WO2019000710A1 - 页面加载方法、装置和电子设备 - Google Patents

页面加载方法、装置和电子设备 Download PDF

Info

Publication number
WO2019000710A1
WO2019000710A1 PCT/CN2017/106373 CN2017106373W WO2019000710A1 WO 2019000710 A1 WO2019000710 A1 WO 2019000710A1 CN 2017106373 W CN2017106373 W CN 2017106373W WO 2019000710 A1 WO2019000710 A1 WO 2019000710A1
Authority
WO
WIPO (PCT)
Prior art keywords
page
browsing
access
user
target
Prior art date
Application number
PCT/CN2017/106373
Other languages
English (en)
French (fr)
Inventor
郭雄辉
Original Assignee
北京金山安全软件有限公司
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 北京金山安全软件有限公司 filed Critical 北京金山安全软件有限公司
Publication of WO2019000710A1 publication Critical patent/WO2019000710A1/zh
Priority to US16/404,450 priority Critical patent/US11036820B2/en

Links

Images

Classifications

    • 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
    • G06F16/957Browsing optimisation, e.g. caching or content distillation
    • G06F16/9577Optimising the visualization of content, e.g. distillation of HTML documents
    • 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
    • G06F16/955Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
    • 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
    • G06F16/957Browsing optimisation, e.g. caching or content distillation
    • 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
    • G06F16/958Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
    • G06F16/972Access to data in other repository systems, e.g. legacy data or dynamic Web page generation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/21Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44Arrangements for executing specific programs
    • G06F9/445Program loading or initiating
    • G06F9/44521Dynamic linking or loading; Link editing at or after load time, e.g. Java class loading

