WO2020199512A1 - 一种题目信息采集的方法及系统 - Google Patents

一种题目信息采集的方法及系统 Download PDF

Info

Publication number
WO2020199512A1
WO2020199512A1 PCT/CN2019/105394 CN2019105394W WO2020199512A1 WO 2020199512 A1 WO2020199512 A1 WO 2020199512A1 CN 2019105394 W CN2019105394 W CN 2019105394W WO 2020199512 A1 WO2020199512 A1 WO 2020199512A1
Authority
WO
WIPO (PCT)
Prior art keywords
question
information
topic
page
mark
Prior art date
Application number
PCT/CN2019/105394
Other languages
English (en)
French (fr)
Inventor
黄雪文
陆开一
Original Assignee
浙江飙速教育科技有限公司
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 浙江飙速教育科技有限公司 filed Critical 浙江飙速教育科技有限公司
Publication of WO2020199512A1 publication Critical patent/WO2020199512A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
    • G09B7/00—Electrically-operated teaching apparatus or devices working with questions and answers

Definitions

  • the present invention relates to the technical field of intelligent learning, in particular to a method and system for collecting topic information.
  • Electronic teaching is the use of modern equipment and equipment to teach through information storage, transmission, mediation and reproduction technology. Compared with traditional teaching modes such as paper books, blackboards and wall charts, electronic teaching can integrate pictures, videos, audios, and interactions, and teach knowledge more vividly, allowing students to master them faster.
  • the patent with publication number CN108052545A discloses a topic input method, device, mobile terminal and storage medium for taking photos to search for questions.
  • the method includes: receiving a camera search request input by a mobile terminal user, and acquiring a mobile terminal camera according to the taking photos to search for questions.
  • the image of the target subject in the preset range in front is outputted, and it is detected whether the moving speed of the mobile terminal is within the preset speed range.
  • the target subject is photographed to obtain the captured image
  • the subject in the target image is captured, and the obtained subject is entered into the preset input box, thereby improving the automation of entering the subject, optimizing the subject input process, and improving the efficiency of photographing and searching the subject.
  • the patent with the publication number CN104348858A discloses a method for uploading Q&A questions based on a mobile smart electronic device, including: establishing a connection between a student mobile device and a teacher device; the student mobile device is one-click Triggered by a photographing instruction, take a picture of a question and answer question to obtain a picture of the question; the student mobile device is triggered by the upload instruction of the student user, and automatically transmits the photographed question photo to the teacher-end device, and the question photo is displayed synchronously On the student mobile device and the teacher device.
  • the invention can improve the efficiency of topic uploading and avoid errors caused by manual input.
  • the above solution can upload the picture of the question by taking a photo, it cannot identify the corresponding question information through the mark, and cannot save the obtained question in the question bank.
  • the purpose of the present invention is to provide a method and system for collecting question information in view of the defects of the prior art.
  • the question corresponding to the mark is obtained by identifying the mark information, and the obtained question information is stored in the question bank to improve learning efficiency.
  • a method for collecting topic information including:
  • the method further includes:
  • step S12 is specifically that the title corresponds to the logo and one title corresponds to one logo; the title on the page picture is determined based on the logo corresponding to the title.
  • the content of the page in the step S11 includes a question, an answer, and a judgment box.
  • the mark is a judgment box and the content of the judgment in the judgment box.
  • the method further includes:
  • a system for collecting topic information including:
  • Get module get the picture of the page where the question is located
  • the collection module collects the logo corresponding to the title in the page picture
  • the extraction module extracts topic information corresponding to the mark.
  • Storage module a way to store identification mark information.
  • the judgment module judges whether the question information exists in the question bank.
  • the logo corresponding to the title in the collected page picture is specifically that the title corresponds to the logo and one title corresponds to one logo; based on the logo corresponding to the title, the logo on the page image is determined topic.
  • this application obtains the question corresponding to the mark through the identification mark information, and determines whether the question information is stored in the question bank. If it does not exist, save it in the question bank, which improves the efficiency of question collection and is helpful Help students improve their learning efficiency.
  • FIG. 1 is a flowchart of a method for collecting topic information provided in the first embodiment
  • Figure 2 is a structural diagram of a topic information collection system provided in the first embodiment
  • Fig. 3 is a flowchart of a method for collecting topic information provided in the second embodiment
  • Fig. 4 is a structural diagram of a topic information collection system provided in the second embodiment.
  • the purpose of the present invention is to provide a method and system for collecting topic information in view of the defects of the prior art.
  • This embodiment provides a method for collecting topic information, as shown in FIG. 1, including the steps:
  • the picture of the page where the question is located is first obtained, where the obtained picture is obtained by taking a photo or scanning a page, and the page is a paper object such as a test paper.
  • the test paper is taken as an example for detailed description.
  • the content of the test paper includes questions, answers, serial numbers, judgment boxes, and QR codes.
  • the serial numbers and questions are generated by printing, handwriting, etc.; the answers are answered by the user who holds the current test paper; the QR code includes the current user’s personal information And the question information of the test paper; the judging box is used to judge whether the answer to the question is correct.
  • the correctness is represented by " ⁇ "
  • the error is represented by " ⁇ ”.
  • the judgment method is not limited to the method provided in this embodiment. Can be set according to the actual situation.
  • the answer is answered by students, and the correctness of the answer is judged by the teacher, but it is not limited to this, and the choice can be made according to the actual situation.
