WO2015139490A1 - 搜索推荐方法和装置 - Google Patents

搜索推荐方法和装置 Download PDF

Info

Publication number
WO2015139490A1
WO2015139490A1 PCT/CN2014/094278 CN2014094278W WO2015139490A1 WO 2015139490 A1 WO2015139490 A1 WO 2015139490A1 CN 2014094278 W CN2014094278 W CN 2014094278W WO 2015139490 A1 WO2015139490 A1 WO 2015139490A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
recommended content
search term
content
search
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/CN2014/094278
Other languages
English (en)
French (fr)
Inventor
黄际洲
雷振
夏德国
赵明华
唐诗慧
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.)
Baidu Online Network Technology Beijing Co Ltd
Original Assignee
Baidu Online Network Technology 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 Baidu Online Network Technology Beijing Co Ltd filed Critical Baidu Online Network Technology Beijing Co Ltd
Publication of WO2015139490A1 publication Critical patent/WO2015139490A1/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
    • 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 network communication technologies, and in particular, to a search recommendation method and apparatus.
  • the search engine can obtain the search result from the server and display it to the user.
  • the search engine can also provide recommendation information to the user, and the search engine can display information related to the search term on the right side of the search result for the user's reference. For example, when the user searches for Korean drama, some specifics are provided on the right side. The Korean drama of the name, the user can select the recommended information to view again.
  • a user When a user conducts a search, it is generally conducted to have a clear search, such as entering a search term with a clear intention. However, at some point, the user also performs some untargeted searches, for example, the user inputs words such as "1”, “asdf”, “ddddd”, etc. with vague intent.
  • the present invention aims to solve at least one of the technical problems in the related art to some extent.
  • Another object of the present invention is to provide a search recommendation device.
  • the search recommendation method includes: receiving a search term input by a user; determining a property of the search term, the property of the search term includes: the search term is clear a word of interest, or the search term is a word with a fuzzy intent; according to the nature of the search word, the corresponding recommended content is presented to the user
  • the search recommendation method proposed by the embodiment of the first aspect of the present invention by recommending a word with a fuzzy intention
  • the recommended content can add interest, for example, the user can view some small jokes, etc.; and can improve the interaction, for example, the user can view more content, and the like, and the user can use the recommended content to complete the specific scene requirement, for example, the user is only in the Measuring the speed of the network, then you can recommend the application of measuring the speed of the network to meet user needs. These can improve the user experience, enhance user stickiness, meet specific scenario needs, and provide new resources for commercial delivery.
  • the search recommendation apparatus includes: a receiving module, configured to receive a search term input by a user; and a determining module, configured to determine a property of the search term, where the search term is The property includes: the search term is a word with a clear purpose, or the search term is a word with a fuzzy intent; the presentation module is configured to display the corresponding recommended content to the user according to the nature of the search term. .
  • the search recommendation device proposed by the embodiment of the second aspect of the present invention can increase the interest by recommending special recommendation content for a word with a fuzzy intention, for example, the user can view some small jokes, etc., and can improve the interaction, for example, the user can View more content, etc., and users can use the recommended content to complete specific scene requirements. For example, if the user is only measuring the network speed, then the application of the network speed can be recommended to meet the user's needs. These can improve the user experience, enhance user stickiness, meet specific scenario needs, and provide new resources for commercial delivery.
  • a client device includes: a housing, a processor, a memory, a circuit board, and a power supply circuit, wherein the circuit board is disposed inside the space enclosed by the housing, and the processor And the memory is disposed on the circuit board; the power circuit is configured to supply power to each circuit or device of the client device; the memory is used to store the executable program code; and the processor is operable to read the executable program code stored in the memory.
  • Executing a program corresponding to the program code configured to: receive a search term input by a user; determine a property of the search term, the property of the search term includes: the search term is a word with a clear purpose, or, The search term is a word with a fuzzy intent; according to the nature of the search term, the corresponding recommended content is presented to the user
  • the client device can increase the interest by recommending special recommended content for words with fuzzy intent, for example, the user can view some small jokes, etc., and can improve the interaction, for example, the user can View more content, etc., and users can use the recommended content to complete specific scene requirements. For example, if the user is only measuring the network speed, then the application of the network speed can be recommended to meet the user's needs. These can improve the user experience, enhance user stickiness, meet specific scenario needs, and provide new resources for commercial delivery.
  • FIG. 1 is a schematic flowchart of a search recommendation method according to an embodiment of the present invention
  • FIG. 2 is a schematic flowchart of a search recommendation method according to another embodiment of the present invention.
  • FIG. 3a is a schematic diagram of a recommended content according to an embodiment of the present invention.
  • FIG. 3b is a schematic diagram of another recommended content in the embodiment of the present invention.
  • FIG. 4 is a schematic diagram of another recommended content in an embodiment of the present invention.
  • FIG. 5 is a schematic flowchart of a search recommendation method according to another embodiment of the present invention.
  • FIG. 6 is a schematic structural diagram of a search recommendation apparatus according to another embodiment of the present invention.
  • FIG. 7 is a schematic structural diagram of a search recommendation apparatus according to another embodiment of the present invention.
  • FIG. 1 is a schematic flowchart of a search recommendation method according to an embodiment of the present invention, where the method includes:
  • S11 The search engine receives the search term input by the user.
  • the search term can be a word with a clear purpose, for example, "How does Tiananmen go", such as the need to obtain clear search results. or,
  • Search terms can also be words that have no clear purpose, that is, words with vague intent, and such word users do not need to obtain explicit search results, for example, "1”, “asdf”, “ddddd”.
  • the search engine determines the nature of the search term, and the properties of the search term include: the search term is a word with a clear purpose, or the search term is a word with a fuzzy intent;
  • search terms can be divided into words with a clear purpose, and words with a fuzzy intent.
  • the search engine can distinguish each word in advance, and divides it into a first group of words for recording words with a clear purpose and a second group of words for recording words with fuzzy intent. After the user inputs the search term, the search engine can view the two sets of words. If the search term is in the first set of words, the search term is determined to be a word with a clear purpose, and if the search term is in the second set of words, the search is determined. Words are words with vague intent.
  • S13 The search engine presents the corresponding recommended content to the user according to the nature of the search term.
  • the recommended content can be displayed on the right side of the search results.
  • the search engine can be similar to the processing in the related art, and the content related to the word with a clear purpose is recommended on the right side. For example, when the user searches for "how to go to Tiananmen," the right side will recommend “Beijing fun.” Land: Temple of Heaven, Summer Palace" and so on.
  • the user since the user inputs a word with a fuzzy intent, it may be because of boring or to measure the network speed, etc., and it is not necessary to obtain a clear search result. Therefore, providing the recommended content of the above special setting can better meet the user's needs. , to improve the fun, can guide users to the resources of interest; and can improve interactivity and improve user stickiness. And the recommended content can be set as a commercial resource, providing another way for commercialization.
  • FIG. 2 is a schematic flowchart of a search recommendation method according to another embodiment of the present invention, where the method includes:
  • the search engine receives a search term input by a user, the search term being a word with a fuzzy intent.
  • S22 The search engine recommends the first recommended content to the user on the right side of the search result.
  • the first recommendation content may include:
  • N and M are preset values.
  • the non-application recommendation content includes at least one of the following items:
  • the first recommendation content includes four applications and the non-application recommended content is a joke. Among them, 4 should be “measuring speed”, “seeing eggs”, “12306” and “163 mailbox”.
  • the above application may include an application that satisfies a specific scenario requirement. For example, if the user inputs a word with a fuzzy intent only to measure the network speed, then the first recommended content may include an application of “measuring network speed” as shown in FIG. 3a. Specific scenario needs.