Definitions

  • the present invention relates to the field of Internet technologies, and in particular, to a page loading method, apparatus, and electronic device.
  • the present invention aims to solve at least one of the technical problems in the related art to some extent.
  • the first object of the present invention is to provide a page loading method for implementing a learning model according to a historical browsing behavior when a user uses a browser, and adaptively learning a model when a page access request is obtained.
  • the browsing mode is selected, and the page is loaded according to the selected browsing manner, which solves the technical problem that the browser loads the page in the prior art in a relatively fixed and single manner.
  • a second object of the present invention is to provide a page loading device.
  • a third object of the present invention is to provide an electronic device.
  • a fourth object of the present invention is to provide a non-transitory computer readable storage medium.
  • a fifth object of the present invention is to provide a computer program product.
  • the first aspect of the present invention provides a page loading method, which includes: collecting historical browsing behaviors when a user uses a browser, and obtaining an access page related to historical browsing behavior and a browsing mode adopted by the user; The learning model is trained according to the access page and the browsing mode adopted by the user, so that the learning model learns the correspondence between the access page and the browsing mode; wherein the browsing mode includes the current tab page browsing and the new label.
  • Page browsing if a page access request is obtained, the trained learning model is used to analyze the target page to be accessed, so as to determine the target browsing mode from the current tab page browsing and the new tab page browsing; according to the target browsing mode, Load the target page.
  • the learning model is trained according to the access page and the browsing manner adopted by the user, including:
  • the learning model is trained by using a training sample set; wherein the learning model is a two-class model.
  • the access page involved in the multiple history browsing behavior is analyzed, and the feature parameters of the multiple access pages are obtained, including:
  • Feature parameters are generated based on the URL of the visited page, the content of the accessed page, the URL of the associated page, and/or the content of the associated page.
  • the trained learning model is used to analyze the target page that needs to be accessed, so as to determine the target browsing from the current tab page browsing and the new tab page browsing. Before the method, it also includes:
  • the page loading method in the embodiment of the present invention collects the historical browsing behavior when the user uses the browser, obtains the access page involved in the historical browsing behavior, and the browsing mode adopted by the user, and learns according to the visiting page and the browsing mode adopted by the user.
  • the model is trained to make the learning model obtain the correspondence between the access page and the browsing mode.
  • the browsing mode includes the current tab page browsing and the new tab page browsing. If the page access request is obtained, the trained learning model is adopted.
  • the target page to be accessed is analyzed to determine the target browsing mode from the current tab page browsing and the new tab page browsing, and the target page is loaded according to the target browsing mode.
  • the learning model is trained according to the historical browsing behavior of the browser, the obtained access page and the browsing mode adopted by the user, and the browsing mode adopted by the user, when the page access request is obtained.
  • the target browsing mode of the page is determined, and the page is loaded according to the target browsing mode, and the user is implemented according to the user's
  • the history browsing behavior, adaptively selecting the browsing mode of the page, and loading the page according to the selected browsing manner solves the technical problem that the browser loads the page in the prior art in a relatively fixed and single manner.
  • the second aspect of the present invention provides a page loading apparatus, including: an acquisition module, configured to collect historical browsing behaviors when a user uses a browser, and obtain an access page and a user involved in historical browsing behavior.
  • the training module is configured to train the learning model according to the access page and the browsing mode adopted by the user, so that the learning model learns the correspondence between the accessed page and the browsing mode; wherein the browsing mode includes the current tab page browsing and the new label.
  • Page browsing is configured to train the learning model according to the access page and the browsing mode adopted by the user, so that the learning model learns the correspondence between the accessed page and the browsing mode; wherein the browsing mode includes the current tab page browsing and the new label.
  • the analysis module is configured to: if the page access request is obtained, use the trained learning model to analyze the target page to be accessed, to determine the target browsing mode from the current tab page browsing and the new tab page browsing;
  • the loading module is used to load the target page according to the target browsing mode.
  • the training module includes:
  • a feature extraction unit configured to analyze an access page involved in multiple historical browsing behaviors, and obtain feature parameters of multiple access pages
  • An annotation unit configured to represent multiple access pages by using feature parameters, and labeling multiple access pages by using a corresponding browsing manner
  • a generating unit configured to generate a training sample set according to the plurality of accessed pages after the labeling
  • the training unit is configured to train the learning model by using a training sample set; wherein the learning model is a two-class model.
  • the feature extraction unit is specifically configured to:
  • Feature parameters are generated based on the URL of the visited page, the content of the accessed page, the URL of the associated page, and/or the content of the associated page.
  • the page loading apparatus further includes:
  • the prompting module is configured to: according to the historical browsing behavior, count the number of times the new tab page is browsed when the target page is involved; if the number of statistics is consistent with the preset condition, the user is prompted to enable the smart multi-label mode; and the obtaining user allows the smart multi-label to be opened. Mode instructions.
  • the page loading device of the embodiment of the present invention collects the historical browsing behavior when the user uses the browser, obtains the access page involved in the historical browsing behavior, and the browsing mode adopted by the user, and learns according to the access page and the browsing mode adopted by the user.
  • the model is trained to make the learning model get the correspondence between the access page and the browsing mode.
  • the browsing mode includes current tab page browsing and new tab page browsing. If a page access request is obtained, the trained learning model is used to analyze the target page to be accessed to browse from the current tab page and create a new tab page. Determine the target browsing mode, and load the target page according to the target browsing mode.
  • the learning model is trained according to the historical browsing behavior of the browser, the obtained access page and the browsing mode adopted by the user, and the browsing mode adopted by the user, when the page access request is obtained.
  • the target browsing mode of the page is determined, and the page is loaded according to the target browsing mode, and the browsing mode of the user is adaptively selected according to the historical browsing behavior of the user, and the page is loaded according to the selected browsing manner, and the solution is solved.
  • the manner in which the browser loads the page is relatively fixed and a single technical problem.
  • an embodiment of the third aspect of the present invention provides an electronic device including: a housing, a processor, a memory, a circuit board, and a power supply circuit, wherein the circuit board is disposed inside the space enclosed by the housing, and is processed. And a memory disposed on the circuit board; a power supply circuit for powering each circuit or device of the electronic device; a memory for storing executable program code; and the processor operating by reading executable program code stored in the memory The program corresponding to the executable program code is used to execute the page loading method described in the first aspect embodiment.
  • a fourth aspect of the present invention provides a non-transitory computer readable storage medium having stored thereon a computer program, which is executed by a processor to implement a page as described in the first aspect of the present invention. Load method.
  • a fifth aspect of the present invention provides a computer program product.
  • an instruction in a computer program product is executed by a processor, the page loading method according to the first aspect embodiment is executed.
  • FIG. 1 is a schematic diagram showing the effect of a browser's multi-tab display mode
  • FIG. 2 is a schematic diagram of a method of loading a page in a new tab by popping up a window
  • FIG. 3 is a schematic flowchart of a page loading method according to an embodiment of the present disclosure
  • FIG. 4 is a schematic structural diagram of a page loading apparatus according to an embodiment of the present invention.
  • FIG. 5 is a schematic structural diagram of another page loading apparatus according to an embodiment of the present disclosure.
  • FIG. 6 is a schematic structural diagram of still another page loading apparatus according to an embodiment of the present invention.
  • FIG. 7 is a schematic structural diagram of an embodiment of an electronic device according to the present invention.
  • the browser When the browser is set to load the page in the new tab page, due to different usage habits, after the new tab page is loaded, the user may close the previous tab page, that is, the user is accustomed to browsing on the original tab page.
  • the existing browser loading method is relatively fixed, or the page is loaded on the original tab page, or the page is loaded on the newly created tab page, and cannot be adaptively adjusted according to the user's usage habits.
  • an embodiment of the present invention provides a page loading method, so as to implement a training model according to a historical browsing behavior when a user uses a browser, and when the page access request is obtained, adaptively select and browse through the learning model. The way, and the page is loaded according to the selected browsing method.
  • FIG. 3 is a schematic flowchart diagram of a page loading method according to an embodiment of the present invention.
  • the page loading method includes the following steps:
  • S301 Collect historical browsing behaviors when the user uses the browser, and obtain an access page related to the historical browsing behavior and a browsing manner adopted by the user.
  • the program When the user uses the browser, the program records the historical browsing behavior of the user using the browser in the background, such as the time of accessing the page, the Uniform Resource Locator (URL) of the accessed page, the content of the accessed page, and the like. In order to get the access page involved in the history browsing behavior and the browsing mode adopted by the user.
  • the URL Uniform Resource Locator
  • browsing methods include current tabbed browsing and new tabbed browsing.
  • the current tab page browsing refers to the browser loading the page on the original tab page after the user clicks the link;
  • the new tab page browsing refers to the browser loading the page on the newly created tab page after the user clicks the link.
  • S302 Train the learning model according to the access page and the browsing mode adopted by the user, so that the learning model learns the correspondence between the access page and the browsing mode.
  • the access pages involved in the multiple history browsing behaviors are analyzed, and the feature parameters of the multiple access pages are obtained. Specifically, for each historical browsing behavior, the URL of the accessed page, the content of the accessed page, the associated page of the accessed page, and the content of the associated page are obtained.
  • the associated page is the page loaded by this tab and the pages loaded by other tabs before the tab page jumps to the access page.
  • the user enters "ordinary world" on the home page of Taobao. After clicking the search, multiple search results appear, and the user clicks on one of the search results, and the page jumps from the search result page to the new tab page.
  • the page loaded by the new tab page is the access page
  • the search result page is the associated page of the access page.
  • the URL of the access page, the content of the access page, the URL of the search result page, and the content of the search result page are obtained.
  • the feature parameter is generated according to the obtained URL of the access page, the content of the accessed page, the URL of the associated page of the accessed page, and the content of the associated page.