  • an examination paper includes one or more pages, and each page of the examination paper includes a two-dimensional code, that is, the content of each page in an examination paper includes a two-dimensional code, where the two-dimensional code includes the user’s Personal information and topic information of the current page.
  • an examination paper includes the first page and the second page.
  • the information of the QR code on the first page includes the user’s personal information and the topic information on the first page; the information of the QR code on the second page includes the user’s Personal information and topic information on the second page.
  • the system automatically recognizes the QR code to match the user's test paper with personal information.
  • the title corresponds to the logo and one title corresponds to one logo; the title on the page picture is determined based on the logo corresponding to the title, where the logo is the judgment box and the content of the judgment in the judgment box.
  • the judgment box is indicated by a square, and the content of the judgment is indicated by “ ⁇ ” for correctness and “ ⁇ ” for errors. It should be noted that the manner in which the evaluation box and evaluation content are expressed is not limited to the manner in this embodiment.
  • the evaluation box and the content in the evaluation box are identified through image recognition technology, where each topic corresponds to the evaluation box and the content in the evaluation box one-to-one.
  • image recognition refers to the use of computers to process, analyze, and understand images to identify various targets and objects in different modes.
  • the corresponding question information is automatically obtained to obtain the question corresponding to the mark and automatically identify the right or wrong of the question, thereby facilitating subsequent answers to the question
  • the correct questions and the wrong questions are stored in the corresponding question bank.
  • the title information corresponding to the logo information is automatically acquired.
  • the system detects the acquired title information, it saves the title information corresponding to the mark in the form of a picture, or extracts the text information on the title, that is, converts the title image into text.
  • the text information includes text, symbols, letters and other information. Specifically, converting the title image into text information is converted by image-to-text, so as to obtain the text information corresponding to the title.
  • the title of the picture or the title of the text information is selected by the user.
  • the user if the user chooses to extract the text information on the topic, it further includes: generating the text information into an electronic topic.
  • the text information is automatically generated as an electronic question, which is convenient for using the electronic question to generate an electronic test paper or for printing to generate a paper test paper.
  • this embodiment also provides a system for collecting topic information, as shown in Figure 2, including:
  • the obtaining module 11 obtains the picture of the page where the question is located
  • the collection module 12 collects the logo corresponding to the title in the page picture
  • the extraction module 13 extracts the title information corresponding to the mark.
  • the content of the page includes a title, an answer, a serial number, a judgment box, and a two-dimensional code.
  • the serial number and question are generated by printing, handwriting, etc.; the answer is answered by the user who holds the current test paper; the QR code includes the current user's personal information and the question information of the test paper; the judgment box is used to judge whether the answer to the question is correct.
  • the logo corresponding to the title in the collected page picture is specifically that the title corresponds to the logo and one title corresponds to one logo; the page is determined based on the logo corresponding to the title The title on the picture, where the mark is the judgment box and the content of the judgment in the judgment box.
  • the evaluation box and the content in the evaluation box are identified through image recognition technology, where each topic corresponds to the evaluation box and the content in the evaluation box one-to-one.
  • the question corresponding to the mark is obtained by identifying the mark information, and at the same time, it is determined whether the question information is stored in the question bank, which improves the efficiency of question collection and helps students improve learning efficiency.
  • This embodiment provides a method for collecting topic information, as shown in FIG. 3, including the steps:
  • the information of the identification mark is preset, where the mark is the judgment box and the content of the judgment in the judgment box. For example, if the judgment box is a square, the answer corresponding to the preset question is correct, and the user “ ⁇ ” indicates that the answer corresponding to the question is wrong is indicated by “ ⁇ ”.
  • the way of preset identification mark information can be automatically generated by the system.
  • the information mode of the preset identification mark can also be set by the user according to the actual situation.
  • the picture of the page where the question is located is first obtained, where the obtained picture is obtained by taking a photo or scanning a page, and the page is a paper object such as a test paper.
  • the test paper is taken as an example for detailed description.
  • the content of the test paper includes questions, answers, serial numbers, judgment boxes, and QR codes.
  • the serial numbers and questions are generated by printing, handwriting, etc.; the answers are answered by the user who holds the current test paper; the QR code includes the current user’s personal information And the question information of the test paper; the judging box is used to judge whether the answer to the question is correct.
  • the correctness is represented by " ⁇ "
  • the error is represented by " ⁇ ”.
  • the judgment method is not limited to the method provided in this embodiment. Can be set according to the actual situation.
  • the answer is answered by students, and the correctness of the answer is judged by the teacher, but it is not limited to this, and the choice can be made according to the actual situation.
  • an examination paper includes one or more pages, and each page of the examination paper includes a two-dimensional code, that is, the content of each page in an examination paper includes a two-dimensional code, where the two-dimensional code includes the user’s Personal information and topic information of the current page.
