CN111914068B - Method for extracting test question knowledge points - Google Patents
Method for extracting test question knowledge points Download PDFInfo
- Publication number
- CN111914068B CN111914068B CN202010850830.9A CN202010850830A CN111914068B CN 111914068 B CN111914068 B CN 111914068B CN 202010850830 A CN202010850830 A CN 202010850830A CN 111914068 B CN111914068 B CN 111914068B
- Authority
- CN
- China
- Prior art keywords
- data
- test question
- knowledge point
- answer
- test
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012360 testing method Methods 0.000 title claims abstract description 133
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000012545 processing Methods 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 11
- 230000009467 reduction Effects 0.000 claims description 6
- 238000009795 derivation Methods 0.000 claims description 5
- 238000003062 neural network model Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 238000013527 convolutional neural network Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Educational Technology (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention relates to a method for extracting test question knowledge points, which comprises the following steps: the server receives the test question content data, analyzes the test question content data according to the knowledge deduction model to obtain test question answer data and first test question condition data; determining whether answer data of the intermediate step is included in answer data of the test questions; when the answer data of the test questions comprise the answer data of the intermediate step, determining second test question condition data corresponding to the answer data of the intermediate step in the first test question condition data; inquiring knowledge point data matched with the second test question condition data in a knowledge point database; obtaining target data according to the knowledge point data and the test question content data; and when the answer data of the test questions does not comprise the answer data of the intermediate step, inquiring knowledge point data matched with the first test question condition data in a knowledge point database, and obtaining target data according to the knowledge point data and the test question content data.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method for extracting test question knowledge points.
Background
With the rapid and stable development of social economy and the national support of education informatization, especially the fund support of basic education informatization, the construction pace of education informatization is quickened. After the education is on the stage of the software market, along with the daily and monthly popularization of the internet technology and the increase of the national importance and investment strength of the education and training industry, the education software already occupies one third of the whole software market, and forms a three-day situation with office software and financial software.
Knowledge extraction refers to the process of identifying, discovering and extracting concepts, types, facts and their related relationships, constraint rules, and steps and rules for problem solving from digital resources. At present, most of the existing test question knowledge points are extracted according to question analysis after the manual question solving. The method for extracting the knowledge points is time-consuming and labor-consuming and has low efficiency.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a method for extracting knowledge points of test questions, which obtains answers of each step and deducing conditions corresponding to the answers of each step in the solution of the test questions through model analysis, and determines all knowledge points related to an entity according to the deducing conditions corresponding to the answers of each step, so that the extracted knowledge points have higher precision, better uniformity and more comprehensive knowledge points.
In order to achieve the above object, the present invention provides a method for extracting knowledge points of a test question, the method for extracting knowledge points of a test question comprising:
the server obtains test question content data according to the image data to be identified, and analyzes the test question content data according to the knowledge deduction model to obtain test question answer data and first test question condition data;
determining whether the answer data of the test questions comprises answer data of an intermediate step;
When the answer data of the test questions comprise intermediate step answer data, determining second test question condition data corresponding to the intermediate step answer data in the first test question condition data;
Inquiring knowledge point data matched with the second test question condition data in a knowledge point database;
obtaining target data according to the knowledge point data and the test question content data;
and when the answer data of the test questions does not comprise answer data of the intermediate step, inquiring knowledge point data matched with the first test question condition data in a knowledge point database, and obtaining target data according to the knowledge point data and the test question content data.
Preferably, before the server receives the test question content data, the method further includes:
The user terminal acquires image data to be identified according to an acquisition instruction input by a user;
The user terminal performs noise reduction processing on the image data to be identified, obtains noise-reduced image data to be identified and sends the noise-reduced image data to a server;
And the server performs recognition processing on the image data to be recognized according to the neural network model to obtain test question content data.
Further preferably, the obtaining, by the user terminal, the image data to be identified according to the obtaining instruction input by the user specifically includes:
the user terminal acquires original image data according to an acquisition instruction input by the user and displays the original image data;
And receiving an area selection instruction input by the user according to the original image data, and obtaining the image data to be identified according to the area selection instruction.
Further preferably, the noise reduction processing includes resizing image data to be recognized and gradation processing.
Preferably, before the analyzing the test question content data according to the knowledge deduction model to obtain test question answer data and first test question condition data, the method further includes:
The knowledge derivative model is trained in accordance with a plurality of derivative theorem data.
Preferably, the target data includes one or more knowledge point data.