  • the obtained feature parameters are used to represent the plurality of access pages, and the plurality of access pages are labeled by using the corresponding browsing manner. For example, when a user browses news through People's Network, after the user clicks on a news link on the home page, the browser loads the news on the newly created tab page. After the user has finished browsing, another click on the news link is clicked, the browser opens the link in the new tab, and the user closes the previous news page. At this point, the access page can be marked as the current tab page view.
  • the plurality of accessed pages after the annotation are used as training samples to generate a training sample set.
  • the learning model is then trained using the training sample set.
  • the learning model is a two-category model (ie, current tab page browsing or new tab page browsing), and the feature parameters of the plurality of training samples are sequentially input into the learning model, and the output is the browsing mode, the current tab page browsing or Create a new tab page.
  • the learning model is trained by acquiring the feature parameters of the plurality of dimensions, so that the output result of the learning model is more accurate.
  • the trained learning model is used to analyze the target page to be accessed, so as to determine the target browsing mode from the current tab page browsing and the new tab page browsing.
  • the user clicks on a link in the browser and the browser gets a page access request.
  • extract the feature parameters of the target page that needs to be accessed such as the URL of the target page, the URL of the associated page of the target page, and the content of the associated page.
  • the feature parameters of the access page are input into the two-category model for analysis, and the browsing result of the target page that needs to be accessed is determined by the output result of the two-category model.
  • the target page is loaded by the current tab page browsing manner. If the output of the binary model is a new tab page view, the target page is loaded by creating a new tab.
  • the statistics involve the target page.
  • the pop-up prompt can be prompted.
  • the way of the box prompts the user to turn on the smart multi-label mode. If the user chooses to enable the smart multi-label mode, after obtaining the instruction that the user is allowed to enable the smart multi-label mode, the smart multi-label mode is turned on according to the instruction. In this mode, after the user clicks on the link, the browser automatically creates a new tab page and loads the page through the new tab page.
  • the smart multi-tag mode is enabled, so that when the user clicks on the link of the website, the newly created tab is automatically created.
  • the page loading method in the embodiment of the present invention collects the historical browsing behavior when the user uses the browser, obtains the access page involved in the historical browsing behavior, and the browsing mode adopted by the user, and learns according to the visiting page and the browsing mode adopted by the user.
  • the model is trained to make the learning model obtain the correspondence between the access page and the browsing mode.
  • the browsing mode includes the current tab page browsing and the new tab page browsing. If the page access request is obtained, the trained learning model is adopted.
  • the target page to be accessed is analyzed to determine the target browsing mode from the current tab page browsing and the new tab page browsing, and the target page is loaded according to the target browsing mode.
  • the learning model is trained according to the historical browsing behavior of the browser, the obtained access page and the browsing mode adopted by the user, and the browsing mode adopted by the user, when the page access request is obtained.
  • the target browsing mode of the page is determined, and the page is loaded according to the target browsing mode, and the browsing mode of the user is adaptively selected according to the historical browsing behavior of the user, and the page is loaded according to the selected browsing manner, and the solution is solved.
  • the manner in which the browser loads the page is relatively fixed and a single technical problem.
  • the present invention also proposes a page loading device.
  • the device includes: an acquisition module 410, a training module 420, an analysis module 430, and a loading module 440.
  • the collecting module 410 is configured to collect historical browsing behaviors when the user uses the browser, and obtain an access page related to the historical browsing behavior and a browsing manner adopted by the user.
  • the training module 420 is configured to train the learning model according to the access page and the browsing mode adopted by the user, so that the learning model is The learning model learns the correspondence between the access page and the browsing mode; wherein the browsing mode includes the current tab page browsing and the new tab page browsing;
  • the analysis module 430 is configured to: if the page access request is obtained, use the trained learning model to analyze the target page to be accessed, to determine the target browsing mode from the current tab page browsing and the new tab page browsing.
  • the loading module 440 is configured to load the target page according to the target browsing mode.
  • the training module 420 includes: a feature extraction unit 421, an annotation unit 422, a generation unit 423, and a training unit 424.
  • the feature extraction unit 421 is configured to analyze the access pages involved in the multiple history browsing behaviors, and obtain the feature parameters of the multiple access pages.
  • the labeling unit 422 is configured to represent a plurality of access pages by using feature parameters, and label the plurality of access pages by using a corresponding browsing manner.
  • the generating unit 423 is configured to generate a training sample set according to the plurality of accessed pages after the labeling.
  • the training unit 424 is configured to train the learning model by using a training sample set; wherein the learning model is a two-class model.
  • the feature extraction unit 421 is specifically configured to acquire, for each historical browsing behavior, a URL of the accessed page, a content of the accessed page, a URL of the associated page of the accessed page, and/or a content of the associated page; wherein the associated page is a tab page jump The page loaded by this tab and/or the page loaded by other tabs before the page is accessed; the feature parameters are generated according to the URL of the visited page, the content of the accessed page, the URL of the associated page, and/or the content of the associated page.
  • the apparatus further includes a prompting module 450.
  • the prompting module 450 is configured to: according to the historical browsing behavior, count the number of times the new tab page is browsed when the target page is involved; if the number of statistics is consistent with the preset condition, the user is prompted to enable the smart multi-label mode; and the user is allowed to enable the smart multi-label mode. instruction.
  • the page loading device of the embodiment of the present invention collects the historical browsing behavior when the user uses the browser, obtains the access page involved in the historical browsing behavior, and the browsing mode adopted by the user, and learns according to the access page and the browsing mode adopted by the user.
  • the model is trained to make the learning model obtain the correspondence between the access page and the browsing mode.
  • the browsing mode includes the current tab page browsing and the new tab page browsing. If the page access request is obtained, the trained learning model is adopted.
  • the target page to be accessed is analyzed to determine the target browsing mode from the current tab page browsing and the new tab page browsing, and the target page is loaded according to the target browsing mode.
  • the root is passed According to the history browsing behavior of the user, the obtained access page and the browsing mode adopted by the user, the learning model is trained by using the access page and the browsing mode adopted by the user, and when the page access request is obtained, the learning model is determined according to the learning model.
  • the target browsing mode of the page, and loading the page according to the target browsing mode realizes the browsing mode according to the user's historical browsing behavior, adaptively selects the browsing mode of the page, and loads the page according to the selected browsing manner, and solves the browser in the prior art.
  • the way to load a page is a fixed, single technical issue.
  • An embodiment of the present invention further provides an electronic device, where the electronic device includes the page loading device according to any of the foregoing embodiments.
  • FIG. 7 is a schematic structural diagram of an embodiment of an electronic device according to the present invention, which may implement the process of the embodiment shown in FIG. 3 of the present invention.
  • the electronic device may include: a housing 71, a processor 72, and a memory 73. a circuit board 74 and a power supply circuit 75, wherein the circuit board 74 is disposed inside the space surrounded by the housing 71, the processor 72 and the memory 73 are disposed on the circuit board 74, and the power supply circuit 75 is used for each circuit of the electronic device Or device power; memory 73 for storing executable program code; processor 72 executing a program corresponding to the executable program code by reading executable program code stored in memory 73 for performing any of the embodiments described above Page loading method.
  • the electronic device exists in a variety of forms including, but not limited to:
  • Mobile communication devices These devices are characterized by mobile communication functions and are mainly aimed at providing voice and data communication.
  • Such terminals include: smart phones (such as iPhone), multimedia phones, functional phones, and low-end phones.
  • Ultra-mobile personal computer equipment This type of equipment belongs to the category of personal computers, has computing and processing functions, and generally has mobile Internet access.
  • Such terminals include: PDAs, MIDs, and UMPC devices, such as the iPad.
  • Portable entertainment devices These devices can display and play multimedia content. Such devices include: audio, video players (such as iPod), handheld game consoles, e-books, and smart toys and portable car navigation devices.
  • the server consists of a processor, a hard disk, a memory, a system bus, etc.
  • the server is similar to a general-purpose computer architecture, but because of the need to provide highly reliable services, processing power and stability High reliability in terms of reliability, security, scalability, and manageability.
  • an embodiment of the present invention provides a non-transitory computer readable storage medium having a computer program stored thereon, which is executed by a processor to implement a page loading method as described in the foregoing embodiments.
  • an embodiment of the present invention provides a computer program product, when an instruction in a computer program product When executed by the processor, the page loading method as described in the above embodiments is performed.
  • the storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).
  • first and second are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated.
  • features defining “first” and “second” may include at least one of the features, either explicitly or implicitly.
  • the meaning of "a plurality” is at least two, such as two, three, etc., unless specifically defined otherwise.
  • a "computer-readable medium” can be any apparatus that can contain, store, communicate, propagate, or transport a program for use in an instruction execution system, apparatus, or device, or in conjunction with the instruction execution system, apparatus, or device.
  • computer readable media include the following: electrical connections (electronic devices) having one or more wires, portable computer disk cartridges (magnetic devices), random access memory (RAM), only Read memory (ROM), erasable editable read only memory (EPROM or flash memory), fiber optic devices, and portable compact disk read only memory (CDROM).
  • the computer readable medium may even be a paper or other suitable medium on which the program can be printed, as it may be optically scanned, for example by paper or other medium, followed by editing, interpretation or, if appropriate, other suitable The method is processed to obtain the program electronically and then stored in computer memory.
  • portions of the invention may be implemented in hardware, software, firmware or a combination thereof.
  • multiple steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system.
  • a suitable instruction execution system For example, if implemented in hardware and in another embodiment, it can be implemented by any one or combination of the following techniques well known in the art: discrete with logic gates for implementing logic functions on data signals Logic circuits, application specific integrated circuits with suitable combinational logic gates, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), and the like.
  • each functional unit in each embodiment of the present invention may be integrated into one processing module, or each unit may exist physically separately, or two or more units may be integrated into one module.
  • the above integrated modules can be implemented in the form of hardware or in the form of software functional modules.
  • the integrated modules, if implemented in the form of software functional modules and sold or used as stand-alone products, may also be stored in a computer readable storage medium.
  • the above mentioned storage medium may be a read only memory, a magnetic disk or an optical disk or the like.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Information Transfer Between Computers (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