  • an examination paper includes the first page and the second page.
  • the information of the QR code on the first page includes the user’s personal information and the topic information on the first page; the information of the QR code on the second page includes the user’s Personal information and topic information on the second page.
  • the system automatically recognizes the QR code to match the user's test paper with personal information.
  • the title corresponds to the logo and one title corresponds to one logo; the title on the page picture is determined based on the logo corresponding to the title, where the logo is the judgment box and the content of the judgment in the judgment box.
  • the judgment box is indicated by a square, and the content of the judgment is indicated by “ ⁇ ” for correctness and “ ⁇ ” for errors. It should be noted that the manner in which the evaluation box and evaluation content are expressed is not limited to the manner in this embodiment.
  • the judgment box and the content in the judgment box are identified through image recognition technology, where each topic corresponds to the judgment box and the content in the judgment box.
  • image recognition refers to the use of computers to process, analyze, and understand images to identify various targets and objects in different modes.
  • the corresponding question information is automatically obtained to obtain the question corresponding to the mark and automatically identify the right or wrong of the question, thereby facilitating subsequent answers to the question
  • the correct questions and the wrong questions are stored in the corresponding question bank.
  • the title information corresponding to the logo information is automatically acquired.
  • the system saves the topic information corresponding to the mark in the form of a picture, or extracts the text information on the topic, that is, converts the topic image into text.
  • the text information includes text, symbols, letters and other information. Specifically, converting the title image into text information is converted by image-to-text, so as to obtain the text information corresponding to the title.
  • the title of the picture or the title of the text information is selected by the user.
  • the user if the user chooses to extract the text information on the topic, it further includes: generating the text information into an electronic topic.
  • the text information is automatically generated as an electronic question, which is convenient for using the electronic question to generate an electronic test paper or for printing to generate a paper test paper.
  • the question bank is divided into a question bank of wrong questions and a question bank of correct questions, wherein the question bank of wrong questions refers to the question bank composed of answering wrong questions, and the question bank of correct questions refers to the question bank composed of answering correct questions. .
  • the questions in the question bank of this embodiment are provided with tags, and the tags refer to the frequency of errors.
  • the question information it is determined whether the question information exists in the question bank. If it does not exist, it is recognized that the mark corresponding to the question is " ⁇ " or " ⁇ ”, and if the mark corresponding to the question is " ⁇ ", then The question is stored in the question bank of the correct question; if the mark corresponding to the question is " ⁇ ", the current question is stored in the question bank of the wrong question.
  • the mark corresponding to the question is " ⁇ "
  • the corresponding question in the question bank of the wrong question is stored in the question bank of the correct question, that is, the current question is stored in the question bank of the correct question, then the question bank of the wrong question The current question does not exist in.
  • setting the error frequency can choose several stars to set the difficulty coefficient. For example, one star means the difficulty coefficient is 1, two stars means the difficulty coefficient is 2, and three stars means the difficulty coefficient is 3, and so on, the more stars are Higher, the greater the degree of difficulty. It should be noted that the setting method is not limited to the setting method in this embodiment.
  • this embodiment also provides a system for collecting topic information, as shown in Figure 2, including:
  • the storage module 10 is a way of storing identification mark information.
  • the obtaining module 11 obtains the picture of the page where the question is located
  • the collection module 12 collects the logo corresponding to the title in the page picture
  • the extraction module 13 extracts topic information corresponding to the mark
  • the judgment module 14 judges whether the question information exists in the question bank.
  • the information of the identification mark is preset.
  • the way of preset identification mark information can be automatically generated by the system.
  • the information mode of the preset identification mark can also be set by the user according to the actual situation.
  • the content of the page includes a title, an answer, a serial number, a judgment box, and a two-dimensional code.
  • the serial number and question are generated by printing, handwriting, etc.; the answer is answered by the user holding the current test paper; the QR code includes the current user's personal information and the question information of the test paper; the judgment box is used to judge whether the answer to the question is correct.
  • the logo corresponding to the title in the collected page picture is specifically that the title corresponds to the logo and one title corresponds to one logo; the page is determined based on the logo corresponding to the title The title on the picture, where the mark is the judgment box and the content of the judgment in the judgment box.
  • the evaluation box and the content in the evaluation box are identified through image recognition technology, where each topic corresponds to the evaluation box and the content in the evaluation box one-to-one.
  • This embodiment obtains the question corresponding to the mark through the identification mark information, and at the same time determines whether the question information is stored in the question bank. If it does not exist, save it in the question bank, which improves the learning efficiency; this embodiment also passes the correct answer to the question The questions with incorrect answers are stored separately to help students improve their learning efficiency.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Educational Administration (AREA)
  • Educational Technology (AREA)
  • General Physics & Mathematics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Electrically Operated Instructional Devices (AREA)

