WO2016201869A1 - 搜索结果优化方法、搜索引擎、设备及非易失性计算机存储介质 - Google Patents

搜索结果优化方法、搜索引擎、设备及非易失性计算机存储介质 Download PDF

Info

Publication number
WO2016201869A1
WO2016201869A1 PCT/CN2015/094336 CN2015094336W WO2016201869A1 WO 2016201869 A1 WO2016201869 A1 WO 2016201869A1 CN 2015094336 W CN2015094336 W CN 2015094336W WO 2016201869 A1 WO2016201869 A1 WO 2016201869A1
Authority
WO
WIPO (PCT)
Prior art keywords
search
user
requirement
information
initial
Prior art date
Application number
PCT/CN2015/094336
Other languages
English (en)
French (fr)
Inventor
许笑天
姜岩
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 US15/523,929 priority Critical patent/US20170337286A1/en
Publication of WO2016201869A1 publication Critical patent/WO2016201869A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24Querying
    • G06F16/245Query processing
    • G06F16/2457Query processing with adaptation to user needs
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24Querying
    • G06F16/248Presentation of query results
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/53Querying
    • G06F16/532Query formulation, e.g. graphical querying
    • 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 disclosure relates to the field of Internet technologies, and in particular, to a search result optimization method, a search engine, a device, and a non-volatile computer storage medium.
  • search engines have become an important tool for people to obtain network information.
  • the user inputs search demand description information, such as a query or image, and the search engine returns search results to the user based on the search demand description information.
  • the search requirement description information input by the user may have multiple semantics or semantics, so the search engine's understanding of the user's search intention may be biased, resulting in lower accuracy of the returned search result.
  • aspects of the present disclosure provide a search result optimization method, a search engine, a device, and a non-volatile computer storage medium to improve the accuracy of search results.
  • a search result optimization method including:
  • a search engine including:
  • a first obtaining module configured to acquire a search requirement description information of the user
  • a second obtaining module configured to obtain an initial search result and search demand optimization information according to the search requirement description information
  • the optimization processing module is configured to perform optimization processing on the initial search result according to the search requirement optimization information selected by the user to obtain a final search result.
  • an apparatus comprising:
  • One or more processors are One or more processors;
  • One or more programs the one or more programs being stored in the memory, when executed by the one or more processors:
  • a non-volatile computer storage medium storing one or more programs when the one or more programs are provided When the sequence is executed by a device, the device is caused:
  • the disclosure does not directly provide the final search result according to the search requirement description information as in the prior art, but obtains the initial search result and the search according to the search requirement description information.
  • the demand optimization information is further optimized according to the search demand selected by the user, and the initial search result is optimized to obtain the final search result, and the search result optimization process by the user participation can improve the matching degree between the search result and the user search requirement, and improve The accuracy of the search results.
  • FIG. 1 is a schematic flowchart of a search result optimization method according to an embodiment of the present disclosure
  • FIG. 2 is a schematic diagram of search demand optimization information according to an embodiment of the present disclosure
  • FIG. 3 is a schematic diagram of another search requirement optimization information according to an embodiment of the present disclosure.
  • FIG. 4 is a schematic diagram of still another search requirement optimization information according to an embodiment of the present disclosure.
  • FIG. 5 is a schematic diagram of still another search requirement optimization information according to an embodiment of the present disclosure.
  • FIG. 6 is a schematic structural diagram of a search engine according to an embodiment of the present disclosure.
  • FIG. 7 is a schematic structural diagram of a search engine according to another embodiment of the present disclosure.
  • FIG. 1 is a schematic flowchart diagram of a search result optimization method according to an embodiment of the present disclosure. As shown in Figure 1, the method includes:
  • This embodiment provides a search result optimization method, which can be executed by a search engine for performing optimization processing of search results.
  • search requirement description information refers to information describing a user's search demand.
  • the search requirement description information may be an image, a keyword, or a combination of an image and a keyword.
  • the user's search requirement description information is obtained.
  • the user's search needs description information will have multiple semantics or understanding, and The user's search needs cannot be clearly expressed, which in turn leads to the search engine not being able to clearly determine the user's search needs based on the search requirement description information.
  • the user's search demand description information is an image, which is specifically a partial photo of a living room, and includes a plurality of objects in the photo, such as a television, a television cabinet, a wall, a wireless router, an electric socket, and the like.
  • the user's search requirements may be various, for example, the user's search needs may be to search for television, or search for a TV cabinet, or search for an interior design, or search for decoration. Or decorating, or searching for wireless routers and more.
  • the search engine cannot accurately determine the user's search needs, so the search engine may return search results related to the TV, but the actual user may want to search through the above image may be interior design, and the search results returned by the search engine may not match the user's search. Demand, resulting in lower accuracy of search results.
  • the search engine cannot determine the user. I want to search for mobile phones, fruits or songs, and I can't accurately understand the user's search needs. Since the current Apple mobile phone is popular and the search volume is large, the search engine provides the user with the search result related to the mobile phone according to the keyword “Apple” input by the user, but actually the user wants to know the variety information of the apple in the fruit, which is visible. Search results returned by search engines do not meet the user's search needs, resulting in lower accuracy of search results.
  • the search result optimization method provided in this embodiment can solve the above problem.
  • the principle of the method in this embodiment is specifically as follows:
  • the search engine After obtaining the search requirement description information of the user, the search engine does not directly give the final search result according to the user's search requirement description information as in the prior art, but according to the user's
  • the search requirement description information gives initial search results and search demand optimization information, and further optimizes the initial search results according to the search demand optimization information selected by the user to obtain a final search result.