一种页面加载方法、装置和电子设备,其中,方法包括:对用户使用浏览器时的历史浏览行为进行采集,得到历史浏览行为涉及的访问页面和用户采用的浏览方式(S301);根据访问页面和用户采用的浏览方式,对学习模型进行训练,以使学习模型学习得到访问页面与浏览方式之间的对应关系(S302);其中,浏览方式包括当前标签页浏览和新建标签页浏览;若获取到页面访问请求,采用训练好的学习模型,对所需访问的目标页面进行分析,以从当前标签页浏览和新建标签页浏览中确定出目标浏览方式(S303);依据目标浏览方式,对目标页面进行加载(S304)。该方法实现了根据用户的历史浏览行为,自适应选择页面的浏览方式,并根据选择的浏览方式加载页面。

Description

页面加载方法、装置和电子设备
相关申请的交叉引用
本申请要求北京金山安全软件有限公司于2017年06月27日提交的、发明名称为“页面加载方法、装置和电子设备”的、中国专利申请号“201710501008.X”的优先权。
技术领域
本发明涉及互联网技术领域,尤其涉及一种页面加载方法、装置和电子设备。
背景技术
随着互联网技术的发展,浏览器已经成为人们生活的一部分,通过浏览器可以搜索、浏览新闻、购物等等。当用户通过搜索引擎进行搜索时,网页中会出现很多满足条件的搜索结果。用户点击某搜索结果,浏览器会固定的在当前标签页中加载,或者固定的通过新建标签页进行加载。可见,现有的浏览器页面加载方式比较单一。
发明内容
本发明旨在至少在一定程度上解决相关技术中的技术问题之一。
为此,本发明的第一个目的在于提出一种页面加载方法,以实现根据用户使用浏览器时的历史浏览行为,对学习模型进行训练,当获取到页面访问请求时,通过学习模型自适应选择浏览方式,并根据选择的浏览方式对页面进行加载,解决了现有技术中浏览器加载页面的方式比较固定、单一的技术问题。
本发明的第二个目的在于提出一种页面加载装置。
本发明的第三个目的在于提出一种电子设备。
本发明的第四个目的在于提出一种非临时性计算机可读存储介质。
本发明的第五个目的在于提出一种计算机程序产品。
为达上述目的,本发明第一方面实施例提出了一种页面加载方法,包括:对用户使用浏览器时的历史浏览行为进行采集,得到历史浏览行为涉及的访问页面和用户采用的浏览方式;根据访问页面和用户采用的浏览方式,对学习模型进行训练,以使学习模型学习得到访问页面与浏览方式之间的对应关系;其中,浏览方式包括当前标签页浏览和新建标签 页浏览;若获取到页面访问请求,采用训练好的学习模型,对所需访问的目标页面进行分析,以从当前标签页浏览和新建标签页浏览中确定出目标浏览方式;依据目标浏览方式,对目标页面进行加载。
可选地,作为第一方面的第一种可能的实现方式,根据访问页面和用户采用的浏览方式,对学习模型进行训练,包括:
对多次历史浏览行为涉及的访问页面进行分析,得到多个访问页面的特征参数;
采用特征参数表征多个访问页面,利用对应的浏览方式对多个访问页面并进行标注;
根据标注后的多个访问页面生成训练样本集;
采用训练样本集,对学习模型进行训练;其中,学习模型为二分类模型。
可选地,作为第一方面的第二种可能的实现方式,对多次历史浏览行为涉及的访问页面进行分析,得到多个访问页面的特征参数,包括:
针对每一历史浏览行为,获取访问页面的URL、访问页面的内容、访问页面的关联页面的URL和/或关联页面的内容;其中,关联页面是本标签页跳转至访问页面之前,本标签页所加载的页面和/或其他标签页已加载的页面;
根据访问页面的URL、访问页面的内容、关联页面的URL和/或关联页面的内容,生成特征参数。
可选地,作为第一方面的第三种可能的实现方式,采用训练好的学习模型,对所需访问的目标页面进行分析,以从当前标签页浏览和新建标签页浏览中确定出目标浏览方式之前,还包括:
根据历史浏览行为,统计涉及目标页面时采用新建标签页浏览的次数;
若统计得到的次数符合预设条件,提示用户开启智能多标签模式;
获取用户允许开启所述智能多标签模式的指令。
本发明实施例的页面加载方法,通过对用户使用浏览器时的历史浏览行为进行采集,得到历史浏览行为涉及的访问页面和用户采用的浏览方式,根据访问页面和用户采用的浏览方式,对学习模型进行训练,使学习模型得到访问页面与浏览方式之间的对应关系,其中,浏览方式包括当前标签页浏览和新建标签页浏览,若获取到页面访问请求,采用训练好的学习模型,对所需访问的目标页面进行分析,以从当前标签页浏览和新建标签页浏览中确定出目标浏览方式,依据目标浏览方式,对目标页面进行加载。本实施例中,通过根据用户使用浏览器的历史浏览行为,得到的访问页面和用户采用的浏览方式,利用访问页面和用户采用的浏览方式,对学习模型进行训练,当获取到页面访问请求时,根据学习模型确定对页面的目标浏览方式,并根据目标浏览方式对页面进行加载,实现了根据用户的 历史浏览行为,自适应选择页面的浏览方式,并根据选择的浏览方式加载页面,解决了现有技术中浏览器加载页面的方式比较固定、单一的技术问题。
为达上述目的,本发明第二方面实施例提出了一种页面加载装置,包括:采集模块,用于对用户使用浏览器时的历史浏览行为进行采集,得到历史浏览行为涉及的访问页面和用户采用的浏览方式;
训练模块,用于根据访问页面和用户采用的浏览方式,对学习模型进行训练,以使学习模型学习得到访问页面与浏览方式之间的对应关系;其中,浏览方式包括当前标签页浏览和新建标签页浏览;
分析模块,用于若获取到页面访问请求,采用训练好的学习模型,对所需访问的目标页面进行分析,以从当前标签页浏览和新建标签页浏览中确定出目标浏览方式;
加载模块,用于依据目标浏览方式,对目标页面进行加载。
可选地,作为第二方面的第一种可能的实现方式,训练模块,包括:
特征提取单元,用于对多次历史浏览行为涉及的访问页面进行分析,得到多个访问页面的特征参数;
标注单元,用于采用特征参数表征多个访问页面,并利用对应的浏览方式对多个访问页面进行标注;
生成单元,用于根据标注后的多个访问页面生成训练样本集;
训练单元,用于采用训练样本集,对学习模型进行训练;其中,学习模型为二分类模型。
可选地,作为第二方面的第二种可能的实现方式,特征提取单元,具体用于:
针对每一历史浏览行为,获取访问页面的URL、访问页面的内容、访问页面的关联页面的URL和/或关联页面的内容;其中,关联页面是本标签页跳转至访问页面之前,本标签页所加载的页面和/或其他标签页已加载的页面;
根据访问页面的URL、访问页面的内容、关联页面的URL和/或关联页面的内容,生成特征参数。
可选地,作为第二方面的第三种可能的实现方式,页面加载装置,还包括:
提示模块,用于根据历史浏览行为,统计涉及目标页面时采用新建标签页浏览的次数;若统计得到的次数符合预设条件,提示用户开启智能多标签模式;获取用户允许开启所述智能多标签模式的指令。
本发明实施例的页面加载装置,通过对用户使用浏览器时的历史浏览行为进行采集,得到历史浏览行为涉及的访问页面和用户采用的浏览方式,根据访问页面和用户采用的浏览方式,对学习模型进行训练,使学习模型得到访问页面与浏览方式之间的对应关系,其 中,浏览方式包括当前标签页浏览和新建标签页浏览,若获取到页面访问请求,采用训练好的学习模型,对所需访问的目标页面进行分析,以从当前标签页浏览和新建标签页浏览中确定出目标浏览方式,依据目标浏览方式,对目标页面进行加载。本实施例中,通过根据用户使用浏览器的历史浏览行为,得到的访问页面和用户采用的浏览方式,利用访问页面和用户采用的浏览方式,对学习模型进行训练,当获取到页面访问请求时,根据学习模型确定对页面的目标浏览方式,并根据目标浏览方式对页面进行加载,实现了根据用户的历史浏览行为,自适应选择页面的浏览方式,并根据选择的浏览方式加载页面,解决了现有技术中浏览器加载页面的方式比较固定、单一的技术问题。
为达上述目的,本发明第三方面实施例提出了一种电子设备,包括:壳体、处理器、存储器、电路板和电源电路,其中,电路板安置在壳体围成的空间内部,处理器和存储器设置在电路板上;电源电路,用于为上述电子设备的各个电路或器件供电;存储器用于存储可执行程序代码;处理器通过读取存储器中存储的可执行程序代码来运行与可执行程序代码对应的程序,用于执行第一方面实施例所述的页面加载方法。
为达上述目的,本发明第四方面实施例提出了一种非临时性计算机可读存储介质,其上存储有计算机程序,该程序被处理器执行时实现如第一方面实施例所述的页面加载方法。
为达上述目的,本发明第五方面实施例提出了一种计算机程序产品,当计算机程序产品中的指令由处理器执行时,执行如第一方面实施例所述的页面加载方法。
附图说明
为了更清楚地说明本发明实施例中的技术方案,下面将对实施例中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。