Abstract

一种题目信息采集的方法及系统，其中，所述方法包括：获取题目所在页面的图片（S11）；采集所述页面图片中的题目所对应的标志（S12）；提取所述标志对应的题目信息（S13）。通过识别标志信息获取标志对应的题目，同时判断题库中是否存储该题目信息，若不存在，则将其保存到题库中，提高了学习效率。

Description

一种题目信息采集的方法及系统 技术领域
本发明涉及智能学习的技术领域，尤其涉及一种题目信息采集的方法及系统。
背景技术
在现代社会，随着互联网的发展，电子化教学越来越普及。电子化教学是使用现代化的设备、器材，通过对信息的储存、传输、调解和再现技术所进行的教学。相对于使用纸质书籍、黑板以及挂图等传统的教学模式，电子化教学能集图片，视频，音频，互动为一体，更加形象生动的进行知识的讲授，让学生能更快的掌握。
在学习过程中，学生会做很多的练习题来巩固自己所学，对于题目的整理需要耗费很多精力和时间，但是随着电子科技和互联网的发展普及，人们的学习方式发生了很大的改变，例如，人们越来越多的通过计算机、手机、平板电脑等终端获取本地或网络上的电子题目进行做题及考试，相比以往在纸质试卷或书本上做题的方式，不仅节约了资源，更具有相当的便利性。
公开号为CN108052545A的专利公开了一种拍照搜题的题目输入方法、装置、移动终端及存储介质，该方法包括：接收移动终端用户输入的拍照搜题请求，根据拍照搜题请求获取移动终端摄像头前方预设范围内目标拍摄对象的图像并输出，检测移动终端的移动速度是否处于预设速度范围，当移动终端的移动速度处于预设速度范围时，对目标拍摄对象进行拍照，获取拍照得到的目标拍摄对象图像中的题目，并将获取的题目输入到预设的输入框中，从而提高了输入题目的自动化程度，优化了题目输入过程，进而提高了拍照搜题的效率。公开号为CN104348858A的专利公开了一种基于移动智能电子设备的答疑题目上传方法，包括：建立学生端移动设备与教师端设备之间的连接；所述学生端移动设备由学生用户的一键式拍照指令触发，对答疑题目进行拍照获得题目照片；所述学生端移动设备由所述学生用户的上传指令触发，自动将拍照所得的题目照片传输至所述教师端设备，所述题目照片同步显示在所述学生端移动设 备和教师端设备上。本发明能够提高题目上传的效率，避免手动输入导致的差错。上述方案虽然可以通过拍照将题目图片上传，但是其不能通过标志识别对应的题目信息，且不能将获取到的题目进行保存到题库中。
发明内容
本发明的目的是针对现有技术的缺陷，提供了一种题目信息采集的方法及系统，通过识别标志信息获取标志对应的题目，将获取的题目信息存储到题库中，提高学习效率。
为了实现以上目的，本发明采用以下技术方案：
一种题目信息采集的方法，包括：
S11.获取题目所在页面的图片；
S12.采集所述页面图片中的题目所对应的标志；
S13.提取所述标志对应的题目信息。
进一步的，所述步骤S11之前还包括步骤：
S10.存储识别标志信息的方式。
进一步的，所述步骤S12具体为所述题目与所述标志相对应且一个题目对应一个标志；基于所述题目对应的标志，确定所述页面图片上的题目。
进一步的，所述步骤S11中页面的内容包括题目、答案、评判框。
进一步的，所述标志为评判框及评判框内评判的内容。
进一步的，所述步骤S13之后还包括步骤：
S14.判断所述题目信息是否存在于题库中，若不存在，则将所述题目信息存入题库。
相应的，还提供一种题目信息采集的系统，包括：
获取模块，获取题目所在页面的图片；
采集模块，采集所述页面图片中的题目所对应的标志；
提取模块，提取所述标志对应的题目信息。
进一步的，还包括：
存储模块，存储识别标志信息的方式。
进一步的，还包括：
判断模块，判断所述题目信息是否存在于题库中。
进一步的，所述采集所述页面图片中的题目所对应的标志具体为所述题目与所述标志相对应且一个题目对应一个标志；基于所述题目对应的标志，确定所述页面图片上的题目。
与现有技术相比，本申请通过识别标志信息获取标志对应的题目，同时判断题库中是否存储了该题目信息，若不存在，则将其保存到题库中，提高了题目采集效率且有助于学生提高学习效率。
附图说明
图1是实施例一提供的一种题目信息采集方法的流程图；
图2是实施例一提供的一种题目信息采集系统的结构图；
图3是实施例二提供的一种题目信息采集方法的流程图；
图4是实施例二提供的一种题目信息采集系统的结构图。
具体实施方式
以下通过特定的具体实例说明本发明的实施方式，本领域技术人员可由本说明书所揭露的内容轻易地了解本发明的其他优点与功效。本发明还可以通过另外不同的具体实施方式加以实施或应用，本说明书中的各项细节也可以基于不同观点与应用，在没有背离本发明的精神下进行各种修饰或改变。需说明的是，在不冲突的情况下，以下实施例及实施例中的特征可以相互组合。
本发明的目的是针对现有技术的缺陷，提供了一种题目信息采集的方法及系统。
实施例一
本实施例提供一种题目信息采集的方法，如图1所示，包括步骤：
S11.获取题目所在页面的图片；
在本实施例中，首先获取题目所在页面的图片，其中，获取的图片是通过拍照或扫描页面获取的，所述页面为试卷等纸质物件。在本实施例中，以试卷为例详细说明。
