WO2016177277A1 - 一种信息推荐方法及装置 - Google Patents

一种信息推荐方法及装置 Download PDF

Info

Publication number
WO2016177277A1
WO2016177277A1 PCT/CN2016/079810 CN2016079810W WO2016177277A1 WO 2016177277 A1 WO2016177277 A1 WO 2016177277A1 CN 2016079810 W CN2016079810 W CN 2016079810W WO 2016177277 A1 WO2016177277 A1 WO 2016177277A1
Authority
WO
WIPO (PCT)
Prior art keywords
input
information
software
semantic analysis
recommendation
Prior art date
Application number
PCT/CN2016/079810
Other languages
English (en)
French (fr)
Inventor
李齐周
操颖平
盛子夏
Original Assignee
阿里巴巴集团控股有限公司
李齐周
操颖平
盛子夏
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 阿里巴巴集团控股有限公司, 李齐周, 操颖平, 盛子夏 filed Critical 阿里巴巴集团控股有限公司
Publication of WO2016177277A1 publication Critical patent/WO2016177277A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor

Definitions

  • the present application relates to the field of computers, and in particular, to an information recommendation method and apparatus.
  • the embodiment of the present application provides a method for information recommendation, which is used to solve the problem that the recommended information solution provided by the prior art may cause waste of computing resources.
  • the embodiment of the present application provides an information recommendation apparatus for solving the problem that the recommended information scheme provided by the prior art may cause waste of computing resources.
  • the embodiment of the present application provides an information recommendation method using input software, which is used to solve the problem that the recommended information scheme provided by the prior art may cause waste of computing resources.
  • An embodiment of the present application provides an information recommendation apparatus using input software, which is used to solve the problem of using existing information.
  • the recommended information scheme provided by the technology may cause a waste of computing resources.
  • An information recommendation method includes: receiving input information sent by an input software through a software interface; and recommending information according to a semantic analysis result of the input information.
  • An information recommendation device includes: a receiving unit, configured to receive input information sent by the input software through a software interface; and a recommending unit, configured to recommend information according to a semantic analysis result of the input information.
  • An information recommendation method using input software comprising: inputting software to acquire information input by using input software; and recommending information according to a semantic analysis result of the input information.
  • An information recommendation device using input software includes: an acquisition unit for inputting software to acquire information input by using input software; and a display unit for recommending information according to a semantic analysis result of the input information.
  • the user can recommend the currently interested information according to the information input by the user in real time, thereby implementing the recommendation.
  • the user's information matches the user's current interests.
  • computing resources are saved.
  • FIG. 1 is a schematic flowchart of a specific implementation process of an information recommendation method according to Embodiment 1 of the present application;
  • FIG. 2 is a schematic structural diagram of an information recommendation apparatus according to Embodiment 2 of the present application.
  • FIG. 3 is a schematic flowchart of a specific implementation process of an information recommendation method using input software according to Embodiment 3 of the present application;
  • 5-1 is a schematic diagram of a method for recommending a product according to Embodiment 5 of the present application.
  • 5-2 is a schematic diagram of a user inputting information by using an input method editor according to Embodiment 5 of the present application;
  • 5-3 is a screenshot of displaying an item in an input method editor window according to Embodiment 5 of the present application.
  • 6-1 is a schematic diagram of a multimedia information recommendation method according to Embodiment 6 of the present application.
  • 6-2 is a screenshot of filling in user registration information in a website provided in Embodiment 6 of the present application.
  • 6-3 is a screenshot of recommending multimedia information when filling in user registration information in a website according to Embodiment 6 of the present application;
  • FIG. 7-1 is a schematic diagram of a method for recommending information applied to a mobile terminal according to Embodiment 7 of the present application;
  • FIG. 7-2 is a screenshot of the use of the instant messaging software of the mobile terminal provided in Embodiment 7 of the present application;
  • FIG. 7-3 is a screenshot of displaying recommended information in the instant messaging software of the mobile terminal according to Embodiment 7 of the present application.
  • Embodiment 1 provides a recommendation information method for solving the problem that the recommendation information scheme provided by the prior art may cause waste of computing resources.
  • a schematic diagram of the specific process of the method is shown in FIG. 1 and includes the following steps:
  • Step 11 Receive input information sent by the input software through the software interface.
  • the input information is information input by using the input software. For example, if the user inputs "want to buy a display" by using the input software, then “want to buy a display” is information input by using the input software, that is, Enter information.
  • the software interface is a bridge between the input software and the receiver.
  • the receiver can receive information input by the input software and input by the user using the input method in real time through the software interface. For example, the user inputs "want to buy a display” by using the input software, and the input method immediately sends "want to buy a display” to the receiver through the software interface, and the receiver can be a receiver to complete the task.
  • the receiver can be placed in the terminal or server.
  • the input software is software for implementing text input, and can be an input method editor with a certain encoding method, for example, the Chinese input method has its own pinyin coding, which is also called the pinyin input method software; it can also be a voice input software. Wait.
  • the input software it can be, but is not limited to, including: text input method software; handwriting input method software; voice input software.
  • the text input method software may be a pinyin input method software, a five-stroke input method software, etc.
  • the handwriting input method software may be an input software having a handwritten character recognition function
  • the voice input software may be an input software having a voice recognition function.
  • the input software may be input software applied to any operating system, for example, applied to a mobile terminal operating system (iOS, Android) software and applied to a personal computer (PC) operating system (Microsoft) Input software for Windows, Linux, Mac OS).
  • a mobile terminal operating system iOS, Android
  • PC personal computer
  • Microsoft Microsoft Input software for Windows, Linux, Mac OS
  • the input software obtains input information in the following manner:
  • the information input by the user through the input software is temporarily stored in the local cache, so the input information can be obtained from the local cache, and the obtained input information is real-time; the information input by the user through the input software is finally displayed in the Text box, so you can also type the text by typing
  • the text in the box is scanned to obtain input information, and the obtained input information is also real-time.
  • the input information is saved in the local cache at this time, and the user's real-time input information can be obtained from the local cache; when the user has already "Want to buy a monitor" is entered in a text box, and the user can input the real-time input information by scanning the text input in the text box.
  • the information that is input refers to the text information obtained by compiling the code input by the user through the input software; the information being input refers to the code that has been input to the input software but has not been compiled. Since both the input information and the information being input can be used as the basis for the recommendation information, at least one type or all of them can be obtained.
  • the information input by the user is “Want to buy a xianshiqi”, which includes the information “I want to buy one” and the information “xianshiqi” that is being input, but because I want to buy one, I want to buy one.
  • “xianshiqi” can not be used as the basis for recommendation information, so it is necessary to obtain two kinds of information at the same time, and select candidate words for the information being input, in order to completely serve as the basis for the recommendation information, such as "want to buy a display" Completely used as the basis for recommendation information.