图1为浏览器的多标签页展现方式的效果示意图;
图2为通过弹出的窗口选择在新建标签页中加载页面的方法的示意图;
图3为本发明实施例所提供的一种页面加载方法的流程示意图;
图4为本发明实施例所提供的一种页面加载装置的结构示意图;
图5为本发明实施例所提供的另一种页面加载装置的结构示意图;
图6为本发明实施例所提供的又一种页面加载装置的结构示意图;
图7为本发明电子设备一个实施例的结构示意图。
具体实施方式
下面详细描述本发明的实施例,所述实施例的示例在附图中示出,其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施例是示例性的,旨在用于解释本发明,而不能理解为对本发明的限制。
下面参考附图描述本发明实施例的页面加载方法、装置和电子设备。
现有的浏览器基本都支持多标签页展现方式,如图1所示,也就是在一个浏览器窗口中可以显示多个标签页。这样用户可以同时浏览多个网页并进行动态切换。
例如,在使用搜索引擎时,网页中会同时出现很多满足条件的搜索结果,这时可能需要打开多个网页并进行比较查看。在浏览器设置成固定在当前标签页加载页面时,为了打开多个网页,如图2所示,可在搜索结果上点击鼠标右键(电脑上),在弹出的对话框中选择“在新标签页中打开链接”,从而可以实现在一个浏览器窗口中展现多个标签页。但是,该方法需要用户主动创建新标签页,操作繁琐。
当浏览器设置成在新建标签页加载页面时,由于使用习惯不同,在新建标签页加载页面后,用户可能会关闭之前的标签页,也就是用户习惯在原标签页上浏览。
可见,现有的浏览器加载方式比较固定,或在原标签页上加载页面,或者在新建标签页上加载页面,不能根据用户的使用习惯自适应调整。
针对这一问题,本发明实施例提出一种页面加载方法,以实现根据用户使用浏览器时的历史浏览行为,对学习模型进行训练,当获取到页面访问请求时,通过学习模型自适应选择浏览方式,并根据选择的浏览方式对页面进行加载。
图3为本发明实施例所提供的一种页面加载方法的流程示意图。
如图3所示,该页面加载方法包括以下步骤:
S301,对用户使用浏览器时的历史浏览行为进行采集,得到历史浏览行为涉及的访问页面和用户采用的浏览方式。
在用户使用浏览器时,通过程序在后台记录用户使用浏览器的历史浏览行为,如访问页面的时间、访问页面的统一资源定位符(Uniform Resource Locator,简称URL)、访问页面的内容等等,以得到历史浏览行为涉及的访问页面和用户采用的浏览方式。
其中,浏览方式包括当前标签页浏览和新建标签页浏览。其中,当前标签页浏览是指用户点击链接后,浏览器在原标签页上加载页面;新建标签页浏览是指用户点击链接后,浏览器在新建标签页上加载页面。
S302,根据访问页面和用户采用的浏览方式,对学习模型进行训练,以使学习模型学习得到访问页面与浏览方式之间的对应关系。
本实施例中,对多次历史浏览行为涉及的访问页面进行分析,得到多个访问页面的特征参数。具体而言,针对每一次历史浏览行为,获取访问页面的URL、访问页面的内容、访问页面的关联页面和关联页面的内容。其中,关联页面是本标签页跳转至访问页面之前,本标签页所加载的页面和其他标签页已加载的页面。
例如,用户在淘宝网首页输入“平凡的世界”,点击搜索后,出现多个搜索结果,用户点击其中一个搜索结果,页面从搜索结果页面跳转至新建标签页。在该次的历史浏览行为中,新建标签页加载的页面为访问页面,则搜索结果页面为访问页面的关联页面。针对此次的历史浏览行为,获取访问页面的URL、访问页面的内容、搜索结果页面的URL和搜索结果页面的内容。
根据获取的访问页面的URL、访问页面的内容、访问页面的关联页面的URL和关联页面的内容,生成特征参数。
在对多个历史浏览行为涉及的访问页面分析之后,采用获取的特征参数表征多个访问页面,并利用对应的浏览方式对多个访问页面进行标注。例如,用户通过人民网浏览新闻时,用户在首页点击某条新闻链接后,浏览器在新建标签页加载该新闻。用户浏览完毕后,又点击了另一条新闻链接,浏览器在新建标签页中打开该链接,同时,用户关闭了之前的新闻页面。这时,可将访问页面标记为当前标签页浏览。
又如,用户浏览购物网站如淘宝网时,为了对比商品,在浏览器窗口中通过多个标签页打开了多个商品链接。对于这种情况,将访问页面标记为新建标签页浏览。
将多个访问页面标注完毕后,将标注后的多个访问页面作为训练样本,从而生成训练样本集。然后,采用训练样本集对学习模型进行训练。在本实施例中,学习模型为二分类模型(即当前标签页浏览或新建标签页浏览两类),将多个训练样本的特征参数依次输入学习模型,输出为浏览方式,当前标签页浏览或新建标签页浏览。
本实施例中,通过获取的多个维度的特征参数,训练学习模型,使学习模型的输出结果更准确。
S303,若获取到页面访问请求,采用训练好的学习模型,对所需访问的目标页面进行分析,以从当前标签页浏览和新建标签页浏览中确定出目标浏览方式。
例如,某时刻用户点击了浏览器中某个链接,这时浏览器获取到页面访问请求。在获取到页面访问请求后,提取需要访问的目标页面的特征参数,如目标页面的URL、目标页面的关联页面的URL和关联页面的内容等。然后,将访问页面的特征参数输入至二分类模型中进行分析,通过二分类模型的输出结果确定需要访问的目标页面的浏览方式。
S304,依据目标浏览方式,对目标页面进行加载。
如果二分类模型的输出结果为当前标签页浏览,则采用当前标签页浏览的方式对目标页面进行加载。如果二分类模型的输出结果为新建标签页浏览,则采用新建标签页的方式对目标页面进行加载。
为了提高页面加载的智能化,在获取页面访问请求后,统计涉及目标页面
时采用新建标签页浏览的次数,若统计得到的次数符合预设条件,如新建标签页浏览的次数超过预设阈值,或者超过全部页面新建标签页浏览的平均次数的若干倍,可通过弹出提示框的方式,提示用户开启智能多标签模式。如果用户选择开启智能多标签模式,在获取用户允许开启智能多标签模式的指令后,根据指令开启智能多标签模式。在该模式下,用户点击链接后,浏览器自动创建新标签页,通过新建标签页加载页面。
例如,某一段时间内,用户在访问一些特定网站时,如淘宝网、京东商城等,通过新建标签页浏览的次数超过预设阈值。在用户下次访问这些网站的网页时,弹出提示框,提示用户是否针对该网站开启智能多标签模式。在接收到用户允许开启智能多标签模式的指令后,开启智能多标签模式,使用户在点击该网站的链接时,自动创建新建标签页。
本发明实施例的页面加载方法,通过对用户使用浏览器时的历史浏览行为进行采集,得到历史浏览行为涉及的访问页面和用户采用的浏览方式,根据访问页面和用户采用的浏览方式,对学习模型进行训练,使学习模型得到访问页面与浏览方式之间的对应关系,其中,浏览方式包括当前标签页浏览和新建标签页浏览,若获取到页面访问请求,采用训练好的学习模型,对所需访问的目标页面进行分析,以从当前标签页浏览和新建标签页浏览中确定出目标浏览方式,依据目标浏览方式,对目标页面进行加载。本实施例中,通过根据用户使用浏览器的历史浏览行为,得到的访问页面和用户采用的浏览方式,利用访问页面和用户采用的浏览方式,对学习模型进行训练,当获取到页面访问请求时,根据学习模型确定对页面的目标浏览方式,并根据目标浏览方式对页面进行加载,实现了根据用户的历史浏览行为,自适应选择页面的浏览方式,并根据选择的浏览方式加载页面,解决了现有技术中浏览器加载页面的方式比较固定、单一的技术问题。
为达上述目的,本发明还提出一种页面加载装置。
如图4所示,该装置包括:采集模块410、训练模块420、分析模块430、加载模块440。
采集模块410用于对用户使用浏览器时的历史浏览行为进行采集,得到历史浏览行为涉及的访问页面和用户采用的浏览方式。
训练模块420用于根据访问页面和用户采用的浏览方式,对学习模型进行训练,以使 学习模型学习得到访问页面与浏览方式之间的对应关系;其中,浏览方式包括当前标签页浏览和新建标签页浏览;
分析模块430用于若获取到页面访问请求,采用训练好的学习模型,对所需访问的目标页面进行分析,以从当前标签页浏览和新建标签页浏览中确定出目标浏览方式。
加载模块440用于依据目标浏览方式,对目标页面进行加载。
在本发明一种可能的实现方式中,如图5所示,训练模块420包括:特征提取单元421、标注单元422、生成单元423、训练单元424。
特征提取单元421用于对多次历史浏览行为涉及的访问页面进行分析,得到多个访问页面的特征参数。
标注单元422用于采用特征参数表征多个访问页面,并利用对应的浏览方式对多个访问页面进行标注。
生成单元423用于根据标注后的多个访问页面生成训练样本集。
