WO2020082938A1 - 标签的处理方法、装置、电子设备及存储介质 - Google Patents

标签的处理方法、装置、电子设备及存储介质 Download PDF

Info

Publication number
WO2020082938A1
WO2020082938A1 PCT/CN2019/106246 CN2019106246W WO2020082938A1 WO 2020082938 A1 WO2020082938 A1 WO 2020082938A1 CN 2019106246 W CN2019106246 W CN 2019106246W WO 2020082938 A1 WO2020082938 A1 WO 2020082938A1
Authority
WO
WIPO (PCT)
Prior art keywords
topic
target
tag
topic tag
verified
Prior art date
Application number
PCT/CN2019/106246
Other languages
English (en)
French (fr)
Inventor
申世伟
Original Assignee
北京达佳互联信息技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京达佳互联信息技术有限公司 filed Critical 北京达佳互联信息技术有限公司
Publication of WO2020082938A1 publication Critical patent/WO2020082938A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35Clustering; Classification
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9535Search customisation based on user profiles and personalisation

Definitions

  • the present application relates to the field of computer application technology, and in particular, to a tag processing method, device, electronic device, and storage medium.
  • the inventor found that because the text information posted by the user on the social networking site or the title text information of the video is generally relatively short, and there are problems with sparse vocabulary and irregular writing, resulting in serious high sparseness and high noise in the information summary data The problem makes it difficult for technicians to analyze and mine the text information posted by users, and it is difficult to extract effective label information from the text information posted by users.
  • embodiments of the present application provide a tag processing method, device, electronic device, and storage medium.
  • a label processing method including:
  • the target topic tag is extracted from the topic tag to be verified.
  • a label processing apparatus including:
  • the original topic tag acquisition module is configured to execute the acquisition of the original topic tag set for the target object in the information sharing platform
  • a topic tag determination module to be verified configured to perform the determination of the topic tag to be verified from the original topic tags
  • a webpage search module configured to perform a webpage search on the topic tag to be verified
  • the target topic tag extraction module is configured to perform a search result obtained according to the web page search to extract the target topic tag from the topic tag to be verified.
  • an electronic device including:
  • Memory for storing processor executable instructions
  • the processor is configured to:
  • the target topic tag is extracted from the topic tag to be verified.
  • a non-transitory computer-readable storage medium when instructions in the storage medium are executed by a processor of an electronic device, enabling the electronic device to execute a label processing method
  • the method includes any one of the label processing methods described above.
  • an application program when instructions in the application program are executed by a processor of an electronic device, enabling the electronic device to execute a label processing method, the method including:
  • the target topic tag is extracted from the topic tag to be verified.
  • the target topic tag is extracted from the topic tag to be verified.
  • the non-standard topic tags that are not suitable for research are effectively filtered from the original topic tags, which is simple and feasible, reduces the workload of technical personnel, improves the extraction efficiency of topic tags, and facilitates technology
  • the staff analyzes and researches the extracted target topic tags, and then grasps the user's attention hot spots, so as to better serve the users.
  • FIG. 1 is a flowchart of a label processing method according to an embodiment of the present application
  • FIG. 2 is a flowchart of another label processing method according to an embodiment of the present application.
  • FIG. 3 is a block diagram of a tag processing device according to an embodiment of the present application.
  • FIG. 4 is a block diagram of another tag processing apparatus according to an embodiment of the present application.
  • Fig. 5 is a block diagram of an electronic device according to an exemplary embodiment; (general structure of a mobile terminal)
  • Fig. 6 is a block diagram of an electronic device according to an exemplary embodiment. (General structure of the server)
  • FIG. 1 it is a flowchart of a tag processing method shown in an embodiment of the present application.
  • the topic tag extraction method is used in a terminal and includes the following steps:
  • step 101 the original topic tag set for the target object in the information sharing platform is obtained.
  • the information sharing platform is a carrier that people use to collect, publish, consult, and share information on the network, for example, various video websites, various community websites, various information exchange platforms such as Weibo, WeChat etc. Users will express their views or show their daily lives by posting personal videos, pictures and text messages on the information sharing platform.
  • the target object in the embodiment of the present application refers to personal video, image information or text information uploaded by the user to the website.
  • users post personal video or image information on the website in addition to text description and title information, they may also give the original topic tag matching the target object in the title information.
  • the original topic tag that matches the content of the text information may also be given in the title information.
  • the information publishing page of the website is set with a entry for a topic tag, instructing the user to set an original topic tag for the posted content.
  • the original topic tag set by the user will appear in the title information of the user's published content.
  • the location and manner of the original topic tags may be different.
  • the original topic tags of some websites appear in the title information, and the original topic tags of some websites appear at the beginning, middle, or end of the text; for example, the original topic tags may be between two "#" on the website page.
  • the text may also be a text between two "*" or some other symbols, which is not specifically limited in the embodiments of the present application.
  • a web crawler technology can be used to selectively access web pages and related links on the World Wide Web (such as various information sharing platforms and websites) according to a predetermined crawling target (such as characters representing original topic tags) , Store the captured web pages for certain analysis, identification and filtering, and then obtain the required information (that is, original topic tags).
  • One piece of information may correspond to one original topic tag, of course, there may be no original topic tag, or one piece of information may correspond to multiple original topic tags. If a piece of information corresponds to multiple original topic tags, you can obtain multiple original topic tags together. Of course, if the content of multiple topic tags is relatively similar, to avoid duplication, you can also obtain only one of the original topic tags. This embodiment of the present application does not specifically limit this.
  • step 102 from the original topic tags, the topic tags to be verified are determined.
  • step 103 a web page search is performed on the topic tag to be verified.
  • the topic tag to be verified is used as a search term, and it is input into a search box of a search engine to perform a web page search.
  • requests (crawler request library) are used to imitate a browser to initiate a request to a search engine website, and webpage searches are sequentially performed on the topic tags to be verified.
  • step 104 the target topic tag is extracted from the topic tags to be verified according to the search results obtained by the web page search.
  • the content of the search display page is parsed to check whether the content contains the URL of an effective encyclopedia website encyclopedia entry. That is, it is verified whether an encyclopedia-type website has included the topic tag to be verified as an encyclopedia entry. If the topic tag has been included in the entry, the search result page will contain an explanation entry for the encyclopedia-type website for the entry.
  • the topic tag that has been included in the encyclopedia entry means that the topic tag is not a tag arbitrarily set by the user, but a valid topic tag.
  • the topic tag is directly regarded as not a valid topic tag.
  • the topic tag may be a tag set arbitrarily by the user, or for technicians, it is a tag that has no value for follow-up research, for example, the tags of # ⁇ ⁇ ⁇ #, # ⁇ ⁇ ⁇ #.
  • BeautifulSoup (Crawler Parsing Library) can be used to formulate a rule when parsing web pages to help crawl the desired content.
  • technicians can filter out non-standard and unsuitable topic tags to be verified as research objects, and can extract effective topic tags more accurately, which provides a reference for the technicians to grasp social hot spots and user concerns. , In turn, can facilitate technicians to provide users with more accurate and valuable push information.
  • the present application by obtaining the original topic tag set for the target object in the information sharing platform, and then determining the topic tag to be verified from the original topic tag, and then performing a web search on the verified topic tag, and finally according to The search results obtained by web search extract the target topic tags from the topic tags to be verified.