  • the application included in the first recommended content may also include an application of one or some merchants, such as an application including the No. 1 store.
  • the M non-apply recommended content is randomly selected from the preset L contents, L>M.
  • the M non-apply recommended content is changed from the L content according to a user selection.
  • the user can click on "More Jokes” in Figure 3a to get additional jokes out of 50 jokes.
  • the above-mentioned recommended content may be other content, for example, the content shown in FIG. 3b.
  • FIG. 3a is an example in which the non-application recommendation content is a joke. It can be understood that the non-application recommendation content may also be other content.
  • the non-application recommendation content is respectively a small game. , pictures, videos, Post it.
  • the user may also share the first recommended content, that is, the method may further include:
  • S23 The search engine acquires the shared content selected by the user in the first recommended content.
  • S24 The search engine shares the shared content to a pre-set website.
  • This embodiment can increase the interest by recommending special recommendation content for words with fuzzy intent, for example, the user can view some small jokes, etc.; and can improve the interaction, for example, the user can view more content, etc., and the user can Use the recommended content to complete the specific scenario requirements. For example, if the user is only measuring the network speed, then the application of the network speed can be recommended to meet the user's needs. These can improve the user experience, enhance user stickiness, meet specific scenario needs, and provide new resources for commercial delivery.
  • FIG. 5 is a schematic flowchart of a search recommendation method according to another embodiment of the present invention, where the method includes:
  • the search engine receives a search term input by the user, and the search term is a word with a fuzzy intent.
  • S52 The search engine determines the user's emotion according to the search term input by the user.
  • the search engine may pre-categorize each word into a kind of emotion classification, and then determine the user's emotion according to the emotion classification to which the search word input by the user belongs, for example, happiness, sadness, boring, and the like. For example, the user enters "boring" to determine that the user's mood is boring.
  • S53 The search engine obtains the recommended content corresponding to the emotion of the user.
  • the search engine may obtain recommended content corresponding to the user's emotion from the local or the server.
  • the correspondence between the user's emotion and the recommended content may be pre-configured in the local or the server. For example, multiple sad songs corresponding to the sad mood may be pre-configured, or multiple jokes corresponding to the happy mood may be pre-configured, or pre-configured. Multiple stickers corresponding to boring emotions.
  • S54 The search engine presents the recommended content corresponding to the user's emotion to the user on the right side of the search result.
  • a joke or the like is recommended to the user.
  • the present embodiment can also detect the user's emotions by providing the user's emotions and providing corresponding recommended content, and provide more suitable recommended content, thereby further improving the user experience and enhancing the user's stickiness.
  • FIG. 6 is a schematic structural diagram of a search recommendation apparatus according to another embodiment of the present invention.
  • the apparatus 60 includes a receiving module 61, a determining module 62, and a presentation module 63.
  • the receiving module 61 is configured to receive a search term input by the user
  • the search term can be a word with a clear purpose, for example, "How does Tiananmen go?" Identify the words of the search results. or,
  • Search terms can also be words that have no clear purpose, that is, words with vague intent, and such word users do not need to obtain explicit search results, for example, "1”, “asdf”, “ddddd”.
  • the determining module 62 is configured to determine a property of the search term, the property of the search term includes: the search term is a word with a clear purpose, or the search term is a word with a fuzzy intent;
  • search terms can be divided into words with a clear purpose, and words with a fuzzy intent.
  • the search engine can distinguish each word in advance, and divides it into a first group of words for recording words with a clear purpose and a second group of words for recording words with fuzzy intent. After the user inputs the search term, the search engine can view the two sets of words. If the search term is in the first set of words, the search term is determined to be a word with a clear purpose, and if the search term is in the second set of words, the search is determined. Words are words with vague intent.
  • the presentation module 63 is configured to present the corresponding recommended content to the user according to the nature of the search term.
  • the recommended content can be displayed on the right side of the search results.
  • the search engine can be similar to the processing in the related art, and the content related to the word with a clear purpose is recommended on the right side. For example, when the user searches for "how to go to Tiananmen," the right side will recommend “Beijing fun.” Land: Temple of Heaven, Summer Palace" and so on.
  • the presentation module is specifically configured to:
  • the search term is a word with a fuzzy intent
  • the first recommended content is presented to the user.
  • the first recommended content includes:
  • N and M are preset values.
  • the non-application recommendation content includes at least one of the following items:
  • the user enters "1".
  • the first recommendation content includes four applications and the non-application recommended content is a joke. Among them, 4 should be “measuring speed”, “seeing eggs”, “12306” and “163 mailbox”.
  • the above application may include an application that satisfies a specific scenario requirement. For example, if the user inputs a word with a fuzzy intent only to measure the network speed, then the first recommended content may include an application of “measuring network speed” as shown in FIG. 3a. Specific scenario needs.
  • the application included in the first recommended content may also include an application of one or some merchants, such as an application including the No. 1 store.
  • the M non-apply recommended content is randomly selected from the preset L contents, L>M.
  • the M non-apply recommended content is changed from the L content according to a user selection.
  • the user can click on "More Jokes” in Figure 3a to get additional jokes out of 50 jokes.
  • the above-mentioned recommended content may be other content, for example, the content shown in FIG. 3b.
  • FIG. 3a is an example in which the non-application recommendation content is a joke. It can be understood that the non-application recommendation content may also be other content.
  • the non-application recommendation content is respectively a small game. , pictures, videos, post it.
  • the first recommendation content includes content corresponding to different emotions
  • the presentation module is specifically configured to:
  • the search engine may pre-categorize each word into a kind of emotion classification, and then determine the user's emotion according to the emotion classification to which the search word input by the user belongs, for example, happiness, sadness, boring, and the like. For example, the user enters "boring" to determine that the user's mood is boring.
  • the search engine may obtain recommended content corresponding to the user's emotion from the local or the server.
  • the correspondence between the user's emotion and the recommended content may be pre-configured in the local or the server. For example, multiple sad songs corresponding to the sad mood may be pre-configured, or multiple jokes corresponding to the happy mood may be pre-configured, or pre-configured. Multiple stickers corresponding to boring emotions.
  • a joke or the like is recommended to the user.
  • the user since the user inputs a word with a fuzzy intent, it may be because of boring or to measure the network speed, etc., and it is not necessary to obtain a clear search result. Therefore, providing the recommended content of the above special setting can better meet the user's needs. , to improve the fun, can guide users to the resources of interest; and can improve interactivity and improve user stickiness. And the recommended content can be set as a commercial resource, providing another way for commercialization. In this embodiment, by determining user emotions and providing corresponding recommended content, the user's emotions can also be perceived, and more Appropriate recommendation content to further enhance the user experience and enhance user stickiness.
  • FIG. 7 is a schematic structural diagram of a search recommendation apparatus according to another embodiment of the present invention.
  • the embodiment further includes an acquisition module 64 and a sharing module 65 on the basis of the previous embodiment.
  • the obtaining module 64 is configured to obtain shared content selected by the user in the first recommended content
  • the sharing module 65 is configured to share the shared content to a pre-set website.
  • This embodiment can increase the interest by recommending special recommendation content for words with fuzzy intent, for example, the user can view some small jokes, etc.; and can improve the interaction, for example, the user can view more content, etc., and the user can Use the recommended content to complete the specific scenario requirements. For example, if the user is only measuring the network speed, then the application of the network speed can be recommended to meet the user's needs. These can improve the user experience, enhance user stickiness, meet specific scenario needs, and provide new resources for commercial delivery.