Further preferably, when the knowledge point data is plural, the obtaining target data according to the knowledge point data and the test question content data is specifically:
determining whether repeated knowledge point data exists in a plurality of knowledge point data;
Deleting the repeated knowledge point data when the repeated knowledge point data exist in the plurality of knowledge point data;
And obtaining the target data according to the de-duplicated knowledge point data and the test question content data.
According to the method for extracting the knowledge points of the test questions, provided by the embodiment of the invention, the answers of each step in the questions are obtained through model analysis, the deducing conditions corresponding to the answers of each step are obtained, and all the knowledge points related to the entity are determined according to the deducing conditions corresponding to the answers of each step, so that the extracted knowledge points are higher in accuracy, better in uniformity and more comprehensive.
Drawings
Fig. 1 is a flowchart of a method for extracting knowledge points of a test question according to an embodiment of the present invention.
Detailed Description
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
The method for extracting the knowledge points of the test questions is used for analyzing the test questions uploaded by the user and extracting the knowledge points in the test questions. The method flow chart is shown in fig. 1, and comprises the following steps:
step 101, a user terminal acquires image data to be identified according to an acquisition instruction input by a user;
In particular, a user terminal may be understood as a smart device, such as a smart phone, with networking capabilities. The user inputs an acquisition instruction to the user terminal. The acquisition instruction may be understood as an instruction to acquire a test question to be uploaded. The test questions to be uploaded can be shot by the camera device or can be manually input by a user in the user terminal. However, whether the test questions to be uploaded are acquired by photographing or manually input, the test questions to be uploaded are data in the form of pictures.
When the test questions to be uploaded are photographed by the photographing device, the user terminal needs to acquire the use permission of devices such as photographing and microphones from the user. After the user terminal obtains the use rights of devices such as an image pickup device, a microphone and the like, the user terminal obtains the original image data through the image pickup device according to the obtaining command input by the user, and displays the original image data to the user. And the user inputs an area selection instruction according to the original image data, and the user terminal obtains the image data to be identified according to the area selection instruction after receiving the area selection instruction. The original image data may be understood as an original photograph taken by a user through the image capturing device. The image data to be identified can be understood as a test question part to be uploaded in the original photo after the user performs regional interception on the original photo. This process can be understood as a process in which the user selects content in a photo that has been taken, which facilitates more efficient identification of the content of the photo subsequently.
Similarly, when the test questions to be uploaded are manually input by the user in the user terminal, the user can select the manually input contents. When selecting, the step is that the user inputs an area selection instruction according to the original image data, and the user terminal obtains the image data to be identified according to the area selection instruction after receiving the area selection instruction.
Step 102, a user terminal performs noise reduction processing on image data to be identified, and sends the noise reduced image data to be identified to a server;
Specifically, since most of the images acquired by the existing image capturing apparatuses are high-resolution color images, the data storage amount of the high-resolution color images is relatively large, which is not beneficial to the subsequent processing of the images. Therefore, after the user terminal acquires the image data to be identified, the user terminal firstly carries out noise reduction treatment on the image data to be identified. Preferably, the noise reduction process includes an image size adjustment and a gradation process. The user terminal scales the image data to be identified to a preset size, and the channel is a single-channel gray image.
Then, the user terminal compresses the noise-reduced image data to be identified, packages the noise-reduced image data and sends the noise-reduced image data to the server so that the server can carry out subsequent processing on the noise-reduced image data to be identified.
Step 103, the server performs recognition processing on the image data to be recognized according to the neural network model to obtain test question content data;
Specifically, the neural network model (Neural Network, NN) is a data model that simulates a human actual neural network, which is a complex network system formed by a large number of simple processing units widely interconnected, and can also be understood as a highly complex nonlinear power learning system. The NN model has the advantage of self-learning function. For example, when image recognition is implemented, only when a plurality of different pictures and corresponding recognized features (recognition results) are input into the NN model, the NN model can obtain a series of new features for predicting output variables through a self-learning function.
Preferably, convolutional neural network models (Convolutional Neural Network, CNN) and cyclic neural network models (Recurrent Neural Network, RNN) are used in embodiments of the present invention to identify image data to be identified. The server decompresses the received compressed package of the image data to be identified, releases the image data to be identified, and identifies the text information on the image data to be identified according to the CNN model and the RNN model to obtain the test question content data in the image data to be identified. The test question content data can be understood to be the test questions uploaded by the user.