  • the matching degree between the search result and the user search requirement can be improved, and the accuracy of the search result can be improved.
  • the search demand optimization information refers to information whose search requirement clarity is higher than the search requirement description information.
  • the search demand optimization information refers to information that can more clearly define the user's search requirements (ie, the search requirement is highly clear) compared to the search requirement description information.
  • the search demand optimization information is also information related to the search requirement description information, and may be, for example, information that further defines the search requirement description information on the attribute, or information that has similar or identical characteristics to the search requirement description information.
  • This embodiment does not limit the implementation form of the search requirement optimization information. Any information form that can more clearly define the user search requirement than the search requirement description information can be used as the search requirement optimization information of the embodiment, such as an image, a keyword, or an image. A combination with a keyword.
  • the foregoing manner of obtaining initial search results and searching for demand optimization information according to the search requirement description information includes:
  • the search demand optimization information is obtained.
  • the search engine identifies the search requirement description information, for example, may be semantic recognition or image recognition, and the like, and determines at least one search requirement that the search requirement description information can express; and determines an initial search requirement from the at least one search requirement.
  • the initial search needs can be Searching for at least one or all of the search requirements; searching according to initial search requirements to obtain initial search results, the initial search results are search results that match the initial search requirements; and, in addition, determining the search based on initial search requirements Demand optimization information to facilitate optimization of initial search results.
  • the embodiment determines the search demand optimization information according to the initial search requirement, and the search demand optimization information has higher definition of the user search requirement.
  • a way to determine search demand optimization information based on initial search requirements includes:
  • At least one of the description information of the remaining search requirements other than the initial search requirement and the description information of the sub-search requirements of the initial search requirement in the at least one search requirement is used as the search demand optimization information.
  • the search requirement description information cannot clearly indicate the user's search requirement
  • the search engine determines at least one search requirement based on the image, including: searching for a television, searching for television Cabinets, search interiors, search for decoration or decor, search for wireless routers, etc.
  • the search engine determines the search television in at least one of the search requirements as an initial search requirement, and searches based on the initial search demand to obtain a search result related to the television as an initial search result; at the same time, the search engine determines to act as The initial search requires searching for the rest of the search needs other than the TV, such as searching for TV cabinets, searching for interior design, searching for decoration or decorating, searching for descriptions of search requirements such as wireless routers, as search demand optimization information.
  • the above search demand optimization information may be an image, a keyword or a combination of an image and a keyword.
  • the description information may be an image including a television cabinet; a description letter for searching for the interior design of the search
  • the information can be the keyword "interior design”; for the search and decoration or decoration search needs, the description information can be an image and keyword "decoration / decoration” including television, TV cabinet, wall, wireless router and other objects.
  • the combination of the search requirements for the search wireless router, the description information may be the keyword "wireless router” and the like.
  • the search demand optimization information is information specifically describing an object or feature in the image, so as to refine the user's search requirement and make the user's search demand more clear. .
  • the search engine may also select the description information of the sub-search requirements of the initial search requirement as the search demand optimization information.
  • the sub-search requirement of the initial search requirement refers to a more explicit user search requirement, and the sub-search requirement has a clearer search requirement than the initial search requirement.
  • the sub-search requirement for searching for a television can be to search for a 64-inch television, or to search for a Haier television, or to search for a domestic television.
  • the search engine determines part of the search requirements from the at least one search requirement as the initial search requirement, the description information of the remaining search requirements is preferentially used as the search demand optimization information.
  • the search demand optimization information may be displayed to the user for the user to select the search demand optimization information used for optimization.
  • the search engine may present the search demand optimization information to the user through a separate window, or may display the search result optimization information in the upper half of the search result page, and the like.
  • the user can determine whether it is necessary to select the search demand optimization information to optimize the initial search result in combination with the initial search result.
  • the initial search result is "TV-related search results”
  • the user needs "interior design”, in which case the user needs to select the search requirements related to "interior design” Optimize the information and optimize the initial search results according to the selected search demand optimization information.
  • the user can issue a selection command to inform the search engine user of the search demand optimization information selected.
  • a search engine can design search demand optimization information into a control, and the user issues a selection instruction by clicking on the relevant search demand optimization information.
  • the search engine may set a selection control in front of the search requirement optimization information for the user to issue a selection instruction, for example, a check box, and the user selects an instruction by selecting a corresponding check box.
  • the user's selection instruction may be received, and the search demand optimization information selected by the user is determined according to the selection instruction.
  • the user may select one or more of the search demand optimization information.
  • the search engine may optimize the initial search result according to the search demand optimization information selected by the user to obtain the final search result.