  • the input information will be completed, and the candidate text will be selected for the information being input, and sent together through the software interface.
  • the recommendation information may include: receiving the specific input information sent by the input software through the software interface; wherein the specific input information refers to the input information that satisfies the semantic analysis trigger condition.
  • the semantic analysis trigger condition may include, but is not limited to, including: a word including the user's intention in the input information, and the like.
  • a word including the user's intention in the input information and the like.
  • the word “yes” in “Recently wanting an mp3” can reflect the user's intention; “look” and “good” in “watching a good movie”; “thinking” and “listening” in “want to listen to music” .
  • Similar words are: need, buy, lack, pay attention, buy, chase, go, etc. These words can reflect the user's intention.
  • the input information When the input information satisfies the semantic analysis trigger condition, the input information is sent through the software interface. For example, if I get “I still have a headset”, the sentence contains the word “missing”, so the semantic analysis trigger condition is met, and then “I still lack a headset” is sent through the software interface; get “Let's watch the movie.” "The sentence contains the words “see” and “go”, so the semantic analysis trigger condition is met, and then "Let's watch the movie” is sent through the software interface.
  • Semantic analysis trigger conditions can be flexibly controlled to flexibly control which information is sent.
  • step 12 the information is recommended based on the semantic analysis result of the input information.
  • Semantic analysis is a logical phase of the compilation process.
  • the task is to review the context-related nature of the source program, and the results of the review can be used as the basis for the recommendation information. For example, if the user enters "I want to buy a monitor", the semantic analysis will review the context-related nature of "I want to buy a monitor.”
  • the result of the review is that the current user has an intention to purchase the display, thereby recommending information related to the display for the current user ( Industry news, sales information, etc.).
  • the execution body of this step may be a server or a function module in the local.
  • the semantic analysis function can be integrated in the input software, or it can be The semantic analysis device of the gate is completed separately. Therefore, according to the semantic analysis result of the input information, the recommendation information may include: recommending the information according to the semantic analysis result of the input information by the semantic analysis device; or recommending the information according to the semantic analysis result of the local input information.
  • the input information may be provided to the semantic analysis device, so that the semantic analysis device performs semantic analysis on the input information, and then recommends the information according to the semantic analysis result; or performs semantic analysis on the input information locally, and then according to the semantic analysis result, Recommended information.
  • the semantic analysis device can be deployed locally or on the server.
  • the recommendation information may include: searching for the information according to the semantic analysis result of the input information; recommending the searched information.
  • the search keyword may be determined according to the semantic analysis result of the input information.
  • the source of the keyword it can be directly extracted from the semantic analysis result, or it can be obtained from the database according to the semantic analysis result.
  • the information received by the user is “Chai Jing is good, and I have time to look at her book.”
  • the book written by Chai Jing can be used as the basis for recommendation information, and then the firewood can be found from the database.
  • the information in the semantic analysis result may be used as a keyword, or the information associated with the information in the semantic analysis result may be used as a keyword.
  • the keywords in the semantic analysis result may be used as a keyword.
  • Word another example, according to the semantic analysis result, recommending to the user about the downtime information, you can determine the "CPU”, “main board”, “memory”, "video card” and other keywords associated with "downtime”;
  • the information is searched; wherein the searched information may include pictures, audio, video, sales information, sales links, and the like.
  • step 11 can only receive the specific input information sent by the input software through the software interface, so as to filter the obtained input information, so for step 12 further, according to the semantic analysis result of the input information,
  • the recommendation information may include: recommendation information according to a semantic analysis result of the specific input information.
  • step 11 when the phrase "I still lack a headset” is obtained, the sentence contains the word "missing”, which satisfies the semantic analysis trigger condition, and is recommended for the user through the semantic analysis result of the whole sentence.
  • Information related to the headset get “Let's watch the movie”, the sentence contains the words "see” and "go”, satisfying the semantic analysis trigger condition, recommending the movie related to the user through the semantic analysis result of the whole sentence Information, you can also recommend the purchase address of the movie ticket.
  • Semantic analysis is only performed on input information that is meaningful to the recommendation information. Similarly, it not only saves computing resources, but also is more targeted.
  • the execution body of this step may be a function module in the local area or a server.
  • the local can be a mobile phone, a tablet computer, a desktop computer, a notebook computer, a wearable smart device, etc.
  • the server can be a server for inputting software, or any server with semantic analysis function.
  • the recommendation information may include: displaying the recommended information at the specified location.
  • the recommended information may be displayed at any position of the screen, for example, displaying a play link of the song recommended by the user at the designated position of the screen; displaying a play link of the TV drama recommended by the user at the designated position of the screen; displaying at the designated position on the screen
  • Product information and purchase links recommended for users may be displayed at any position of the screen, for example, displaying a play link of the song recommended by the user at the designated position of the screen; displaying a play link of the TV drama recommended by the user at the designated position of the screen; displaying at the designated position on the screen
  • Product information and purchase links recommended for users may be displayed at any position of the screen, for example, displaying a play link of the song recommended by the user at the designated position of the screen; displaying a play link of the TV drama recommended by the user at the designated position of the screen; displaying at the designated position on the screen
  • Product information and purchase links recommended for users may be displayed at any position of the screen, for example, displaying a play link of the song recommended by the user
  • the display function may be integrated into the input software to display the recommended information at the specified location, which may include: displaying the recommended information in the input software window.
  • a location for recommending information can be expanded in the input software window.
  • the current sense can be recommended for the user according to the information input by the user in real time.
  • the information of interest, and thus the recommendation to the user matches the user's current interests.
  • computing resources are saved.
  • execution bodies of the steps of the method provided in Embodiment 1 may all be the same device, or the steps of the method may also be performed by different devices.
  • the execution body of step 11 may be device 1
  • the execution body of step 12 may be device 2
  • the execution body of step 11 and step 12 may be device 1;
  • Embodiment 2 provides a recommendation information device for solving the problem that the recommendation information scheme provided by the prior art may cause waste of computing resources.
  • the device comprises:
  • the receiving unit 21 can be configured to receive input information sent by the input software through a software interface, where the input information is information input by using the input software;
  • the recommendation unit 22 can be used to recommend information based on the semantic analysis result of the input information.