  • the embodiment of the invention further provides a client device, which comprises a casing, a processor, a memory, a circuit board and a power supply circuit, wherein the circuit board is disposed inside the space enclosed by the casing, the processor and the memory Set on the circuit board; power circuit for powering various circuits or devices of the client device; memory for storing executable program code; the processor running and executing the program by reading executable program code stored in the memory
  • the program corresponding to the code is used to perform the following steps:
  • the search term can be a word with a clear purpose, for example, "How does Tiananmen go", such as the need to obtain clear search results. or,
  • Search terms can also be words that have no clear purpose, that is, words with vague intent, and such word users do not need to obtain explicit search results, for example, "1”, “asdf”, “ddddd”.
  • S12' determining a property of the search term, the property of the search term includes: the search term is a word with a clear purpose, or the search term is a word with a fuzzy intent;
  • search terms can be divided into words with a clear purpose, and words with a fuzzy intent.
  • the search engine can distinguish each word in advance, and divides it into a first group of words for recording words with a clear purpose and a second group of words for recording words with fuzzy intent. After the user inputs the search term, the search engine can view the two sets of words. If the search term is in the first set of words, the search term is determined to be a word with a clear purpose, and if the search term is in the second set of words, the search is determined. Words are words with vague intent.
  • the recommended content can be displayed on the right side of the search results.
  • the search engine can be similar to the processing in the related technology, and the recommendation and the right side are on the right.
  • the content related to the purpose of the word for example, when the user searches for "how to go to Tiananmen", the right side will recommend "Beijing fun place: Temple of Heaven, Summer Palace" and so on.
  • the user since the user inputs a word with a fuzzy intent, it may be because of boring or to measure the network speed, etc., and it is not necessary to obtain a clear search result. Therefore, providing the recommended content of the above special setting can better meet the user's needs. , to improve the fun, can guide users to the resources of interest; and can improve interactivity and improve user stickiness. And the recommended content can be set as a commercial resource, providing another way for commercialization.
  • the processor runs a program corresponding to the executable program code by reading executable program code stored in the memory for performing the following steps:
  • the search engine receives a search term input by the user, the search term being a word with a fuzzy intent.
  • S22' The search engine recommends the first recommended content to the user on the right side of the search result.
  • the first recommendation content may include:
  • N and M are preset values.
  • the non-application recommendation content includes at least one of the following items:
  • the first recommendation content includes four applications and the non-application recommended content is a joke. Among them, 4 should be “measuring speed”, “seeing eggs”, “12306” and “163 mailbox”.
  • the above application may include an application that satisfies a specific scenario requirement. For example, if the user inputs a word with a fuzzy intent only to measure the network speed, then the first recommended content may include an application of “measuring network speed” as shown in FIG. 3a. Specific scenario needs.
  • the application included in the first recommended content may also include an application of one or some merchants, such as an application including the No. 1 store.
  • the M non-apply recommended content is randomly selected from the preset L contents, L>M.
  • the M non-apply recommended content is changed from the L content according to a user selection.
  • the user can click on "More Jokes” in Figure 3a to get additional jokes out of 50 jokes.
  • the above-mentioned recommended content may be other content, for example, the content shown in FIG. 3b.
  • FIG. 3a is an example in which the non-application recommendation content is a joke. It can be understood that the non-application recommendation content may also be other content.
  • the non-application recommendation content is respectively a small game. , pictures, videos, post it.
  • the user may also share the first recommended content, that is, the method may further include:
  • S23' The search engine acquires the shared content selected by the user in the first recommended content.
  • S24' The search engine shares the shared content to a pre-set website.
  • This embodiment can increase the interest by recommending special recommendation content for words with fuzzy intent, for example, the user can view some small jokes, etc.; and can improve the interaction, for example, the user can view more content, etc., and the user can Use the recommended content to complete the specific scenario requirements. For example, if the user is only measuring the network speed, then the application of the network speed can be recommended to meet the user's needs. These can improve the user experience, enhance user stickiness, meet specific scenario needs, and provide new resources for commercial delivery.
  • the processor runs a program corresponding to the executable program code by reading executable program code stored in the memory for performing the following steps:
  • the search engine receives a search term input by the user, the search term being a word with a fuzzy intent.
  • S52' The search engine determines the emotion of the user according to the search term input by the user.
  • the search engine may pre-categorize each word into a kind of emotion classification, and then determine the user's emotion according to the emotion classification to which the search word input by the user belongs, for example, happiness, sadness, boring, and the like. For example, the user enters "boring" to determine that the user's mood is boring.
  • S53' The search engine acquires recommended content corresponding to the emotion of the user.
  • the search engine may obtain recommended content corresponding to the user's emotion from the local or the server.
  • the correspondence between the user's emotion and the recommended content may be pre-configured in the local or the server. For example, multiple sad songs corresponding to the sad mood may be pre-configured, or multiple jokes corresponding to the happy mood may be pre-configured, or pre-configured. Multiple stickers corresponding to boring emotions.
  • S54' The search engine presents the recommended content corresponding to the user's emotion to the user on the right side of the search result.
  • a joke or the like is recommended to the user.
  • This embodiment can also determine the user's emotions and provide corresponding recommended content on the basis of the above embodiments. Perceive user sentiment, provide more appropriate recommended content, further improve user experience and enhance user stickiness.
  • An embodiment of the present invention further provides an electronic device, including:
  • One or more processors are One or more processors;
  • One or more programs the one or more programs being stored in the memory, and when executed by the one or more processors, do the following:
  • the property of the search term includes: the search term is a word with a clear purpose, or the search term is a word with a fuzzy intent;
  • the corresponding recommended content is presented to the user.
  • portions of the invention may be implemented in hardware, software, firmware or a combination thereof.
  • multiple steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system.
  • a suitable instruction execution system For example, if implemented in hardware, as in another embodiment, it can be implemented by any one or combination of the following techniques well known in the art: having logic gates for implementing logic functions on data signals. Discrete logic circuits, application specific integrated circuits with suitable combinational logic gates, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.
  • each functional unit in each embodiment of the present invention may be integrated into one processing module, or each unit may exist physically separately, or two or more units may be integrated into one module.
  • the above integrated modules can be implemented in the form of hardware or in the form of software functional modules.
  • the integrated modules, if implemented in the form of software functional modules and sold or used as stand-alone products, may also be stored in a computer readable storage medium.
  • the above mentioned storage medium may be a read only memory, a magnetic disk or an optical disk or the like.
  • the terms “installation”, “connected”, “connected”, “fixed” and the like shall be understood broadly, and may be either a fixed connection or a detachable connection, unless explicitly stated and defined otherwise. , or integrated; can be mechanical connection, or can be electrical connection; can be directly connected, or can be indirectly connected through an intermediate medium, can be the internal communication of two elements or the interaction of two elements.
  • installation can be understood on a case-by-case basis.
  • the first feature "on” or “under” the second feature may be a direct contact of the first and second features, or the first and second features may be indirectly through an intermediate medium, unless otherwise explicitly stated and defined. contact.
  • the first feature "above”, “above” and “above” the second feature may be that the first feature is directly above or above the second feature, or merely that the first feature level is higher than the second feature.
  • the first feature “below”, “below” and “below” the second feature may be that the first feature is directly below or obliquely below the second feature, or merely that the first feature level is less than the second feature.

