CN113673475A - Answering method based on image information - Google Patents
Answering method based on image information Download PDFInfo
- Publication number
- CN113673475A CN113673475A CN202111022961.9A CN202111022961A CN113673475A CN 113673475 A CN113673475 A CN 113673475A CN 202111022961 A CN202111022961 A CN 202111022961A CN 113673475 A CN113673475 A CN 113673475A
- Authority
- CN
- China
- Prior art keywords
- information
- user
- question
- topic
- image data
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000012360 testing method Methods 0.000 claims abstract description 49
- 238000012545 processing Methods 0.000 claims abstract description 11
- 230000009467 reduction Effects 0.000 claims abstract description 10
- 238000003062 neural network model Methods 0.000 claims abstract description 5
- 230000008569 process Effects 0.000 description 9
- 238000013528 artificial neural network Methods 0.000 description 7
- 238000013527 convolutional neural network Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 238000013144 data compression Methods 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
- 230000000694 effects Effects 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
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9035—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Abstract
The invention relates to an image information-based answering method, which comprises the following steps: the user terminal acquires image data to be identified through the camera device according to an acquisition instruction input by a first user; the user terminal carries out noise reduction processing on the image data to be identified to obtain noise-reduced image data to be identified and sends the noise-reduced image data to the server; the image data to be identified carries a user ID of a first user; the server identifies image data to be identified according to the neural network model to obtain first question information; the first topic information carries a user ID of a first user; analyzing the first question information to obtain keyword information; searching second question information matched with the keyword information in a test question database according to the keyword information; and sending the second topic information to the user terminal according to the user ID of the first user, so that the user terminal can display the second topic information.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an image information-based answering method.
Background
With the rapid and stable development of social economy and the strong support of the nation on education informatization, particularly the fund support on basic education informatization, the construction pace of the education informatization is accelerated. Since education stepped on the stage of software market, along with the change of internet technology and the gradual popularization, and the national emphasis on education and training industry and the increase of investment, education software occupies one third of the whole software market, and forms a three-day-down situation with office software and financial software.
In the existing online answering method, a user takes a picture of a question to be answered and uploads the picture to a server, and the server identifies the picture and searches answers in a question bank. If the current question to be answered is not recorded in the question bank, an effective answer cannot be provided for the user, so that the current online answering method is poor in answering ability and cannot meet the needs of the user.
Disclosure of Invention
The invention aims to provide an answer method based on image information aiming at the defects of the prior art, which determines the examination point of a question to be answered through a keyword of the question to be answered, and matches at least the question and the answer of the examination point of the question to be answered all the time in a question library, so that when the question and the answer which are the same as the question to be answered are provided for a student, the question and the answer which are the same as the examination point of the question to be answered can be provided for the student, the student can refer to the question, and the learning efficiency of the student is improved.
In order to achieve the above object, the present invention provides an image information-based answering method, including:
the user terminal acquires image data to be identified through the camera device according to an acquisition instruction input by a first user;
the user terminal performs noise reduction processing on the image data to be identified to obtain noise-reduced image data to be identified and sends the noise-reduced image data to a server; the image data to be identified carries a user I D of a first user;
the server identifies the image data to be identified according to the neural network model to obtain first question information; the first topic information carries a user I D of the first user;
analyzing the first question information to obtain keyword information;
searching second question information matched with the keyword information in a test question database according to the keyword information;
and sending the second topic information to a user terminal according to the user I D of the first user, so that the user terminal displays the second topic information.
Preferably, before the user terminal acquires the image data to be recognized through the camera device according to the acquisition instruction input by the first user, the method further includes:
the user terminal receives first user account information input by the first user; the first user account information includes the user I D of the first user, the first user grade information, and the region information of the first user.
Preferably, the method further comprises:
and the user terminal acquires the region information of the first user through a positioning module.
Preferably, the step of acquiring, by the user terminal, the image data to be recognized through the camera device according to the acquisition instruction input by the first user specifically includes:
the user terminal acquires original image data according to an acquisition instruction input by a first user and displays the original image data;
and receiving a region selection instruction input by the first user according to the original image data, and obtaining the image data to be identified according to the region selection instruction.
Preferably, the test question database includes second question information, grade information corresponding to the second question information, and region information corresponding to the second question information.
Further preferably, the searching, according to the keyword information, for the second topic information matched with the keyword information in the test question database specifically includes:
acquiring the first user grade information corresponding to the user I D of the first user and the region information of the first user;
determining target test question range data matched with the first user grade information and the first user region information and target test question range out-of-range data unmatched with the first user grade information and the first user region information in a test question database according to the first user grade information and the first user region information;
and searching second subject information matched with the keyword information in the test subject range data according to the keyword information.