  • the receiving unit 21 can be used to:
  • Recommendation unit 22 which can be used to:
  • Recommendation information based on the results of semantic analysis of specific input information.
  • the input software obtains input information in the following manner:
  • the recommendation unit 22 can be used to:
  • the recommendation unit 22 can be used to:
  • the semantic analysis device the semantic analysis result of the input information, recommendation information; or
  • Recommendation information based on local semantic analysis of input information.
  • the recommendation unit 22 can be used to:
  • the recommendation unit 22 can be used to:
  • the input software includes at least one of the following:
  • the current sense can be recommended for the user according to the information input by the user in real time.
  • the information of interest enables the information recommended to the user to match the current interest of the user.
  • computing resources are saved.
  • Embodiment 3 provides an information recommendation method using input software for solving the problem that the recommended information scheme provided by the prior art may cause waste of computing resources. Assuming that the execution subject is input software, the specific process diagram of the method is as shown in FIG. 3, and includes the following steps:
  • step 31 the input software acquires information input using the input software.
  • the input software acquires the information input by using the input software, and may include: the input software acquires the input information from a local cache; or the input software scans the text input in the text box to obtain the The information entered.
  • step 32 the information is recommended based on the semantic analysis result of the input information.
  • the input software can first obtain the information input by using the input software, and according to the semantic analysis result of the input information, the recommendation information, so that the user can be recommended according to the information input by the user in real time.
  • the information of interest in turn, enables the information recommended to the user to match the current interest of the user.
  • computing resources are saved.
  • Embodiment 4 provides an information recommendation apparatus using input software for solving the problem that the recommended information scheme provided by the prior art may cause waste of computing resources.
  • the device comprises:
  • the obtaining unit 41 is configured to input software to obtain information input by using the input software
  • the display unit 42 can be used to recommend information based on the semantic analysis result of the input information.
  • the obtaining unit 41 can be used to:
  • the input software obtains the input information from the local cache; or
  • the input software obtains the input information by scanning the text entered in the text box.
  • the input software can first obtain the information input by using the input software, and according to the semantic analysis result of the input information, the recommendation information, so that the user can be recommended according to the information input by the user in real time.
  • the information of interest in turn, enables the information recommended to the user to match the current interest of the user.
  • computing resources are saved.
  • Embodiment 5 provides a method of recommending a commodity.
  • the execution entity is a function module in the terminal, and the application scenario is in the microblog status text box.
  • the schematic diagram of the method is as shown in Figure 5-1, and includes the following steps:
  • Step 51 as shown in FIG. 5-2, the user input information that satisfies the semantic analysis trigger condition sent by the input method software (hereinafter referred to as “input method”) through the software interface: “I want to buy a display”, wherein The input method "xian” is selected as “xian'shi'qi”.
  • step 52 a semantic analysis is performed on "I want to buy a monitor.”
  • Step 53 Determine a keyword "display" according to the result of the semantic analysis.
  • Step 54 Search for related products according to keywords.
  • Step 55 displays the searched product image in the input method window, and the image can be used as an entrance to the purchase link.
  • the input information of the input method software can be received in real time, the input information is semantically analyzed, and then the product recommendation is performed. Thereby, the user's purchase intention can be known in real time, and the product recommendation can be made. In turn, the product recommendation is matched with the user's current purchase intention.
  • Embodiment 6 provides a multimedia information recommendation method. Assume that the execution subject is a server, and the application scenario is in the “user name text box” of the website user registration process.
  • the schematic diagram of the method is as shown in FIG. 6-1, and includes the following steps:
  • Step 61 receives the Pinyin input method sent through the software interface, "Want to listen to Jay Chou's quietness", wherein “Want to listen to Jay Chou” is the user's input to the personal microblog status box to be released. Information, the input method for the "anjing" selected the candidate text "quiet”.
  • Step 62 a semantic analysis of "want to listen to the quietness of Jay Chou".
  • step 63 according to the result of the semantic analysis, the keyword "Jay Chou is quiet" is determined.
  • Step 64 search for Jay Chou's quiet multimedia information based on the keywords.
  • Step 65 as shown in FIG. 6-3, at the designated position, the searched “Jay Chou-Quiet” music play button icon plays music when the play button icon receives the click command.
  • the input information is semantically analyzed, and then the multimedia information is recommended. Therefore, the user's expectation for a certain multimedia information can be known in real time, and multimedia information recommendation can be performed. In turn, the multimedia information recommendation is matched with the current expectation of the user.
  • Embodiment 7 provides an information recommendation method applied to a mobile terminal. Assume that the execution subject is a mobile terminal, and the application scenario is in the instant messaging software. The schematic diagram of the method is as shown in FIG. 7-1, and includes the following steps:
  • Step 71 receives the “recently wanted computer” input by the input method through the software interface.
  • step 72 a semantic analysis is performed on "recently wanting to hack the computer".
  • step 73 the keyword "CPU" is determined according to the result of the semantic analysis.
  • Step 74 Search for product information of the CPU according to the keyword.
  • Step 75 displays the searched product picture of the "CPU" at a specified position in the screen of the mobile terminal.
  • step 76 the product icon receives the click instruction, and displays the product detail page through the browser of the mobile terminal.
  • the input information of the user using the mobile terminal input method software can be received in real time, the input information is semantically analyzed, and then the information recommendation is performed. Thereby, the user's interest can be understood in real time, and information recommendation can be made. In turn, the information recommendation is matched with the current interest of the user.
  • embodiments of the present application can be provided as a method, system, or computer program product.
  • the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment in combination of software and hardware.
  • the application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.
  • a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
  • processors CPUs
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • the memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory.
  • RAM random access memory
  • ROM read only memory
  • Memory is an example of a computer readable medium.
  • Computer readable media includes both permanent and non-persistent, removable and non-removable media.
  • Information storage can be implemented by any method or technology.
  • the information can be computer readable instructions, data structures, modules of programs, or other data.
  • Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory. (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disk read only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, Magnetic cassette tape, magnetic tape storage or other magnetic storage device or any other non-transportable medium that can be used for storage can be calculated Information accessed by the device.
  • computer readable media does not include temporary storage of computer readable media, such as modulated data signals and carrier waves.
  • embodiments of the present application can be provided as a method, system, or computer program product.
  • the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment in combination of software and hardware.
  • the application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