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (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

一种搜索推荐方法和装置,为根据用户输入的搜索词向用户提供合适的推荐内容。该搜索推荐方法包括接收用户输入的搜索词;确定所述搜索词的性质,所述搜索词的性质包括:所述搜索词是具有明确目的的词,或者,所述搜索词是具有模糊意图的词;根据所述搜索词的性质,向所述用户展现相应的推荐内容。该方法能够根据用户输入的搜索词向用户提供合适的推荐内容。

Description

搜索推荐方法和装置
相关申请的交叉引用
本申请要求百度在线网络技术(北京)有限公司于2014年03月17日提交的、发明名称为“搜索推荐方法和装置”的、中国专利申请号“201410098806.9”的优先权。
技术领域
本发明涉及网络通信技术领域,尤其涉及一种搜索推荐方法和装置。
背景技术
用户经常在互联网的海量信息中搜索需要的信息,搜索引擎渐渐成为必不可少的工具。用户输入搜索词后,搜索引擎可以从服务器获取搜索结果并显示给用户。为了提高用户体验,搜索引擎还可以向用户提供推荐信息,搜索引擎可以在搜索结果的右侧显示与搜索词相关的信息,以供用户参考,例如,用户搜索韩剧时,在右侧提供一些具体名字的韩剧,用户可以选择推荐的信息进行再次查看。
用户在进行搜索时,一般是进行有明确的搜索,例如输入有明确意图的搜索词。但是,一些时候,用户也会进行一些无明确目的的搜索,例如,用户输入“1”、“asdf”、“ddddd”等这类具有模糊意图的词。
相关技术中,对于此类具有模糊意图的词依然在右侧中提供与这些词相关的内容,但是,这种推荐内容显然是不合适的。
发明内容
本发明旨在至少在一定程度上解决相关技术中的技术问题之一。
为此,本发明的一个目的在于提出一种搜索推荐方法,该方法可以根据用户输入的搜索词向用户提供合适的推荐内容。
本发明的另一个目的在于提出一种搜索推荐装置。
为达到上述目的,本发明第一方面实施例提出的搜索推荐方法,包括:接收用户输入的搜索词;确定所述搜索词的性质,所述搜索词的性质包括:所述搜索词是具有明确目的的词,或者,所述搜藏词是具有模糊意图的词;根据所述搜索词的性质,向所述用户展现相应的推荐内容
本发明第一方面实施例提出的搜索推荐方法,通过对具有模糊意图的词,推荐特别 的推荐内容,可以增加趣味性,例如用户可以查看一些小笑话等;以及可以提高互动性,例如用户可以查看更多的内容等,并且用户可以采用推荐内容完成特定场景需求,例如,用户只是在测网速,那么可以推荐测网速的应用来满足用户需求。这些都可以提高用户体验,增强用户粘性,满足特定场景需求,以及,为商业投放提供新的资源。
为达到上述目的,本发明第二方面实施例提出的搜索推荐装置,包括:接收模块,用于接收用户输入的搜索词;确定模块,用于确定所述搜索词的性质,所述搜索词的性质包括:所述搜索词是具有明确目的的词,或者,所述搜藏词是具有模糊意图的词;展现模块,用于根据所述搜索词的性质,向所述用户展现相应的推荐内容。
本发明第二方面实施例提出的搜索推荐装置,通过对具有模糊意图的词,推荐特别的推荐内容,可以增加趣味性,例如用户可以查看一些小笑话等;以及可以提高互动性,例如用户可以查看更多的内容等,并且用户可以采用推荐内容完成特定场景需求,例如,用户只是在测网速,那么可以推荐测网速的应用来满足用户需求。这些都可以提高用户体验,增强用户粘性,满足特定场景需求,以及,为商业投放提供新的资源。
为达到上述目的,本发明第三方面实施例提出的客户端设备,包括:壳体、处理器、存储器、电路板和电源电路,其中,电路板安置在壳体围成的空间内部,处理器和存储器设置在电路板上;电源电路,用于为客户端设备的各个电路或器件供电;存储器用于存储可执行程序代码;处理器通过读取存储器中存储的可执行程序代码来运行与可执行程序代码对应的程序,以用于执行以下步骤:接收用户输入的搜索词;确定所述搜索词的性质,所述搜索词的性质包括:所述搜索词是具有明确目的的词,或者,所述搜藏词是具有模糊意图的词;根据所述搜索词的性质,向所述用户展现相应的推荐内容
本发明第三方面实施例提出的客户端设备,通过对具有模糊意图的词,推荐特别的推荐内容,可以增加趣味性,例如用户可以查看一些小笑话等;以及可以提高互动性,例如用户可以查看更多的内容等,并且用户可以采用推荐内容完成特定场景需求,例如,用户只是在测网速,那么可以推荐测网速的应用来满足用户需求。这些都可以提高用户体验,增强用户粘性,满足特定场景需求,以及,为商业投放提供新的资源。
本发明附加的方面和优点将在下面的描述中部分给出,部分将从下面的描述中变得明显,或通过本发明的实践了解到。
附图说明
本发明上述的和/或附加的方面和优点从下面结合附图对实施例的描述中将变得明显和容易理解,其中:
图1为本发明一实施例提出的搜索推荐方法的流程示意图;
图2为本发明另一实施例提出的搜索推荐方法的流程示意图;
图3a为本发明实施例中一种推荐内容的示意图;
图3b为本发明实施例中另一种推荐内容的示意图;
图4为本发明实施例中另一种推荐内容的示意图;
图5为本发明另一实施例提出的搜索推荐方法的流程示意图;
图6为本发明另一实施例提出的搜索推荐装置的结构示意图;
图7为本发明另一实施例提出的搜索推荐装置的结构示意图。
具体实施方式
下面详细描述本发明的实施例,所述实施例的示例在附图中示出,其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施例是示例性的,仅用于解释本发明,而不能理解为对本发明的限制。相反,本发明的实施例包括落入所附加权利要求书的精神和内涵范围内的所有变化、修改和等同物。
图1为本发明一实施例提出的搜索推荐方法的流程示意图,该方法包括:
S11:搜索引擎接收用户输入的搜索词。
其中,搜索词可以为具有明确目的的词,例如,“天安门怎么走”这类需要获取明确搜索结果的词。或者,
搜索词也可以为不具有明确目的的词,也就是具有模糊意图的词,这类词用户并不需要获取明确的搜索结果,例如,“1”,“asdf”,“ddddd”这类词。
S12:搜索引擎确定所述搜索词的性质,所述搜索词的性质包括:所述搜索词是具有明确目的的词,或者,所述搜藏词是具有模糊意图的词;
如上所述,搜索词可以分为具有明确目的的词,以及,具有模糊意图的词。
搜索引擎可以预先对每个词进行区分,分为第一组词和第二组词,第一组词用于记录具有明确目的的词,第二组词用于记录具有模糊意图的词。当用户输入搜索词后,搜索引擎可以查看该两组词,如果搜索词在第一组词中,则确定搜索词为具有明确目的的词,如果搜索词在第二组词中,则确定搜索词为具有模糊意图的词。
S13:搜索引擎根据所述搜索词的性质,向所述用户展现相应的推荐内容。
其中,推荐内容可以在搜索结果的右侧展现。
对于具有明确目的的词,搜索引擎可以类似相关技术中的处理,在右侧推荐与具有明确目的的词相关的内容,例如,当用户搜索“天安门怎么走”时,右侧会推荐“北京好玩的地:天坛、颐和园…”等。
而对于具有模糊意图的词,如用户搜索“1”时,搜索引擎不再是提供“相关数字:2、 3…”这类相关的词,而是针对具有模糊意图的词特别设置推荐内容。该推荐内容可以提供良好互动性和趣味性,或者,满足特点场景的需求。
本实施例中,由于用户输入具有模糊意图的词时,可能是因为无聊或者要测网速等,并不是要获取明确搜索结果,因此,提供上述特别设置的推荐内容,可以更好满足用户需要,提高趣味性,可以将用户引导到感兴趣的资源;并且可以提高互动性,提高用户粘性。并且推荐内容可以设置为商业化的资源,为商业化的投放提供另一种途径。
图2为本发明另一实施例提出的搜索推荐方法的流程示意图,该方法包括:
S21:搜索引擎接收用户输入的搜索词,该搜索词是具有模糊意图的词。
例如,如图3a所示,用户输入“1”。
S22:搜索引擎在搜索结果的右侧向用户推荐第一推荐内容。
第一推荐内容可以包括:
N个应用;和/或,
M个非应用的推荐内容;
其中,N和M为预先设定的数值。
其中,所述非应用的推荐内容包括如下项中的至少一项:
笑话,游戏,图片,视频,贴吧。
参见图3a,本实施例以第一推荐内容包括4个应用及非应用的推荐内容是笑话为例。其中,4个应该分别为“测网速”、“看彩蛋”、“12306”和“163邮箱”。
上述的应用可以包括满足特定场景需求的应用,例如,用户输入具有模糊意图的词只是要测网速,那么第一推荐内容中就可以如图3a所示包括“测网速”的应用以满足特定场景需求。
另外,作为商业投放的途径,第一推荐内容中包含的应用也可以包括一个或一些商家的应用,如包括1号店的应用。
其中,所述M个非应用的推荐内容是从预先设定的L个内容中随机选取的,L>M。
例如,对于笑话推荐,参见图3a,可以每次推荐2个笑话,并且可以预先配置50个笑话,这2个笑话是在这50个笑话中随机选取的。
进一步的,所述M个非应用的推荐内容根据用户选择从所述L个内容中进行更改。
例如,用户可以点击图3a中的“更多笑话”以获取50个笑话中另外的笑话。