  • the non-standard topic tags that are not suitable for research are effectively filtered from the original topic tags, which is simple and feasible, reduces the workload of technical personnel, improves the extraction efficiency of topic tags, and facilitates technology
  • the staff analyzes and researches the extracted target topic tags, and then grasps the user's attention hot spots, so as to better serve the users.
  • the topic tag extraction method is used in the terminal and includes the following steps:
  • step 201 the title information set for the target object in the information sharing platform is obtained.
  • the target object refers to the information content posted by the user in the information sharing platform, that is, video, text, pictures and other information.
  • the user When the user publishes the information, the user will set the title information for the information content. It also includes the topic tag set by the user for this piece of information. For example, the user posted a video of himself doing yoga, and the user set the following title information for the video: Enjoying the stretching of the limb # ⁇ #, where "sports" is the original topic tag.
  • a web crawler tool can be used to obtain the title information.
  • step 202 the original topic tag set by the user is extracted from the title information.
  • the original topic tags set by the user are extracted through symbol recognition. For example, the text content between the symbols "##" can be extracted from the title information.
  • the rules for setting the original topic tags may not be consistent. For example, some websites may also use the symbol "**" to set the original topic tags. Therefore, in specific implementation, it is necessary to pay attention to the rules for accurately identifying the settings on different information sharing platforms.
  • the time when the user posted the original topic tag can also be extracted. You can put all the acquired original topic tags into the original topic tag library for subsequent use.
  • step 203 it is determined that the frequency of occurrence of the original topic tag within a preset time period.
  • a preset time range is first set, for example, it can be set as a time zone from 00:00 on August 10, 2018 to 23:59 on September 10, 2018. Then, count the frequency of occurrence of each original topic tag in this preset time period, that is, the total number of occurrences.
  • the statistics may be performed in the original topic tag library formed in the previous step.
  • step 204 the original topic tags whose occurrence frequency is greater than the preset frequency threshold are determined as the topic tags to be verified.
  • a preset frequency threshold needs to be set (for example, the preset frequency threshold is set to 30 days 100 occurrences in total), the original topic tags whose occurrence frequency is less than the preset frequency threshold are eliminated, and the original topic tags whose occurrence frequency is greater than the preset frequency threshold are determined as the topic tags to be verified. In this way, the original topic tags that appear in the original topic tag library too frequently and are not suitable as research objects are filtered.
  • the frequency of appearance of the original topic tags is sorted, and the original topic tags whose occurrence frequencies are within a preset range are determined as the topic tags to be verified. For example, if the preset range of original topic tags' appearance frequency is set as the top 80%, then the occurrence frequency of all original topic tags that appear within the preset time is sorted, and the original topic tags whose appearance frequency ranks in the top 80% are determined Topic tag to be verified.
  • step 205 a web page search is performed on the topic tag to be verified.
  • step 205 may refer to step 103, and details are not described here.
  • step 206 the first source code of the search page is obtained.
  • the search result page is displayed, and at this time, the first source code of the search result page is obtained.
  • step 207 it is determined whether the target address link is included in the hypertext reference field of the first source code.
  • the target address link refers to a link of an entry page of a knowledge-type website or an encyclopedia-type website.
  • the hypertext reference field in the webpage can be parsed. For example, you can use the web page parsing tool Beautiful Soup (crawler parsing library); the hypertext reference field in the web page, for example, can be the "href" field, which is used to specify the URL of the hyperlink target (Uniform Resource Locator, unified resource positioning symbol).
  • search engine search using the topic tag “basketball” in the previous example as a search term.
  • topic tag of "basketball” has been used as an entry by an encyclopedia site, then the tag of "basketball” is a target topic tag.
  • a directory of encyclopedia-type websites may be established to facilitate verification of whether the target address link included in the hypertext reference field in the first source code is a link to an encyclopedia entry page of an encyclopedia website.
  • step 208 if the target address link is included in the hypertext reference field of the first source code, the topic tag to be verified is determined as the target topic tag.
  • the topic tag to be verified is considered to be the target topic tag.
  • the specific rule can be: if an encyclopedia-type website puts the topic tag to be verified into the encyclopedia entry, it is considered that the topic tag to be verified is the target topic tag; Only after the tag is included in the encyclopedia entry, the topic tag to be verified is considered the target topic tag.
  • the specific rule for determining the target topic tag is not specifically limited.
  • step 209 the target page corresponding to the target address link is acquired.
  • the target page corresponding to the target address link refers to an encyclopedia entry page corresponding to the target topic tag in an encyclopedia-type website.
  • an encyclopedia entry page corresponding to the target topic tag "basketball”.
  • step 210 the second source code of the target page is obtained.
  • the target page that is, the encyclopedia entry page corresponding to the target topic tag in the encyclopedia-type website, and the corresponding second source code can be obtained.
  • step 211 the title field and / or attribute field in the second source code is parsed to obtain the category to which the target topic tag belongs.
  • a webpage parsing tool such as BeautifulSoup (Crawler Parsing Library) can be used to parse the second source code. For example, it involves parsing the "title” field and "meta” (attribute) field of a web page, so as to obtain the category to which the target topic tag belongs.
  • the "Title” field of the web page is used to define the title of the web page. By parsing the "title” field, you can view the classification of the title. For example, the target topic label “basketball”, in the second source code of the encyclopedia entry page of the encyclopedia-type website where it is located, the page “title” is “basketball (ball sport)", so it is determined that basketball is a kind of ball. Belongs to the sports category, so that the category to which the hashtag # basketball # belongs is "sports" category.
  • the "meta” field of a webpage is used to describe the attributes of an HTML webpage document, such as author, date and time, webpage description, keywords, page refresh, etc.
  • "Meta” contains sub-fields such as description, keywords, and http-equiv. Among them, the "description” subfield can view the specific content of the description of the title. For example, to search for the target topic label "One Piece", in the second source code of the encyclopedia entry page of an encyclopedia type site, the content of the "description” field of the page is "" King of the Sea “is a young manga work painted by cartoonist Oda Eiichiro In “Weekly Teen Jump” started serialization on the 34th of 1997 ", from which we can know that” One Piece "is a comic. Thus, it is acquired that the category to which the target topic tag # ⁇ # belongs is the "comic" category.
  • the technician After obtaining the category to which the original topic tag belongs, the technician can understand the user's behavior preferences according to the category of the original topic tag that the user often sets, so that the user can push information that more closely matches the user's preferences; in addition, the user When searching using topic tags, if there is no search content that can be accurately matched, the technician can recommend content information in related categories for the user according to the category to which the topic tags belong.
  • the embodiment of the present application extracts the original topic tag from the title information, then determines the topic tag to be verified according to the frequency of occurrence of the original topic tag, then parses the first source code page to obtain the target topic tag, and finally parses the second Source code page to get the category to which the target topic tag belongs.
  • the tag processing apparatus 300 includes an original topic tag acquisition module 301, a topic tag determination module 302 to be verified, a web page search module 303, and a target topic tag extraction module 304.
  • the original topic tag acquisition module 301 is configured to execute the acquisition of the original topic tag set for the target object in the information sharing platform;
  • the topic tag to be verified determination module 302 is configured to perform the determination of the topic tag to be verified from the original topic tags
  • the webpage search module 303 is configured to perform webpage search on the topic tag to be verified
  • the target topic tag extraction module 304 is configured to perform a search result obtained from a web page search to extract the target topic tag from the topic tags to be verified.