试卷的内容包括题目、答案、序号、评判框、二维码，其中，序号、题目 通过印刷、手写等方式生成；答案通过持有当前试卷的用户做答；二维码包括当前用户的个人信息及试卷的题目信息；评判框用于评判题目的答案是否正确，在本实施例中，正确用“√”表示，错误用“×”表示，评判的方式不仅限于本实施例所提供的方式，可根据实际情况设定。本实施例中答案通过学生做答，评判答案的对错通过老师评定，但不局限于此，可根据实际情况做出选择。
在本实施例中，一份试卷包括一页或多页，其中每页试卷都包括二维码，即一份试卷内的每一页的内容都包含二维码，其中二维码包括用户的个人信息及当前页面的题目信息。例如，一份试卷包括第一页和第二页，其中第一页中的二维码的信息包括用户个人信息及第一页的题目信息；第二页中的二维码的信息包括用户的个人信息及第二页的题目信息。
当获取到题目所在页面的图片的同时系统自动识别二维码，使用户的试卷与个人信息匹配。
S12.采集所述页面图片中的题目所对应的标志；
题目与所述标志相对应且一个题目对应一个标志；基于所述题目对应的标志，确定所述页面图片上的题目，其中，标志为评判框及评判框内评判的内容。
在本实施例中，评判框用方格表示，评判的内容为正确用“√”表示，错误用“×”表示。需要说明的是，评判框和评判内容的表示方式不仅限于本实施例中的方式。
当获取到页面的图片后，通过图像识别技术识别评判框及评判框中的内容，其中，每个题目与评判框及评判框中的内容一一对应。
其中，图像识别是指利用计算机对图像进行处理、分析和理解，以识别各种不同模式的目标和对像的技术。
本实施例中识别到评判框及评判框中的内容后，自动获取相对应的题目信息，以获得与所述标志相对应的题目且自动识别所述题目的对错，从而有利于后续将答题正确的题目与答题错误的题目分别存储到相应的题库中。
S13.提取所述标志对应的题目信息；
在本实施例中，获取到所述标志信息后，则自动获取标志信息对应的题目信息。系统检测到已获取的题目信息后，将所述标志对应的题目信息以图片的 形式保存，或者提取所述题目上的文本信息，即将题目图像转换为文字。其中，文本信息包括文字、符号、字母等信息。具体的，将题目图像转换为文本信息是通过图像转换文本的方式转换的，以获取题目对应的文本信息。
需要说明的是，在本实施例中，采用图片的题目或采用文本信息的题目是通过用户自定义选择。
在本实施例中，若用户选择提取所述题目上的文本信息后，还包括：将所述文本信息生成电子题目。
在本实施例中，提取到题目图像对应的文本信息后，将所述文本信息自动生成电子题目，便于利用所述电子题目生成电子试卷或便于打印生成纸质试卷。
相应的，本实施例还提供一种题目信息采集的系统，如图2所示，包括：
获取模块11，获取题目所在页面的图片；
采集模块12，采集所述页面图片中的题目所对应的标志；
提取模块13，提取所述标志对应的题目信息。
在本实施例中，所述页面的内容包括题目、答案、序号、评判框、二维码。
其中，序号、题目通过印刷、手写等方式生成；答案通过持有当前试卷的用户做答；二维码包括当前用户的个人信息及试卷的题目信息；评判框用于评判题目的答案是否正确。
在本实施例中，所述采集所述页面图片中的题目所对应的标志具体为所述题目与所述标志相对应且一个题目对应一个标志；基于所述题目对应的标志，确定所述页面图片上的题目，其中，所述标志为评判框及评判框内评判的内容。
当获取到页面的图片后，通过图像识别技术识别评判框及评判框中的内容，其中，每个题目与评判框及评判框中的内容一一对应。
本实施例通过识别标志信息获取标志对应的题目，同时判断题库中是否存储了该题目信息，提高了题目采集效率且有助于学生提高学习效率。
实施例二
本实施例提供一种题目信息采集的方法，如图3所示，包括步骤：
S10.存储识别标志信息的方式；
本实施例中，预设识别标志的信息，其中，标志为评判框及评判框内评判 的内容。例如，评判框为方格，则预设题目对应的答案是正确用户“√”表示，题目对应的答案是错误用“×”表示。
可选的，预设识别标志信息的方式可通过系统自动生成。
可选的，预设识别标志的信息方式也可通过用户根据实际情况设定。
S11.获取题目所在页面的图片；
在本实施例中，首先获取题目所在页面的图片，其中，获取的图片是通过拍照或扫描页面获取的，所述页面为试卷等纸质物件。在本实施例中，以试卷为例详细说明。
试卷的内容包括题目、答案、序号、评判框、二维码，其中，序号、题目通过印刷、手写等方式生成；答案通过持有当前试卷的用户做答；二维码包括当前用户的个人信息及试卷的题目信息；评判框用于评判题目的答案是否正确，在本实施例中，正确用“√”表示，错误用“×”表示，评判的方式不仅限于本实施例所提供的方式，可根据实际情况设定。本实施例中答案通过学生做答，评判答案的对错通过老师评定，但不局限于此，可根据实际情况做出选择。
在本实施例中，一份试卷包括一页或多页，其中每页试卷都包括二维码，即一份试卷内的每一页的内容都包含二维码，其中二维码包括用户的个人信息及当前页面的题目信息。例如，一份试卷包括第一页和第二页，其中第一页中的二维码的信息包括用户个人信息及第一页的题目信息；第二页中的二维码的信息包括用户的个人信息及第二页的题目信息。
当获取到题目所在页面的图片的同时系统自动识别二维码，使用户的试卷与个人信息匹配。