Further preferably, when second topic information matched with the keyword information is not found in the test question range data according to the keyword information, the method further includes:
searching second subject information matched with the keyword information in the data outside the target test subject range according to the keyword information;
and sending the second topic information to a user terminal according to the user I D of the first user.
Preferably, the second topic information includes answer information of the second topic;
and sending the second topic information and the answer information of the second topic to a user terminal according to the user I D of the first user.
Preferably, after the sending of the second topic information to the user terminal according to the user I D of the first user, the method further includes:
receiving feedback information input by the first user; determining whether the feedback information is first feedback information;
when the feedback information is first feedback information, sending the first topic information to the server;
and the server updates the test question database according to the first question information.
Further preferably, after the server updates the test question database according to the first question information, the method further includes:
the server receives answer information of a first topic of the first topic information input by a second user according to the first topic information; the answer information for the first topic includes a user I D of the first user;
and sending the first topic information and the answer information of the first topic to a user terminal according to the user I D of the first user.
According to the image information-based answering method provided by the embodiment of the invention, the examination point of the question to be answered is determined through the keyword of the question to be answered, and at least the question and the answer of the examination point of the question to be answered are matched in the question library, so that when the question and the answer which are the same as the question to be answered are provided for the students, the question and the answer which are the same as the examination point of the question to be answered can be provided for the students for reference, and the learning efficiency of the students is improved.
Drawings
Fig. 1 is a flowchart of an answering method based on image information according to an embodiment of the present invention.
Detailed Description
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
The answer method based on the image information is realized in an intelligent terminal which can be connected to a network and is used for providing answers of test questions uploaded by a user for the user. The flow chart of the method is shown in figure 1, and the method comprises the following steps:
in particular, the user terminal may be understood as a smart device with a networking function, such as a smart phone. The camera device may be a part of the user terminal, or may be a separate device separately attached to the user terminal.
The first user may be understood as a party who presents a question, such as a student or a parent of a student. When a first user presents a question and needs to be answered, account information is firstly logged in a user terminal. The first user account information includes the user I D of the first user, the first user grade information, and the region information where the first user is located. Wherein the user I D of the first user may be understood as the unique identity of the first user. The first user grade information may be understood as the workover grade information of the student, such as the fifth grade of the primary school or the higher and middle grade. The regional information of the first user can be understood as the school district information of the students, such as the hai lake district of Beijing or Tianjin. The region information of the first user can be input by the user, or can be obtained by the user terminal through a positioning module in the user terminal.
Preferably, the region information of the first user is acquired by the user terminal through a positioning module in the user terminal by default. When the first user needs to change the region information of the first user, the changed region information of the first user can be manually input.
The first user inputs an acquisition instruction to the user terminal after logging in the account information. The obtaining instruction can be understood as a photographing instruction, and this process can be understood as a process in which the first user photographs the to-be-solved question through the camera device by using the user terminal.
Before the user terminal receives the acquisition instruction, the user terminal needs to acquire the use permission of devices such as a camera and a microphone from the first user. After the user terminal acquires the use authority of the devices such as the camera and the microphone, the user terminal acquires original image data through the camera device according to an acquisition instruction input by a first user and displays the original image data to the first user. And the first user inputs an area selection instruction according to the original image data, and the user terminal receives the area selection instruction and then obtains the image data to be identified according to the area selection instruction. The original image data can be understood as an original photo taken by the first user through the camera device. The image data to be recognized can be understood as the question part to be solved in the original photo after the first user conducts region interception on the original photo. The process can be understood as a process of selecting the content in the shot photo by the first user, and is beneficial to more efficiently identifying the photo content subsequently.
102, the user terminal carries out noise reduction processing on image data to be recognized and sends the image data to be recognized after noise reduction to a server;
specifically, most of images acquired by the existing image capturing apparatus are high-resolution color images, and the data storage amount of the high-resolution color images is relatively large, which is not beneficial to subsequent image processing. Therefore, after the user terminal acquires the image data to be identified, the noise reduction processing is firstly carried out on the image data to be identified. Preferably, the noise reduction processing includes image resizing and gradation processing. The user terminal zooms the image data to be recognized into a preset size, and the channel is a single-channel gray image.