  • FIG. 4 of an embodiment of the present application provides another label processing apparatus.
  • the label processing apparatus specifically includes:
  • the original topic tag acquisition module 301 includes:
  • the title information obtaining submodule 3011 is configured to execute the title information set for the target object in the obtaining information sharing platform;
  • the original topic tag extraction submodule 3012 is configured to perform extraction of the original topic tags set by the user from the title information.
  • the topic tag determination module 302 to be verified includes:
  • the frequency determining sub-module 3021 is configured to perform determining the frequency of occurrence of original topic tags within a preset time period
  • the topic tag to be verified sub-module 3022 is configured to perform the determination of the original topic tag whose appearance frequency is greater than a preset frequency threshold as the topic tag to be verified.
  • the target topic tag extraction module 304 includes:
  • the first source code obtaining submodule 3041 is configured to execute obtaining the first source code of the search page
  • the judging sub-module 3042 is configured to execute judging whether the target address link is included in the hypertext reference field of the first source code
  • the target topic tag determination sub-module 3043 is configured to execute the determination of the topic tag to be verified as the target topic tag if the target address link is included in the hypertext reference field of the source code.
  • the target page obtaining module 305 is configured to perform obtaining a target page corresponding to the target address link
  • the category determination module 306 is configured to perform classification of target topic tags according to the target page.
  • the classification determination module 306 includes:
  • the second source code obtaining submodule 3061 is configured to execute obtaining the second source code of the target page
  • the category acquisition submodule 3062 is configured to perform parsing of the title field and / or attribute field in the second source code to obtain the category to which the target topic tag belongs.
  • Fig. 5 is a block diagram of an electronic device 500 for label processing according to an exemplary embodiment.
  • the electronic device 500 may be a mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical device, fitness device, personal digital assistant, or the like.
  • the electronic device 500 may include one or more of the following components: a processing component 502, a memory 504, a power component 506, a multimedia component 508, an audio component 510, an input / output (I / O) interface 512, and a sensor component 514 , Communication component 516 and processor 520.
  • the processing component 502 generally controls the overall operations of the electronic device 500, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations.
  • the processing component 502 may include one or more processors 520 to execute instructions to complete all or part of the steps of the above method.
  • the processing component 502 may include one or more modules to facilitate interaction between the processing component 502 and other components.
  • the processing component 502 may include a multimedia module to facilitate interaction between the multimedia component 508 and the processing component 502.
  • the memory 504 is configured to store various types of data to support operation at the device 500. Examples of these data include instructions for any application or method operating on the electronic device 500, contact data, phone book data, messages, pictures, videos, and so on.
  • the memory 504 may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable Programmable read only memory (EPROM), programmable read only memory (PROM), read only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.
  • SRAM static random access memory
  • EEPROM electrically erasable programmable read only memory
  • EPROM erasable Programmable read only memory
  • PROM programmable read only memory
  • ROM read only memory
  • magnetic memory flash memory
  • flash memory magnetic disk or optical disk.
  • the power supply component 506 provides power to various components of the electronic device 500.
  • the power supply component 506 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 500.
  • the multimedia component 508 includes a screen between the electronic device 500 and the user that provides an output interface.
  • the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user.
  • the touch panel includes one or more touch sensors to sense touch, swipe, and gestures on the touch panel. The touch sensor may not only sense the boundary of the touch or sliding action, but also detect the duration and pressure related to the touch or sliding operation.
  • the multimedia component 508 includes a front camera and / or a rear camera. When the device 500 is in an operation mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.
  • the audio component 510 is configured to output and / or input audio signals.
  • the audio component 510 includes a microphone (MIC), and when the electronic device 500 is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal.
  • the received audio signal may be further stored in the memory 504 or transmitted via the communication component 516.
  • the audio component 510 further includes a speaker for outputting audio signals.
  • the I / O interface 512 provides an interface between the processing component 502 and a peripheral interface module.
  • the peripheral interface module may be a keyboard, a click wheel, or a button. These buttons may include, but are not limited to: home button, volume button, start button, and lock button.
  • the sensor component 514 includes one or more sensors for providing the electronic device 500 with status assessment in various aspects.
  • the sensor component 514 can detect the on / off state of the device 500, and the relative positioning of the components, such as the display and the keypad of the electronic device 500, and the sensor component 514 can also detect the position of the electronic device 500 or a component of the electronic device 500 Changes, the presence or absence of user contact with the electronic device 500, the orientation or acceleration / deceleration of the electronic device 500, and the temperature change of the electronic device 500.
  • the sensor assembly 514 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact.
  • the sensor component 514 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications.
  • the sensor assembly 514 may also include an acceleration sensor, a gyro sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
  • the communication component 516 is configured to facilitate wired or wireless communication between the electronic device 500 and other devices.
  • the electronic device 500 can access a wireless network based on a communication standard, such as WiFi, an operator network (such as 2G, 3G, 4G, or 5G), or a combination thereof.
  • the communication component 516 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel.
  • the communication component 516 also includes a near field communication (NFC) module to facilitate short-range communication.
  • the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.
  • RFID radio frequency identification
  • IrDA infrared data association
  • UWB ultra wideband
  • Bluetooth Bluetooth
  • the electronic device 500 may be one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field Programming gate array (FPGA), controller, microcontroller, microprocessor or other electronic components are implemented to perform the above method.
  • ASICs application specific integrated circuits
  • DSPs digital signal processors
  • DSPDs digital signal processing devices
  • PLDs programmable logic devices
  • FPGA field Programming gate array
  • controller microcontroller, microprocessor or other electronic components are implemented to perform the above method.
  • a non-transitory computer-readable storage medium including instructions is also provided, for example, a memory 504 including instructions, and the above instructions may be executed by the processor 520 of the electronic device 500 to complete the method of extracting the above topic tags .
  • the non-transitory computer-readable storage medium may be ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, or the like.
  • Fig. 6 is a block diagram of an electronic device 600 for label processing according to an exemplary embodiment.
  • the electronic device 600 may be provided as a server.
  • the electronic device 600 includes a processing component 622, which further includes one or more processors, and memory resources represented by the memory 632, for storing instructions executable by the processing component 622, such as application programs.
  • the application programs stored in the memory 632 may include one or more modules each corresponding to a set of instructions.
  • the processing component 622 is configured to execute instructions to execute the above-mentioned topic tag extraction method.
  • the electronic device 600 may also include a power component 626 configured to perform power management of the electronic device 600, a wired or wireless network interface 650 configured to connect the electronic device 600 to the network, and an input output (I / O) interface 658 .
  • the electronic device 600 can operate an operating system based on the memory 632, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, or the like.
  • An embodiment of the present application also provides an application program.
  • the electronic device can execute a label processing method, including:
  • the target topic tag is extracted from the topic tags to be verified.