S12.采集所述页面图片中的题目所对应的标志；
题目与所述标志相对应且一个题目对应一个标志；基于所述题目对应的标志，确定所述页面图片上的题目，其中，标志为评判框及评判框内评判的内容。
在本实施例中，评判框用方格表示，评判的内容为正确用“√”表示，错误用“×”表示。需要说明的是，评判框和评判内容的表示方式不仅限于本实施例中的方式。
当获取到页面的图片后，通过图像识别技术识别评判框及评判框中的内 容，其中，每个题目与评判框及评判框中的内容一一对应。
其中，图像识别是指利用计算机对图像进行处理、分析和理解，以识别各种不同模式的目标和对像的技术。
本实施例中识别到评判框及评判框中的内容后，自动获取相对应的题目信息，以获得与所述标志相对应的题目且自动识别所述题目的对错，从而有利于后续将答题正确的题目与答题错误的题目分别存储到相应的题库中。
S13.提取所述标志对应的题目信息；
在本实施例中，获取到所述标志信息后，则自动获取标志信息对应的题目信息。系统检测到已获取的题目信息后，将所述标志对应的题目信息以图片的形式保存，或者提取所述题目上的文本信息，即将题目图像转换为文字。其中，文本信息包括文字、符号、字母等信息。具体的，将题目图像转换为文本信息是通过图像转换文本的方式转换的，以获取题目对应的文本信息。
需要说明的是，在本实施例中，采用图片的题目或采用文本信息的题目是通过用户自定义选择。
在本实施例中，若用户选择提取所述题目上的文本信息后，还包括：将所述文本信息生成电子题目。
在本实施例中，提取到题目图像对应的文本信息后，将所述文本信息自动生成电子题目，便于利用所述电子题目生成电子试卷或便于打印生成纸质试卷。
S14.判断所述题目信息是否存在于题库中，若不存在，则将所述题目信息存入题库。
在本实施例中，所述题库分为错题的题库和正确题的题库，其中，错题的题库指答题错误的题目归纳组成的题库，正确题的题库指答题正确的题目归纳组成的题库。
可选的，本实施例题库中的题目设置有标签，所述标签指错误的频率。
在本实施例中，判断所述题目信息是否存在于题库中，若不存在，则识别所述题目对应的标志为“√”或者“×”，若题目对应的标志为“√”，则将所述题目存储于正确题的题库中；若题目对应的标志为“×”，则将当前题目存储于错误题的题库中。
若所述题目信息存在于题库中，判断所述题目信息存储的位置，即存储于错题的题库还是正确题的题库；
若存储于错误的题库中；
则识别当前题目对应的标志为“√”或者“×”；
若题目对应的标志为“√”，则将所述错误题的题库中相对应的题目存储于正确题的题库中，即当前的题目存储的位置是正确题的题库中，则错误题的题库中不存在当前的题目。
若题目对应的标志为“×”，则修改所述错误题的题库中相对应的题目的标签，即修改错误频率。其中，设置错误频率可选用几颗星来设定难度系数，如一颗星表示难度系数为1、两颗星表示难度系数为2、三颗星表示难度系数为3，以此类推，星值越高，难度系数越大。需要说明的是，该设置方式不仅限于本实施例中的设定方式。
若存储于正确的题库中；
则识别当前题目对应的标志为“√”或者“×”；
若题目对应的标志为“错”，则将所述正确题的题库中相对应的题目存储于错误题的题库中，即当前的题目存储的位置是错误题的题库中，则正确题的题库中不存在当前的题目。
若题目对应的标志为“√”，则不做处理。
本实施例可通过对标志进行识别，将答案为正确的题目与答案为错误的题目分别存储于两个题库中，便于学生快速查漏补缺，提高学习效率。
相应的，本实施例还提供一种题目信息采集的系统，如图2所示，包括：
存储模块10，存储识别标志信息的方式。
获取模块11，获取题目所在页面的图片；
采集模块12，采集所述页面图片中的题目所对应的标志；
提取模块13，提取所述标志对应的题目信息；
判断模块14，判断所述题目信息是否存在于题库中。
在本实施例中，预设识别标志的信息。
可选的，预设识别标志信息的方式可通过系统自动生成。
可选的，预设识别标志的信息方式也可通过用户根据实际情况设定。
在本实施例中，所述页面的内容包括题目、答案、序号、评判框、二维码。
其中，序号、题目通过印刷、手写等方式生成；答案通过持有当前试卷的用户做答；二维码包括当前用户的个人信息及试卷的题目信息；评判框用于评判题目的答案是否正确。
在本实施例中，所述采集所述页面图片中的题目所对应的标志具体为所述题目与所述标志相对应且一个题目对应一个标志；基于所述题目对应的标志，确定所述页面图片上的题目，其中，所述标志为评判框及评判框内评判的内容。
当获取到页面的图片后，通过图像识别技术识别评判框及评判框中的内容，其中，每个题目与评判框及评判框中的内容一一对应。
在本实施例中，判断所述题目信息是否存在于题库中，若不存在，则将当前题目存储于题库中。
本实施例通过识别标志信息获取标志对应的题目，同时判断题库中是否存储该题目信息，若不存在，则将其保存到题库中，提高了学习效率；本实施例还通过将答案正确的题目与答案错误的题目分别存储，有助于学生提高学习效率。
本文中所描述的具体实施例仅仅是对本发明精神作举例说明。本发明所属技术领域的技术人员可以对所描述的具体实施例做各种各样的修改或补充或采用类似的方式替代，但并不会偏离本发明的精神或者超越所附权利要求书所定义的范围。