And then, the user terminal compresses the image data to be recognized after the noise reduction, and packages and sends the image data to be recognized to the server, so that the server can perform subsequent processing on the image data to be recognized after the noise reduction. And the image data to be identified after noise reduction carries the user I D of the first user, so that the server distinguishes which user the current image data to be identified is sent by, and acquires other account information of the first user according to the user ID.
103, the server identifies image data to be identified according to the neural network model to obtain first question information;
specifically, a Neural Network (NN) is a data model simulating a human real neural Network, which is a complex Network system formed by a large number of simple processing units widely connected to each other, and can also be understood as a highly complex nonlinear dynamical learning system. The NN model has the advantage of self-learning function. For example, when image recognition is implemented, a number of different pictures and corresponding recognized features (recognition results) are input into the NN model, and the NN model obtains a series of new features for predicting output variables through a self-learning function.
Preferably, in the embodiment of the present invention, a convolutional neural Network model (Convo l i ona l neural Network, CNN) and a Recurrent neural Network model (RNN) are used to identify the image data to be identified. The server decompresses the received image data compression packet to be recognized, releases the image data to be recognized, and recognizes character information on the image data to be recognized according to the CNN model and the RNN model to obtain first topic information in the image data to be recognized. The first topic information can be understood as the text information of the topic to be solved uploaded by the first user.
specifically, the server firstly segments the first topic information according to a preset grammar model to obtain one or more character string information, and then selects one or more keyword information from the one or more character string information according to a preset semantic model. The process can be understood as a process of removing worthless words such as auxiliary words in the question and extracting key information which has a key effect on answering in the question. Here, the keyword information may be understood as the examination point information.
In a specific example, when the titles captured by the user terminal are:
“--Do you know Pau l i s boy i n C l ass 5？
--Yes.He i s very good at p l ayi ng basketba l l.
A.ta l l B.ta l l er C.ta l l est D.the ta l l est”
the keyword information to the title of the server according to the preset grammar model and the preset semantic model includes "ta l, ta l er, ta l est, and ta l est".
In a specific example, when the titles captured by the user terminal are:
"if parabola y ═ x2There is no intersection of +2x + c with the x-axis, writing a value that satisfies condition c: ___ are provided. "
The keyword information to the title of the server according to the preset grammar model and the preset semantic model comprises' parabola, y ═ x2+2x + c, intersection and written c value ".
specifically, the test question database includes the second question information, the grade information corresponding to the second question information, and the region information corresponding to the second question information. Corresponding to the grade information of the first user and the region information of the first user, the grade information of the second user can be understood as grade information of a second topic, and the region information of the second user can be understood as school district information of the second topic.
First, the server acquires first user grade information corresponding to a user ID of a first user and information of an area where the first user is located according to the user ID of the first user carried by first topic information.
And then, the server determines target test question range data matched with the first user grade information and the first user region information and target test question out-of-range data unmatched with the first user grade information and the first user region information in the test question database according to the first user grade information and the first user region information.
In a specific example, the test question database includes "the questions of the first-middle-grade of Beijing, the second-middle-grade of Beijing, the third-middle-grade of Beijing, and the third-middle-grade of Shanghai city". When the grade information of the first user and the regional information of the first user are 'junior-middle-first grade' and 'Beijing City', respectively, the target test question range data is a question of 'first middle-first grade of Beijing City' in the test question database, and the data outside the target test question range is a question of 'second middle-first grade of Beijing City, a question of first middle-third grade of Shanghai City' in the test question database.
And finally, the server searches second subject information matched with the keyword information in the test subject range data according to the keyword information. And when the second topic information matched with the key word information cannot be searched in the test topic range data according to the key word information, searching the second topic information matched with the key word information in the data outside the target test topic range according to the key word information. The second topic information includes answer information of the second topic for the first user to further understand the topic answer.
The process can be understood as a process that the server finds the question which is the same as or similar to the question to be solved and the answer in the question bank according to the examination point information of the question to be solved. It should be noted that, because the number of students is huge, the teacher of each school may set questions according to his/her own judgment, and it is not practical to record all known questions in the question database (question bank). However, if the current question database does not include the second question information which is the same as the first question information (question to be solved), the answer cannot be returned to the student, and the learning efficiency of the student is affected. However, although it is impractical to enter all known topics in the test question database, the test points per grade, per subject, are not changed during the same year or for a certain period of time. Therefore, the test question database only needs to include the questions of all current grades, all subjects and all examination points, and is continuously complete. The second topic information matched in the process is not always the same as the first topic information, but is consistent with the keywords (examination points of the topics to be solved) of the first topic information, so that when the second topic information which is the same as the first topic information is provided for students, the second topic information which is the same as the examination points of the first topic information is provided for the students to refer to, and the learning efficiency of the students is improved.