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 Transfer Between Computers (AREA)

Abstract

一种标签的处理方法、装置、电子设备及存储介质,所述方法包括:通过获取信息分享平台中针对目标对象设置的原始话题标签(101),然后从所述原始话题标签中,确定待验证话题标签(102),再对所述待验证话题标签进行网页搜索(103),最后根据所述网页搜索获得的搜索结果,从所述待验证话题标签中提取出目标话题标签(104)。通过上述方法,有效地从原始话题标签中过滤掉了不规范的、不适合作为研究对象的话题标签,且简单可行,降低了技术人员的工作量,提高了话题标签的提取效率,方便了技术人员对提取出的目标话题标签进行分析研究,进而掌握用户关注热点,以更好地为用户服务。

Description

标签的处理方法、装置、电子设备及存储介质
相关申请的交叉引用
本申请要求在2018年10月23日提交中国专利局、申请号201811238336.6、发明名称为“标签的处理方法、装置、电子设备及存储介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及计算机应用技术领域,尤其涉及一种标签的处理方法、装置、电子设备及存储介质。
背景技术
随着互联网的迅猛发展,人们越来越乐于通过在社交网站发布文本信息或视频来表达观点和展现日常生活。用户在社交网站上发布的文本信息或视频往往蕴含着一定时期内的社会热点和大众的关注点,对这些内容进行研究,有利于技术人员更好地发掘用户需求,为用户推送更为有价值的信息。
但是发明人发现由于用户在社交网站上发布的文本信息或者视频的标题文本信息一般长度都比较短,且存在词汇稀疏、书写不规范的问题,导致了信息汇总数据中严重的高稀疏和高噪音问题,从而使得技术人员对用户发布的文本信息的分析和挖掘产生了困难,难以从用户发布的文本信息中提取出有效的标签信息。
发明内容
为克服现有技术中难以从用户发布的文本信息中提取有效的标签信息的问题,本申请实施例提供一种标签的处理方法、装置、电子设备及存储介质。
根据本申请实施例的第一方面,提供一种标签的处理方法,包括:
获取信息分享平台中,针对目标对象设置的原始话题标签;
从所述原始话题标签中,确定待验证话题标签;
对所述待验证话题标签进行网页搜索;
根据所述网页搜索获得的搜索结果,从所述待验证话题标签中提取出目标话题标签。
根据本申请实施例的第二方面,提供一种标签的处理装置,包括:
原始话题标签获取模块,被配置为执行获取信息分享平台中,针对目标对象设置的原始话题标签;
待验证话题标签确定模块,被配置为执行从所述原始话题标签中,确定待验证话题标签;
网页搜索模块,被配置为执行对所述待验证话题标签进行网页搜索;
目标话题标签提取模块,被配置为执行根据所述网页搜索获得的搜索结果,从所述待验证话题标签中提取出目标话题标签。
根据本申请实施例的第三方面,提供一种电子设备,包括:
处理器;
用于存储处理器可执行指令的存储器;
其中,所述处理器被配置为:
获取信息分享平台中,针对目标对象设置的原始话题标签;
从所述原始话题标签中,确定待验证话题标签;
对所述待验证话题标签进行网页搜索;
根据所述网页搜索获得的搜索结果,从所述待验证话题标签中提取出目标话题标签。
根据本申请实施例的第四方面,提供一种非临时性计算机可读存储介质,当所述存储介质中的指令由电子设备的处理器执行时,使得电子设备能够执行一种标签的处理方法,所述方法包括上述任意一项所述的标签的处理方法。根据本申请实施例的第五方面,提供一种应用程序,当所述应用程序中的指令由电子设备的处理器执行时,使得电子设备能够执行一种标签处理方法,所述方法包括:
获取信息分享平台中,针对目标对象设置的原始话题标签;
从所述原始话题标签中,确定待验证话题标签;
对所述待验证话题标签进行网页搜索;
根据所述网页搜索获得的搜索结果,从所述待验证话题标签中提取出目标话题标签。在本申请实施例中,通过获取信息分享平台中,针对目标对象设置的原始话题标签,然后从所述原始话题标签中,确定待验证话题标签,再对所述待验证话题标签进行网页搜索,最后根据所述网页搜索获得的搜索结果,从所述待验证话题标签中提取出目标话题标签。通过上述方法,有效地从原始话题标签中过滤掉了不规范的、不适合作为研究对象的话题标签,且简单可行,降低了技术人员的工作量,提高了话题标签的提取效率,方便了技术人员对提取出的目标话题标签进行分析研究,进而掌握用户关注热点,以更好地为用户服务。
应当理解的是,以上的一般描述和后文的细节描述仅是示例性和解释性的,并不能限制本申请。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分,示出了符合本申请的实施例,并与说明书一起用于解释本申请的原理。
图1是根据本申请实施例示出的一种标签的处理方法的流程图;
图2是根据本申请实施例示出的另一种标签的处理方法的流程图;
图3是根据本申请实施例示出的一种标签的处理装置的框图;
图4是根据本申请实施例示出的另一种标签的处理装置的框图;
图5是根据一示例性实施例示出的一种电子设备的框图;(移动终端的一般结构)
图6是根据一示例性实施例示出的一种电子设备的框图。(服务器的一般结构)
具体实施方式
这里将详细地对示例性实施例进行说明,其示例表示在附图中。下面的描述涉及附图时,除非另有表示,不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本申请相一致的所有实施方式。相反,它们仅是与如所附权利要求书中所详述的、本申请的一些方面相一致的装置和方法的例子。
在一个实施例中,参阅图1,为本申请实施例示出的一种标签的处理方法的流程图,如图1所示,话题标签的提取方法用于终端中,包括以下步骤:
在步骤101中,获取信息分享平台中,针对目标对象设置的原始话题标签。
在本申请实施例中,信息分享平台即是人们在网络上用来收集、发布、查阅、共享信息的载体,例如,各类视频网站、各类社区网站、各类信息交流平台如微博、微信等。用户会通过在信息分享平台中发布个人视频、图片及文字信息等,来表达观点或展现日常生活。
本申请实施例中的目标对象,指用户上传到网站的个人视频、图像信息或文字信息等内容。用户在网站发布个人视频或图像信息时,除了进行文字描述和添加标题信息,可能还会在标题信息中同时给出与该目标对象匹配的原始话题标签。另外,在用户不发布任何视频和图像信息,只发布文字信息的情况下,可能也会在标题信息中同时给出与该文字信息的内容匹配的原始话题标签。
具体地,用户在网站发布信息时,网站的信息发布页面设置有话题标签的填写项,指示用户为发布的内容设置原始话题标签。用户发布了信息后,用户设置的原始话题标签会出现在用户发布内容的标题信息中。在不同的信息分享平台上,原始话题标签出现的位置和方式可能是不同的。例如,有些网站的原始话题标签出现在标题信息中,有些网站的原始话题标签出现在正文的开头、中间或结尾;又例如,原始话题标签在网站页面上可能是两个“#”之间的文字,也可能是两个“*”之间的文字,或是其他一些符号,本申请实 施例对此不做具体限定。
在本申请实施例中,首先需要获取针对目标对象设置的原始话题标签。在一个实施例中,可以通过网络爬虫技术,根据既定的抓取目标(如代表原始话题标签的字符),有选择地访问万维网上的网页与相关的链接(如各类信息分享平台、网站),将抓取到的网页存储,进行一定的分析、识别和过滤,进而获得所需要的信息(即原始话题标签)。
例如,在一个社交网站上,用户发布了一段和朋友打篮球的视频,设置标题信息如下:“#篮球#久违的朋友,久违的篮球!”在这段文字信息中,位于两个“#”之间的“篮球”是原始话题标签。
一条信息可以对应一个原始话题标签,当然也可能没有原始话题标签,还可能一条信息对应多个原始话题标签。如果一条信息对应有多个原始话题标签,则可以将多个原始话题标签一并获取,当然,如果多个话题标签的内容比较相似,为了避免重复,也可以只获取其中的一个原始话题标签,本申请实施例对此不做具体限定。
在步骤102中,从原始话题标签中,确定待验证话题标签。
在本申请实施例中,由于用户给定的原始话题标签数量过于庞大,不利于研究分析,所以需要把一些出现频次比较低的话题标签剔除,以减少样本数量,确定出待验证话题标签,简化研究过程,使研究结果更为准确。
在步骤103中,对待验证话题标签进行网页搜索。
在本申请实施例中,将待验证话题标签作为搜索词,输入搜索引擎的搜索框中,进行网页搜索。具体地,使用requests(爬虫请求库)模仿浏览器对搜索引擎网站发起请求,对待验证话题标签依次进行网页搜索。
现有的搜索引擎种类很多,本申请实施例对所采用的搜索引擎不做具体限定。
在步骤104中,根据网页搜索获得的搜索结果,从待验证话题标签中提取出目标话题标签。