  • an optimization process is: re-searching according to the search requirement optimization information selected by the user to obtain a final search result.
  • This optimization method re-searches for more and more accurate search results.
  • Another way to optimize the processing is to filter the initial search results according to the search demand optimization information selected by the user to obtain the final search result.
  • This optimization method directly filters from existing results and is more efficient in obtaining accurate search results.
  • the method for obtaining the search requirement description information of the user may be: acquiring the search demand optimization information in the last optimization operation selected by the user as the search requirement description information in the current optimization operation of the user.
  • This embodiment means that the user can perform multiple optimization operations repeatedly until the desired effect of the user is reached or the search cannot be further given.
  • the demand optimization information is reached or the set repetitive execution condition is reached.
  • the repeated execution condition may be a preset maximum number of repeated executions or a maximum search time allowed for the set single search.
  • the keyword belongs to the information in the form of text, and its meaning expression is relatively clear; and compared with the keyword, the number of objects in the image is large, and the meaning expression is relatively ambiguous, so the method provided by the embodiment is particularly applicable.
  • the search engine searches based on the image information, and outputs the initial search result and the search demand optimization information.
  • the search demand optimization information is a picture, or as shown in FIG. 3, the search demand optimization information is a keyword, and As shown in FIG. 2 or FIG.
  • the image or keyword as the search demand optimization information is located above the initial search result; if the user wants to optimize the search result, the corresponding search demand optimization information may be clicked, and the search result is optimized accordingly, and At the same time, new search demand optimization information will also be generated.
  • the new search demand optimization information is a picture, or as shown in FIG. 5, the new search demand optimization information is a keyword, and as shown in FIG. 4 or FIG. 5 As shown, the picture or keyword as the search demand optimization information is located above the optimized search result; this is repeated until the search result is automatically determined to be optimal and the operation ends.
  • the user can continue to participate after uploading the image information, continue to limit the search results in the form of pictures or keywords, and achieve the purpose of actively optimizing the search results, which can not only improve the final search results and the user's search requirements.
  • Matching degree improve the accuracy of the final search results, and also enhance the user's product participation and improve user experience.
  • FIG. 6 is a schematic structural diagram of a search engine according to an embodiment of the present disclosure. As shown in FIG. 6, the search engine includes a first obtaining module 61, a second obtaining module 62, and an optimization processing module 63.
  • the first obtaining module 61 is configured to acquire search requirement description information of the user.
  • the second obtaining module 62 is configured to obtain an initial search result and search demand optimization information according to the search requirement description information acquired by the first obtaining module 61.
  • the optimization processing module 63 is configured to perform optimization processing on the initial search result obtained by the second obtaining module 62 according to the search requirement optimization information selected by the user to obtain a final search result.
  • the second obtaining module 62 is specifically configured to:
  • the search demand optimization information is determined according to the initial search requirements.
  • the second acquisition module 62 determines the search requirement optimization information according to the initial search requirement
  • the second obtaining module 62 is specifically configured to:
  • At least one of the description information of the remaining search requirements other than the initial search requirement and the description information of the sub-search requirements of the initial search requirement in the at least one search requirement is used as the search demand optimization information.
  • the search engine further includes: a presentation module 64, a receiving module 65, and a determining module 66.
  • the presentation module 64 is configured to display the search requirement optimization information obtained by the second obtaining module 62 for the user to select.
  • the receiving module 65 is configured to receive a selection instruction of the user, where the selection instruction indicates the search requirement optimization information selected by the user.
  • the determining module 66 is configured to determine, according to the selection instruction received by the receiving module 65, the search demand optimization information selected by the user.
  • the optimization processing module 63 is specifically configured to:
  • the initial search results are filtered according to the search demand optimization information selected by the user to obtain the final search result.
  • the first obtaining module 61 is specifically configured to: obtain search requirement optimization information in a last optimization operation selected by the user, as the search requirement description information in the current optimization operation of the user.
  • the search requirement description information is an image, but is not limited thereto.
  • the search requirement description information may also be a keyword or a combination of a keyword and an image.
  • the search demand optimization information is at least one of an image and a keyword.
  • the search engine provided by the embodiment obtains the search requirement description information of the user
  • the final search result is not directly obtained according to the search requirement description information as in the prior art, but the initial search result and the search are obtained according to the search requirement description information.
  • the demand optimization information is further optimized according to the search demand selected by the user, and the initial search result is optimized to obtain the final search result, and the search result optimization process by the user participation can improve the matching degree between the search result and the user search requirement, and improve The accuracy of the search results.
  • the disclosed system, apparatus, and method may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • there may be another division manner for example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or may have two or more unit sets. In one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional units.
  • the above-described integrated unit implemented in the form of a software functional unit can be stored in a computer readable storage medium.
  • the above software functional unit is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor to perform the methods of the various embodiments of the present disclosure. Part of the steps.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like, which can store program codes. .