Step 104, analyzing the test question content data according to the knowledge deduction model to obtain test question answer data and first test question condition data;
Specifically, the knowledge derivative model is obtained by training in advance according to a plurality of derivative theorem data. The knowledge derivation model can be understood as a model for automatically solving problems, and the derivation theorem data can be understood as the existing theory, including known grammar logic, calculation logic, formulas, theorem, axiom, and information of a problem solving method.
Because the knowledge deduction model is trained by a plurality of pieces of theorem data, after the test question content data is input into the knowledge deduction model, the knowledge deduction model can analyze the test question content data according to the deduction theorem data to obtain test question answers and deduction conditions corresponding to the test question answers. The test question answer data may be understood as a test question answer including each step of the process of solving the questions. The first test question condition data may be understood as a derivation condition corresponding to a test question answer including each step of the solution process.
In a specific example, the test question content data is: 2 cos 30-2 sin 30-3 tan 45++ 1-tan 60| according to the knowledge derivation model, the answer data of the test questions are obtained by analysis:
The first test question condition data comprises "When a <0, |a|= -a", "a+a=2a", and "-1+3-1=1".
Step 105, determining whether answer data of the intermediate step is included in answer data of the test questions;
Specifically, if the process of solving the questions includes a plurality of steps, the answer data of the test questions includes answer data of intermediate steps. The answer data of the intermediate steps can be understood as the answer of each step of the process of solving the questions.
In the above specific example, the intermediate step answer data is And/>
Since each question solving process may correspond to one knowledge point, if knowledge points are extracted only according to the last question solving step or the most complex one-step question solving step in the answer, the obtained knowledge points are not comprehensive. When the answer data of the test question includes answer data of intermediate steps, it is explained that a plurality of steps are needed to be solved, and the test question may include a plurality of knowledge points, step 108 is executed after the following steps 106-107 are executed. When the answer data of the test question does not include answer data of the intermediate step, the test question can be solved only by one step, and the test question only includes one knowledge point, and the following step 106' is executed and then the step 108 is directly executed.
Step 106, determining second test question condition data corresponding to the intermediate step data in the first test question condition data;
Specifically, when the answer data of the test question includes answer data of the intermediate step, it is explained that the test question may include a plurality of knowledge points, and the server needs to extract each knowledge point. The server determines second test question condition data corresponding to each intermediate step answer data among the first test question condition data according to the intermediate step answer data. The second test question condition data can be understood as the deducing condition corresponding to the answer of the intermediate step.
In the above specific example, the intermediate step answer data The corresponding second test question condition data is/>Sum of "tan45°=1Intermediate step answer data/>The corresponding second test question condition data is "when a <0, |a|= -a".
Step 107, inquiring knowledge point data matched with the second test question condition data in a knowledge point database;
Specifically, the knowledge point database stores the correspondence between test question condition data and knowledge point data. That is, the server may find knowledge point data corresponding to the test question condition data from the test question condition data. And inquiring the obtained knowledge point data matched with the second test question condition data in the knowledge point database by the server, namely obtaining the knowledge point of the current test question.
In the above specific example, in the knowledge point database, the second test question condition data"Tan45°=1" and/>The corresponding knowledge point data is the trigonometric function value of the special angle. The knowledge point data corresponding to the second test question condition data of |a|= -a ' is ' absolute value definition ' when a < 0. The server performs/>, according to the second test question condition data“tan45°=1”、/>And "when a <0, |a|= -a", the queried knowledge point data are "trigonometric function value of special angle" and "absolute value definition".
Step 106', inquiring knowledge point data matched with the first test question condition data in a knowledge point database;
Specifically, when the answer data of the test question does not include the answer data of the intermediate step, the test question is described to only include one knowledge point, and the server only needs to query knowledge point data matched with the first test question condition data in the knowledge point database according to the first test question condition data. And the server queries the obtained knowledge point data matched with the condition data of the first test question in the knowledge point database, namely the unique knowledge point of the current test question.
Step 108, obtaining target data according to the knowledge point data and the test question content data;
specifically, if the server obtains multiple knowledge point data according to the steps, the server first determines whether repeated data exists in the knowledge point data. And deleting repeated knowledge point data when repeated data exist in the knowledge point data, namely performing de-duplication processing on a plurality of knowledge point data. And then the server obtains target data according to the de-duplicated knowledge point data and the test question content data. If the server is one according to the knowledge point data obtained in the steps, the target data is directly obtained according to the knowledge point data and the test question content data without a repeated step.