在本申请实施例中,在搜索结果页面中,解析搜索展示页面的内容,可 以查看其内容中是否含有效的百科类型网站百科知识词条的网址。即验证是否有百科类型网站已将该待验证话题标签作为百科词条收入,如果该话题标签已被收入词条,则搜索结果页面中就会包含百科类型网站对该词条的解释条目。已经被收入百科词条的话题标签,意味着该话题标签不是用户随意设置的标签,而是一个有效的话题标签。
如果搜索页面中不存在有效的百科类型网站对该待验证话题标签的解释条目,则直接认为该话题标签不是一个有效的话题标签。可能该话题标签是用户随意设置的标签,或者对于技术人员来说,是没有后续研究价值的标签,比如,#今天天气真好#、#该睡觉了#这一类的标签。
在一个实施例中,可以利用BeautifulSoup(爬虫解析库)在解析网页时制定一个规则,帮助抓取想要的内容。
采用上述技术方案,使技术人员过滤了不规范的、不适合作为研究对象的待验证话题标签,能够比较准确地提取到有效的话题标签,为技术人员掌握社会热点、用户关注热点提供了参考依据,进而可以方便技术人员为用户提供更为精准、有价值的推送信息。
综上,在本申请实施例中,通过获取信息分享平台中,针对目标对象设置的原始话题标签,然后从原始话题标签中,确定待验证话题标签,再对待验证话题标签进行网页搜索,最后根据网页搜索获得的搜索结果,从待验证话题标签中提取出目标话题标签。通过上述方法,有效地从原始话题标签中过滤掉了不规范的、不适合作为研究对象的话题标签,且简单可行,降低了技术人员的工作量,提高了话题标签的提取效率,方便了技术人员对提取出的目标话题标签进行分析研究,进而掌握用户关注热点,以更好地为用户服务。
在一个实施例中,参阅图2,为本申请实施例示出的另一种标签的处理方法。如图2所示,话题标签的提取方法用于终端中,包括以下步骤:
在步骤201中,获取信息分享平台中,针对目标对象设置的标题信息。
在本申请实施例中,目标对象指的是用户在信息分享平台中发布的信息 内容,即视频、文字、图片等信息,用户在发布信息时,会针对信息内容设置标题信息,该标题信息中还包括用户为该条信息设置的话题标签。例如,用户发布了一条自己做瑜伽的视频,用户为该视频设置了如下的标题信息:享受肢体伸展的愉悦#运动#,其中,“运动”就是原始话题标签。
具体地,可以使用网络爬虫工具获取标题信息。
在步骤202中,从标题信息中,提取用户设置的原始话题标签。
在本申请实施例中,在获取到标题信息后,通过符号识别提取用户设置的原始话题标签。例如,可以从标题信息中提取符号“##”之间的文本内容。
在不同的信息分享平台,原始话题标签的设置规则可能不太一致,例如,有些网站中也可能使用符号“**”来设置原始话题标签。所以在具体实施中,要在不同的信息分享平台,注意准确识别设置的规则。
在提取原始话题标签时,可以一并提取用户发布该原始话题标签的时间。可以将获取到的所有原始话题标签放入原始话题标签库中,以供后续使用。
在步骤203中,确定预设时间段内,原始话题标签的出现频次。
在本申请实施例中,首先设置一个预设时间范围,例如可以设置为2018年8月10日00:00——2018年9月10日23:59这个时间区段。然后,统计在这个预设时间区段内,各个原始话题标签出现的频次,即出现的总数量。
在一个实施例中,可以在之前步骤形成的原始话题标签库中进行统计。
在步骤204中,将出现频次大于预设频次阈值的原始话题标签确定为待验证话题标签。
在本申请实施例中,因为出现频次过低的原始话题标签可能不属于社会热点话题和用户关注的热点话题,所以需要设定一个预设频次阈值(例如,将预设频次阈值设为30天共出现100次),则将出现频次小于预设频次阈值的原始话题标签剔除,将出现频次大于预设频次阈值的原始话题标签确定为待验证话题标签。这样,就过滤了原始话题标签库中出现频次过低的、不适合作为研究对象的原始话题标签。
可选地,对原始话题标签的出现频次进行排序,将出现频次在预设范围内的原始话题标签确定为待验证话题标签。例如,将原始话题标签出现频次的预设范围定为前80%,则对预设时间内出现的所有原始话题标签的出现频次进行排序,将出现频次的排名在前80%的原始话题标签确定为待验证话题标签。
在步骤205中,对待验证话题标签进行网页搜索。
在本申请实施例中,步骤205可以参照步骤103,此处不再赘述。
在步骤206中,获取搜索页面的第一源代码。
在本申请实施例中,将待验证话题标签放入搜索引擎的搜索框中搜索之后,会展现出搜索结果页面,此时,获取搜索结果页面的第一源代码。
在步骤207中,判断第一源代码的超文本引用字段中是否包含目标地址链接。
在本申请实施例中,目标地址链接指的是知识类型网站或百科类型网站词条页面的链接。利用网页解析工具,对第一源代码页面进行解析,可以解析网页里的超文本引用字段。例如可以使用网页解析工具Beautiful Soup(爬虫解析库);网页里的超文本引用字段,例如可以是“href”字段,“href”字段用于指定超链接目标的URL(Uniform Resource Locator,统一资源定位符)。在本申请实施例中,可查看“href”字段引用的超链接目标的URL中是否有包含百科类型网站百科词条的网址链接。如果有,则说明该待验证话题标签已被百科类型网站收入百科词条,意味着该待验证话题标签是有一定影响力、知名度或者热度的,这种话题标签是具备研究价值的,这是一个有效的话题标签。
例如,将前文示例中的待验证话题标签“篮球”作为搜索词进行搜索引擎搜索,在得到的第一源代码页面中,某个“href”字段后面,是一个百科类型网站的百科词条页面的地址链接,那么,这就意味着“篮球”这个话题标签已被百科类型网站作为词条收入,那么,“篮球”这个标签就是一个目标话题标签。
可选地,可以建立百科类型网站的名录,以方便验证第一源代码中的超文本引用字段中包含的目标地址链接,是否是百科类网站百科词条页面的链接。
在步骤208中,在第一源代码的超文本引用字段中包含目标地址链接的情况下,将待验证话题标签确定为目标话题标签。
在本申请实施例中,若源代码的超文本引用字段中包含百科类型网站百科词条页面的地址链接,则认为待验证话题标签为目标话题标签。
具体规则可以是:有一个百科类型网站把待验证话题标签收进了百科词条,则认为待验证话题标签是目标话题标签;也可以是:达到了预设数量的百科类型网站把待验证话题标签收进了百科词条,才认为待验证话题标签是目标话题标签。在本申请实施例中,对确定目标话题标签的具体规则不做具体限定。
在步骤209中,获取与目标地址链接对应的目标页面。
在本申请实施例中,目标地址链接对应的目标页面,指在百科类型网站中与目标话题标签对应的百科词条页面。例如,在百度百科网站中与目标话题标签“篮球”对应的百科词条页面。
在步骤210中,获取目标页面的第二源代码。
在本申请实施例中,可以获取目标页面,即在百科类型网站中与目标话题标签对应的百科词条页面,对应的第二源代码。
在步骤211中,解析第二源代码中的标题字段和/或属性字段,获取目标话题标签所属的分类。
在本申请实施例中,可以利用网页解析工具,例如BeautifulSoup(爬虫解析库)解析第二源代码。例如涉及到解析网页的“title”(标题)字段和“meta”(属性)字段,从而获取到目标话题标签所属的分类。
网页的“Title”字段,用来定义网页的标题。通过解析“title”字段,可以查看对该标题的划分类别。例如,目标话题标签“篮球”,所在的百科类型网站的百科词条页面的第二源代码中,页面“title”是“篮球(球类运动)”, 因此确定篮球是一种球类,是属于运动类别,从而获取到话题标签#篮球#的所属的分类是“运动”类别。
网页的“meta”字段,用来描述一个HTML网页文档的属性,例如作者、日期和时间、网页描述、关键词、页面刷新等。“meta”其下包含description(描述)、Keywords(关键词)、http-equiv(网页文件头)等子字段。其中,“description”子字段可以查看对该标题描述的具体内容。例如,搜索目标话题标签“海贼王”,在百科类型网站的百科词条页面的第二源代码中,页面“description”字段内容为“《航海王》是漫画家尾田荣一郎作画的少年漫画作品,在《周刊少年Jump》1997年34号开始连载”,从中可以知道“海贼王”是一部漫画。由此,获取到目标话题标签#海贼王#所属的分类是“漫画”类别。
当然,本领域技术人员也可以通过在第二源代码中解析其他字段来获取目标话题标签所属的分类,在本申请实施例中,对此不做具体限定。
在获取到原始话题标签所属的分类后,技术人员可以根据用户经常设置的原始话题标签所属的类别,了解到用户的行为偏好,从而可以为用户推送更为匹配用户喜好的信息;另外,在用户使用话题标签进行搜索时,若没有能够精确匹配的搜索内容,技术人员可以根据话题标签所属的类别,为用户推荐相关类别的内容信息。
综上,本申请实施例通过从标题信息中提取原始话题标签,然后根据原始话题标签的出现频次确定待验证话题标签,再通过解析第一源代码页面,获得目标话题标签,最后通过解析第二源代码页面,获取目标话题标签所属的分类。通过上述方法,过滤出了不规范的、不适合作为研究对象的原始话题标签,最终提取出了目标话题标签,并获取了目标话题标签的分类,从而为技术人员更好地发掘用户需求、为用户推送更有价值的信息提供了参考依据。