Claims (10)

  1. 一种题目信息采集的方法，其特征在于，包括：
    S11.获取题目所在页面的图片；
    S12.采集所述页面图片中的题目所对应的标志；
    S13.提取所述标志对应的题目信息。
  2. 根据权利要求1所述的一种题目信息采集的方法，其特征在于，所述步骤S11之前还包括步骤：
    S10.存储识别标志信息的方式。
  3. 根据权利要求1或2所述的一种题目信息采集的方法，其特征在于，所述步骤S12具体为所述题目与所述标志相对应且一个题目对应一个标志；基于所述题目对应的标志，确定所述页面图片上的题目。
  4. 根据权利要求1或2所述的一种题目信息采集的方法，其特征在于，所述步骤S11中页面的内容包括题目、答案、评判框。
  5. 根据权利要求4所述的一种题目信息采集的方法，其特征在于，所述标志为评判框及评判框内评判的内容。
  6. 根据权利要求1或2或5所述的一种题目信息采集的方法，其特征在于，所述步骤S13之后还包括步骤：
    S14.判断所述题目信息是否存在于题库中，若不存在，则将所述题目信息存入题库。
  7. 一种题目信息采集的系统，其特征在于，包括：
    获取模块，获取题目所在页面的图片；
    采集模块，采集所述页面图片中的题目所对应的标志；
    提取模块，提取所述标志对应的题目信息。
  8. 根据权利要求7所述的一种题目信息采集的系统，其特征在于，还包括：
    存储模块，存储识别标志信息的方式。
  9. 根据权利要求7或8所述的一种题目信息采集的系统，其特征在于，还包括：
    判断模块，判断所述题目信息是否存在于题库中。
  10. 根据权利要求7或8所述的一种题目信息采集的系统，其特征在于， 所述采集所述页面图片中的题目所对应的标志具体为所述题目与所述标志相对应且一个题目对应一个标志；基于所述题目对应的标志，确定所述页面图片上的题目。
PCT/CN2019/105394 2019-03-29 2019-09-11 一种题目信息采集的方法及系统 WO2020199512A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910246957.7 2019-03-29
CN201910246957.7A CN110033662A (zh) 2019-03-29 2019-03-29 一种题目信息采集的方法及系统

Publications (1)

Publication Number Publication Date
WO2020199512A1 true WO2020199512A1 (zh) 2020-10-08

Family

ID=67236991

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/105394 WO2020199512A1 (zh) 2019-03-29 2019-09-11 一种题目信息采集的方法及系统

Country Status (2)