一种信息推荐方法,用于解决采用现有技术提供的推荐信息方案可能导致计算资源浪费的问题。方法包括:接收输入软件通过软件接口发送的输入信息(11);其中,输入信息是利用所述输入软件输入的信息;根据对输入信息的语义分析结果,推荐信息(12)。还公开了一种信息推荐装置、以及一种利用输入软件的信息推荐方法及装置。

Description

一种信息推荐方法及装置 技术领域
本申请涉及计算机领域,尤其涉及一种信息推荐方法及装置。
背景技术
随着互联网的普及,各种各样的信息出现在网络中,方便用户查找。为了满足不同用户的个性化需求,信息推荐孕育而生,不再需要用户自己查找,而是根据用户的历史行为,推测出用户的兴趣和需求,然后包含兴趣和需求的信息推荐给用户。比如,获取到用户最近3天在各大数码信息网站看手机,就可以推测出该用户对手机有需求,可以在第4天用户浏览购物网站时为他推荐手机的销售信息。
然而,用户的兴趣和需求有可能随时在变化,甚至于一秒钟的时间就会改变需求。现有技术基于用户的历史行为做出的推测,只是用户的历史兴趣和需求,而非当前的兴趣和需求。比如,一位母亲在购物网站看了一个小时婴儿奶瓶,但突然想到奶粉没了,这一秒钟的需求马上由奶瓶转换为奶粉,但现有技术还会根据前一小时的用户历史行为为该用户推荐奶瓶,显然,这些推荐信息与用户当前兴趣不匹配,造成了计算资源的浪费。
发明内容
本申请实施例提供一种信息推荐方法,用于解决采用现有技术提供的推荐信息方案可能导致计算资源浪费的问题。
本申请实施例提供一种信息推荐装置,用于解决采用现有技术提供的推荐信息方案可能导致计算资源浪费的问题。
本申请实施例提供一种利用输入软件的信息推荐方法,用于解决采用现有技术提供的推荐信息方案可能导致计算资源浪费的问题。
本申请实施例提供一种利用输入软件的信息推荐装置,用于解决采用现有 技术提供的推荐信息方案可能导致计算资源浪费的问题。
本申请实施例采用下述技术方案:
一种信息推荐方法,包括:接收输入软件通过软件接口发送的输入信息;根据对输入信息的语义分析结果,推荐信息。
一种信息推荐装置,包括:接收单元,用于接收输入软件通过软件接口发送的输入信息;推荐单元,用于根据对输入信息的语义分析结果,推荐信息。
一种利用输入软件的信息推荐方法,包括:输入软件获取利用输入软件输入的信息;根据对所述输入的信息的语义分析结果,推荐信息。
一种利用输入软件的信息推荐装置,包括:获取单元,用于输入软件获取利用输入软件输入的信息;展示单元,用于根据对所述输入的信息的语义分析结果,推荐信息。
本申请实施例采用的上述至少一个技术方案能够达到以下有益效果:
由于可以先接收输入软件通过软件接口发送的输入信息,再根据对输入信息的语义分析结果,推荐信息,从而可以根据用户实时输入的信息,为用户推荐当前感兴趣的信息,进而实现了推荐给用户的信息与用户当前的兴趣相匹配。此外,还节约了计算资源。
附图说明
此处所说明的附图用来提供对本申请的进一步理解,构成本申请的一部分,本申请的示意性实施例及其说明用于解释本申请,并不构成对本申请的不当限定。在附图中:
图1为本申请实施例1提供的一种信息推荐方法的具体实现流程示意图;
图2为本申请实施例2提供的一种信息推荐装置的具体结构示意图;
图3为本申请实施例3提供的一种利用输入软件的信息推荐方法的具体实现流程示意图;
图4为本申请实施例4提供的一种利用输入软件的信息推荐装置的具体结 构示意图;
图5-1为本申请实施例5提供的一种商品的推荐方法的示意图;
图5-2为本申请实施例5提供的用户利用输入法编辑器输入信息的示意图;
图5-3为本申请实施例5提供的在输入法编辑器窗口中展示商品的截图;
图6-1为本申请实施例6提供的一种多媒体信息推荐方法的示意图;
图6-2为本申请实施例6提供的网站中填写用户注册信息的截图;
图6-3为本申请实施例6提供的在网站中填写用户注册信息时推荐多媒体信息的截图;
图7-1为本申请实施例7提供的一种应用于移动终端的信息推荐方法的示意图;
图7-2为本申请实施例7提供的移动终端的即时通信软件的使用截图;
图7-3为本申请实施例7提供的在移动终端的即时通信软件中展示推荐信息的截图。
具体实施方式
为使本申请的目的、技术方案和优点更加清楚,下面将结合本申请具体实施例及相应的附图对本申请技术方案进行清楚、完整地描述。显然,所描述的实施例仅是本申请一部分实施例,而不是全部的实施例。基于本申请中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本申请保护的范围。
以下结合附图,详细说明本申请各实施例提供的技术方案。
实施例1
实施例1提供了一种推荐信息方法,用于解决采用现有技术提供的推荐信息方案可能导致计算资源浪费的问题。该方法的具体流程示意图如图1所示,包括下述步骤:
步骤11,接收输入软件通过软件接口发送的输入信息。
针对步骤11而言,输入信息是利用输入软件输入的信息,比如,用户利用输入软件输入了“想买一台显示器”,那么“想买一台显示器”就是利用输入软件输入的信息,也就是输入信息。
软件接口是输入软件与接收方的一座桥梁,接收方可以通过该软件接口,接收输入软件发送的用户利用该输入法实时输入的信息。比如,用户利用输入软件输入了“想买一台显示器”,该输入法通过软件接口,立刻将“想买一台显示器”发送给接收方,接收方可以是一个接收器来完成该任务,该接收器可以布设在终端或服务器中。
输入软件是实现文字输入的软件,可以是自带某种编码方式的输入法编辑器,例如中文输入法中自带拼音编码,也即通常所说的拼音输入法软件;还可以是语音输入软件等。
所以,针对输入软件而言,可以但不限于包括:文字输入法软件;手写输入法软件;语音输入软件。比如,文字输入法软件可以是拼音输入法软件、五笔输入法软件等,手写输入法软件可以是具有手写文字识别功能的输入软件,语音输入软件可以是具有语音识别功能的输入软件。
需要说明的是,输入软件可以是应用于任何操作系统中的输入软件,比如,应用于移动终端操作系统中(iOS、Android)软件和应用于个人电脑(personal computer,PC)操作系统中(Microsoft Windows、Linux、Mac OS)的输入软件。
针对步骤11进一步而言,输入软件采用下述方式获取输入信息:
从本地缓存中获取输入信息;或通过对输入在文本框中的文本进行扫描,获取输入信息。
具体地,用户通过输入软件输入的信息,会临时存储在本地缓存中,所以可以从本地缓存中获取输入信息,并且获取的输入信息具有实时性;用户通过输入软件输入的信息,最终会显示在文本框中,所以也可以通过对输入对文本 框中的文本进行扫描,获取输入信息,获取的输入信息也具有实时性。比如,当用户在输入软件中输入“想买一台显示器”,此时会将该输入的信息保存在本地缓存中,这时就可以从本地缓存中获取用户实时的输入信息;当用户已经将“想买一台显示器”输入在某个文本框中,这时就可以通过对输入在文本框中的文本进行扫描,获取用户实时的输入信息。
在实际应用中,用户的输入习惯各不相同,有人习惯一次输入一整句话,有人习惯将一整句话分成几部分依次输入。比如,在拼音输入法软件中,有人会输入“xiang’mai’yi’tai’xian’shi’qi”这一整句的拼音并转换为文字“想买一台显示器”;还有人会先输入“xiang’mai’yi’tai”这部分的拼音,转换为文字“想买一台”,再输入“xian’shi’qi”这部分的拼音,转换为文字“显示器”。这里所说的“xiang’mai’yi’tai’xian’shi’qi”是正在输入的信息,而“想买一台显示器”是完成输入的信息。
完成输入的信息,是指通过输入软件对用户输入的编码进行编译后得到的文字信息;正在输入的信息是指已输入到输入软件但未完成编译的编码。由于完成输入的信息和正在输入的信息都可以作为推荐信息的依据,所以可以至少获取一种,或者获取全部。比如,获取到的用户输入的信息为“想买一台xianshiqi”,其中包含完成输入的信息“想买一台”和正在输入的信息“xianshiqi”,但由于单独获取“想买一台”或“xianshiqi”都不能完全作为推荐信息的依据,所以就需要同时获取两种信息,并为正在输入的信息挑选出候选文字,才能完全作为推荐信息的依据,比如“想买一台显示器”就可以完全作为推荐信息的依据。将完成输入的信息,以及为正在输入的信息挑选出候选文字,一起通过软件接口进行发送。