在一个实施例中,参阅图3为本申请实施例示出的一种标签处理装置框图。参照图3,该标签处理装置300包括原始话题标签获取模块301,待验证 话题标签确定模块302,网页搜索模块303,目标话题标签提取模块304。
该原始话题标签获取模块301被配置为执行获取信息分享平台中,针对目标对象设置的原始话题标签;
待验证话题标签确定模块302,被配置为执行从原始话题标签中,确定待验证话题标签;
网页搜索模块303,被配置为执行对待验证话题标签进行网页搜索;
目标话题标签提取模块304,被配置为执行根据网页搜索获得的搜索结果,从待验证话题标签中提取出目标话题标签。
在图3的基础上,本申请实施例图4提供另一种标签处理装置,该标签处理装置具体包括:
原始话题标签获取模块301包括:
标题信息获取子模块3011,被配置为执行在获取信息分享平台中,针对目标对象设置的标题信息;
原始话题标签提取子模块3012,被配置为执行从标题信息中,提取用户设置的原始话题标签。
待验证话题标签确定模块302包括:
频次确定子模块3021,被配置为执行确定预设时间段内,原始话题标签的出现频次;
待验证话题标签确定子模块3022,被配置为执行将出现频次大于预设频次阈值的原始话题标签确定为待验证话题标签。
目标话题标签提取模块304包括:
第一源代码获取子模块3041,被配置为执行获取搜索页面的第一源代码;
判断子模块3042,被配置为执行判断第一源代码的超文本引用字段中是否包含目标地址链接;
目标话题标签确定子模块3043,被配置为执行在源代码的超文本引用字段中包含目标地址链接的情况下,将待验证话题标签确定为目标话题标签。
标签处理装置还包括:
目标页面获取模块305,被配置为执行获取与目标地址链接对应的目标页面;
分类确定模块306,被配置为执行根据目标页面,确定目标话题标签的分类。
分类确定模块306包括:
第二源代码获取子模块3061,被配置为执行获取目标页面的第二源代码;
分类获取子模块3062,被配置为执行解析第二源代码中的标题字段和/或属性字段,获取目标话题标签所属的分类。
关于上述实施例中的装置,其中各个模块执行操作的具体方式已经在有关该方法的实施例中进行了详细描述,此处将不做详细阐述说明。
图5是根据一示例性实施例示出的一种用于标签处理的电子设备500的框图。例如,电子设备500可以是移动电话,计算机,数字广播终端,消息收发设备,游戏控制台,平板设备,医疗设备,健身设备,个人数字助理等。
参照图5,电子设备500可以包括以下一个或多个组件:处理组件502,存储器504,电源组件506,多媒体组件508,音频组件510,输入/输出(I/O)的接口512,传感器组件514,通信组件516以及处理器520。
处理组件502通常控制电子设备500的整体操作,诸如与显示,电话呼叫,数据通信,相机操作和记录操作相关联的操作。处理组件502可以包括一个或多个处理器520来执行指令,以完成上述的方法的全部或部分步骤。此外,处理组件502可以包括一个或多个模块,便于处理组件502和其他组件之间的交互。例如,处理组件502可以包括多媒体模块,以方便多媒体组件508和处理组件502之间的交互。
存储器504被配置为存储各种类型的数据以支持在设备500的操作。这些数据的示例包括用于在电子设备500上操作的任何应用程序或方法的指令,联系人数据,电话簿数据,消息,图片,视频等。存储器504可以由任何类型的易失性或非易失性存储设备或者它们的组合实现,如静态随机存取存储器(SRAM),电可擦除可编程只读存储器(EEPROM),可擦除可编程只读 存储器(EPROM),可编程只读存储器(PROM),只读存储器(ROM),磁存储器,快闪存储器,磁盘或光盘。
电源组件506为电子设备500的各种组件提供电力。电源组件506可以包括电源管理系统,一个或多个电源,及其他与为电子设备500生成、管理和分配电力相关联的组件。
多媒体组件508包括在电子设备500和用户之间的提供一个输出接口的屏幕。在一些实施例中,屏幕可以包括液晶显示器(LCD)和触摸面板(TP)。如果屏幕包括触摸面板,屏幕可以被实现为触摸屏,以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。触摸传感器可以不仅感测触摸或滑动动作的边界,而且还检测与触摸或滑动操作相关的持续时间和压力。在一些实施例中,多媒体组件508包括一个前置摄像头和/或后置摄像头。当设备500处于操作模式,如拍摄模式或视频模式时,前置摄像头和/或后置摄像头可以接收外部的多媒体数据。每个前置摄像头和后置摄像头可以是一个固定的光学透镜系统或具有焦距和光学变焦能力。
音频组件510被配置为输出和/或输入音频信号。例如,音频组件510包括一个麦克风(MIC),当电子设备500处于操作模式,如呼叫模式、记录模式和语音识别模式时,麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器504或经由通信组件516发送。在一些实施例中,音频组件510还包括一个扬声器,用于输出音频信号。
I/O接口512为处理组件502和外围接口模块之间提供接口,上述外围接口模块可以是键盘,点击轮,按钮等。这些按钮可包括但不限于:主页按钮、音量按钮、启动按钮和锁定按钮。
传感器组件514包括一个或多个传感器,用于为电子设备500提供各个方面的状态评估。例如,传感器组件514可以检测到设备500的打开/关闭状态,组件的相对定位,例如组件为电子设备500的显示器和小键盘,传感器组件514还可以检测电子设备500或电子设备500一个组件的位置改变,用 户与电子设备500接触的存在或不存在,电子设备500方位或加速/减速和电子设备500的温度变化。传感器组件514可以包括接近传感器,被配置用来在没有任何的物理接触时检测附近物体的存在。传感器组件514还可以包括光传感器,如CMOS或CCD图像传感器,用于在成像应用中使用。在一些实施例中,该传感器组件514还可以包括加速度传感器,陀螺仪传感器,磁传感器,压力传感器或温度传感器。
通信组件516被配置为便于电子设备500和其他设备之间有线或无线方式的通信。电子设备500可以接入基于通信标准的无线网络,如WiFi,运营商网络(如2G、3G、4G或5G),或它们的组合。在一个示例性实施例中,通信组件516经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中,通信组件516还包括近场通信(NFC)模块,以促进短程通信。例如,在NFC模块可基于射频识别(RFID)技术,红外数据协会(IrDA)技术,超宽带(UWB)技术,蓝牙(BT)技术和其他技术来实现。
在示例性实施例中,电子设备500可以被一个或多个应用专用集成电路(ASIC)、数字信号处理器(DSP)、数字信号处理设备(DSPD)、可编程逻辑器件(PLD)、现场可编程门阵列(FPGA)、控制器、微控制器、微处理器或其他电子元件实现,用于执行上述方法。
在示例性实施例中,还提供了一种包括指令的非临时性计算机可读存储介质,例如包括指令的存储器504,上述指令可由电子设备500的处理器520执行以完成上述话题标签的提取方法。例如,非临时性计算机可读存储介质可以是ROM、随机存取存储器(RAM)、CD-ROM、磁带、软盘和光数据存储设备等。
图6是根据一示例性实施例示出的一种用于标签处理的电子设备600的框图。例如,电子设备600可以被提供为一服务器。参照图6,电子设备600包括处理组件622,其进一步包括一个或多个处理器,以及由存储器632所代表的存储器资源,用于存储可由处理组件622的执行的指令,例如应用程序。 存储器632中存储的应用程序可以包括一个或一个以上的每一个对应于一组指令的模块。此外,处理组件622被配置为执行指令,以执行上述话题标签的提取方法。
电子设备600还可以包括一个电源组件626被配置为执行电子设备600的电源管理,一个有线或无线网络接口650被配置为将电子设备600连接到网络,和一个输入输出(I/O)接口658。电子设备600可以操作基于存储在存储器632的操作系统,例如Windows ServerTM,Mac OS XTM,UnixTM,LinuxTM,FreeBSDTM或类似。
本申请实施例还提供一种应用程序,当应用程序中的指令由电子设备的处理器执行时,使得电子设备能够执行一种标签处理方法,包括:
获取信息分享平台中,针对目标对象设置的原始话题标签;
从原始话题标签中,确定待验证话题标签;
对待验证话题标签进行网页搜索;
根据网页搜索获得的搜索结果,从待验证话题标签中提取出目标话题标签。
本领域技术人员在考虑说明书及实践这里公开的发明后,将容易想到本申请的其它实施方案。本申请旨在涵盖本申请的任何变型、用途或者适应性变化,这些变型、用途或者适应性变化遵循本申请的一般性原理并包括本申请未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的,本申请的真正范围和精神由下面的权利要求指出。