训练单元424用于采用训练样本集,对学习模型进行训练;其中,学习模型为二分类模型。
特征提取单元421具体用于针对每一历史浏览行为,获取访问页面的URL、访问页面的内容、访问页面的关联页面的URL和/或关联页面的内容;其中,关联页面是本标签页跳转至访问页面之前,本标签页所加载的页面和/或其他标签页已加载的页面;根据访问页面的URL、访问页面的内容、关联页面的URL和/或关联页面的内容,生成特征参数。
进一步地,如图6所示,该装置还包括提示模块450。
提示模块450用于根据历史浏览行为,统计涉及目标页面时采用新建标签页浏览的次数;若统计得到的次数符合预设条件,提示用户开启智能多标签模式;获取用户允许开启智能多标签模式的指令。
需要说明的是,前述对页面加载方法的解释说明,也适用于该实施例的对页面加载装置的解释说明,在此不再赘述。
本发明实施例的页面加载装置,通过对用户使用浏览器时的历史浏览行为进行采集,得到历史浏览行为涉及的访问页面和用户采用的浏览方式,根据访问页面和用户采用的浏览方式,对学习模型进行训练,使学习模型得到访问页面与浏览方式之间的对应关系,其中,浏览方式包括当前标签页浏览和新建标签页浏览,若获取到页面访问请求,采用训练好的学习模型,对所需访问的目标页面进行分析,以从当前标签页浏览和新建标签页浏览中确定出目标浏览方式,依据目标浏览方式,对目标页面进行加载。本实施例中,通过根 据用户使用浏览器的历史浏览行为,得到的访问页面和用户采用的浏览方式,利用访问页面和用户采用的浏览方式,对学习模型进行训练,当获取到页面访问请求时,根据学习模型确定对页面的目标浏览方式,并根据目标浏览方式对页面进行加载,实现了根据用户的历史浏览行为,自适应选择页面的浏览方式,并根据选择的浏览方式加载页面,解决了现有技术中浏览器加载页面的方式比较固定、单一的技术问题。
本发明实施例还提供一种电子设备,电子设备包含前述任一实施例所述的页面加载装置。
图7为本发明电子设备一个实施例的结构示意图,可以实现本发明图3所示实施例的流程,如图7所示,上述电子设备可以包括:壳体71、处理器72、存储器73、电路板74和电源电路75,其中,电路板74安置在壳体71围成的空间内部,处理器72和存储器73设置在电路板74上;电源电路75,用于为上述电子设备的各个电路或器件供电;存储器73用于存储可执行程序代码;处理器72通过读取存储器73中存储的可执行程序代码来运行与可执行程序代码对应的程序,用于执行前述任一实施例所述的页面加载方法。
处理器72对上述步骤的具体执行过程以及处理器72通过运行可执行程序代码来进一步执行的步骤,可以参见本发明图3所示实施例的描述,在此不再赘述。
该电子设备以多种形式存在,包括但不限于:
(1)移动通信设备:这类设备的特点是具备移动通信功能,并且以提供话音、数据通信为主要目标。这类终端包括:智能手机(例如iPhone)、多媒体手机、功能性手机,以及低端手机等。
(2)超移动个人计算机设备:这类设备属于个人计算机的范畴,有计算和处理功能,一般也具备移动上网特性。这类终端包括:PDA、MID和UMPC设备等,例如iPad。
(3)便携式娱乐设备:这类设备可以显示和播放多媒体内容。该类设备包括:音频、视频播放器(例如iPod),掌上游戏机,电子书,以及智能玩具和便携式车载导航设备。
(4)服务器:提供计算服务的设备,服务器的构成包括处理器、硬盘、内存、系统总线等,服务器和通用的计算机架构类似,但是由于需要提供高可靠的服务,因此在处理能力、稳定性、可靠性、安全性、可扩展性、可管理性等方面要求较高。
(5)其他具有数据交互功能的电子设备。
为达上述目的,本发明实施例提出一种非临时性计算机可读存储介质,其上存储有计算机程序,该程序被处理器执行时实现如上述实施例所述的页面加载方法。
为达上述目的,本发明实施例提出一种计算机程序产品,当计算机程序产品中的指令 由处理器执行时,执行如上述实施例所述的页面加载方法。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程,是可以通过计算机程序来指令相关的硬件来完成,所述的程序可存储于一计算机可读取存储介质中,该程序在执行时,可包括如上述各方法的实施例的流程。其中,所述的存储介质可为磁碟、光盘、只读存储记忆体(Read-Only Memory,ROM)或随机存储记忆体(Random Access Memory,RAM)等。
在本说明书的描述中,参考术语“一个实施例”、“一些实施例”、“示例”、“具体示例”、或“一些示例”等的描述意指结合该实施例或示例描述的具体特征、结构、材料或者特点包含于本发明的至少一个实施例或示例中。在本说明书中,对上述术语的示意性表述不必须针对的是相同的实施例或示例。而且,描述的具体特征、结构、材料或者特点可以在任一个或多个实施例或示例中以合适的方式结合。此外,在不相互矛盾的情况下,本领域的技术人员可以将本说明书中描述的不同实施例或示例以及不同实施例或示例的特征进行结合和组合。
此外,术语“第一”、“第二”仅用于描述目的,而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此,限定有“第一”、“第二”的特征可以明示或者隐含地包括至少一个该特征。在本发明的描述中,“多个”的含义是至少两个,例如两个,三个等,除非另有明确具体的限定。
流程图中或在此以其他方式描述的任何过程或方法描述可以被理解为,表示包括一个或更多个用于实现定制逻辑功能或过程的步骤的可执行指令的代码的模块、片段或部分,并且本发明的优选实施方式的范围包括另外的实现,其中可以不按所示出或讨论的顺序,包括根据所涉及的功能按基本同时的方式或按相反的顺序,来执行功能,这应被本发明的实施例所属技术领域的技术人员所理解。
在流程图中表示或在此以其他方式描述的逻辑和/或步骤,例如,可以被认为是用于实现逻辑功能的可执行指令的定序列表,可以具体实现在任何计算机可读介质中,以供指令执行系统、装置或设备(如基于计算机的系统、包括处理器的系统或其他可以从指令执行系统、装置或设备取指令并执行指令的系统)使用,或结合这些指令执行系统、装置或设备而使用。就本说明书而言,"计算机可读介质"可以是任何可以包含、存储、通信、传播或传输程序以供指令执行系统、装置或设备或结合这些指令执行系统、装置或设备而使用的装置。计算机可读介质的更具体的示例(非穷尽性列表)包括以下:具有一个或多个布线的电连接部(电子装置),便携式计算机盘盒(磁装置),随机存取存储器(RAM),只 读存储器(ROM),可擦除可编辑只读存储器(EPROM或闪速存储器),光纤装置,以及便携式光盘只读存储器(CDROM)。另外,计算机可读介质甚至可以是可在其上打印所述程序的纸或其他合适的介质,因为可以例如通过对纸或其他介质进行光学扫描,接着进行编辑、解译或必要时以其他合适方式进行处理来以电子方式获得所述程序,然后将其存储在计算机存储器中。
应当理解,本发明的各部分可以用硬件、软件、固件或它们的组合来实现。在上述实施方式中,多个步骤或方法可以用存储在存储器中且由合适的指令执行系统执行的软件或固件来实现。如,如果用硬件来实现和在另一实施方式中一样,可用本领域公知的下列技术中的任一项或他们的组合来实现:具有用于对数据信号实现逻辑功能的逻辑门电路的离散逻辑电路,具有合适的组合逻辑门电路的专用集成电路,可编程门阵列(PGA),现场可编程门阵列(FPGA)等。
本技术领域的普通技术人员可以理解实现上述实施例方法携带的全部或部分步骤是可以通过程序来指令相关的硬件完成,所述的程序可以存储于一种计算机可读存储介质中,该程序在执行时,包括方法实施例的步骤之一或其组合。
此外,在本发明各个实施例中的各功能单元可以集成在一个处理模块中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个模块中。上述集成的模块既可以采用硬件的形式实现,也可以采用软件功能模块的形式实现。所述集成的模块如果以软件功能模块的形式实现并作为独立的产品销售或使用时,也可以存储在一个计算机可读取存储介质中。
上述提到的存储介质可以是只读存储器,磁盘或光盘等。尽管上面已经示出和描述了本发明的实施例,可以理解的是,上述实施例是示例性的,不能理解为对本发明的限制,本领域的普通技术人员在本发明的范围内可以对上述实施例进行变化、修改、替换和变型。
以上所述,仅为本发明的具体实施方式,但本发明的保护范围并不局限于此,任何熟悉本技术领域的技术人员在本发明揭露的技术范围内,可轻易想到的变化或替换,都应涵盖在本发明的保护范围之内。因此,本发明的保护范围应以权利要求的保护范围为准。