Landscapes

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

Abstract

本公开提供一种搜索结果优化方法、搜索引擎、设备及非易失性计算机存储介质。该优化方法包括:获取用户的搜索需求描述信息;根据所述搜索需求描述信息获得初始搜索结果以及搜索需求优化信息;根据所述用户选择的搜索需求优化信息,对所述初始搜索结果进行优化处理,以获得最终搜索结果。本公开可以提高搜索结果的准确度。

Description

搜索结果优化方法、搜索引擎、设备及非易失性计算机存储介质
本申请要求了申请日为2015年06月18日,申请号为201510340517.X发明名称为“搜索结果优化方法及搜索引擎”的中国专利申请的优先权。
技术领域
本公开涉及互联网技术领域,特别涉及一种搜索结果优化方法、搜索引擎、设备及非易失性计算机存储介质。
背景技术
随着互联网技术的不断发展以及信息的不断膨胀,人们对于网络信息的使用需求越来越高,搜索引擎成为人们获取网络信息的重要工具。用户输入搜索需求描述信息,例如关键字(query)或图像,搜索引擎根据搜索需求描述信息向用户返回搜索结果。
在现有技术中,用户输入的搜索需求描述信息可能存在多种语义或者语义比较宽泛,所以搜索引擎对用户搜索意图的理解可能会有偏差,导致返回的搜索结果的准确度较低。
发明内容
本公开的多个方面提供一种搜索结果优化方法、搜索引擎、设备及非易失性计算机存储介质,用以提高搜索结果的准确度。
本公开的一方面,提供一种搜索结果优化方法,包括:
获取用户的搜索需求描述信息;
根据所述搜索需求描述信息获得初始搜索结果以及搜索需求优化信息;
根据所述用户选择的搜索需求优化信息,对所述初始搜索结果进行优化处理,以获得最终搜索结果。
本公开的另一方面,提供一种搜索引擎,包括:
第一获取模块,用于获取用户的搜索需求描述信息;
第二获取模块,用于根据所述搜索需求描述信息获得初始搜索结果以及搜索需求优化信息;
优化处理模块,用于根据所述用户选择的搜索需求优化信息,对所述初始搜索结果进行优化处理,以获得最终搜索结果。
本公开的另一方面,提供一种设备,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:
获取用户的搜索需求描述信息;
根据所述搜索需求描述信息获得初始搜索结果以及搜索需求优化信息;
根据所述用户选择的搜索需求优化信息,对所述初始搜索结果进行优化处理,以获得最终搜索结果。
本公开的另一方面,提供一种非易失性计算机存储介质,所述非易失性计算机存储介质存储有一个或者多个程序,当所述一个或者多个程 序被一个设备执行时,使得所述设备:
获取用户的搜索需求描述信息;
根据所述搜索需求描述信息获得初始搜索结果以及搜索需求优化信息;
根据所述用户选择的搜索需求优化信息,对所述初始搜索结果进行优化处理,以获得最终搜索结果。
由上述技术方案可知,本公开获取用户的搜索需求描述信息之后,并不是像现有技术那样直接根据搜索需求描述信息给出最终搜索结果,而是根据该搜索需求描述信息获得初始搜索结果以及搜索需求优化信息,进一步根据用户选择的搜索需求优化信息,对初始搜索结果进行优化处理,以获得最终搜索结果,通过用户参与的搜索结果优化处理,能够提高搜索结果与用户搜索需求的匹配度,提高搜索结果的准确度。
附图说明
为了更清楚地说明本公开实施例中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍,显而易见地,下面描述中的附图是本公开的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。
图1为本公开一实施例提供的搜索结果优化方法的流程示意图;
图2为本公开一实施例提供的一种搜索需求优化信息的示意图;
图3为本公开一实施例提供的另一种搜索需求优化信息的示意图;
图4为本公开一实施例提供的又一种搜索需求优化信息的示意图;
图5为本公开一实施例提供的又一种搜索需求优化信息的示意图;
图6为本公开一实施例提供的搜索引擎的结构示意图;
图7为本公开另一实施例提供的搜索引擎的结构示意图。
具体实施方式
为使本公开实施例的目的、技术方案和优点更加清楚,下面将结合本公开实施例中的附图,对本公开实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例是本公开一部分实施例,而不是全部的实施例。基于本公开中的实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例,都属于本公开保护的范围。
图1为本公开一实施例提供的搜索结果优化方法的流程示意图。如图1所示,该方法包括:
101、获取用户的搜索需求描述信息。
102、根据上述搜索需求描述信息获得初始搜索结果以及搜索需求优化信息。
103、根据用户选择的搜索需求优化信息,对初始搜索结果进行优化处理,以获得最终搜索结果。
本实施例提供一种搜索结果优化方法,可由搜索引擎来执行,用以进行搜索结果的优化处理。
在实际搜索应用中,当用户需要进行搜索时,一般会输入搜索需求描述信息,搜索需求描述信息是指描述用户搜索需求的信息。在本实施例中,搜索需求描述信息可以是图像、关键字或者图像与关键字的组合。对搜索引擎来说,获取用户的搜索需求描述信息。
在一些情况下,用户的搜索需求描述信息会有多种语义或理解,并 不能很明确的表达用户的搜索需求,进而导致搜索引擎无法根据搜索需求描述信息明确确定用户的搜索需求。
举例说明,假设用户的搜索需求描述信息为一图像,该图像具体为一客厅局部照片,在该照片中包括多个对象,例如电视机、电视柜、背景墙、无线路由器、电插座等等。对于这种同时包括多个对象的图像,其所表达的用户的搜索需求可能有多种,例如用户的搜索需求可以是搜索电视,或者是搜索电视柜,或者是搜索屋内设计,或者是搜索装饰或装潢,或者是搜索无线路由器等等。搜索引擎无法准确确定用户的搜索需求,所以搜索引擎可能返回与电视机有关的搜索结果,但实际用户通过上述图像想要搜索的可能是室内设计,可见搜索引擎返回的搜索结果不符合用户的搜索需求,导致搜索结果的准确度较低。
举例说明,假设用户的搜索需求描述信息为一关键字,例如“苹果”,该“苹果”可以理解为手机品牌,也可以理解为水果,还可以理解为歌曲名等,所以搜索引擎无法确定用户是希望搜索手机、水果还是歌曲,无法准确理解用户的搜索需求。由于当前苹果手机比较热门,搜索量较大,所以搜索引擎根据用户输入的关键字“苹果”提供给用户的是与手机有关的搜索结果,而实际上用户希望了解水果中苹果的品种信息,可见搜索引擎返回的搜索结果不符合用户的搜索需求,导致搜索结果的准确度较低。