Claims (14)

  1. 一种标签的处理方法,所述方法包括:
    获取信息分享平台中,针对目标对象设置的原始话题标签;
    从所述原始话题标签中,确定待验证话题标签;
    对所述待验证话题标签进行网页搜索;
    根据所述网页搜索获得的搜索结果,从所述待验证话题标签中提取出目标话题标签。
  2. 根据权利要求1所述的方法,所述根据所述网页搜索获得的搜索结果,从所述待验证话题标签中提取出目标话题标签,包括:
    获取所述网页搜索页面的第一源代码;
    判断所述第一源代码的超文本引用字段中是否包含目标地址链接;
    在所述第一源代码的超文本引用字段中包含目标地址链接的情况下,将所述待验证话题标签确定为目标话题标签。
  3. 根据权利要求1所述的方法,所述从所述原始话题标签中,确定待验证话题标签,包括:
    确定预设时间段内,所述原始话题标签的出现频次;
    将出现频次大于预设频次阈值的原始话题标签确定为待验证话题标签。
  4. 根据权利要求1所述的方法,在根据所述网页搜索获得的搜索结果,从所述待验证话题标签中提取出目标话题标签之后,还包括:
    获取与所述目标地址链接对应的目标页面;
    根据所述目标页面,确定所述目标话题标签的分类。
  5. 根据权利要求4所述的方法,所述根据所述目标页面,确定所述目标话题标签的分类,包括:
    获取所述目标页面的第二源代码;
    解析所述第二源代码中的标题字段和/或属性字段,获取所述目标话题标签所属的分类。
  6. 根据权利要求1所述的方法,所述获取信息分享平台中,针对目标对象设置的原始话题标签,包括:
    获取信息分享平台中,针对目标对象设置的标题信息;
    从所述标题信息中,提取用户设置的原始话题标签。
  7. 一种标签的处理装置,所述装置包括:
    原始话题标签获取模块,被配置为执行获取信息分享平台中,针对目标对象设置的原始话题标签;
    待验证话题标签确定模块,被配置为执行从所述原始话题标签中,确定待验证话题标签;
    网页搜索模块,被配置为执行对所述待验证话题标签进行网页搜索;
    目标话题标签提取模块,被配置为执行根据所述网页搜索获得的搜索结果,从所述待验证话题标签中提取出目标话题标签。
  8. 根据权利要求7所述的装置,所述目标话题标签提取模块包括:
    第一源代码获取子模块,被配置为执行获取所述网页搜索页面的第一源代码;
    判断子模块,被配置为执行判断所述第一源代码的超文本引用字段中是否包含目标地址链接;
    目标话题标签确定子模块,被配置为执行在所述第一源代码的超文本引用字段中包含目标地址链接的情况下,将所述待验证话题标签确定为目标话题标签。
  9. 根据权利要求7所述的装置,所述待验证话题标签确定模块包括:
    频次确定子模块,被配置为执行确定预设时间段内,所述原始话题标签的出现频次;
    待验证话题标签确定子模块,被配置为执行将出现频次大于预设频次阈值的原始话题标签确定为待验证话题标签。
  10. 根据权利要求7所述的装置,所述装置还包括:
    目标页面获取模块,被配置为执行获取与所述目标地址链接对应的目标 页面;
    分类确定模块,被配置为执行根据所述目标页面,确定所述目标话题标签的分类。
  11. 根据权利要求10所述的装置,所述分类确定模块包括:
    第二源代码获取子模块,被配置为执行获取所述目标页面的第二源代码;
    分类获取子模块,被配置为执行解析所述第二源代码中的标题字段和/或属性字段,获取所述目标话题标签所属的分类。
  12. 根据权利要求7所述的装置,所述原始话题标签获取模块包括:
    标题信息获取子模块,被配置为执行获取信息分享平台中,针对目标对象设置的标题信息;
    原始话题标签提取子模块,被配置为执行从所述标题信息中,提取原始话题标签。
  13. 一种电子设备,包括:
    处理器;
    用于存储处理器可执行指令的存储器;
    其中,所述处理器被配置为执行上述权利要求1-6任意一项所述的标签标签的处理方法。
  14. 一种非临时性计算机可读存储介质,当所述存储介质中的指令由电子设备的一个或多个处理器执行时,使得所述电子设备的一个或多个处理器能够执行一种标签的处理方法,所述方法包括上述权利要求1-6任意一项所述的标签的处理方法。
PCT/CN2019/106246 2018-10-23 2019-09-17 标签的处理方法、装置、电子设备及存储介质 WO2020082938A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811238336.6A CN109614482B (zh) 2018-10-23 2018-10-23 标签的处理方法、装置、电子设备及存储介质
CN201811238336.6 2018-10-23