In addition, because the examination points of each grade and each region are different, the matching efficiency can be greatly reduced by unconditionally matching the second question information in the test question database. And the search range of the test question database is narrowed through the student age information and the area information of the students, and the second question information matched with the first question information is preferentially searched from the target test question range data matched with the current student age information and the area information of the students, so that the matching efficiency is improved.
In a specific example, the titles photographed by the user terminal are:
“--Do you know Pau l i s boy i n Cl ass 5？--Yes.He i s very good at p l ay i ng basketba l l.
A.ta l l B.ta l l er C.ta l l est D.the ta l l est”。
then the server searches a second topic information matched with the keyword information in the test topic database according to the keyword information "ta l l, ta l er, ta l est and ta l est" as follows:
“L i Dong i s the th i rd boy i n our c l ass and he i s very good at p l ay i ng basketba l l.
A.ta l l B.ta l l er C.ta l l est D.the ta l l est”
the second question is the answer message "Lidong is the boy with the third highest in our class, and he is good at playing basketball. If the ordinal number before the highest ranking adjective is modified, the ordinal word should be placed after the definite article so as to be '… … th most … … th'. From the sentence meaning, in combination with the context and the given options, ta l est is known to be in agreement. Therefore, C is selected. "
In this example, the first user does not obtain the same question as the photographed question, but obtains the question and the question analysis in which the examination points in the photographed question coincide, and the first user can easily think of the answer to the photographed question from the question analysis.
specifically, the server transmits the second topic information and the answer information of the second topic to the user terminal according to the user I D of the first user. And the user terminal displays the second topic information and the answer information of the second topic to the first user.
Preferably, after the user terminal displays the second topic information and the answer information of the second topic to the first user, the first user may feed back the satisfaction of the second topic information and the answer information of the second topic matched by the current server. The user terminal receives feedback information input by a first user. The feedback information includes first feedback information and second feedback information. The first feedback information can be understood as dissatisfied feedback that the first user cannot answer the first topic information according to the second topic information and the answer information of the second topic matched by the server. The second feedback information can be understood as "satisfied" feedback that the first user can answer the first topic information according to the second topic information matched by the server and the answer information of the second topic.
The user terminal determines whether the feedback information is first feedback information. When the feedback information is the first feedback information, it represents that the first user cannot answer the first topic information according to the second topic information and the answer information of the second topic matched by the server, that is, the second topic information and the answer information of the second topic matched by the server are invalid, and the user terminal sends the first topic information to the server. And the server updates the first question information to the test question database. At this time, the first question information does not have the corresponding answer information of the first question information in the test question database. The answer information of the first question information needs to be uploaded to a test question database by the second user according to the first question information. Corresponding to the first user, the second user may be understood as the party answering the question, e.g. a teacher.
And the second user acquires the first question information which is not solved from the server through the user terminal and inputs the solving information of the first question information according to the first question information. The user terminal sends the answer information of the first question information to the server, the server stores the answer information of the first question information into the test question database, and meanwhile, the server sends the first question information and the answer information of the first question to the user terminal used by the first user according to the user ID of the first user carried by the first question information so that the first user can check the answer information of the first question information. At this time, the answer information of the corresponding first question information already exists in the test question database.
Further preferably, the answer information of the first topic information carries a user ID of the second user. That is, the first user can see which second user has solved the current first topic information. If the first user still feels that the answer information given by the second user is not enough to answer the current question, the second user can be directly asked questions through the user ID of the second user.
According to the image information-based answering method provided by the embodiment of the invention, the examination point of the question to be answered is determined through the keyword of the question to be answered, and at least the question and the answer of the examination point of the question to be answered are matched in the question library, so that when the question and the answer which are the same as the question to be answered are provided for the students, the question and the answer which are the same as the examination point of the question to be answered can be provided for the students for reference, and the learning efficiency of the students is improved.