And finally, the server stores the target data into a test question database for later use. The target data may be understood as data including test questions and test question knowledge point information. In the above specific example, the target data is: "2cos30 ° -2sin30 ° +3tan 45+|1-tan 60 ° | examine trigonometric function value and absolute value definition of specific angle".
According to the method for extracting the knowledge points of the test questions, provided by the embodiment of the invention, the answers of each step in the questions are obtained through model analysis, the deducing conditions corresponding to the answers of each step are obtained, and all the knowledge points related to the entity are determined according to the deducing conditions corresponding to the answers of each step, so that the extracted knowledge points are higher in accuracy, better in uniformity and more comprehensive.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of function in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied in hardware, in a software module executed by a user terminal, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The foregoing detailed description of the invention has been presented for purposes of illustration and description, and it should be understood that the invention is not limited to the particular embodiments disclosed, but is intended to cover all modifications, equivalents, alternatives, and improvements within the spirit and principles of the invention.
Claims (5)
1. The extraction method of the test question knowledge points is characterized by comprising the following steps of:
The server obtains test question content data according to the image data to be identified, and analyzes the test question content data according to the knowledge deduction model to obtain test question answer data and first test question condition data; the first test question condition data is a deducing condition corresponding to a test question answer in each step of the question solving process;
determining whether the answer data of the test questions comprises answer data of an intermediate step; the answer data of the intermediate steps are answers of each step of the process of solving the questions;
When the answer data of the test questions comprise intermediate step answer data, determining second test question condition data corresponding to the intermediate step answer data in the first test question condition data; the second test question condition data is a deducing condition corresponding to the answer of the intermediate step;
Inquiring knowledge point data matched with the second test question condition data in a knowledge point database;
obtaining target data according to the knowledge point data and the test question content data;
inquiring knowledge point data matched with the first test question condition data in a knowledge point database when the answer data of the test questions does not comprise the answer data of the intermediate step, and obtaining target data according to the knowledge point data and the test question content data;
Before the server receives the test question content data, the method further comprises the following steps:
The user terminal acquires image data to be identified according to an acquisition instruction input by a user;
The user terminal performs noise reduction processing on the image data to be identified, obtains noise-reduced image data to be identified and sends the noise-reduced image data to a server;
The server performs recognition processing on the image data to be recognized according to a neural network model to obtain test question content data;
The user terminal obtains the image data to be identified according to the obtaining instruction input by the user specifically comprises the following steps:
the user terminal acquires original image data according to an acquisition instruction input by the user and displays the original image data;
And receiving an area selection instruction input by the user according to the original image data, and obtaining the image data to be identified according to the area selection instruction.
2. The method according to claim 1, wherein the noise reduction processing includes adjusting the size of the image data to be recognized and gray scale processing.
3. The method according to claim 1, wherein before the analyzing the question content data according to the knowledge derivation model to obtain the question answer data and the first question condition data, the method further comprises:
The knowledge derivative model is trained in accordance with a plurality of derivative theorem data.
4. The method for extracting a question knowledge point according to claim 1, wherein the target data includes one or more knowledge point data.