Publications (1)

Publication Number Publication Date
WO2020082938A1 true WO2020082938A1 (zh) 2020-04-30

Family

ID=66002944

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/106246 WO2020082938A1 (zh) 2018-10-23 2019-09-17 标签的处理方法、装置、电子设备及存储介质

Country Status (2)

Country Link
CN (1) CN109614482B (zh)
WO (1) WO2020082938A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112818271A (zh) * 2021-01-27 2021-05-18 北京小米移动软件有限公司 一种网页显示方法、装置、终端设备及介质
CN113569067A (zh) * 2021-07-27 2021-10-29 深圳Tcl新技术有限公司 标签分类方法、装置、电子设备及计算机可读存储介质
CN116821523A (zh) * 2023-08-30 2023-09-29 山西合力思创科技股份有限公司 一种人员匹配逻辑校验方法、装置、电子设备及存储介质

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109614482B (zh) * 2018-10-23 2022-06-03 北京达佳互联信息技术有限公司 标签的处理方法、装置、电子设备及存储介质
CN110674349B (zh) * 2019-09-27 2023-03-14 北京字节跳动网络技术有限公司 视频poi识别方法、装置及电子设备
CN110889055A (zh) * 2019-11-29 2020-03-17 京东方科技集团股份有限公司 交互方法、交互系统、电子设备及存储介质
CN111767439B (zh) * 2020-06-28 2023-12-15 百度在线网络技术(北京)有限公司 基于页面分类标签的推荐方法、设备和介质
CN111897996B (zh) * 2020-08-10 2023-10-31 北京达佳互联信息技术有限公司 话题标签推荐方法、装置、设备及存储介质
CN113378061B (zh) * 2021-07-02 2023-05-30 抖音视界有限公司 一种信息搜索方法、装置、计算机设备及存储介质
CN113778295B (zh) * 2021-09-28 2023-08-08 北京字跳网络技术有限公司 一种书籍推荐方法、装置、计算机设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102314456A (zh) * 2010-06-30 2012-01-11 百度在线网络技术(北京)有限公司 网页划词搜索方法及系统
CN102890698A (zh) * 2012-06-20 2013-01-23 杜小勇 微博话题标签自动化描述方法
CN103870573A (zh) * 2014-03-18 2014-06-18 北京奇虎科技有限公司 对网址进行分析的方法和装置
CN108090070A (zh) * 2016-11-22 2018-05-29 北京高地信息技术有限公司 一种中文实体属性抽取方法
CN109614482A (zh) * 2018-10-23 2019-04-12 北京达佳互联信息技术有限公司 标签的处理方法、装置、电子设备及存储介质

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5143057B2 (ja) * 2009-03-02 2013-02-13 日本電信電話株式会社 重要キーワード抽出装置及び方法及びプログラム
CN102768663A (zh) * 2011-05-05 2012-11-07 腾讯科技(深圳)有限公司 一种网页标题的提取方法、装置及信息处理系统
CN104239340B (zh) * 2013-06-19 2018-03-16 北京搜狗信息服务有限公司 搜索结果筛选方法与装置
CN103823868B (zh) * 2014-02-26 2017-05-03 中国科学院计算技术研究所 一种面向在线百科的事件识别方法和事件关系抽取方法
WO2015152647A1 (en) * 2014-04-02 2015-10-08 Samsung Electronics Co., Ltd. Method and system for content searching
CN105488077B (zh) * 2014-10-10 2020-04-28 腾讯科技(深圳)有限公司 生成内容标签的方法和装置
CN105808695A (zh) * 2016-03-03 2016-07-27 陈包容 一种获取聊天回复内容的方法及装置
CN107436922B (zh) * 2017-07-05 2021-06-08 北京百度网讯科技有限公司 文本标签生成方法和装置
CN108009216A (zh) * 2017-11-17 2018-05-08 无锡雅座在线科技股份有限公司 目标对象的处理方法、装置和系统、存储介质、处理器
CN108009293B (zh) * 2017-12-26 2022-08-23 北京百度网讯科技有限公司 视频标签生成方法、装置、计算机设备和存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102314456A (zh) * 2010-06-30 2012-01-11 百度在线网络技术(北京)有限公司 网页划词搜索方法及系统
CN102890698A (zh) * 2012-06-20 2013-01-23 杜小勇 微博话题标签自动化描述方法
CN103870573A (zh) * 2014-03-18 2014-06-18 北京奇虎科技有限公司 对网址进行分析的方法和装置
CN108090070A (zh) * 2016-11-22 2018-05-29 北京高地信息技术有限公司 一种中文实体属性抽取方法
CN109614482A (zh) * 2018-10-23 2019-04-12 北京达佳互联信息技术有限公司 标签的处理方法、装置、电子设备及存储介质

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112818271A (zh) * 2021-01-27 2021-05-18 北京小米移动软件有限公司 一种网页显示方法、装置、终端设备及介质
CN113569067A (zh) * 2021-07-27 2021-10-29 深圳Tcl新技术有限公司 标签分类方法、装置、电子设备及计算机可读存储介质
CN116821523A (zh) * 2023-08-30 2023-09-29 山西合力思创科技股份有限公司 一种人员匹配逻辑校验方法、装置、电子设备及存储介质
CN116821523B (zh) * 2023-08-30 2023-11-24 山西合力思创科技股份有限公司 一种人员匹配逻辑校验方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
CN109614482B (zh) 2022-06-03
CN109614482A (zh) 2019-04-12

Similar Documents

Publication Publication Date Title
WO2020082938A1 (zh) 标签的处理方法、装置、电子设备及存储介质
CN108121736B (zh) 一种主题词确定模型的建立方法、装置及电子设备
US9524714B2 (en) Speech recognition apparatus and method thereof
CN107526744B (zh) 一种基于搜索的信息展示方法和装置
TW201826805A (zh) 播放處理方法、裝置和設備
CN110399548A (zh) 一种搜索处理方法、装置、电子设备以及存储介质
CN111783001A (zh) 页面显示方法、装置、电子设备和存储介质
JP2018504727A (ja) 参考文書の推薦方法及び装置
CN111708943B (zh) 一种搜索结果展示方法、装置和用于搜索结果展示的装置
US10783192B1 (en) System, method, and user interface for a search engine based on multi-document summarization
CN110019675B (zh) 一种关键词提取的方法及装置
CN102968473A (zh) 基于人脸图像的信息检索方法及系统
WO2019109663A1 (zh) 一种跨语言搜索方法和装置、一种用于跨语言搜索的装置
CN107622074A (zh) 一种数据处理方法、装置和计算设备
US11651039B1 (en) System, method, and user interface for a search engine based on multi-document summarization
CN110309324B (zh) 一种搜索方法及相关装置
CN108717403B (zh) 一种处理方法、装置和用于处理的装置
CN113869063A (zh) 数据推荐方法、装置、电子设备及存储介质
CN111241844A (zh) 一种信息推荐方法及装置
CN110110046B (zh) 同名实体推荐方法及装置
CN105677709A (zh) 一种信息处理方法和装置、一种用于信息处理的装置
CN107784037B (zh) 信息处理方法和装置、用于信息处理的装置
CN106886541B (zh) 一种数据搜索方法、装置以及一种用于数据搜索的装置
CN112328809A (zh) 实体分类方法、装置及计算机可读存储介质
CN110020106B (zh) 一种推荐方法、推荐装置和用于推荐的装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19876176

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: 19876176

Country of ref document: EP

Kind code of ref document: A1