在实际应用中,有这么一种情况,并不是用户通过输入软件输入的所有信息都值得作为推荐信息的依据。比如,日常用语“你好”、“拜拜”等,作为推荐信息的依据就意义不是很大。若直接根据这样的信息,为用户推荐信息(比如,推荐“你好”在不同语种中的写法等),一般情况下,用户不会在意这些, 所以这显然会导致计算资源的浪费,并且一些用户可能会认为这些多余。
所以,接收输入软件通过软件接口发送的输入信息,推荐信息,可以包括:接收输入软件通过软件接口发送的特定输入信息;其中,特定输入信息是指满足语义分析触发条件的输入信息。
具体地,语义分析触发条件可以但不限于包括:输入的信息中包含用户意图的词语等。比如:“最近想要一个mp3”中的“要”字就能够体现用户的意图;“看电影不错”中的“看”和“不错”;“想听音乐”中的“想”“听”。类似的词语有:需要、买、缺、关注、置办、追、去等等,这些词语都可以体现用户的意图。
当输入信息满足语义分析触发条件时,再将输入信息通过软件接口进行发送。比如,获取到“我还缺一耳机”,句中包含“缺”字,所以满足了语义分析触发条件,再将“我还缺一耳机”通过软件接口进行发送;获取到“咱们看电影去吧”,句中包含“看”和“去”字,所以满足了语义分析触发条件,再将“咱们看电影去吧”通过软件接口进行发送。
先根据语义分析触发条件,对获取到的输入信息进行过滤,再将输入信息进行发送,只发送对推荐信息有很大意义的输入信息,这样不仅节约了计算资源,还更加有针对性。语义分析触发条件可以灵活控制,从而灵活控制发送哪些信息。
步骤12,根据对输入信息的语义分析结果,推荐信息。
语义分析是编译过程的一个逻辑阶段,任务是对源程序进行上下文有关性质的审查,审查的结果就可以作为推荐信息的依据。比如,用户输入“我想买显示器”,语义分析就对“我想买显示器”进行上下文有关性质的审查,审查结果就是当前用户有购买显示器的意向,从而为当前用户推荐与显示器相关的信息(行业新闻、销售信息等)。
该步骤的执行主体,可以是服务器,也可以是本地中的功能模块。
针对步骤12而言,语义分析的功能可以集成在输入软件中,也可以由专 门的语义分析设备单独完成。所以,根据对输入信息的语义分析结果,推荐信息,可以包括:根据语义分析设备对输入信息的语义分析结果,推荐信息;或根据本地对输入信息的语义分析结果,推荐信息。
具体地,可以将输入信息提供给语义分析设备,以使得语义分析设备对输入信息进行语义分析,再根据语义分析结果,推荐信息;或在本地对输入信息进行语义分析,再根据语义分析结果,推荐信息。其中,语义分析设备可以布设在本地,也可以布设在服务器。
在实际应用中,根据对输入信息的语义分析结果,进行推荐信息时,会根据语义分析结果,搜索出一些具有针对性的信息,而不仅仅是简单的搜索所有与语义分析结果有关的信息。
所以,根据对输入信息的语义分析结果,推荐信息,可以包括:根据对输入信息的语义分析结果,搜索信息;推荐搜索到的信息。
具体地,可以先根据对输入信息的语义分析结果,确定出搜索关键字。
针对关键字的来源而言,其可以是从语义分析结果中直接提取出的,也可以是根据语义分析结果从数据库中获得的。比如,接收到用户输入的信息是“柴静好样的,有空再看看她的书”,根据语义分析,可以将柴静写的书作为推荐信息的依据,再从数据库中查找到柴静写过的书有几本,然后确定出书的名称,并把书的作者和名称作为关键字。
针对关键字的确定方式而言,可以将从语义分析结果中的信息作为关键字,也可以将与语义分析结果中的信息相关联的信息作为关键字。比如,根据语义分析结果,推荐给用户关于耳机的信息,可以直接提取“耳机”这个关键字,也可以确定出与“耳机”相关联的“耳麦”、“音响”、“播放器”等关键字;又如,根据语义分析结果,推荐给用户关于攒机的信息,就可以确定出与“攒机”相关联的“CPU”、“主板”、“内存”、“显卡”等关键字;
再根据这些关键字,搜索信息;其中,搜索出的信息可以包括图片、音频、视频、销售信息、销售链接等。
在步骤11中介绍了,步骤11可以只接收输入软件通过软件接口发送的特定输入信息,以便对获取到的输入信息进行过滤,所以针对步骤12进一步而言,根据对输入信息的语义分析结果,推荐信息,可以包括:根据对特定输入信息的语义分析结果,推荐信息。
比如,以步骤11中的举例来说,当获取到“我还缺一耳机”,句中包含“缺”字,满足了语义分析触发条件,通过对整句话的语义分析结果,为用户推荐与耳机相关的信息;获取到“咱们看电影去吧”,句中包含“看”和“去”字,满足了语义分析触发条件,通过对整句话的语义分析结果,为用户推荐电影相关的信息,还可以推荐电影票的购买地址。
只对对推荐信息有很大意义的输入信息做语义分析,同样,不仅节约了计算资源,还更加有针对性。
该步骤的执行主体可以是本地中的功能模块,也可以是服务器。其中,本地可以是手机、平板电脑、台式电脑、笔记本电脑、可穿戴智能设备等;服务器,可以是输入软件的服务器,也可以是任何具备语义分析功能的服务器等。
在一种实施方式中,为了实现信息展示的效果,推荐信息,可以包括:在指定位置展示推荐的信息。
具体地,可以在屏幕的任一位置展示推荐的信息,比如,在屏幕指定位置展示为用户推荐的歌曲的播放链接;在屏幕指定位置展示为用户推荐的电视剧的播放链接;在屏幕指定位置展示为用户推荐的商品信息及购买链接等。
在一种实施方式中,可以将展示功能集成在输入软件中,在指定位置展示推荐的信息,可以包括:在输入软件窗口中展示推荐的信息。
具体地,可以在输入软件窗口中,扩展出一个用于推荐信息的位置。
采用实施例1提供的该方法,由于可以先接收输入软件通过软件接口发送的输入信息,再根据对输入信息的语义分析结果,推荐信息,从而可以根据用户实时输入的信息,为用户推荐当前感兴趣的信息,进而实现了推荐给用户的 信息与用户当前的兴趣相匹配。此外,还节约了计算资源。
需要说明的是,实施例1所提供方法的各步骤的执行主体均可以是同一设备,或者,该方法的各步骤也可以由不同设备作为执行主体。比如,步骤11的执行主体可以为设备1,步骤12的执行主体可以为设备2;又比如,步骤11和步骤12的执行主体可以为设备1;等等。
实施例2
基于相同的发明构思,实施例2提供了一种推荐信息装置,用于解决采用现有技术提供的推荐信息方案可能导致计算资源浪费的问题。如图2所示,该装置包括:
接收单元21,可以用于接收输入软件通过软件接口发送的输入信息;其中,输入信息是利用输入软件输入的信息;
推荐单元22,可以用于根据对输入信息的语义分析结果,推荐信息。
在一种实施方式中,接收单元21,可以用于:
接收输入软件通过软件接口发送的特定输入信息;其中,特定输入信息是指满足语义分析触发条件的输入信息。
推荐单元22,可以用于:
根据对特定输入信息的语义分析结果,推荐信息。
在一种实施方式中,输入软件采用下述方式获取输入信息:
从本地缓存中获取输入信息;或
通过对输入在文本框中的文本进行扫描,获取输入信息。
在一种实施方式中,推荐单元22,可以用于:
根据对输入信息的语义分析结果,搜索信息;
推荐搜索到的信息。
在一种实施方式中,推荐单元22,可以用于:
根据语义分析设备对输入信息的语义分析结果,推荐信息;或
根据本地对输入信息的语义分析结果,推荐信息。
在一种实施方式中,推荐单元22,可以用于:
在指定位置展示推荐的信息。
在一种实施方式中,推荐单元22,可以用于:
在输入软件窗口中展示推荐的信息。
在一种实施方式中,输入软件,包括下述至少一种:
文字输入法软件;
手写输入法软件;
语音输入软件。
采用实施例2提供的该装置,由于可以先接收输入软件通过软件接口发送的输入信息,再根据对输入信息的语义分析结果,推荐信息,从而可以根据用户实时输入的信息,为用户推荐当前感兴趣的信息,进而实现了推荐给用户的信息与用户当前的兴趣相匹配。此外,还节约了计算资源。