Claims (11)

  1. 一种页面加载方法,其特征在于,包括以下步骤:
    对用户使用浏览器时的历史浏览行为进行采集,得到所述历史浏览行为涉及的访问页面和用户采用的浏览方式;
    根据所述访问页面和用户采用的浏览方式,对学习模型进行训练,以使学习模型学习得到访问页面与浏览方式之间的对应关系;其中,所述浏览方式包括当前标签页浏览和新建标签页浏览;
    若获取到页面访问请求,采用训练好的学习模型,对所需访问的目标页面进行分析,以从当前标签页浏览和新建标签页浏览中确定出目标浏览方式;
    依据所述目标浏览方式,对所述目标页面进行加载。
  2. 根据权利要求1所述的页面加载方法,其特征在于,所述根据所述访问页面和用户采用的浏览方式,对学习模型进行训练,包括:
    对多次历史浏览行为涉及的访问页面进行分析,得到多个访问页面的特征参数;
    采用特征参数表征多个访问页面,利用对应的浏览方式对多个访问页面并进行标注;
    根据标注后的多个访问页面生成训练样本集;
    采用所述训练样本集,对所述学习模型进行训练;其中,所述学习模型为二分类模型。
  3. 根据权利要求2所述的页面加载方法,其特征在于,所述对多次历史浏览行为涉及的访问页面进行分析,得到多个访问页面的特征参数,包括:
    针对每一历史浏览行为,获取所述访问页面的URL、所述访问页面的内容、所述访问页面的关联页面的URL和/或所述关联页面的内容;其中,所述关联页面是本标签页跳转至所述访问页面之前,所述本标签页所加载的页面和/或其他标签页已加载的页面;
    根据所述访问页面的URL、所述访问页面的内容、所述关联页面的URL和/或所述关联页面的内容,生成所述特征参数。
  4. 根据权利要求1-3任一项所述的页面加载方法,其特征在于,所述采用训练好的学习模型,对所需访问的目标页面进行分析,以从当前标签页浏览和新建标签页浏览中确定出目标浏览方式之前,还包括:
    根据所述历史浏览行为,统计涉及所述目标页面时采用新建标签页浏览的次数;
    若统计得到的次数符合预设条件,提示用户开启智能多标签模式;
    获取用户允许开启所述智能多标签模式的指令。
  5. 一种页面加载装置,其特征在于,包括:
    采集模块,用于对用户使用浏览器时的历史浏览行为进行采集,得到所述历史浏览行为涉及的访问页面和用户采用的浏览方式;
    训练模块,用于根据所述访问页面和用户采用的浏览方式,对学习模型进行训练,以 使学习模型学习得到访问页面与浏览方式之间的对应关系;其中,所述浏览方式包括当前标签页浏览和新建标签页浏览;
    分析模块,用于若获取到页面访问请求,采用训练好的学习模型,对所需访问的目标页面进行分析,以从当前标签页浏览和新建标签页浏览中确定出目标浏览方式;
    加载模块,用于依据所述目标浏览方式,对所述目标页面进行加载。
  6. 根据权利要求5所述的页面加载装置,其特征在于,所述训练模块,包括:
    特征提取单元,用于对多次历史浏览行为涉及的访问页面进行分析,得到多个访问页面的特征参数;
    标注单元,用于采用特征参数表征多个访问页面,并利用对应的浏览方式对多个访问页面进行标注;
    生成单元,用于根据标注后的多个访问页面生成训练样本集;
    训练单元,用于采用所述训练样本集,对所述学习模型进行训练;其中,所述学习模型为二分类模型。
  7. 根据权利要求6所述的页面加载装置,其特征在于,所述特征提取单元,具体用于:
    针对每一历史浏览行为,获取所述访问页面的URL、所述访问页面的内容、所述访问页面的关联页面的URL和/或所述关联页面的内容;其中,所述关联页面是本标签页跳转至所述访问页面之前,所述本标签页所加载的页面和/或其他标签页已加载的页面;
    根据所述访问页面的URL、所述访问页面的内容、所述关联页面的URL和/或所述关联页面的内容,生成所述特征参数。
  8. 根据权利要求5-7任一项所述的页面加载装置,其特征在于,所述装置,还包括:
    提示模块,用于根据所述历史浏览行为,统计涉及所述目标页面时采用新建标签页浏览的次数;若统计得到的次数符合预设条件,提示用户开启智能多标签模式;获取用户允许开启所述智能多标签模式的指令。
  9. 一种电子设备,其特征在于,包括:壳体、处理器、存储器、电路板和电源电路,其中,电路板安置在壳体围成的空间内部,处理器和存储器设置在电路板上;电源电路,用于为上述电子设备的各个电路或器件供电;存储器用于存储可执行程序代码;处理器通过读取存储器中存储的可执行程序代码来运行与可执行程序代码对应的程序,用于执行权利要求1-4任一项所述的页面加载方法。
  10. 一种非临时性计算机可读存储介质,其上存储有计算机程序,其特征在于,该程序被处理器执行时实现如权利要求1-4任一项所述的页面加载方法。
  11. 一种计算机程序产品,其特征在于,当所述计算机程序产品中的指令由处理器执行时,执行如权利要求1-4任一项所述的页面加载方法。
PCT/CN2017/106373 2017-06-27 2017-10-16 页面加载方法、装置和电子设备 WO2019000710A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US16/404,450 US11036820B2 (en) 2017-06-27 2019-05-06 Page loading method and electronic device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710501008.X 2017-06-27
CN201710501008.XA CN107220094B (zh) 2017-06-27 2017-06-27 页面加载方法、装置和电子设备

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US16/404,450 Continuation US11036820B2 (en) 2017-06-27 2019-05-06 Page loading method and electronic device

Publications (1)

Publication Number Publication Date
WO2019000710A1 true WO2019000710A1 (zh) 2019-01-03

Family

ID=59950435

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/106373 WO2019000710A1 (zh) 2017-06-27 2017-10-16 页面加载方法、装置和电子设备

Country Status (3)

Country Link
US (1) US11036820B2 (zh)
CN (1) CN107220094B (zh)
WO (1) WO2019000710A1 (zh)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110263273A (zh) * 2019-05-21 2019-09-20 深圳壹账通智能科技有限公司 页面回退方法及相关装置
CN112506582A (zh) * 2020-12-18 2021-03-16 北京百度网讯科技有限公司 小程序数据包处理方法、装置、设备及介质
CN113077305A (zh) * 2021-03-23 2021-07-06 上海尊溢商务信息咨询有限公司 页面处理方法、系统、电子设备及存储介质
CN113158102A (zh) * 2021-02-23 2021-07-23 北京三快在线科技有限公司 页面配置方法、装置、电子设备和计算机可读介质
CN113704596A (zh) * 2020-05-21 2021-11-26 北京沃东天骏信息技术有限公司 用于生成召回信息集合的方法和装置
CN113806653A (zh) * 2021-09-22 2021-12-17 未鲲(上海)科技服务有限公司 页面预加载方法、装置、计算机设备及存储介质
CN117253624A (zh) * 2023-11-02 2023-12-19 银川童宜棠互联网医院有限公司 一种基于人工智能的医学健康知识普及方法、装置及介质