本实施例提供的搜索结果优化方法可以解决上述问题,本实施例方法的原理具体如下:
搜索引擎在获取用户的搜索需求描述信息后,并不像现有技术那样直接根据用户的搜索需求描述信息给出最终搜索结果,而是根据用户的 搜索需求描述信息给出初始搜索结果以及搜索需求优化信息,进一步根据用户选择的搜索需求优化信息对初始搜索结果进行优化处理,以获得最终搜索结果。在本实施例中,由于用户可以在获得初始搜索结果之后,继续基于搜索需求优化信息参与对初始搜索结果的优化处理,因此可以提高搜索结果与用户搜索需求的匹配度,提高搜索结果的准确度。
在本实施例中,搜索需求优化信息是指搜索需求明确度高于搜索需求描述信息的信息。简单来说,搜索需求优化信息是指与搜索需求描述信息相比,能够更加明确用户搜索需求(即搜索需求明确度高)的信息。同时,搜索需求优化信息也是与搜索需求描述信息相关的信息,例如可以是在属性上对搜索需求描述信息作出进一步限定的信息,或者是与搜索需求描述信息具有相似或相同特征的信息。
本实施例并不限定搜索需求优化信息的实现形式,凡是能够比搜索需求描述信息更加明确用户搜索需求的信息形式均可作为本实施例的搜索需求优化信息,例如可以是图像、关键字或者图像与关键字的组合。
在一可选实施方式中,上述根据搜索需求描述信息获得初始搜索结果以及搜索需求优化信息的方式包括:
根据搜索需求描述信息,确定至少一种搜索需求;
根据至少一种搜索需求中的初始搜索需求进行搜索,获得初始搜索结果;
根据初始搜索需求,获得搜索需求优化信息。
具体的,搜索引擎对搜索需求描述信息进行识别,例如可以是语义识别或图像识别等,确定该搜索需求描述信息可表达的至少一种搜索需求;从至少一种搜索需求中,确定初始搜索需求,初始搜索需求可以是 至少一种搜素需求中的部分或全部的搜索需求;根据初始搜索需求进行搜索,获得初始搜索结果,初始搜索结果是与初始搜索需求相匹配的搜索结果;另外,根据初始搜索需求,确定搜索需求优化信息,以便于对初始搜索结果进行优化处理。
值得说明的是,由于需要对初始搜索结果进行优化,故本实施例根据初始搜索需求确定搜索需求优化信息,该搜索需求优化信息对用户搜索需求的明确度更高。
一种根据初始搜索需求,确定搜索需求优化信息的方式包括:
将至少一种搜索需求中除初始搜索需求之外的其余搜索需求的描述信息以及初始搜索需求的子搜索需求的描述信息中的至少一个,作为搜索需求优化信息。
举例说明,以用户的搜索需求描述信息为上述客厅局部照片为例,搜索需求描述信息无法明确表示用户的搜索需求,搜索引擎基于该图像确定至少一种搜索需求,包括:搜索电视机,搜索电视柜,搜索室内设计,搜索装饰或装潢,搜索无线路由器等。假设搜索引擎确定至少一种搜索需求中的搜索电视机作为初始搜索需求,并基于该初始搜索需求进行搜索,获得与电视机有关的搜索结果作为初始搜索结果;与此同时,搜索引擎确定除作为初始搜索需求的搜索电视机之外的其余搜索需求,例如搜索电视柜、搜索室内设计、搜索装饰或装潢、搜索无线路由器等搜索需求的描述信息,作为搜索需求优化信息。
值得说明的是,上述搜索需求优化信息可以是图像,关键字或者图像与关键字的组合。例如,对于搜索电视柜的搜索需求,其描述信息可以是一张包括电视柜的图像;对于搜索室内设计的搜索需求,其描述信 息可以是关键字“室内设计”;对于搜索装饰或装潢的搜索需求,其描述信息可以是一张包括电视机、电视柜、背景墙、无线路由器等对象的图像与关键字“装饰/装潢”的组合;对于搜索无线路由器的搜索需求,其描述信息可以是关键词“无线路由器”等。值得说明的是,在搜索需求描述信息为图像的情况下,搜索需求优化信息是具体描述该图像中某个对象或特征的信息,以便于细化用户的搜索需求,使用户的搜索需求更加明确。
进一步,搜索引擎还可以选择初始搜索需求的子搜索需求的描述信息作为搜索需求优化信息。初始搜索需求的子搜索需求是指更加明确的用户搜索需求,该子搜索需求的搜索需求明确度高于初始搜索需求。例如,搜索电视机的子搜索需求可以是搜索64英寸电视机,或搜索海尔电视机,或搜索国产电视机等。
值得说明的是,在搜索引擎从至少一种搜索需求中确定部分搜索需求作为初始搜索需求的情况下,优先将其余搜索需求的描述信息作为搜索需求优化信息。
可选的,在获得搜索需求优化信息之后,可以向用户展示搜索需求优化信息,以供用户选择优化使用的搜索需求优化信息。在具体展现形式上,搜索引擎可以通过一独立窗口向用户展现搜索需求优化信息,或者也可以将搜索结果优化信息展示在搜索结果页面的上半部分,等等。
用户在看到搜索需求优化信息之后,可以结合初始搜索结果确定是否需要选择搜索需求优化信息以对初始搜索结果进行优化处理。例如,初始搜索结果是“与电视机有关的搜索结果”,而用户需要的是“室内设计”,对于这种情况,用户需要选择与“室内设计”相关的搜索需求 优化信息,根据选择的搜索需求优化信息对初始搜索结果进行优化处理。用户可以发出选择指令,告知搜索引擎用户所选择的搜索需求优化信息。
例如,搜索引擎可以将搜索需求优化信息设计成一个控件,用户通过点击相关的搜索需求优化信息而发出选择指令。或者,搜索引擎可以在搜索需求优化信息前面设置选择控件,以供用户发出选择指令使用,例如可以是一勾选框,用户通过选中相应勾选框而出发选择指令。
对搜索引擎来说,在向用户展现搜索需求优化信息之后,可以接收用户的选择指令,根据该选择指令,确定用户选择的搜索需求优化信息。
对于具有多个搜索需求优化信息的情况,用户可以选择其中一个或多个搜索需求优化信息。
在确定用户选择的搜索需求优化信息之后,搜索引擎可以根据用户选择的搜索需求优化信息,对初始搜索结果进行优化处理,以获得最终搜索结果。
可选的,一种优化处理的方式为:根据用户选择的搜索需求优化信息重新进行搜索,以获得最终搜索结果。这种优化方式重新进行搜索,可以获得更多更准确的搜索结果。
另一种优化处理的方式为:根据用户选择的搜索需求优化信息对初始搜索结果进行筛选,以获得最终搜索结果。这种优化方式直接从已有结果中进行筛选,获取准确搜索结果的效率更高。
在一可选实施方式中,上述获取用户的搜索需求描述信息的方式可以是:获取用户选择的上一优化操作过程中的搜索需求优化信息作为用户本次优化操作中的搜索需求描述信息。该实施方式意味着用户可以重复执行多次优化操作,直到达到用户期望的效果或者无法进一步给出搜 索需求优化信息为止或者达到设定的重复执行条件。其中,重复执行条件可以是预设的最大重复执行次数,或者是设定的单次搜索所允许的最大搜索时间。