另外,上述的推荐内容也可以是其他内容,例如,图3b所示的内容。
上述的图3a以非应用的推荐内容是笑话为例,可以理解的是,该非应用的推荐内容还可以是其他内容,例如,参见图4,分别给出了非应用的推荐内容是小游戏、图片、视频、 贴吧。
可以理解的是,本实施例给出的应用以及非应用的推荐内容只是一种示例,还可以展现其他的推荐内容。
进一步的,用户还可以对第一推荐内容进行分享,即该方法还可以包括:
S23:搜索引擎获取用户在所述第一推荐内容中选取的分享内容。
S24:搜索引擎将所述分享内容分享到预先设定的网站。
例如,用户要分享“彩蛋”,那么如图3所示,可以将“我在无聊中发现了百度的彩蛋池”分享到设定的网站,例如,微博、人人或者微信等。
本实施例通过对具有模糊意图的词,推荐特别的推荐内容,可以增加趣味性,例如用户可以查看一些小笑话等;以及可以提高互动性,例如用户可以查看更多的内容等,并且用户可以采用推荐内容完成特定场景需求,例如,用户只是在测网速,那么可以推荐测网速的应用来满足用户需求。这些都可以提高用户体验,增强用户粘性,满足特定场景需求,以及,为商业投放提供新的资源。
图5为本发明另一实施例提出的搜索推荐方法的流程示意图,该方法包括:
S51:搜索引擎接收用户输入的搜索词,该搜索词是具有模糊意图的词。
S52:搜索引擎根据用户输入的搜索词确定用户的情绪。
其中,搜索引擎可以预先将每个词归于一种情绪分类中,再根据用户输入的搜索词属于的情绪分类,确定用户的情绪,例如,快乐、忧伤、无聊等。例如,用户输入“无聊”可以确定用户情绪是无聊的。
S53:搜索引擎获取与用户的情绪对应的推荐内容。
其中,搜索引擎可以从本地或者从服务器中获取与用户情绪对应的推荐内容。而本地或者服务器中可以预先配置用户情绪与推荐内容的对应关系,例如,可以预先配置与忧伤情绪对应的多首忧伤的歌曲,或者,预先配置与快乐情绪对应的多个笑话,或者,预先配置与无聊情绪对应的多个贴吧。
S54:搜索引擎在搜索结果的右侧向用户展现与用户的情绪对应的推荐内容。
例如,用户快乐时,向用户推荐笑话等。
本实施例在上述实施例的基础上,通过确定用户情绪并提供相应的推荐内容,还可以察觉用户情绪,提供更适宜的推荐内容,进一步提高用户体验,增强用户粘性。
图6为本发明另一实施例提出的搜索推荐装置的结构示意图,该装置60包括接收模块61、确定模块62和展现模块63。
接收模块61用于接收用户输入的搜索词;
其中,搜索词可以为具有明确目的的词,例如,“天安门怎么走”这类需要获取 明确搜索结果的词。或者,
搜索词也可以为不具有明确目的的词,也就是具有模糊意图的词,这类词用户并不需要获取明确的搜索结果,例如,“1”,“asdf”,“ddddd”这类词。
确定模块62用于确定所述搜索词的性质,所述搜索词的性质包括:所述搜索词是具有明确目的的词,或者,所述搜藏词是具有模糊意图的词;
如上所述,搜索词可以分为具有明确目的的词,以及,具有模糊意图的词。
搜索引擎可以预先对每个词进行区分,分为第一组词和第二组词,第一组词用于记录具有明确目的的词,第二组词用于记录具有模糊意图的词。当用户输入搜索词后,搜索引擎可以查看该两组词,如果搜索词在第一组词中,则确定搜索词为具有明确目的的词,如果搜索词在第二组词中,则确定搜索词为具有模糊意图的词。
展现模块63用于根据所述搜索词的性质,向所述用户展现相应的推荐内容。
其中,推荐内容可以在搜索结果的右侧展现。
对于具有明确目的的词,搜索引擎可以类似相关技术中的处理,在右侧推荐与具有明确目的的词相关的内容,例如,当用户搜索“天安门怎么走”时,右侧会推荐“北京好玩的地:天坛、颐和园…”等。
而对于具有模糊意图的词,如用户搜索“1”时,搜索引擎不再是提供“相关数字:2、3…”这类相关的词,而是针对具有模糊意图的词特别设置推荐内容。该推荐内容可以提供良好互动性和趣味性,或者,满足特点场景的需求。
一个实施例中,所述展现模块具体用于:
当所述搜索词是具有模糊意图的词时,向所述用户展现第一推荐内容。
一个实施例中,所述第一推荐内容包括:
N个应用;和/或,
M个非应用的推荐内容;
其中,N和M为预先设定的数值。
一个实施例中,所述非应用的推荐内容包括如下项中的至少一项:
笑话,游戏,图片,视频,贴吧。
例如,如图3a所示,用户输入“1”。参见图3a,本实施例以第一推荐内容包括4个应用及非应用的推荐内容是笑话为例。其中,4个应该分别为“测网速”、“看彩蛋”、“12306”和“163邮箱”。
上述的应用可以包括满足特定场景需求的应用,例如,用户输入具有模糊意图的词只是要测网速,那么第一推荐内容中就可以如图3a所示包括“测网速”的应用以满足特定场景需求。
另外,作为商业投放的途径,第一推荐内容中包含的应用也可以包括一个或一些商家的应用,如包括1号店的应用。
一个实施例中,所述M个非应用的推荐内容是从预先设定的L个内容中随机选取的,L>M。
例如,对于笑话推荐,参见图3a,可以每次推荐2个笑话,并且可以预先配置50个笑话,这2个笑话是在这50个笑话中随机选取的。
一个实施例中,所述M个非应用的推荐内容根据用户选择从所述L个内容中进行更改。
例如,用户可以点击图3a中的“更多笑话”以获取50个笑话中另外的笑话。
另外,上述的推荐内容也可以是其他内容,例如,图3b所示的内容。
上述的图3a以非应用的推荐内容是笑话为例,可以理解的是,该非应用的推荐内容还可以是其他内容,例如,参见图4,分别给出了非应用的推荐内容是小游戏、图片、视频、贴吧。
可以理解的是,本实施例给出的应用以及非应用的推荐内容只是一种示例,还可以展现其他的推荐内容。
一个实施例中,所述第一推荐内容包括分别与不同情绪对应的内容,所述展现模块具体用于:
根据所述具有模糊意图的词,确定所述用户的情绪;
根据所述用户的情绪,向所述用户展现所述第一推荐内容中与所述用户的情绪对应的内容。
其中,搜索引擎可以预先将每个词归于一种情绪分类中,再根据用户输入的搜索词属于的情绪分类,确定用户的情绪,例如,快乐、忧伤、无聊等。例如,用户输入“无聊”可以确定用户情绪是无聊的。
其中,搜索引擎可以从本地或者从服务器中获取与用户情绪对应的推荐内容。而本地或者服务器中可以预先配置用户情绪与推荐内容的对应关系,例如,可以预先配置与忧伤情绪对应的多首忧伤的歌曲,或者,预先配置与快乐情绪对应的多个笑话,或者,预先配置与无聊情绪对应的多个贴吧。
例如,用户快乐时,向用户推荐笑话等。
本实施例中,由于用户输入具有模糊意图的词时,可能是因为无聊或者要测网速等,并不是要获取明确搜索结果,因此,提供上述特别设置的推荐内容,可以更好满足用户需要,提高趣味性,可以将用户引导到感兴趣的资源;并且可以提高互动性,提高用户粘性。并且推荐内容可以设置为商业化的资源,为商业化的投放提供另一种途径。本实施例通过确定用户情绪并提供相应的推荐内容,还可以察觉用户情绪,提供更 适宜的推荐内容,进一步提高用户体验,增强用户粘性。
图7为本发明另一实施例提出的搜索推荐装置的结构示意图,本实施例在上一实施例的基础上还包括获取模块64和分享模块65。
获取模块64用于获取用户在所述第一推荐内容中选取的分享内容;
分享模块65用于将所述分享内容分享到预先设定的网站。
例如,用户要分享“彩蛋”,那么如图3所示,可以将“我在无聊中发现了百度的彩蛋池”分享到设定的网站,例如,微博、人人或者微信等。
本实施例通过对具有模糊意图的词,推荐特别的推荐内容,可以增加趣味性,例如用户可以查看一些小笑话等;以及可以提高互动性,例如用户可以查看更多的内容等,并且用户可以采用推荐内容完成特定场景需求,例如,用户只是在测网速,那么可以推荐测网速的应用来满足用户需求。这些都可以提高用户体验,增强用户粘性,满足特定场景需求,以及,为商业投放提供新的资源。
本发明实施例还提供了一种客户端设备,该客户端设备包括壳体、处理器、存储器、电路板和电源电路,其中,电路板安置在壳体围成的空间内部,处理器和存储器设置在电路板上;电源电路,用于为客户端设备的各个电路或器件供电;存储器用于存储可执行程序代码;处理器通过读取存储器中存储的可执行程序代码来运行与可执行程序代码对应的程序,以用于执行以下步骤:
S11’:接收用户输入的搜索词。
其中,搜索词可以为具有明确目的的词,例如,“天安门怎么走”这类需要获取明确搜索结果的词。或者,
搜索词也可以为不具有明确目的的词,也就是具有模糊意图的词,这类词用户并不需要获取明确的搜索结果,例如,“1”,“asdf”,“ddddd”这类词。
S12’:确定所述搜索词的性质,所述搜索词的性质包括:所述搜索词是具有明确目的的词,或者,所述搜藏词是具有模糊意图的词;
如上所述,搜索词可以分为具有明确目的的词,以及,具有模糊意图的词。
搜索引擎可以预先对每个词进行区分,分为第一组词和第二组词,第一组词用于记录具有明确目的的词,第二组词用于记录具有模糊意图的词。当用户输入搜索词后,搜索引擎可以查看该两组词,如果搜索词在第一组词中,则确定搜索词为具有明确目的的词,如果搜索词在第二组词中,则确定搜索词为具有模糊意图的词。
S13’:根据所述搜索词的性质,向所述用户展现相应的推荐内容。
其中,推荐内容可以在搜索结果的右侧展现。
对于具有明确目的的词,搜索引擎可以类似相关技术中的处理,在右侧推荐与具有明 确目的的词相关的内容,例如,当用户搜索“天安门怎么走”时,右侧会推荐“北京好玩的地:天坛、颐和园…”等。
而对于具有模糊意图的词,如用户搜索“1”时,搜索引擎不再是提供“相关数字:2、3…”这类相关的词,而是针对具有模糊意图的词特别设置推荐内容。该推荐内容可以提供良好互动性和趣味性,或者,满足特点场景的需求。
本实施例中,由于用户输入具有模糊意图的词时,可能是因为无聊或者要测网速等,并不是要获取明确搜索结果,因此,提供上述特别设置的推荐内容,可以更好满足用户需要,提高趣味性,可以将用户引导到感兴趣的资源;并且可以提高互动性,提高用户粘性。并且推荐内容可以设置为商业化的资源,为商业化的投放提供另一种途径。
另一实施例中,处理器通过读取存储器中存储的可执行程序代码来运行与可执行程序代码对应的程序,以用于执行以下步骤:
S21’:搜索引擎接收用户输入的搜索词,该搜索词是具有模糊意图的词。
例如,如图3a所示,用户输入“1”。
S22’:搜索引擎在搜索结果的右侧向用户推荐第一推荐内容。
第一推荐内容可以包括:
N个应用;和/或,
M个非应用的推荐内容;
其中,N和M为预先设定的数值。
其中,所述非应用的推荐内容包括如下项中的至少一项:
笑话,游戏,图片,视频,贴吧。
参见图3a,本实施例以第一推荐内容包括4个应用及非应用的推荐内容是笑话为例。其中,4个应该分别为“测网速”、“看彩蛋”、“12306”和“163邮箱”。
上述的应用可以包括满足特定场景需求的应用,例如,用户输入具有模糊意图的词只是要测网速,那么第一推荐内容中就可以如图3a所示包括“测网速”的应用以满足特定场景需求。
另外,作为商业投放的途径,第一推荐内容中包含的应用也可以包括一个或一些商家的应用,如包括1号店的应用。
其中,所述M个非应用的推荐内容是从预先设定的L个内容中随机选取的,L>M。
例如,对于笑话推荐,参见图3a,可以每次推荐2个笑话,并且可以预先配置50个笑话,这2个笑话是在这50个笑话中随机选取的。
进一步的,所述M个非应用的推荐内容根据用户选择从所述L个内容中进行更改。
例如,用户可以点击图3a中的“更多笑话”以获取50个笑话中另外的笑话。
另外,上述的推荐内容也可以是其他内容,例如,图3b所示的内容。
上述的图3a以非应用的推荐内容是笑话为例,可以理解的是,该非应用的推荐内容还可以是其他内容,例如,参见图4,分别给出了非应用的推荐内容是小游戏、图片、视频、贴吧。
可以理解的是,本实施例给出的应用以及非应用的推荐内容只是一种示例,还可以展现其他的推荐内容。
进一步的,用户还可以对第一推荐内容进行分享,即该方法还可以包括:
S23’:搜索引擎获取用户在所述第一推荐内容中选取的分享内容。
S24’:搜索引擎将所述分享内容分享到预先设定的网站。
例如,用户要分享“彩蛋”,那么如图3所示,可以将“我在无聊中发现了百度的彩蛋池”分享到设定的网站,例如,微博、人人或者微信等。
本实施例通过对具有模糊意图的词,推荐特别的推荐内容,可以增加趣味性,例如用户可以查看一些小笑话等;以及可以提高互动性,例如用户可以查看更多的内容等,并且用户可以采用推荐内容完成特定场景需求,例如,用户只是在测网速,那么可以推荐测网速的应用来满足用户需求。这些都可以提高用户体验,增强用户粘性,满足特定场景需求,以及,为商业投放提供新的资源。
另一实施例中,处理器通过读取存储器中存储的可执行程序代码来运行与可执行程序代码对应的程序,以用于执行以下步骤:
S51’:搜索引擎接收用户输入的搜索词,该搜索词是具有模糊意图的词。
S52’:搜索引擎根据用户输入的搜索词确定用户的情绪。
其中,搜索引擎可以预先将每个词归于一种情绪分类中,再根据用户输入的搜索词属于的情绪分类,确定用户的情绪,例如,快乐、忧伤、无聊等。例如,用户输入“无聊”可以确定用户情绪是无聊的。
S53’:搜索引擎获取与用户的情绪对应的推荐内容。
其中,搜索引擎可以从本地或者从服务器中获取与用户情绪对应的推荐内容。而本地或者服务器中可以预先配置用户情绪与推荐内容的对应关系,例如,可以预先配置与忧伤情绪对应的多首忧伤的歌曲,或者,预先配置与快乐情绪对应的多个笑话,或者,预先配置与无聊情绪对应的多个贴吧。
S54’:搜索引擎在搜索结果的右侧向用户展现与用户的情绪对应的推荐内容。
例如,用户快乐时,向用户推荐笑话等。
本实施例在上述实施例的基础上,通过确定用户情绪并提供相应的推荐内容,还可以 察觉用户情绪,提供更适宜的推荐内容,进一步提高用户体验,增强用户粘性。
本发明实施例还提出了一种电子设备,包括:
一个或者多个处理器;
存储器;
一个或者多个程序,所述一个或者多个程序存储在所述存储器中,当被所述一个或者多个处理器执行时进行如下操作:
接收用户输入的搜索词;
确定所述搜索词的性质,所述搜索词的性质包括:所述搜索词是具有明确目的的词,或者,所述搜藏词是具有模糊意图的词;
根据所述搜索词的性质,向所述用户展现相应的推荐内容。
需要说明的是,在本发明的描述中,术语“第一”、“第二”等仅用于描述目的,而不能理解为指示或暗示相对重要性。此外,在本发明的描述中,除非另有说明,“多个”的含义是两个或两个以上。
流程图中或在此以其他方式描述的任何过程或方法描述可以被理解为,表示包括一个或更多个用于实现特定逻辑功能或过程的步骤的可执行指令的代码的模块、片段或部分,并且本发明的优选实施方式的范围包括另外的实现,其中可以不按所示出或讨论的顺序,包括根据所涉及的功能按基本同时的方式或按相反的顺序,来执行功能,这应被本发明的实施例所属技术领域的技术人员所理解。
应当理解,本发明的各部分可以用硬件、软件、固件或它们的组合来实现。在上述实施方式中,多个步骤或方法可以用存储在存储器中且由合适的指令执行系统执行的软件或固件来实现。例如,如果用硬件来实现,和在另一实施方式中一样,可用本领域公知的下列技术中的任一项或他们的组合来实现:具有用于对数据信号实现逻辑功能的逻辑门电路的离散逻辑电路,具有合适的组合逻辑门电路的专用集成电路,可编程门阵列(PGA),现场可编程门阵列(FPGA)等。
本技术领域的普通技术人员可以理解实现上述实施例方法携带的全部或部分步骤是可以通过程序来指令相关的硬件完成,所述的程序可以存储于一种计算机可读存储介质中,该程序在执行时,包括方法实施例的步骤之一或其组合。
此外,在本发明各个实施例中的各功能单元可以集成在一个处理模块中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个模块中。上述集成的模块既可以采用硬件的形式实现,也可以采用软件功能模块的形式实现。所述集成的模块如果以软件功能模块的形式实现并作为独立的产品销售或使用时,也可以存储在一个计算机可读取存储介质中。
上述提到的存储介质可以是只读存储器,磁盘或光盘等。
在本说明书的描述中,参考术语“一个实施例”、“一些实施例”、“示例”、“具体示例”、或“一些示例”等的描述意指结合该实施例或示例描述的具体特征、结构、材料或者特点包含于本发明的至少一个实施例或示例中。在本说明书中,对上述术语的示意性表述不一定指的是相同的实施例或示例。而且,描述的具体特征、结构、材料或者特点可以在任何的一个或多个实施例或示例中以合适的方式结合。
在本发明的描述中,需要理解的是,术语“中心”、“纵向”、“横向”、“长度”、“宽度”、“厚度”、“上”、“下”、“前”、“后”、“左”、“右”、“竖直”、“水平”、“顶”、“底”“内”、“外”、“顺时针”、“逆时针”、“轴向”、“径向”、“周向”等指示的方位或位置关系为基于附图所示的方位或位置关系,仅是为了便于描述本发明和简化描述,而不是指示或暗示所指的装置或元件必须具有特定的方位、以特定的方位构造和操作,因此不能理解为对本发明的限制。
在本发明中,除非另有明确的规定和限定,术语“安装”、“相连”、“连接”、“固定”等术语应做广义理解,例如,可以是固定连接,也可以是可拆卸连接,或成一体;可以是机械连接,也可以是电连接;可以是直接相连,也可以通过中间媒介间接相连,可以是两个元件内部的连通或两个元件的相互作用关系。对于本领域的普通技术人员而言,可以根据具体情况理解上述术语在本发明中的具体含义。
在本发明中,除非另有明确的规定和限定,第一特征在第二特征“上”或“下”可以是第一和第二特征直接接触,或第一和第二特征通过中间媒介间接接触。而且,第一特征在第二特征“之上”、“上方”和“上面”可是第一特征在第二特征正上方或斜上方,或仅仅表示第一特征水平高度高于第二特征。第一特征在第二特征“之下”、“下方”和“下面”可以是第一特征在第二特征正下方或斜下方,或仅仅表示第一特征水平高度小于第二特征。
尽管上面已经示出和描述了本发明的实施例,可以理解的是,上述实施例是示例性的,不能理解为对本发明的限制,本领域的普通技术人员在本发明的范围内可以对上述实施例进行变化、修改、替换和变型。