Families Citing this family (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107220094B (zh) * 2017-06-27 2019-06-28 北京金山安全软件有限公司 页面加载方法、装置和电子设备
CN108460590B (zh) * 2018-02-06 2021-02-02 北京三快在线科技有限公司 信息推荐的方法、装置及电子设备
US10795965B2 (en) * 2018-03-30 2020-10-06 Microsoft Technology Licensing, Llc Distributed in-browser deep learning for predictive pre-fetching
CN108595573B (zh) * 2018-04-16 2021-02-26 Oppo广东移动通信有限公司 页面显示方法、装置、存储介质及电子设备
CN110796462B (zh) * 2018-08-01 2024-04-16 北京京东尚科信息技术有限公司 流量引导的方法和装置
CN111368180B (zh) * 2018-12-25 2023-06-09 阿里巴巴集团控股有限公司 页面展示方法、装置及电子设备
CN110018869B (zh) * 2019-02-20 2021-02-05 创新先进技术有限公司 通过强化学习向用户展示页面的方法及装置
CN110275746B (zh) * 2019-04-12 2022-03-04 创新先进技术有限公司 页面展示的控制方法及装置
CN111158785B (zh) * 2019-12-30 2023-09-22 掌阅科技股份有限公司 电子书应用启动功能页面的确定方法、设备及存储介质
CN112541142B (zh) * 2020-12-16 2024-07-09 深圳市欢太科技有限公司 一种网页显示方法、装置、存储介质及电子设备
CN112597421A (zh) * 2020-12-29 2021-04-02 上海硬通网络科技有限公司 落地页处理方法、装置及电子设备
CN112632210B (zh) * 2020-12-30 2023-04-25 湖南虹康规划勘测咨询有限公司 一种地理信息大数据管理方法、系统以及存储介质
CN113535311A (zh) * 2021-07-29 2021-10-22 展讯半导体(成都)有限公司 一种页面显示方法、装置及电子设备
CN113590985B (zh) * 2021-09-29 2022-01-04 北京每日优鲜电子商务有限公司 页面跳转配置方法、装置、电子设备和计算机可读介质
CN114357280A (zh) * 2021-11-29 2022-04-15 泰康保险集团股份有限公司 一种信息推送方法、装置、电子设备及计算机可读介质
CN116776016B (zh) * 2023-06-06 2024-02-27 广东保伦电子股份有限公司 一种无需注册特定人员访问浏览器页面的实现方法及终端

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090282023A1 (en) * 2008-05-12 2009-11-12 Bennett James D Search engine using prior search terms, results and prior interaction to construct current search term results
CN103268352A (zh) * 2013-06-03 2013-08-28 贝壳网际(北京)安全技术有限公司 一种标签页显示方法、装置和浏览器装置
CN105224623A (zh) * 2015-09-22 2016-01-06 北京百度网讯科技有限公司 数据模型的训练方法及装置
CN106649347A (zh) * 2015-10-30 2017-05-10 北京国双科技有限公司 一种兴趣信息的识别方法及装置
US20170139879A1 (en) * 2015-11-18 2017-05-18 Google Inc. Simulated hyperlinks on a mobile device
CN107220094A (zh) * 2017-06-27 2017-09-29 北京金山安全软件有限公司 页面加载方法、装置和电子设备

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070128899A1 (en) * 2003-01-12 2007-06-07 Yaron Mayer System and method for improving the efficiency, comfort, and/or reliability in Operating Systems, such as for example Windows
US7305389B2 (en) * 2004-04-15 2007-12-04 Microsoft Corporation Content propagation for enhanced document retrieval
US7885986B2 (en) * 2007-06-27 2011-02-08 Microsoft Corporation Enhanced browsing experience in social bookmarking based on self tags
US8190590B2 (en) * 2007-08-15 2012-05-29 Martin Edward Lawlor System and method for the creation and access of dynamic course content
CN103678325B (zh) * 2012-09-03 2018-11-23 百度在线网络技术(北京)有限公司 一种用于提供与初始页面相对应的浏览页面的方法和设备
WO2014151664A1 (en) * 2013-03-14 2014-09-25 Balderdash Inc. Systems and methods for providing relevant pathways through linked information
US9661088B2 (en) * 2013-07-01 2017-05-23 24/7 Customer, Inc. Method and apparatus for determining user browsing behavior
US20150163311A1 (en) * 2013-11-26 2015-06-11 Martin Charles Heath Systems and methods for capturing, managing, and triggering user journeys associated with trackable digital objects
US9519408B2 (en) * 2013-12-31 2016-12-13 Google Inc. Systems and methods for guided user actions
US9900394B2 (en) * 2014-05-30 2018-02-20 Microsoft Technology Licensing, Llc User-specific and user-activity-based routing within a website

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090282023A1 (en) * 2008-05-12 2009-11-12 Bennett James D Search engine using prior search terms, results and prior interaction to construct current search term results
CN103268352A (zh) * 2013-06-03 2013-08-28 贝壳网际(北京)安全技术有限公司 一种标签页显示方法、装置和浏览器装置
CN105224623A (zh) * 2015-09-22 2016-01-06 北京百度网讯科技有限公司 数据模型的训练方法及装置
CN106649347A (zh) * 2015-10-30 2017-05-10 北京国双科技有限公司 一种兴趣信息的识别方法及装置
US20170139879A1 (en) * 2015-11-18 2017-05-18 Google Inc. Simulated hyperlinks on a mobile device
CN107220094A (zh) * 2017-06-27 2017-09-29 北京金山安全软件有限公司 页面加载方法、装置和电子设备

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110263273A (zh) * 2019-05-21 2019-09-20 深圳壹账通智能科技有限公司 页面回退方法及相关装置
CN113704596A (zh) * 2020-05-21 2021-11-26 北京沃东天骏信息技术有限公司 用于生成召回信息集合的方法和装置
CN112506582A (zh) * 2020-12-18 2021-03-16 北京百度网讯科技有限公司 小程序数据包处理方法、装置、设备及介质
CN112506582B (zh) * 2020-12-18 2024-04-09 北京百度网讯科技有限公司 小程序数据包处理方法、装置、设备及介质
CN113158102A (zh) * 2021-02-23 2021-07-23 北京三快在线科技有限公司 页面配置方法、装置、电子设备和计算机可读介质
CN113077305A (zh) * 2021-03-23 2021-07-06 上海尊溢商务信息咨询有限公司 页面处理方法、系统、电子设备及存储介质
CN113077305B (zh) * 2021-03-23 2024-03-29 上海尊溢商务信息咨询有限公司 页面处理方法、系统、电子设备及存储介质
CN113806653A (zh) * 2021-09-22 2021-12-17 未鲲(上海)科技服务有限公司 页面预加载方法、装置、计算机设备及存储介质
CN113806653B (zh) * 2021-09-22 2024-04-05 北京快阅读科技有限公司 页面预加载方法、装置、计算机设备及存储介质
CN117253624A (zh) * 2023-11-02 2023-12-19 银川童宜棠互联网医院有限公司 一种基于人工智能的医学健康知识普及方法、装置及介质
CN117253624B (zh) * 2023-11-02 2024-03-05 银川童宜棠互联网医院有限公司 一种基于人工智能的医学健康知识普及方法、装置及介质

Also Published As

Publication number Publication date
CN107220094B (zh) 2019-06-28
CN107220094A (zh) 2017-09-29
US20190361942A1 (en) 2019-11-28
US11036820B2 (en) 2021-06-15

Similar Documents

Publication Publication Date Title
WO2019000710A1 (zh) 页面加载方法、装置和电子设备
US10902077B2 (en) Search result aggregation method and apparatus based on artificial intelligence and search engine
AU2014284401B2 (en) Method and apparatus for determining user browsing behavior
US10733197B2 (en) Method and apparatus for providing information based on artificial intelligence
US10212170B1 (en) User authentication using client-side browse history
US10552887B1 (en) Web-based automated product demonstration
CN104504133B (zh) 应用程序的推荐方法及装置
US20130132851A1 (en) Sentiment estimation of web browsing user
WO2017076038A1 (zh) 搜索推荐方法及装置
US9712520B1 (en) User authentication using client-side browse history
US11132209B2 (en) Integrated profile simulation for dynamic content
US20180011933A1 (en) Method, apparatus, and server for generating hotspot content
US20190347068A1 (en) Personal history recall
CN107273393A (zh) 用于移动设备的图像搜索方法、装置及数据处理系统
US9646104B1 (en) User tracking based on client-side browse history
CN107315833A (zh) 基于应用程序的检索与下载的方法和装置
US11960834B2 (en) Reader mode-optimized attention application
US20180240023A1 (en) Methods and systems for selecting targeted content by machine learning algorithm
US10031970B1 (en) Search engine optimization in social question and answer systems
US11630865B2 (en) User reaction based information options
US10290022B1 (en) Targeting content based on user characteristics
CN107357796B (zh) 一种网络信息获取方法、设备及可编程设备
CN113377196B (zh) 数据推荐方法、装置、电子设备及可读存储介质
US20240169003A1 (en) Server and method for generating digital content for users of a recommendation system
US11520839B2 (en) User based network document modification

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: 17915414

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: 17915414

Country of ref document: EP

Kind code of ref document: A1