实施例3
实施例3提供了一种利用输入软件的信息推荐方法,用于解决采用现有技术提供的推荐信息方案可能导致计算资源浪费的问题。假设执行主体是输入软件,该方法的具体流程示意图如图3所示,包括下述步骤:
步骤31,输入软件获取利用输入软件输入的信息。
在一种实施方式中,输入软件获取利用输入软件输入的信息,可以包括:输入软件从本地缓存中获取所述输入的信息;或输入软件通过对输入在文本框中的文本进行扫描,获取所述输入的信息。
步骤32,根据对输入的信息的语义分析结果,推荐信息。
由于该方法的执行主体是输入软件,具体实施方式与实施例1类似,所以不再赘述。
采用实施例3提供的该方法,由于输入软件可以先获取利用该输入软件输入的信息,再根据对输入的信息的语义分析结果,推荐信息,从而可以根据用户实时输入的信息,为用户推荐当前感兴趣的信息,进而实现了推荐给用户的信息与用户当前的兴趣相匹配。此外,还节约了计算资源。
实施例4
基于相同的发明构思,实施例4提供了一种利用输入软件的信息推荐装置,用于解决采用现有技术提供的推荐信息方案可能导致计算资源浪费的问题。如图4所示,该装置包括:
获取单元41,可以用于输入软件获取利用输入软件输入的信息;
展示单元42,可以用于根据对输入的信息的语义分析结果,推荐信息。
在一种实施方式中,获取单元41,可以用于:
输入软件从本地缓存中获取输入的信息;或
输入软件通过对输入在文本框中的文本进行扫描,获取输入的信息。
采用实施例4提供的该装置,由于输入软件可以先获取利用该输入软件输入的信息,再根据对输入的信息的语义分析结果,推荐信息,从而可以根据用户实时输入的信息,为用户推荐当前感兴趣的信息,进而实现了推荐给用户的信息与用户当前的兴趣相匹配。此外,还节约了计算资源。
实施例5
基于相同的发明构思,实施例5提供了一种商品的推荐方法。假设执行主体是终端中的功能模块,应用场景为在微博状态文本框中,该方法的示意图如图5-1所示,包括下述步骤:
步骤51,如图5-2所示,接收输入法软件(下文简称“输入法”)通过软件接口发送的满足语义分析触发条件的用户输入的信息:“好想买一台显示器”,其中,输入法为“xian’shi’qi”选取了候选文字“显示器”。
步骤52,对“好想买一台显示器”进行语义分析。
步骤53,根据语义分析结果,确定出关键字“显示器”。
步骤54,根据关键字,搜索相关商品。
步骤55,如图5-3所示,将搜索到的商品图片展示在输入法窗口中,图片可以作为进入购买链接的入口。
采用实施例5提供的该方法,由于可以实时接收输入法软件的输入信息,再对输入信息进行语义分析,然后进行商品推荐。从而可以实时了解用户的购买意向,并进行商品推荐。进而实现了商品推荐与用户当前的购买意向相匹配。
实施例6
基于相同的发明构思,实施例6提供了一种多媒体信息推荐方法。假设执行主体是服务器,应用场景为在网站用户注册流程的“用户名文本框”中,该方法的示意图如图6-1所示,包括下述步骤:
步骤61,如图6-2所示,接收拼音输入法通过软件接口发送的“想听周杰伦的安静”,其中,“想听周杰伦的”是用户输入到个人微博状态框中的待发布的信息,输入法为“anjing”选取了候选文字“安静”。
步骤62,对“想听周杰伦的安静”进行语义分析。
步骤63,根据语义分析结果,确定出关键字“周杰伦安静”。
步骤64,根据关键字,搜索周杰伦安静的多媒体信息。
步骤65,如图6-3所示,在指定位置,将搜索到的“周杰伦-安静”的音乐播放按钮图标,当该播放按钮图标接收到单击指令时,播放音乐。
采用实施例6提供的该方法,由于可以实时接收用户利用输入法软件的输入的信息,再对输入信息进行语义分析,然后进行多媒体信息推荐。从而可以实时了解用户对于某种多媒体信息的期望,并进行多媒体信息推荐。进而实现了多媒体信息推荐与用户当前的期望相匹配。
实施例7
基于相同的发明构思,实施例7提供了一种应用于移动终端的信息推荐方法。假设执行主体是移动终端,应用场景为在即时通信软件中,该方法的示意图如图7-1所示,包括下述步骤:
步骤71,如图7-2所示,接收输入法通过软件接口发送的利用该输入法输入的“最近想攒电脑”。
步骤72,对“最近想攒电脑”进行语义分析。
步骤73,根据语义分析结果,确定出关键字“CPU”。
步骤74,根据关键字,搜索CPU的商品信息。
步骤75,如图7-3所示,在移动终端的屏幕中的指定位置,显示搜索到的“CPU”的商品图片。
步骤76,该商品图标接收到点击指令,通过移动终端的浏览器,显示商品详情页。
采用实施例7提供的该方法,由于可以实时接收用户利用移动终端输入法软件的输入信息,再对输入信息进行语义分析,然后进行信息推荐。从而可以实时了解用户的兴趣,并进行信息推荐。进而实现了信息推荐与用户当前的兴趣相匹配。
本领域内的技术人员应明白,本申请的实施例可提供为方法、系统、或计算机程序产品。因此,本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且,本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本申请是参照根据本申请实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和 /或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器,使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中,使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品,该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上,使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理,从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
在一个典型的配置中,计算设备包括一个或多个处理器(CPU)、输入/输出接口、网络接口和内存。
内存可能包括计算机可读介质中的非永久性存储器,随机存取存储器(RAM)和/或非易失性内存等形式,如只读存储器(ROM)或闪存(flash RAM)。内存是计算机可读介质的示例。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括,但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带,磁带磁磁盘存储或其他磁性存储设备或任何其他非传输介质,可用于存储可以被计算 设备访问的信息。按照本文中的界定,计算机可读介质不包括暂存电脑可读媒体(transitory media),如调制的数据信号和载波。
还需要说明的是,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、商品或者设备不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、商品或者设备所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括要素的过程、方法、商品或者设备中还存在另外的相同要素。
本领域技术人员应明白,本申请的实施例可提供为方法、系统或计算机程序产品。因此,本申请可采用完全硬件实施例、完全软件实施例或结合软件和硬件方面的实施例的形式。而且,本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
以上仅为本申请的实施例而已,并不用于限制本申请。对于本领域技术人员来说,本申请可以有各种更改和变化。凡在本申请的精神和原理之内所作的任何修改、等同替换、改进等,均应包含在本申请的权利要求范围之内。