5. The method for extracting a knowledge point of a test question according to claim 4, wherein when the knowledge point data is plural, the obtaining target data according to the knowledge point data and the content data of the test question is specifically:
determining whether repeated knowledge point data exists in a plurality of knowledge point data;
Deleting the repeated knowledge point data when the repeated knowledge point data exist in the plurality of knowledge point data;
And obtaining the target data according to the de-duplicated knowledge point data and the test question content data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010850830.9A CN111914068B (en) | 2020-08-21 | 2020-08-21 | Method for extracting test question knowledge points |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010850830.9A CN111914068B (en) | 2020-08-21 | 2020-08-21 | Method for extracting test question knowledge points |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111914068A CN111914068A (en) | 2020-11-10 |
CN111914068B true CN111914068B (en) | 2024-05-10 |
Family
ID=73279439
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010850830.9A Active CN111914068B (en) | 2020-08-21 | 2020-08-21 | Method for extracting test question knowledge points |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111914068B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113688262A (en) * | 2021-09-01 | 2021-11-23 | 北京云蝶智学科技有限公司 | Data classification method |
CN113673475A (en) * | 2021-09-01 | 2021-11-19 | 北京云蝶智学科技有限公司 | Answering method based on image information |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103955525A (en) * | 2014-05-09 | 2014-07-30 | 北京奇虎科技有限公司 | Method and client for searching answer to test question |
CN107343223A (en) * | 2017-07-07 | 2017-11-10 | 北京慕华信息科技有限公司 | The recognition methods of video segment and device |
CN107967254A (en) * | 2017-10-31 | 2018-04-27 | 科大讯飞股份有限公司 | Knowledge point Forecasting Methodology and device, storage medium, electronic equipment |
CN108763588A (en) * | 2018-06-19 | 2018-11-06 | 深圳习习网络科技有限公司 | A kind of knowledge point quantitative analysis method and device |
CN110096589A (en) * | 2019-03-14 | 2019-08-06 | 杭州笔声智能科技有限公司 | A kind of examination question feedback and recommendation explanation method and system based on image recognition technology |
CN110309300A (en) * | 2018-08-23 | 2019-10-08 | 北京慧经知行信息技术有限公司 | A method of identification natural sciences knowledge-ID |
CN110659352A (en) * | 2019-10-10 | 2020-01-07 | 浙江蓝鸽科技有限公司 | Test question and test point identification method and system |
-
2020
- 2020-08-21 CN CN202010850830.9A patent/CN111914068B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103955525A (en) * | 2014-05-09 | 2014-07-30 | 北京奇虎科技有限公司 | Method and client for searching answer to test question |
CN107343223A (en) * | 2017-07-07 | 2017-11-10 | 北京慕华信息科技有限公司 | The recognition methods of video segment and device |
CN107967254A (en) * | 2017-10-31 | 2018-04-27 | 科大讯飞股份有限公司 | Knowledge point Forecasting Methodology and device, storage medium, electronic equipment |
CN108763588A (en) * | 2018-06-19 | 2018-11-06 | 深圳习习网络科技有限公司 | A kind of knowledge point quantitative analysis method and device |
CN110309300A (en) * | 2018-08-23 | 2019-10-08 | 北京慧经知行信息技术有限公司 | A method of identification natural sciences knowledge-ID |
CN110096589A (en) * | 2019-03-14 | 2019-08-06 | 杭州笔声智能科技有限公司 | A kind of examination question feedback and recommendation explanation method and system based on image recognition technology |
CN110659352A (en) * | 2019-10-10 | 2020-01-07 | 浙江蓝鸽科技有限公司 | Test question and test point identification method and system |
Non-Patent Citations (1)
Title |
---|
高中化学教科书课后习题难度预估方法研究;韩云凤;张雨强;杨兴兴;;化学教育;20160602(第11期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN111914068A (en) | 2020-11-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2020119419A1 (en) | Image recognition-based testing and apparatus, and computer device and storage medium | |
CN107679466B (en) | Information output method and device | |
JP6731529B1 (en) | Single-pixel attack sample generation method, device, equipment and storage medium | |
CN111914068B (en) | Method for extracting test question knowledge points | |
US20200125836A1 (en) | Training Method for Descreening System, Descreening Method, Device, Apparatus and Medium | |
CN108549848B (en) | Method and apparatus for outputting information | |
CN109377494B (en) | Semantic segmentation method and device for image | |
DE112019000334T5 (en) | VALIDATE THE IDENTITY OF A REMOTE USER BY COMPARISON ON THE BASIS OF THRESHOLD VALUES | |
CN110929785B (en) | Data classification method, device, terminal equipment and readable storage medium | |
CN110807472B (en) | Image recognition method and device, electronic equipment and storage medium | |
US20220237917A1 (en) | Video comparison method and apparatus, computer device, and storage medium | |
CN109165574B (en) | Video detection method and device | |
CN108399401B (en) | Method and device for detecting face image | |
CN111274853B (en) | Image processing method and device | |
CN111310837A (en) | Vehicle refitting recognition method, device, system, medium and equipment | |
CN111652242B (en) | Image processing method, device, electronic equipment and storage medium | |
CN110839242A (en) | Abnormal number identification method and device | |
CN108921792B (en) | Method and device for processing pictures | |
CN115359390A (en) | Image processing method and device | |
CN112434547B (en) | User identity auditing method and device | |
CN111259689B (en) | Method and device for transmitting information | |
CN113689418B (en) | Formula calculation method based on image recognition | |
WO2021008026A1 (en) | Video classification method and apparatus, computer device and storage medium | |
CN113688262A (en) | Data classification method | |
CN113705706A (en) | Data classification method based on image recognition |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |