyperlink label, and determine a word segment selected by the user;
  • An update module 48 configured to combine the search term with a word segment selected by a user to generate a new search term
  • the new search term is "thickness + down jacket.”
  • the searching module 49 is configured to perform information search according to the new search term and return the search result to the client.
  • search for the search result corresponding to "thickness + down jacket” and return it to the client for display.
  • a new search based on the search result may be initiated, which is convenient for the user to initiate the search, and
  • the word segmentation is used as a title, in theory, it can display unlimited word segmentation, which can expand the number of new search words and better meet user needs.
  • Any process or method description in the flowcharts or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a particular logical function or process.
  • the scope of the preferred embodiments of the present application includes additional implementations, in which the functions may be performed in a substantially simultaneous manner or in the reverse order depending on the functions involved, in accordance with the illustrated or discussed order. a person skilled in the art to which the embodiment of the present application pertains The staff understands.
  • portions of the application can 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 application 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)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Computational Linguistics (AREA)
  • Library & Information Science (AREA)
  • Artificial Intelligence (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

本申请提出一种信息搜索方法和装置，该信息搜索方法包括：接收用户输入的搜索词；根据所述搜索词获取搜索结果；获取所述搜索结果的描述信息；从所述描述信息抽取一个或多个分词；将所述一个或多个分词进行组合，生成所述搜索结果的标题，至少一个分词分别携带超链接标签；将携带超链接标签的分词组合后的标题返回给用户端显示。该方法能够方便用户发起搜索，且可供用户选择的搜索词数量较大。

Description

信息搜索方法和装置 技术领域
本申请涉及互联网技术领域，尤其涉及一种信息搜索方法和装置。
背景技术
用户在信息搜索时，可以采用输入法输入搜索词，触发搜索。但是，当用户在移动终端上的应用程序内进行搜索时，如果采用输入法输入，由于移动终端的尺寸比较小，用户采用输入法进行搜索词的输入并不方便。为了提升用户输入搜索词的便利性，可以在输入框的下拉区域、页面的导航区域显示可供用户选择的搜索词。
但是，这种方式显示的可供选择的搜索词通常能够显示的数量是有限的。
发明内容
本申请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，本申请的一个目的在于提出一种信息搜索方法，该方法可以方便用户发起搜索，且可供用户选择的搜索词数量较大。
本申请的另一个目的在于提出一种信息搜索装置。
为达到上述目的，本申请第一方面实施例提出的信息搜索方法，包括：接收用户输入的搜索词；根据所述搜索词获取搜索结果；获取所述搜索结果的描述信息；从所述描述信息抽取一个或多个分词；将所述一个或多个分词进行组合，生成所述搜索结果的标题，至少一个分词分别携带超链接标签；将携带超链接标签的分词组合后的标题返回给用户端显示。
本申请第一方面实施例提出的信息搜索方法，通过从搜索结果的描述信息中抽取一个或多个分词，并在至少一个分词中携带超链接标签，可以发起基于搜索结果的新的搜索，方便用户发起搜索，并且由于组合后的分词是作为标题，理论上可以展示无限的分词，从而可以扩大新的搜索词的数量，更好的满足用户需求。
为达到上述目的，本申请第二方面实施例提出的信息搜索装置，包括：接收模块，用于接收用户输入的搜索词；第一获取模块，用于根据所述搜索词获取搜索结果；第二获取模块，用于获取所述搜索结果的描述信息；抽取模块， 用于从所述描述信息抽取一个或多个分词；生成模块，用于将所述一个或多个分词进行组合，生成所述搜索结果的标题，至少一个分词分别携带超链接标签；发送模块，用于将携带超链接标签的分词组合后的标题返回给用户端显示。
本申请第二方面实施例提出的信息搜索系统，通过从搜索结果的描述信息中抽取一个或多个分词，并在至少一个分词中携带超链接标签，可以发起基于搜索结果的新的搜索，方便用户发起搜索，并且由于组合后的分词是作为标题，理论上可以展示无限的分词，从而可以扩大新的搜索词的数量，更好的满足用户需求。
本申请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，或通过本申请的实践了解到。
附图说明
本申请上述的和/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1a是本申请一实施例提出的信息搜索方法的流程示意图；
图1b是本申请一实施例提出的信息搜索方法的流程示意图；
图2是本申请另一实施例提出的信息搜索方法的流程示意图；
图3是本申请实施例中展示的搜索结果的示意图；
图4是本申请另一实施例提出的信息搜索装置的结构示意图；
图5是本申请另一实施例提出的信息搜索装置的结构示意图。
具体实施方式
下面详细描述本申请的实施例，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，仅用于解释本申请，而不能理解为对本申请的限制。相反，本申请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1a是本申请一实施例提出的信息搜索方法的流程示意图，该方法包括：
S11：接收用户输入的搜索词。
例如，用户可以在客户端输入搜索词，客户端接收到用户输入的搜索词后，可以将该搜索词发送给服务端。
另外，用户输入到客户端的搜索词不限于采用输入法输入，还可以是在导航、下拉框等区域点击选择的搜索词后输入的，或者，还可以是语音输入的搜索词，当然，可以理解的是，如果是采用语音输入，则服务端在接收到语音数据后可以先进行语音识别将其转换文字，再在数据库中查找相应的搜索结果。
S12：根据所述搜索词获取搜索结果。
服务端接收到搜索词后，可以在数据库中进行查找，查找与搜索词对应的搜索结果。
以商品搜索为例，假设搜索词是“羽绒服”，则服务端可以获取与“羽绒服”对应的商品的信息，商品的信息例如包括：商品的原始标题，商品的图片、商品详情等。
S13：获取所述搜索结果的描述信息。
所述描述信息可以是搜索结果的标题或详情描述等。
S14：从所述描述信息抽取一个或多个分词。
例如，服务端可以对搜索结果的标题进行分词和标识，并从中抽取一个或多个分词，或者，从标题之外的其余描述信息中抽取分词。
商品标题例如包括：原始标题、或者对原始标题进行缩减后得到的短标题。例如，用户在搜索“羽绒服”时，得到的一个搜索结果(商品)的原始标题是“南极人新款中年男士加厚毛领羽绒服男外套”，则可以从这个原始标题中提取关键词。或者，
可以先对原始标题进行转换，得到短标题，短标题是指保留原始标题中的关键信息，以缩减原始标题的长度。例如，可以预先配置短标题候选集，短标题候选集中包括多个短标题，之后，从原始标题中提取出属于短标题候选集的短标题。例如，短标题候选集中包括：“加厚毛领羽绒服”、“生机勃勃的多肉”等，由于原始标题中包括属于短标题候选集的“加厚毛领羽绒服”，则提取出的短标题是“加厚毛领羽绒服”。在获取短标题后，关键词也可以是从短标题中提取的。
商品标题之外的数据例如包括：商品的特征数据，或者，商品所属的店铺的特征数据。特征数据例如具体是卖点，卖点是指能够吸引用户、描述商品或店铺的非物理属性，通过统计获得的信息。商品的特征数据例如包括：“超高好评率”、“大学生最爱”、“胖mm福音”等，店铺的特征数据例如包括：“金牌卖家”、“6年老店”等。之后，可以从这些标题之外的数据中提取出关键词。
S15：将所述一个或多个分词进行组合，生成所述搜索结果的标题，至少 一个分词分别携带超链接标签。
例如，搜索结果中包括原始标题，如原始标题是“南极人新款中年男士加厚毛领羽绒服男外套”，在可以从中提取出“加厚”、“毛领”、“羽绒服”这些分词，假设携带超链接标签的分词是“加厚”，则可以得到搜索结果的标题是“加厚毛绒羽绒服”，其中的“加厚”是指加入超链接后的分词。超链接是网站中使用比较频繁的HTML元素，通过设置HTML元素可以在关键词上增加超链接，从而完成页面之间的跳转。
S16：将携带超链接标签的分词组合后的标题返回给用户端显示。
例如，服务端将组合后的标题发送给客户端，客户端在搜索结果页上，在商品标题的展示位置展示处理后的标题，如“加厚毛绒羽绒服”。
一些实施例中，参见图1b，该方法还可以包括：
S17：接收用户对携带超链接标签的分词的选择信息，确定用户选择的分词；
例如，向用户展示“加厚毛绒羽绒服”后，假设用户点击了“加厚”，则确定选择的分词是“加厚”。
S18：将所述搜索词与用户选择的分词进行组合，生成新的搜索词。
例如，新的搜索词是“加厚+羽绒服”。
S19：根据新的搜索词进行信息的搜索，并将搜索结果返回至用户端。
例如，搜索“加厚+羽绒服”对应的搜索结果，并返回给用户端进行展示。
本实施例中，通过从搜索结果的描述信息中抽取一个或多个分词，并在至少一个分词中携带超链接标签，可以发起基于搜索结果的新的搜索，方便用户发起搜索，并且由于组合后的分词是作为标题，理论上可以展示无限的分词，从而可以扩大新的搜索词的数量，更好的满足用户需求。
图2是本申请另一实施例提出的信息搜索方法的流程示意图，本实施例以商品搜索为例。该方法包括：
S21：接收用户输入的搜索词。
例如，用户可以在客户端输入搜索词，客户端接收到用户输入的搜索词后，可以将该搜索词发送给服务端。
用户输入到客户端的搜索词不限于采用输入法输入，还可以是在导航、下拉框等区域点击选择的搜索词后输入的，或者，还可以是语音输入的搜索词，当然，可以理解的是，如果是采用语音输入，则服务端在接收到语音数据后可以先进行语音识别将其转换文字，再在数据库中查找相应的搜索结果。
S22：根据所述搜索词获取对应的商品，并获取商品的原始标题。
服务端接收到搜索词后，可以在数据库中进行查找，查找与搜索词对应的搜索结果。
以商品搜索为例，假设搜索词是“羽绒服”，则服务端可以获取与“羽绒服”对应的商品的信息，商品的信息例如包括：商品的原始标题，商品的图片、商品详情等。
例如，原始标题是“南极人新款中年男士加厚毛领羽绒服男外套”。
S23：获取预设的短标题候选集。
其中，可以在服务端上预设短标题候选集，短标题候选集内包括多个短标题，例如，短标题候选集中包括：“加厚毛领羽绒服”、“生机勃勃的多肉”等。
S24：从原始标题中提取出短标题。
从原始标题中提取出属于短标题候选集的短标题。例如，由于原始标题中包括属于短标题候选集的“加厚毛领羽绒服”，则提取出的短标题是“加厚毛领羽绒服”。
另外，在原始标题中提取短标题之前，还可以对原始标题进行分词、词性标注等，从而方便短标题提取。
S25：将短标题分为一个或多个分词。
本实施例中，假设获取的分词是从短标题中提取的，如将短标题分为“加厚”和“羽绒服”。
可以理解的是，还可以从商品标题之外的数据中提取分词。商品标题之外的数据例如包括：商品的特征数据，或者，商品所属的店铺的特征数据。特征数据例如具体是卖点，卖点是指能够吸引用户、描述商品或店铺的非物理属性，通过统计获得的信息。商品的特征数据例如包括：“超高好评率”、“大学生最爱”、“胖mm福音”等，店铺的特征数据例如包括：“金牌卖家”、“6年老店”等。之后，可以从这些标题之外的数据中提取出关键词。
S26：在至少一个分词上携带超链接标签，并组合带有超链接标签的分词与其他分词，得到处理后的商品标题。
例如，处理后的标题是“加厚毛绒羽绒服”，其中的“加厚”是指加入超链接标签后的分词。超链接是网站中使用比较频繁的HTML元素，通过设置HTML元素可以在关键词上增加超链接，从而完成页面之间的跳转。
S27：展示处理后的商品标题。
例如，服务端在获取处理后的搜索结果后，将处理后的搜索结果发送给客 户端，客户端在搜索结果页上，在商品标题的展示位置展示处理后的标题。例如，参见图3，展示处理后的商品标题31，处理后的标题如“加厚毛绒羽绒服”。
S28：当用户点击处理后的商品标题中带有超链接标签的分词后，将上述搜索词和点击的分词作为新的搜索词，发起新的搜索。
例如，当用户点击“加厚”后，可以发起以“羽绒服加厚”作为新的搜索词的新的搜索，并展示与“羽绒服加厚”对应的搜索结果。
本实施例中，通过展示处理后的商品标题，其中包括带有超链接标签的分词，可以发起基于搜索结果的新的搜索，由于关键词是展示在商品标题上，理论上可以展示无限的分词，从而可以扩大新的搜索词的数量，更好的满足用户需求。本实施例将关键词加在商品标题上，可以方便用户查看到。通过用户点击带有超链接标签的分词就发起新的搜索，可以加快搜索速度。通过从商品的特征数据或店铺的特征数据中提取分词，可以引导用户发起对之前本不会搜索的搜索词的搜索。
图4是本申请另一实施例提出的信息搜索装置的结构示意图，该系统40包括：
接收模块41，用于接收用户输入的搜索词；
例如，用户可以在客户端输入搜索词，客户端接收到用户输入的搜索词后，可以将该搜索词发送给服务端。
另外，用户输入到客户端的搜索词不限于采用输入法输入，还可以是在导航、下拉框等区域点击选择的搜索词后输入的，或者，还可以是语音输入的搜索词，当然，可以理解的是，如果是采用语音输入，则服务端在接收到语音数据后可以先进行语音识别将其转换文字，再在数据库中查找相应的搜索结果。
第一获取模块42，用于根据所述搜索词获取搜索结果；
服务端接收到搜索词后，可以在数据库中进行查找，查找与搜索词对应的搜索结果。
以商品搜索为例，假设搜索词是“羽绒服”，则服务端可以获取与“羽绒服”对应的商品的信息，商品的信息例如包括：商品的原始标题，商品的图片、商品详情等。
第二获取模块43，用于获取所述搜索结果的描述信息；
可选的，当用于商品搜索时，所述搜索结果包括：与所述搜索词对应的商品的信息，所述搜索结果的描述信息包括如下项中的一项或多项：
所述商品的标题；
所述商品的特征数据；
所述商品所属的店铺的特征数据。
抽取模块44，用于从所述描述信息抽取一个或多个分词；
例如，服务端可以对搜索结果的标题进行分词和标识，并从中抽取一个或多个分词，或者，从标题之外的其余描述信息中抽取分词。
商品标题例如包括：原始标题、或者对原始标题进行缩减后得到的短标题。例如，用户在搜索“羽绒服”时，得到的一个搜索结果(商品)的原始标题是“南极人新款中年男士加厚毛领羽绒服男外套”，则可以从这个原始标题中提取关键词。或者，
可以先对原始标题进行转换，得到短标题，短标题是指保留原始标题中的关键信息，以缩减原始标题的长度。例如，可以预先配置短标题候选集，短标题候选集中包括多个短标题，之后，从原始标题中提取出属于短标题候选集的短标题。例如，短标题候选集中包括：“加厚毛领羽绒服”、“生机勃勃的多肉”等，由于原始标题中包括属于短标题候选集的“加厚毛领羽绒服”，则提取出的短标题是“加厚毛领羽绒服”。在获取短标题后，关键词也可以是从短标题中提取的。
商品标题之外的数据例如包括：商品的特征数据，或者，商品所属的店铺的特征数据。特征数据例如具体是卖点，卖点是指能够吸引用户、描述商品或店铺的非物理属性，通过统计获得的信息。商品的特征数据例如包括：“超高好评率”、“大学生最爱”、“胖mm福音”等，店铺的特征数据例如包括：“金牌卖家”、“6年老店”等。之后，可以从这些标题之外的数据中提取出关键词。
可选的，所述商品的标题包括：所述商品的原始标题，所述抽取模块43具体用于：
对所述商品的原始标题进行长度缩减，转换为短标题；
将所述短标题分为一个或多个分词。
可选的，所述抽取模块44用于对所述原始标题进行长度缩减，转换为短标题，包括：
获取预设的短标题候选集，所述短标题候选集中包括多个短标题；
在所述原始标题中提取出属于所述短标题候选集的短标题。
生成模块45，用于将所述一个或多个分词进行组合，生成所述搜索结果的标题，至少一个分词分别携带超链接标签；
例如，搜索结果中包括原始标题，如原始标题是“南极人新款中年男士加 厚毛领羽绒服男外套”，在可以从中提取出“加厚”、“毛领”、“羽绒服”这些分词，假设携带超链接标签的分词是“加厚”，则可以得到搜索结果的标题是“加厚毛绒羽绒服”，其中的“加厚”是指加入超链接后的分词。超链接是网站中使用比较频繁的HTML元素，通过设置HTML元素可以在关键词上增加超链接，从而完成页面之间的跳转。
发送模块46，用于将携带超链接标签的分词组合后的标题返回给用户端显示。
例如，服务端将组合后的标题发送给客户端，客户端在搜索结果页上，在商品标题的展示位置展示处理后的标题，如“加厚毛绒羽绒服”。
一些实施例中，参见图5，该装置40还包括：
确定模块47，用于接收用户对携带超链接标签的分词的选择信息，确定用户选择的分词；
例如，向用户展示“加厚毛绒羽绒服”后，假设用户点击了“加厚”，则确定选择的分词是“加厚”。
更新模块48，用于将所述搜索词与用户选择的分词进行组合，生成新的搜索词；
例如，新的搜索词是“加厚+羽绒服”。
搜索模块49，用于根据新的搜索词进行信息的搜索，并将搜索结果返回至用户端。
例如，搜索“加厚+羽绒服”对应的搜索结果，并返回给用户端进行展示。
本实施例中，通过从搜索结果的描述信息中抽取一个或多个分词，并在至少一个分词中携带超链接标签，可以发起基于搜索结果的新的搜索，方便用户发起搜索，并且由于组合后的分词是作为标题，理论上可以展示无限的分词，从而可以扩大新的搜索词的数量，更好的满足用户需求。
需要说明的是，在本申请的描述中，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，在本申请的描述中，除非另有说明，“多个”的含义是指至少两个。
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，并且本申请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，这应被本申请的实施例所属技术领域的技术人 员所理解。
应当理解，本申请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，在本申请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申请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申请的实施例，可以理解的是，上述实施例是示例性的，不能理解为对本申请的限制，本领域的普通技术人员在本申请的范围内可以对上述实施例进行变化、修改、替换和变型。

Claims (10)

  1. 一种信息搜索方法，其特征在于，包括：
    接收用户输入的搜索词；
    根据所述搜索词获取搜索结果；
    获取所述搜索结果的描述信息；
    从所述描述信息抽取一个或多个分词；
    将所述一个或多个分词进行组合，生成所述搜索结果的标题，至少一个分词携带超链接标签；
    将携带超链接标签的分词组合后的标题返回给用户端显示。
  2. 根据权利要求1所述的方法，其特征在于，还包括：
    接收用户对携带超链接标签的分词的选择信息，确定用户选择的分词；
    将所述搜索词与用户选择的分词进行组合，生成新的搜索词；
    根据新的搜索词进行信息的搜索，并将搜索结果返回至用户端。
  3. 根据权利要求1所述的方法，其特征在于，当用于商品搜索时，所述搜索结果包括：与所述搜索词对应的商品的信息，所述搜索结果的描述信息包括如下项中的一项或多项：
    所述商品的标题；
    所述商品的特征数据；
    所述商品所属的店铺的特征数据。
  4. 根据权利要求3所述的方法，其特征在于，所述商品的标题包括：所述商品的原始标题，所述从所述描述信息抽取一个或多个分词，包括：
    对所述商品的原始标题进行长度缩减，转换为短标题；
    将所述短标题分为一个或多个分词。
  5. 根据权利要求4所述的方法，其特征在于，所述对所述原始标题进行长度缩减，转换为短标题，包括：
    获取预设的短标题候选集，所述短标题候选集中包括多个短标题；
    在所述原始标题中提取出属于所述短标题候选集的短标题。
  6. 一种信息搜索装置，其特征在于，包括：
    接收模块，用于接收用户输入的搜索词；
    第一获取模块，用于根据所述搜索词获取搜索结果；
    第二获取模块，用于获取所述搜索结果的描述信息；
    抽取模块，用于从所述描述信息抽取一个或多个分词；
    生成模块，用于将所述一个或多个分词进行组合，生成所述搜索结果的标题，至少一个分词分别携带超链接标签；
    发送模块，用于将携带超链接标签的分词组合后的标题返回给用户端显示。
  7. 根据权利要求6所述的装置，其特征在于，还包括：
    确定模块，用于接收用户对携带超链接标签的分词的选择信息，确定用户选择的分词；
    更新模块，用于将所述搜索词与用户选择的分词进行组合，生成新的搜索词；
    搜索模块，用于根据新的搜索词进行信息的搜索，并将搜索结果返回至用户端。
  8. 根据权利要求6所述的装置，其特征在于，当用于商品搜索时，所述搜索结果包括：与所述搜索词对应的商品的信息，所述搜索结果的描述信息包括如下项中的一项或多项：
    所述商品的标题；
    所述商品的特征数据；
    所述商品所属的店铺的特征数据。
  9. 根据权利要求8所述的装置，其特征在于，所述商品的标题包括：所述商品的原始标题，所述抽取模块具体用于：
    对所述商品的原始标题进行长度缩减，转换为短标题；
    将所述短标题分为一个或多个分词。
  10. 根据权利要求9所述的装置，其特征在于，所述抽取模块用于对所述原始标题进行长度缩减，转换为短标题，包括：
    获取预设的短标题候选集，所述短标题候选集中包括多个短标题；
    在所述原始标题中提取出属于所述短标题候选集的短标题。
PCT/CN2016/098817 2015-09-22 2016-09-13 信息搜索方法和装置 WO2017050149A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
EP16848031.7A EP3355204A4 (en) 2015-09-22 2016-09-13 METHOD AND DEVICE FOR INFORMATION SEARCH
JP2018515095A JP2018533136A (ja) 2015-09-22 2016-09-13 情報検索方法及び装置
US15/927,999 US20180210961A1 (en) 2015-09-22 2018-03-21 Information search method and apparatus

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510609758.X 2015-09-22
CN201510609758.XA CN106547794B (zh) 2015-09-22 2015-09-22 信息搜索方法和装置

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US15/927,999 Continuation US20180210961A1 (en) 2015-09-22 2018-03-21 Information search method and apparatus

Publications (1)

Publication Number Publication Date
WO2017050149A1 true WO2017050149A1 (zh) 2017-03-30

Family

ID=58364446

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/098817 WO2017050149A1 (zh) 2015-09-22 2016-09-13 信息搜索方法和装置

Country Status (5)

Country Link
US (1) US20180210961A1 (zh)
EP (1) EP3355204A4 (zh)
JP (1) JP2018533136A (zh)
CN (1) CN106547794B (zh)
WO (1) WO2017050149A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109902152A (zh) * 2019-03-21 2019-06-18 北京百度网讯科技有限公司 用于检索信息的方法和装置
CN110096501A (zh) * 2018-09-04 2019-08-06 中国平安人寿保险股份有限公司 基于标签的数据搜索方法、装置、介质及电子设备

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108228907B (zh) * 2018-02-08 2021-04-23 北京三快在线科技有限公司 一种推荐信息的方法、装置、电子设备及存储介质
CN110781365B (zh) * 2018-07-13 2023-04-28 阿里巴巴集团控股有限公司 商品搜索方法、装置、系统及电子设备
CN109543113B (zh) * 2018-12-21 2022-02-01 北京字节跳动网络技术有限公司 确定点击推荐词的方法、装置、存储介质及电子设备
CN113139849A (zh) * 2021-04-26 2021-07-20 北京沃东天骏信息技术有限公司 一种商品搜索方法和装置
CN115033799B (zh) * 2022-07-04 2023-01-17 郑州易赛诺信息技术有限公司 一种商品搜索方法、系统及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1808426A (zh) * 2005-01-17 2006-07-26 马岩 一种通用的文件搜索系统及方法
CN101137983A (zh) * 2005-01-10 2008-03-05 梅林格有限公司 嵌入式翻译增强的搜索
CN104317929A (zh) * 2014-10-31 2015-01-28 北京奇虎科技有限公司 搜索结果呈现优化方法和装置
CN104331472A (zh) * 2014-11-03 2015-02-04 百度在线网络技术（北京）有限公司 分词训练数据的构造方法和装置

Family Cites Families (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2003075186A1 (en) * 2002-03-01 2003-09-12 Paul Jeffrey Krupin A method and system for creating improved search queries
US8856163B2 (en) * 2003-07-28 2014-10-07 Google Inc. System and method for providing a user interface with search query broadening
CN1779627A (zh) * 2004-11-19 2006-05-31 张逶 网络关键词搜索结果顶屏、显示屏、密集文字链按钮显示
US20060143080A1 (en) * 2004-12-29 2006-06-29 Ashutosh Garg Generating and/or serving dynamic promotional offers such as coupons and advertisements
WO2009019858A1 (ja) * 2007-08-08 2009-02-12 Panasonic Corporation 番組検索支援装置およびその方法
WO2009040574A1 (en) * 2007-09-24 2009-04-02 Taptu Ltd Search results with search query suggestions
JP2010146366A (ja) * 2008-12-19 2010-07-01 Toshiba Corp 情報提供サーバ
JP4876164B2 (ja) * 2009-12-28 2012-02-15 楽天株式会社 情報検索装置、件数決定方法、情報検索プログラム及び情報検索システム
JP5084858B2 (ja) * 2010-03-16 2012-11-28 ヤフー株式会社 サマリ作成装置、サマリ作成方法及びプログラム
US20150161217A1 (en) * 2010-04-26 2015-06-11 Google Inc. Related images
US8635107B2 (en) * 2011-06-03 2014-01-21 Adobe Systems Incorporated Automatic expansion of an advertisement offer inventory
US9256680B2 (en) * 2012-02-02 2016-02-09 Microsoft Technology Licensing, Llc Biasing search results toward topics of interest using embedded relevance links
CN103810198B (zh) * 2012-11-09 2017-03-01 阿里巴巴集团控股有限公司 一种商品信息的搜索方法及装置
CN104216918B (zh) * 2013-06-04 2019-02-01 腾讯科技（深圳）有限公司 关键词搜索方法和系统
CN103577595B (zh) * 2013-11-15 2017-09-22 北京奇虎科技有限公司 基于当前浏览页面的关键词推送方法及装置
CN104537057B (zh) * 2014-12-26 2016-06-29 奇飞翔艺（北京）软件有限公司 数据搜索方法及客户端
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
CN105574174B (zh) * 2015-12-18 2019-11-26 北京奇虎科技有限公司 基于搜索提示的搜索方法及装置
CN105528446A (zh) * 2015-12-23 2016-04-27 北京奇虎科技有限公司 满足延伸产品需求的摘要生成方法及装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101137983A (zh) * 2005-01-10 2008-03-05 梅林格有限公司 嵌入式翻译增强的搜索
CN1808426A (zh) * 2005-01-17 2006-07-26 马岩 一种通用的文件搜索系统及方法
CN104317929A (zh) * 2014-10-31 2015-01-28 北京奇虎科技有限公司 搜索结果呈现优化方法和装置
CN104331472A (zh) * 2014-11-03 2015-02-04 百度在线网络技术（北京）有限公司 分词训练数据的构造方法和装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3355204A4 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110096501A (zh) * 2018-09-04 2019-08-06 中国平安人寿保险股份有限公司 基于标签的数据搜索方法、装置、介质及电子设备
CN109902152A (zh) * 2019-03-21 2019-06-18 北京百度网讯科技有限公司 用于检索信息的方法和装置
CN109902152B (zh) * 2019-03-21 2021-07-06 北京百度网讯科技有限公司 用于检索信息的方法和装置

Also Published As

Publication number Publication date
US20180210961A1 (en) 2018-07-26
JP2018533136A (ja) 2018-11-08
CN106547794B (zh) 2020-04-14
EP3355204A1 (en) 2018-08-01
CN106547794A (zh) 2017-03-29
EP3355204A4 (en) 2019-03-06

Similar Documents

Publication Publication Date Title
WO2017050149A1 (zh) 信息搜索方法和装置
JP5857124B2 (ja) 画像解析装置、画像解析システム、画像解析方法
KR101511050B1 (ko) 상품 정보를 제공하고 표시하는 방법, 장치, 시스템 및 컴퓨터 프로그램
AU2009337678B2 (en) Visualizing site structure and enabling site navigation for a search result or linked page
CN103514299B (zh) 信息搜索方法和装置
US10592565B2 (en) Method and apparatus for providing recommended information
WO2016091114A1 (zh) 一种信息推送方法和装置
JP2015191655A (ja) 推奨ページを生成するための方法及び装置
US9324102B2 (en) System and method to retrieve relevant inventory using sketch-based query
WO2016090960A1 (zh) 搜索建议的展示方法和装置
US11100169B2 (en) Alternative query suggestion in electronic searching
CN108255999A (zh) 内容推荐方法及装置
WO2016127568A1 (zh) 搜索推荐方法和装置
WO2016107125A1 (zh) 信息搜索方法及装置
US20230177087A1 (en) Dynamic content delivery search system
CN104778273A (zh) 一种用于购物网站的大数据分析系统
JP2018504686A (ja) 検索データを処理するための方法及び装置
US10643142B2 (en) Search term prediction
KR102150572B1 (ko) 무한 검색 결과 페이지
AU2022429021A1 (en) Video generating method and apparatus, electronic device, and readable storage medium
TW201828111A (zh) 資訊搜索方法和裝置
JP2016192067A (ja) 検索装置
KR20170083171A (ko) 학술정보 태그 클라우드를 위한 방법 및 시스템
US20160189219A1 (en) Simplified overlay ads

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: 16848031

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2018515095

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 2016848031

Country of ref document: EP