Claims (20)

  1. 一种信息推荐方法,其特征在于,包括:
    接收输入软件通过软件接口发送的输入信息;其中,输入信息是利用所述输入软件输入的信息;
    根据对输入信息的语义分析结果,推荐信息。
  2. 如权利要求1所述的方法,其特征在于,接收输入软件通过软件接口发送的输入信息,包括:
    接收输入软件通过软件接口发送的特定输入信息;其中,特定输入信息是指满足语义分析触发条件的输入信息。
    根据对输入信息的语义分析结果,推荐信息,包括:
    根据对特定输入信息的语义分析结果,推荐信息。
  3. 如权利要求1所述的方法,其特征在于,输入软件采用下述方式获取所述输入信息:
    从本地缓存中获取所述输入信息;或
    通过对输入在文本框中的文本进行扫描,获取所述输入信息。
  4. 如权利要求1所述的方法,其特征在于,根据对输入信息的语义分析结果,推荐信息,包括:
    根据对输入信息的语义分析结果,搜索信息;
    推荐搜索到的信息。
  5. 如权利要求1所述的方法,其特征在于,根据对输入信息的语义分析结果,推荐信息,包括:
    根据语义分析设备对输入信息的语义分析结果,推荐信息;或
    根据本地对输入信息的语义分析结果,推荐信息。
  6. 如权利要求1所述的方法,其特征在于,推荐信息,包括:
    在指定位置展示推荐的信息。
  7. 如权利要求2所述的方法,其特征在于,在指定位置展示推荐的信息, 包括:
    在输入软件窗口中展示推荐的信息。
  8. 如权利要求1所述的方法,其特征在于,输入软件,包括下述至少一种:
    文字输入法软件;
    手写输入法软件;
    语音输入软件。
  9. 一种信息推荐装置,其特征在于,包括:
    接收单元,用于接收输入软件通过软件接口发送的输入信息;其中,输入信息是利用所述输入软件输入的信息;
    推荐单元,用于根据对输入信息的语义分析结果,推荐信息。
  10. 如权利要求9所述的装置,其特征在于,接收单元,用于:
    接收输入软件通过软件接口发送的特定输入信息;其中,特定输入信息是指满足语义分析触发条件的输入信息。
    推荐单元,用于:
    根据对特定输入信息的语义分析结果,推荐信息。
  11. 如权利要求9所述的装置,其特征在于,输入软件采用下述方式获取所述输入信息:
    从本地缓存中获取所述输入信息;或
    通过对输入在文本框中的文本进行扫描,获取所述输入信息。
  12. 如权利要求9所述的装置,其特征在于,推荐单元,用于:
    根据对输入信息的语义分析结果,搜索信息;
    推荐搜索到的信息。
  13. 如权利要求9所述的装置,其特征在于,推荐单元,用于:
    根据语义分析设备对输入信息的语义分析结果,推荐信息;或
    根据本地对输入信息的语义分析结果,推荐信息。
  14. 如权利要求9所述的装置,其特征在于,推荐单元,用于:
    在指定位置展示推荐的信息。
  15. 如权利要求10所述的装置,其特征在于,推荐单元,用于:
    在输入软件窗口中展示推荐的信息。
  16. 如权利要求9所述的装置,其特征在于,输入软件,包括下述至少一种:
    文字输入法软件;
    手写输入法软件;
    语音输入软件。
  17. 一种利用输入软件的信息推荐方法,其特征在于,包括:
    输入软件获取利用输入软件输入的信息;
    根据对所述输入的信息的语义分析结果,推荐信息。
  18. 如权利要求17所述的方法,其特征在于,输入软件获取利用输入软件输入的信息,包括:
    输入软件从本地缓存中获取所述输入的信息;或
    输入软件通过对输入在文本框中的文本进行扫描,获取所述输入的信息。
  19. 一种利用输入软件的信息推荐装置,其特征在于,包括:
    获取单元,用于输入软件获取利用输入软件输入的信息;
    展示单元,用于根据对所述输入的信息的语义分析结果,推荐信息。
  20. 如权利要求19所述的装置,其特征在于,获取单元,用于:
    输入软件从本地缓存中获取所述输入的信息;或
    输入软件通过对输入在文本框中的文本进行扫描,获取所述输入的信息。
PCT/CN2016/079810 2015-05-04 2016-04-21 一种信息推荐方法及装置 WO2016177277A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510221530.3A CN106202087A (zh) 2015-05-04 2015-05-04 一种信息推荐方法及装置
CN201510221530.3 2015-05-04