值得说明的是,关键字属于文本形式的信息,其含义表达相对比较明确;而与关键字相比,图像中的对象数量较多、含义表达也较为晦涩,所以本实施例提供的方法尤其适用于搜索需求描述信息包括图像的情况。
以图像搜索为例,用户启动图像搜索功能之后,进入拍摄过程,用户拍摄并上传图像信息,之后,搜索引擎基于图像信息进行搜索,输出初始搜索结果以及搜索需求优化信息。用户除了可以直接浏览初始搜索结果之外,还可以看到搜索需求优化信息,如图2所示,搜索需求优化信息为图片,或者如图3所示,搜索需求优化信息为关键字,且如图2或图3所示,作为搜索需求优化信息的图片或关键字位于初始搜索结果上方;如果用户希望优化搜索结果,可以点击相应的搜索需求优化信息,则搜索结果会随之被优化,且同时也会产生新的搜索需求优化信息,如图4所示,新的搜索需求优化信息为图片,或者如图5所示,新的搜索需求优化信息为关键字,且如图4或图5所示,作为搜索需求优化信息的图片或关键字位于优化后的搜索结果上方;如此反复,直到搜索结果被自动判定为最优后结束操作。
由上述可见,用户在上传完图像信息后还可以继续参与,以图片或者关键字的形式继续对搜索结果进行范围限定,达到主动优化搜索结果的目的,不仅可以提高最终搜索结果与用户搜索需求的匹配度,提高最终搜索结果的准确度,而且还可以加强用户的产品参与感,提高用户体验度。
需要说明的是,对于前述的各方法实施例,为了简单描述,故将其都表述为一系列的动作组合,但是本领域技术人员应该知悉,本公开并不受所描述的动作顺序的限制,因为依据本公开,某些步骤可以采用其他顺序或者同时进行。其次,本领域技术人员也应该知悉,说明书中所描述的实施例均属于优选实施例,所涉及的动作和模块并不一定是本公开所必须的。
在上述实施例中,对各个实施例的描述都各有侧重,某个实施例中没有详述的部分,可以参见其他实施例的相关描述。
图6为本公开一实施例提供的搜索引擎的结构示意图。如图6所示,该搜索引擎包括:第一获取模块61、第二获取模块62和优化处理模块63。
第一获取模块61,用于获取用户的搜索需求描述信息。
第二获取模块62,用于根据第一获取模块61获取的搜索需求描述信息获得初始搜索结果以及搜索需求优化信息。
优化处理模块63,用于根据用户选择的搜索需求优化信息,对第二获取模块62获得的初始搜索结果进行优化处理,以获得最终搜索结果。
在一可选实施方式中,第二获取模块62具体可用于:
根据搜索需求描述信息,确定至少一种搜索需求;
根据至少一种搜索需求中的初始搜索需求进行搜索,获得初始搜索结果;
根据初始搜索需求,确定搜索需求优化信息。
进一步,第二获取模块62在根据初始搜索需求,确定搜索需求优化信息时,具体用于:
将至少一种搜索需求中除初始搜索需求之外的其余搜索需求的描述信息以及初始搜索需求的子搜索需求的描述信息中的至少一个,作为搜索需求优化信息。
在一可选实施方式中,如图7所示,该搜索引擎还包括:展现模块64、接收模块65和确定模块66。
展现模块64,用于展现第二获取模块62获得的搜索需求优化信息,以供用户选择。
接收模块65,用于接收用户的选择指令,选择指令指示用户选择的搜索需求优化信息。
确定模块66,用于根据接收模块65接收的选择指令,确定用户选择的搜索需求优化信息。
在一可选实施方式中,优化处理模块63具体用于:
根据用户选择的搜索需求优化信息重新进行搜索,以获得最终搜索结果;或者
根据用户选择的搜索需求优化信息对初始搜索结果进行筛选,以获得最终搜索结果。
在一可选实施方式中,第一获取模块61具体可用于:获取用户选择的上一优化操作中的搜索需求优化信息,作为用户本次优化操作中的搜索需求描述信息。
在一可选实施方式中,搜索需求描述信息为图像,但不限于此。搜索需求描述信息还可以是关键字或者关键字与图像的组合。
在一可选实施方式中,搜索需求优化信息为图像和关键字中的至少一个。
本实施例提供的搜索引擎,获取用户的搜索需求描述信息之后,并不是像现有技术那样直接根据搜索需求描述信息给出最终搜索结果,而是根据该搜索需求描述信息获得初始搜索结果以及搜索需求优化信息,进一步根据用户选择的搜索需求优化信息,对初始搜索结果进行优化处理,以获得最终搜索结果,通过用户参与的搜索结果优化处理,能够提高搜索结果与用户搜索需求的匹配度,提高搜索结果的准确度。
所属领域的技术人员可以清楚地了解到,为描述的方便和简洁,上述描述的***,装置和单元的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。
在本公开所提供的几个实施例中,应该理解到,所揭露的***,装置和方法,可以通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,例如多个单元或组件可以结合或者可以集成到另一个***,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口,装置或单元的间接耦合或通信连接,可以是电性,机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外,在本公开各个实施例中的各功能单元可以集成在一个处理单元中,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 成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用硬件加软件功能单元的形式实现。
上述以软件功能单元的形式实现的集成的单元,可以存储在一个计算机可读取存储介质中。上述软件功能单元存储在一个存储介质中,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)或处理器(processor)执行本公开各个实施例所述方法的部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(Read-Only Memory,ROM)、随机存取存储器(Random Access Memory,RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
最后应说明的是:以上实施例仅用以说明本公开的技术方案,而非对其限制;尽管参照前述实施例对本公开进行了详细的说明,本领域的普通技术人员应当理解:其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分技术特征进行等同替换;而这些修改或者替换,并不使相应技术方案的本质脱离本公开各实施例技术方案的精神和范围。

Claims (18)

  1. 一种搜索结果优化方法,其特征在于,包括:
    获取用户的搜索需求描述信息;
    根据所述搜索需求描述信息获得初始搜索结果以及搜索需求优化信息;
    根据所述用户选择的搜索需求优化信息,对所述初始搜索结果进行优化处理,以获得最终搜索结果。
  2. 根据权利要求1所述的方法,其特征在于,所述根据所述搜索需求描述信息获得初始搜索结果以及搜索需求优化信息,包括:
    根据所述搜索需求描述信息,确定至少一种搜索需求;
    根据所述至少一种搜索需求中的初始搜索需求进行搜索,获得所述初始搜索结果;
    根据所述初始搜索需求,确定所述搜索需求优化信息。
  3. 根据权利要求2所述的方法,其特征在于,所述根据所述初始搜索需求,确定所述搜索需求优化信息,包括:
    将所述至少一种搜索需求中除所述初始搜索需求之外的其余搜索需求的描述信息以及所述初始搜索需求的子搜索需求的描述信息中的至少一个,作为所述搜索需求优化信息。
  4. 根据权利要求1-3任一项所述的方法,其特征在于,所述根据所述用户选择的搜索需求优化信息,对所述搜索结果进行优化处理之前,包括:
    展现所述搜索需求优化信息,以供所述用户选择;
    接收所述用户的选择指令,所述选择指令指示所述用户选择的搜索 需求优化信息;
    根据所述选择指令,确定所述用户选择的搜索需求优化信息。
  5. 根据权利要求1-4任一项所述的方法,其特征在于,所述根据所述用户选择的搜索需求优化信息,对所述初始搜索结果进行优化处理,以获得最终搜索结果,包括:
    根据所述用户选择的搜索需求优化信息重新进行搜索,以获得所述最终搜索结果;或者
    根据所述用户选择的搜索需求优化信息对所述初始搜索结果进行筛选,以获得所述最终搜索结果。
  6. 根据权利要求1-5任一项所述的方法,其特征在于,所述获取用户的搜索需求描述信息,包括:
    获取所述用户选择的上一优化操作中的搜索需求优化信息,作为所述用户本次优化操作中的搜索需求描述信息。
  7. 根据权利要求1-6任一项所述的方法,其特征在于,所述搜索需求描述信息为图像。
  8. 根据权利要求1-7任一项所述的方法,其特征在于,所述搜索需求优化信息为图像和关键字中的至少一个。
  9. 一种搜索引擎,其特征在于,包括:
    第一获取模块,用于获取用户的搜索需求描述信息;
    第二获取模块,用于根据所述搜索需求描述信息获得初始搜索结果以及搜索需求优化信息;
    优化处理模块,用于根据所述用户选择的搜索需求优化信息,对所述初始搜索结果进行优化处理,以获得最终搜索结果。
  10. 根据权利要求9所述的搜索引擎,其特征在于,所述第二获取模块具体用于:
    根据所述搜索需求描述信息,确定至少一种搜索需求;
    根据所述至少一种搜索需求中的初始搜索需求进行搜索,获得所述初始搜索结果;
    根据所述初始搜索需求,确定所述搜索需求优化信息。
  11. 根据权利要求10所述的搜索引擎,其特征在于,所述第二获取模块具体用于:
    将所述至少一种搜索需求中除所述初始搜索需求之外的其余搜索需求的描述信息以及所述初始搜索需求的子搜索需求的描述信息中的至少一个,作为所述搜索需求优化信息。
  12. 根据权利要求9-11任一项所述的搜索引擎,其特征在于,还包括:
    展现模块,用于展现所述搜索需求优化信息,以供所述用户选择;
    接收模块,用于接收所述用户的选择指令,所述选择指令指示所述用户选择的搜索需求优化信息;
    确定模块,用于根据所述选择指令,确定所述用户选择的搜索需求优化信息。
  13. 根据权利要求9-12任一项所述的搜索引擎,其特征在于,所述优化处理模块具体用于:
    根据所述用户选择的搜索需求优化信息重新进行搜索,以获得所述最终搜索结果;或者
    根据所述用户选择的搜索需求优化信息对所述初始搜索结果进行筛 选,以获得所述最终搜索结果。
  14. 根据权利要求9-13任一项所述的搜索引擎,其特征在于,所述第一获取模块具体用于:
    获取所述用户选择的上一优化操作中的搜索需求优化信息,作为所述用户本次优化操作中的搜索需求描述信息。
  15. 根据权利要求9-14任一项所述的搜索引擎,其特征在于,所述搜索需求描述信息为图像。
  16. 根据权利要求9-15任一项所述的搜索引擎,其特征在于,所述搜索需求优化信息为图像和关键字中的至少一个。
  17. 一种设备,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:
    获取用户的搜索需求描述信息;
    根据所述搜索需求描述信息获得初始搜索结果以及搜索需求优化信息;
    根据所述用户选择的搜索需求优化信息,对所述初始搜索结果进行优化处理,以获得最终搜索结果。
  18. 一种非易失性计算机存储介质,所述非易失性计算机存储介质存储有一个或者多个程序,当所述一个或者多个程序被一个设备执行时,使得所述设备:
    获取用户的搜索需求描述信息;
    根据所述搜索需求描述信息获得初始搜索结果以及搜索需求优化信息;
    根据所述用户选择的搜索需求优化信息,对所述初始搜索结果进行优化处理,以获得最终搜索结果。
PCT/CN2015/094336 2015-06-18 2015-11-11 搜索结果优化方法、搜索引擎、设备及非易失性计算机存储介质 WO2016201869A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US15/523,929 US20170337286A1 (en) 2015-06-18 2015-11-11 Search result optimizing method, search engine, an apparatus and non-volatile computer storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510340517.XA CN104951534B (zh) 2015-06-18 2015-06-18 搜索结果优化方法及搜索引擎
CN201510340517.X 2015-06-18

Publications (1)

Publication Number Publication Date
WO2016201869A1 true WO2016201869A1 (zh) 2016-12-22

Family

ID=54166192

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/094336 WO2016201869A1 (zh) 2015-06-18 2015-11-11 搜索结果优化方法、搜索引擎、设备及非易失性计算机存储介质

Country Status (3)

Country Link
US (1) US20170337286A1 (zh)
CN (1) CN104951534B (zh)
WO (1) WO2016201869A1 (zh)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104951534B (zh) * 2015-06-18 2019-07-23 百度在线网络技术(北京)有限公司 搜索结果优化方法及搜索引擎
CN105808657A (zh) * 2016-02-29 2016-07-27 浪潮软件集团有限公司 一种对搜索结果和搜索引擎进行优化的方法
CN108710706A (zh) * 2018-05-28 2018-10-26 江苏中安环能新能源科技有限公司 一种搜索方法、***及装置
CN110765169B (zh) * 2019-09-06 2024-07-12 锦上花(北京)科技有限公司 信息推荐方法、装置、计算机设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101364239A (zh) * 2008-10-13 2009-02-11 中国科学院计算技术研究所 一种分类目录自动构建方法及相关***
US20140136536A1 (en) * 2012-11-13 2014-05-15 Microsoft Corporation Intent-Based Presentation of Search Results
CN104123285A (zh) * 2013-04-24 2014-10-29 阿里巴巴集团控股有限公司 搜索结果的导航方法及装置
CN104462325A (zh) * 2014-12-02 2015-03-25 百度在线网络技术(北京)有限公司 搜索推荐方法及装置
CN104951534A (zh) * 2015-06-18 2015-09-30 百度在线网络技术(北京)有限公司 搜索结果优化方法及搜索引擎

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1825395A4 (en) * 2004-10-25 2010-07-07 Yuanhua Tang FULL TEXT INTERROGATION AND RESEARCH SYSTEMS AND METHODS OF USE
US8868548B2 (en) * 2010-07-22 2014-10-21 Google Inc. Determining user intent from query patterns
US9305024B2 (en) * 2011-05-31 2016-04-05 Facebook, Inc. Computer-vision-assisted location accuracy augmentation
CN104239340B (zh) * 2013-06-19 2018-03-16 北京搜狗信息服务有限公司 搜索结果筛选方法与装置
CN104424286A (zh) * 2013-08-30 2015-03-18 北京四维图新科技股份有限公司 一种搜索信息的方法和***
US9424598B1 (en) * 2013-12-02 2016-08-23 A9.Com, Inc. Visual search in a controlled shopping environment
CN103778227B (zh) * 2014-01-23 2016-11-02 西安电子科技大学 从检索图像中筛选有用图像的方法
CN104598617A (zh) * 2015-01-30 2015-05-06 百度在线网络技术(北京)有限公司 一种搜索结果展示方法及装置
WO2016170269A1 (fr) * 2015-04-20 2016-10-27 Qwant Procédé de recherche de pages accessibles sur un réseau
US10664515B2 (en) * 2015-05-29 2020-05-26 Microsoft Technology Licensing, Llc Task-focused search by image

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101364239A (zh) * 2008-10-13 2009-02-11 中国科学院计算技术研究所 一种分类目录自动构建方法及相关***
US20140136536A1 (en) * 2012-11-13 2014-05-15 Microsoft Corporation Intent-Based Presentation of Search Results
CN104123285A (zh) * 2013-04-24 2014-10-29 阿里巴巴集团控股有限公司 搜索结果的导航方法及装置
CN104462325A (zh) * 2014-12-02 2015-03-25 百度在线网络技术(北京)有限公司 搜索推荐方法及装置
CN104951534A (zh) * 2015-06-18 2015-09-30 百度在线网络技术(北京)有限公司 搜索结果优化方法及搜索引擎

Also Published As

Publication number Publication date
CN104951534B (zh) 2019-07-23
US20170337286A1 (en) 2017-11-23
CN104951534A (zh) 2015-09-30

Similar Documents

Publication Publication Date Title
US11657084B2 (en) Correlating image annotations with foreground features
JP6487201B2 (ja) 推奨ページを生成するための方法及び装置
KR101864240B1 (ko) 객체 검색 방법 및 장치
US10726063B2 (en) Topic profile query creation
US20160162602A1 (en) Methods and apparatus for proximally informed database searches
CN104077415B (zh) 搜索方法及装置
WO2016201869A1 (zh) 搜索结果优化方法、搜索引擎、设备及非易失性计算机存储介质
US20150294018A1 (en) Method and apparatus for recommending keywords
CN111327955B (zh) 基于用户画像的点播方法、存储介质及智能电视
CN102368262A (zh) 一种提供与查询序列相对应的搜索建议的方法与设备
EP2430575A1 (en) Search method, apparatus and system
US11048736B2 (en) Filtering search results using smart tags
WO2017096896A1 (zh) 资源搜索方法以及服务器
US11709881B2 (en) Visual menu
JP7146961B2 (ja) 音声パッケージの推薦方法、装置、電子機器および記憶媒体
CN104881431B (zh) 一种用于在计算机设备中获得搜索结果页的方法和装置
US20230086735A1 (en) Systems and methods for retrieving videos using natural language description
TW201629802A (zh) 資訊搜索系統及方法
JP2017500632A (ja) 補助情報へのアクセスを提供するための方法およびシステム
US20180018389A1 (en) Method and apparatus for keyword-based text retrieval
Yi et al. Autog: A visual query autocompletion framework for graph databases
WO2017097102A1 (zh) 检索方法和检索装置
US10241988B2 (en) Prioritizing smart tag creation
CA2845268A1 (en) Systems and methods for providing and accessing visual product representations of a project
CN105589863B (zh) 一种搜索方法及数据处理方法、装置及***

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: 15895437

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: 15895437

Country of ref document: EP

Kind code of ref document: A1