Claims (17)

  1. 一种搜索推荐方法,其特征在于,包括:
    接收用户输入的搜索词;
    确定所述搜索词的性质,所述搜索词的性质包括:所述搜索词是具有明确目的的词,或者,所述搜藏词是具有模糊意图的词;
    根据所述搜索词的性质,向所述用户展现相应的推荐内容。
  2. 根据权利要求1所述的方法,其特征在于,所述根据所述搜索词的性质,向所述用户展现相应的推荐内容,包括:
    当所述搜索词是具有模糊意图的词时,向所述用户展现第一推荐内容。
  3. 根据权利要求2所述的方法,其特征在于,所述第一推荐内容包括:
    N个应用;和/或,
    M个非应用的推荐内容;
    其中,N和M为预先设定的数值。
  4. 根据权利要求3所述的方法,其特征在于,所述非应用的推荐内容包括如下项中的至少一项:
    笑话,游戏,图片,视频,贴吧。
  5. 根据权利要求3所述的方法,其特征在于,所述M个非应用的推荐内容是从预先设定的L个内容中随机选取的,L>M。
  6. 根据权利要求5所述的方法,其特征在于,所述M个非应用的推荐内容根据用户选择从所述L个内容中进行更改。
  7. 根据权利要求2所述的方法,其特征在于,还包括:
    获取用户在所述第一推荐内容中选取的分享内容;
    将所述分享内容分享到预先设定的网站。
  8. 根据权利要求2所述的方法,其特征在于,所述第一推荐内容包括分别与不同情绪对应的内容,所述向所述用户展现第一推荐内容,包括:
    根据所述具有模糊意图的词,确定所述用户的情绪;
    根据所述用户的情绪,向所述用户展现所述第一推荐内容中与所述用户的情绪对应的内容。
  9. 一种搜索推荐装置,其特征在于,包括:
    接收模块,用于接收用户输入的搜索词;
    确定模块,用于确定所述搜索词的性质,所述搜索词的性质包括:所述搜索词是具有 明确目的的词,或者,所述搜藏词是具有模糊意图的词;
    展现模块,用于根据所述搜索词的性质,向所述用户展现相应的推荐内容。
  10. 根据权利要求9所述的装置,其特征在于,所述展现模块具体用于:
    当所述搜索词是具有模糊意图的词时,向所述用户展现第一推荐内容。
  11. 根据权利要求10所述的装置,其特征在于,所述第一推荐内容包括:
    N个应用;和/或,
    M个非应用的推荐内容;
    其中,N和M为预先设定的数值。
  12. 根据权利要求11所述的装置,其特征在于,所述非应用的推荐内容包括如下项中的至少一项:
    笑话,游戏,图片,视频,贴吧。
  13. 根据权利要求11所述的装置,其特征在于,所述M个非应用的推荐内容是从预先设定的L个内容中随机选取的,L>M。
  14. 根据权利要求13所述的装置,其特征在于,所述M个非应用的推荐内容根据用户选择从所述L个内容中进行更改。
  15. 根据权利要求10所述的装置,其特征在于,还包括:
    获取模块,用于获取用户在所述第一推荐内容中选取的分享内容;
    分享模块,用于将所述分享内容分享到预先设定的网站。
  16. 根据权利要求10所述的装置,其特征在于,所述第一推荐内容包括分别与不同情绪对应的内容,所述展现模块具体用于:
    根据所述具有模糊意图的词,确定所述用户的情绪;
    根据所述用户的情绪,向所述用户展现所述第一推荐内容中与所述用户的情绪对应的内容。
  17. 一种电子设备,其特征在于,包括:
    一个或者多个处理器;
    存储器;
    一个或者多个程序,所述一个或者多个程序存储在所述存储器中,当被所述一个或者多个处理器执行时进行如下操作:
    接收用户输入的搜索词;
    确定所述搜索词的性质,所述搜索词的性质包括:所述搜索词是具有明确目的的词,或者,所述搜藏词是具有模糊意图的词;
    根据所述搜索词的性质,向所述用户展现相应的推荐内容。
PCT/CN2014/094278 2014-03-17 2014-12-18 搜索推荐方法和装置 Ceased WO2015139490A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201410098806.9A CN104063418A (zh) 2014-03-17 2014-03-17 搜索推荐方法和装置
CN201410098806.9 2014-03-17

Publications (1)

Publication Number Publication Date
WO2015139490A1 true WO2015139490A1 (zh) 2015-09-24

Family

ID=51551133

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2014/094278 Ceased WO2015139490A1 (zh) 2014-03-17 2014-12-18 搜索推荐方法和装置

Country Status (2)

Country Link
CN (1) CN104063418A (zh)
WO (1) WO2015139490A1 (zh)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104063418A (zh) * 2014-03-17 2014-09-24 百度在线网络技术(北京)有限公司 搜索推荐方法和装置
CN104778261B (zh) * 2015-04-21 2018-06-19 无锡天脉聚源传媒科技有限公司 搜索处理方法及装置
CN105389361A (zh) * 2015-11-05 2016-03-09 百度在线网络技术(北京)有限公司 搜索推荐方法及装置
CN106899755B (zh) * 2017-01-18 2021-02-23 宇龙计算机通信科技(深圳)有限公司 信息分享方法、信息分享装置及终端
CN109190051B (zh) * 2018-11-29 2020-11-03 广东省科技基础条件平台中心 一种用户行为分析方法和基于该分析方法的资源推荐方法
CN110955830B (zh) * 2019-11-22 2021-02-19 拉扎斯网络科技(上海)有限公司 信息处理方法、装置、电子设备及计算机可读存储介质
CN112860995B (zh) * 2021-02-04 2024-10-15 北京百度网讯科技有限公司 交互方法、装置、客户端、服务器以及存储介质
CN120234442A (zh) * 2023-12-29 2025-07-01 北京字跳网络技术有限公司 一种多媒体内容的确定方法、装置、电子设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101566988A (zh) * 2008-04-24 2009-10-28 华为技术有限公司 一种模糊语义搜索方法、系统及设备
CN102567408A (zh) * 2010-12-31 2012-07-11 阿里巴巴集团控股有限公司 推荐搜索关键词的方法和装置
CN103714088A (zh) * 2012-10-09 2014-04-09 深圳市世纪光速信息技术有限公司 搜索词获取方法、服务器、搜索词推荐方法及系统
CN104063418A (zh) * 2014-03-17 2014-09-24 百度在线网络技术(北京)有限公司 搜索推荐方法和装置

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007077991A1 (ja) * 2006-01-06 2007-07-12 Sony Corporation 情報処理装置および方法、並びにプログラム
CN102810103A (zh) * 2011-06-03 2012-12-05 腾讯科技(深圳)有限公司 搜索结果分享方法及系统
CN103455499A (zh) * 2012-05-29 2013-12-18 北京百度网讯科技有限公司 移动终端中根据搜索词自动匹配搜索类型的方法及系统
CN103530389B (zh) * 2013-10-22 2017-08-22 北京奇虎科技有限公司 一种提高停用词搜索有效性的方法和装置
CN103593410B (zh) * 2013-10-22 2017-04-12 上海交通大学 通过替换概念性词语进行搜索推荐的系统

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101566988A (zh) * 2008-04-24 2009-10-28 华为技术有限公司 一种模糊语义搜索方法、系统及设备
CN102567408A (zh) * 2010-12-31 2012-07-11 阿里巴巴集团控股有限公司 推荐搜索关键词的方法和装置
CN103714088A (zh) * 2012-10-09 2014-04-09 深圳市世纪光速信息技术有限公司 搜索词获取方法、服务器、搜索词推荐方法及系统
CN104063418A (zh) * 2014-03-17 2014-09-24 百度在线网络技术(北京)有限公司 搜索推荐方法和装置

Also Published As

Publication number Publication date
CN104063418A (zh) 2014-09-24

Similar Documents

Publication Publication Date Title
JP6564364B2 (ja) タグ付き検索結果の維持
KR102290150B1 (ko) 메시징 시스템을 통해 미디어를 공유하고 리믹스하는 기술
US10891679B2 (en) Generating media recommendations based upon beats per minute
CN104462262B (zh) 一种实现语音搜索的方法、装置和浏览器客户端
CN102542410B (zh) 与背景和基于任务的计算环境的交互
US10223451B2 (en) Ranking search results based upon content creation trends
US11316940B1 (en) Music discovery using messages of a messaging platform
US8528053B2 (en) Disambiguating online identities
WO2017161784A1 (zh) 推荐内容的展示方法和装置
CN104063418A (zh) 搜索推荐方法和装置
CN106164909A (zh) 自然语言输入的任务完成
CN106789543A (zh) 会话中实现表情图像发送的方法和装置
CN105528135A (zh) 信息的展现方法、装置和电子装置
KR101708048B1 (ko) 검색 추천 방법 및 장치
US9542495B2 (en) Targeted content provisioning based upon tagged search results
TW201502947A (zh) 使直接app動作浮現
CN114969524A (zh) 信息搜索方法、装置、设备及介质
CN104331465A (zh) 移动终端的搜索方法及装置
CN114450680A (zh) 内容项目模块布置
US20150026196A1 (en) Location-aware content detection
WO2016078519A1 (zh) 搜索方法和装置
CN106202484A (zh) 一种推荐浏览信息的方法及一种客户端
CN104794115A (zh) 应用推荐方法和系统
WO2016155142A1 (zh) 信息搜索方法和信息搜索装置
CN103049469A (zh) 自传界面

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: 14886507

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: 14886507

Country of ref document: EP

Kind code of ref document: A1