Publications (1)

Publication Number Publication Date
WO2016177277A1 true WO2016177277A1 (zh) 2016-11-10

Family

ID=57218034

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/079810 WO2016177277A1 (zh) 2015-05-04 2016-04-21 一种信息推荐方法及装置

Country Status (2)

Country Link
CN (1) CN106202087A (zh)
WO (1) WO2016177277A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111353836A (zh) * 2018-12-20 2020-06-30 百度在线网络技术(北京)有限公司 商品推荐方法、装置及设备

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110009437A (zh) * 2018-01-05 2019-07-12 北京搜狗科技发展有限公司 推荐方法和装置、用于推荐的装置
CN111489131A (zh) * 2019-01-25 2020-08-04 北京搜狗科技发展有限公司 一种信息推荐方法及装置
CN110334941A (zh) * 2019-07-01 2019-10-15 百度在线网络技术(北京)有限公司 无人物流车调度方法、装置、电子设备和可读存储介质
CN110598098A (zh) * 2019-08-30 2019-12-20 北京搜狗科技发展有限公司 一种信息推荐方法、装置和用于信息推荐的装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102236646A (zh) * 2010-04-20 2011-11-09 得利在线信息技术(北京)有限公司 对象级垂直搜索引擎个性化排序算法iRank
CN103235802A (zh) * 2013-04-16 2013-08-07 武汉理工大学 用户复杂需求获取方法与系统
CN103839169A (zh) * 2012-11-21 2014-06-04 大连灵动科技发展有限公司 一种基于频率矩阵和文本相似度的个性化商品推荐方法
CN104090958A (zh) * 2014-07-04 2014-10-08 许昌学院 一种基于领域本体的语义信息检索系统及方法
CN104216931A (zh) * 2013-05-29 2014-12-17 酷盛(天津)科技有限公司 实时推荐系统及方法

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102362275A (zh) * 2009-03-23 2012-02-22 富士通株式会社 内容推荐方法、推荐信息生成方法、内容推荐程序、内容推荐服务器以及内容提供系统
CN102323919A (zh) * 2011-08-12 2012-01-18 百度在线网络技术(北京)有限公司 一种基于用户情绪指示信息显示输入信息的方法与设备
US20140280314A1 (en) * 2013-03-14 2014-09-18 Advanced Search Laboratories, lnc. Dimensional Articulation and Cognium Organization for Information Retrieval Systems
US20140337372A1 (en) * 2013-05-13 2014-11-13 Samsung Electronics Co., Ltd. Method of providing program using semantic mashup technology
CN104133855B (zh) * 2014-07-11 2017-12-19 中安消技术有限公司 一种输入法智能联想的方法及装置
CN104298429B (zh) * 2014-09-25 2018-05-04 北京搜狗科技发展有限公司 一种基于输入的信息展示方法和输入法系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102236646A (zh) * 2010-04-20 2011-11-09 得利在线信息技术(北京)有限公司 对象级垂直搜索引擎个性化排序算法iRank
CN103839169A (zh) * 2012-11-21 2014-06-04 大连灵动科技发展有限公司 一种基于频率矩阵和文本相似度的个性化商品推荐方法
CN103235802A (zh) * 2013-04-16 2013-08-07 武汉理工大学 用户复杂需求获取方法与系统
CN104216931A (zh) * 2013-05-29 2014-12-17 酷盛(天津)科技有限公司 实时推荐系统及方法
CN104090958A (zh) * 2014-07-04 2014-10-08 许昌学院 一种基于领域本体的语义信息检索系统及方法

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111353836A (zh) * 2018-12-20 2020-06-30 百度在线网络技术(北京)有限公司 商品推荐方法、装置及设备

Also Published As

Publication number Publication date
CN106202087A (zh) 2016-12-07

Similar Documents

Publication Publication Date Title
WO2016177277A1 (zh) 一种信息推荐方法及装置
US9524714B2 (en) Speech recognition apparatus and method thereof
WO2018149115A1 (zh) 用于提供搜索结果的方法和装置
US9342233B1 (en) Dynamic dictionary based on context
US20140172412A1 (en) Action broker
US20130086056A1 (en) Gesture based context menus
US8700594B2 (en) Enabling multidimensional search on non-PC devices
US10210146B2 (en) Productivity tools for content authoring
RU2685991C1 (ru) Основанные на контексте мгновенные поисковые рекомендации
TW201702907A (zh) 一種資訊搜尋導航方法及裝置
CN105283843B (zh) 可嵌入的媒体内容搜索微件
US20210279297A1 (en) Linking to a search result
US11748797B2 (en) System and method for providing recommendations to a target user based upon review and ratings data
CN102214208A (zh) 一种基于非结构化文本生成结构化信息实体的方法与设备
US20140164366A1 (en) Flat book to rich book conversion in e-readers
US20150046462A1 (en) Identifying actions in documents using options in menus
JP2023515158A (ja) デジタルアクション実行のためのインターフェースおよびモード選択
KR102551343B1 (ko) 전자 장치 및 그 제어 방법
US20180285444A1 (en) Rewriting contextual queries
CN106156109B (zh) 一种搜索方法及装置
WO2017083205A1 (en) Provide interactive content generation for document
US11151129B1 (en) Modifying query in discourse context
US20230401250A1 (en) Systems and methods for generating interactable elements in text strings relating to media assets
US20130179832A1 (en) Method and apparatus for displaying suggestions to a user of a software application
Dessi et al. Supporting semantic web search and structured queries on mobile devices

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: 16789271

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: 16789271

Country of ref document: EP

Kind code of ref document: A1