Country Link
CN (1) CN110033662A (zh)
WO (1) WO2020199512A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110033662A (zh) * 2019-03-29 2019-07-19 金华市花儿教育咨询有限公司 一种题目信息采集的方法及系统
CN112307158A (zh) * 2019-08-30 2021-02-02 北京字节跳动网络技术有限公司 一种信息检索方法、装置、设备及介质
CN113448925A (zh) * 2021-06-25 2021-09-28 东莞市小精灵教育软件有限公司 试题图片优化方法、装置、计算机设备及存储介质

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102915428A (zh) * 2011-08-05 2013-02-06 北京五岳鑫信息技术股份有限公司 一种基于8字码的试卷分数自动识别处理方法
CN106781784A (zh) * 2017-01-04 2017-05-31 王骁乾 一种智能批改系统
CN110033662A (zh) * 2019-03-29 2019-07-19 金华市花儿教育咨询有限公司 一种题目信息采集的方法及系统

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN100541496C (zh) * 2007-08-14 2009-09-16 新诺亚舟科技（深圳）有限公司 在个人手持学习终端上实现的针对试题的搜索与学习相结合的方法
CN103914567A (zh) * 2014-04-23 2014-07-09 北京奇虎科技有限公司 匹配目标试题答案的方法和装置
CN103971553A (zh) * 2014-05-29 2014-08-06 深圳图瑞交互信息技术有限公司 反馈式教学系统和反馈式教学方法
CN105096677A (zh) * 2015-08-19 2015-11-25 北京京东方多媒体科技有限公司 一种教学系统及其工作方法
CN106023698A (zh) * 2016-07-29 2016-10-12 李铧 一种作业及练习册自动批阅方法
CN106775241B (zh) * 2016-12-15 2019-08-13 网易（杭州）网络有限公司 信息呈现方法、设备和计算机可读存储介质
CN107578659A (zh) * 2017-09-27 2018-01-12 广东小天才科技有限公司 电子题目的生成方法、生成装置及终端
CN107895142A (zh) * 2017-10-26 2018-04-10 湖南考神信息科技有限责任公司 一种基于视觉标记的试卷试题内容自动分割方法及系统
CN108090445A (zh) * 2017-12-17 2018-05-29 张玉存 一种纸质作业或试卷的电子批改方法
CN109472014A (zh) * 2018-10-30 2019-03-15 南京红松信息技术有限公司 一种错题集自动识别生成方法及其装置

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102915428A (zh) * 2011-08-05 2013-02-06 北京五岳鑫信息技术股份有限公司 一种基于8字码的试卷分数自动识别处理方法
CN106781784A (zh) * 2017-01-04 2017-05-31 王骁乾 一种智能批改系统
CN110033662A (zh) * 2019-03-29 2019-07-19 金华市花儿教育咨询有限公司 一种题目信息采集的方法及系统

Also Published As

Publication number Publication date
CN110033662A (zh) 2019-07-19

Similar Documents

Publication Publication Date Title
US20210020059A1 (en) Answer evaluation method, answer evaluation system, electronic device, and medium
WO2021073332A1 (zh) 用于辅助数学应用题的方法及装置
CN109359215B (zh) 视频智能推送方法和系统
WO2020199512A1 (zh) 一种题目信息采集的方法及系统
US20200286402A1 (en) Method and system for assisting with math problem
CN105224665A (zh) 一种错题管理方法及系统
US20090268039A1 (en) Apparatus and method for outputting multimedia and education apparatus by using camera
CN112115301A (zh) 一种基于课堂笔记的视频标注方法及系统
CN111242045A (zh) 自动化作业习题对错指示方法及系统
CN112837031A (zh) 一种基于高速扫描并打印的作业自动批阅方法及装置
CN106295514A (zh) 一种图像识别题目显示答案的方法及装置
KR20130021684A (ko) 답안지 관리 시스템 및 그 방법
CN110879987B (zh) 一种识别试题作答内容的方法
CN111489596A (zh) 一种直播教学过程中进行信息反馈的方法及装置
CN114140282B (zh) 一种基于深度学习的普教课堂答题快速评审方法及装置
CN107886791B (zh) 一种基于教学数据的智能共享方法及其系统
WO2015178014A1 (ja) 学習支援システム、学習支援サーバ、学習支援方法、及び学習支援プログラム
CN111464743A (zh) 一种摄影构图匹配方法及系统
CN111461248A (zh) 一种摄影构图线匹配方法、装置、设备及存储介质
CN112307158A (zh) 一种信息检索方法、装置、设备及介质
CN108776794B (zh) 基于大数据与人工智能的教学效果画像方法和机器人系统
CN116107441B (zh) 教学及考试用智能笔及其控制系统
CN211124089U (zh) 一种习题数据采集装置
CN111899136A (zh) 以人脸识别为基础的智能化伴学系统的移动终端的使用方法
CN111899135A (zh) 以人脸识别为基础的智能化伴学方法及系统

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: 19923260

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: 19923260

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 19923260

Country of ref document: EP

Kind code of ref document: A1