Those of skill would further appreciate that the various illustrative components 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 components and steps have been described above generally in terms of their functionality in order to clearly illustrate this 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 implementation. 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. A software module may reside 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 above embodiments are provided to further explain the objects, technical solutions and advantages of the present invention in detail, it should be understood that the above embodiments are merely exemplary embodiments of the present invention and are not intended to limit the scope of the present invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. An image information-based answering method is characterized by comprising the following steps:
the user terminal acquires image data to be identified through the camera device according to an acquisition instruction input by a first user;
the user terminal performs noise reduction processing on the image data to be identified to obtain noise-reduced image data to be identified and sends the noise-reduced image data to a server; the image data to be identified carries a user ID of a first user;
the server identifies the image data to be identified according to the neural network model to obtain first question information; the first topic information carries a user ID of the first user;
analyzing the first question information to obtain keyword information;
searching second question information matched with the keyword information in a test question database according to the keyword information;
and sending the second topic information to a user terminal according to the user ID of the first user, so that the user terminal can display the second topic information.
2. The image-information-based answering method according to claim 1, wherein before the user terminal acquires the image data to be recognized through the camera device according to the acquisition instruction input by the first user, the method further comprises:
the user terminal receives first user account information input by the first user; the first user account information comprises a user ID of the first user, first user grade information and region information of the first user.
3. The image information-based answering method according to claim 1, further comprising:
and the user terminal acquires the region information of the first user through a positioning module.
4. The image-information-based answering method according to claim 1, wherein the step of acquiring, by the user terminal, the image data to be recognized through the camera device according to the acquisition instruction input by the first user is specifically:
the user terminal acquires original image data according to an acquisition instruction input by a first user and displays the original image data;
and receiving a region selection instruction input by the first user according to the original image data, and obtaining the image data to be identified according to the region selection instruction.
5. The image information-based answering method according to claim 1, wherein the test question database includes second question information, grade information corresponding to the second question information, and region information corresponding to the second question information.
6. The image information-based answering method according to claim 5, wherein the searching for the second question information matching the keyword information in the test question database according to the keyword information specifically comprises:
acquiring the first user grade information corresponding to the user ID of the first user and the region information of the first user;
determining target test question range data matched with the first user grade information and the first user region information and target test question range out-of-range data unmatched with the first user grade information and the first user region information in a test question database according to the first user grade information and the first user region information;
and searching second subject information matched with the keyword information in the test subject range data according to the keyword information.
7. The image-information-based answering method according to claim 6, wherein when second question information matching the keyword information is not found in the test question range data according to the keyword information, the method further comprises:
searching second subject information matched with the keyword information in the data outside the target test subject range according to the keyword information;
and sending the second topic information to a user terminal according to the user ID of the first user.
8. The image-information-based answering method according to claim 1, wherein the second topic information includes answer information of the second topic;
and sending the second topic information and the answer information of the second topic to a user terminal according to the user ID of the first user.
9. The image-information-based answering method according to claim 1, wherein after said sending the second topic information to the user terminal according to the user ID of the first user, the method further comprises:
receiving feedback information input by the first user; determining whether the feedback information is first feedback information;
when the feedback information is first feedback information, sending the first topic information to the server;
and the server updates the test question database according to the first question information.
10. The image information-based answering method according to claim 9, wherein after the server updates the test question database according to the first question information, the method further comprises:
the server receives answer information of a first topic of the first topic information input by a second user according to the first topic information; the answer information of the first topic comprises a user ID of the first user;
and sending the first question information and the answer information of the first question to a user terminal according to the user ID of the first user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111022961.9A CN113673475A (en) | 2021-09-01 | 2021-09-01 | Answering method based on image information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111022961.9A CN113673475A (en) | 2021-09-01 | 2021-09-01 | Answering method based on image information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113673475A true CN113673475A (en) | 2021-11-19 |
Family
ID=78548059
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111022961.9A Pending CN113673475A (en) | 2021-09-01 | 2021-09-01 | Answering method based on image information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113673475A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104506898A (en) * | 2015-01-12 | 2015-04-08 | 北京东方皆冠科技有限公司 | Image information processing method and system |
| CN109583401A (en) * | 2018-12-05 | 2019-04-05 | 广东小天才科技有限公司 | It is a kind of automatically generate answer search topic method and user equipment |
| JP2019212002A (en) * | 2018-06-05 | 2019-12-12 | 公益財団法人大学セミナーハウス | Examination management device |
| CN111914068A (en) * | 2020-08-21 | 2020-11-10 | 广州云蝶科技有限公司 | Method for extracting knowledge points of test questions |
| CN112860845A (en) * | 2020-12-24 | 2021-05-28 | 北京高途云集教育科技有限公司 | Test question retrieval method and device, electronic equipment and storage medium |
-
2021
- 2021-09-01 CN CN202111022961.9A patent/CN113673475A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104506898A (en) * | 2015-01-12 | 2015-04-08 | 北京东方皆冠科技有限公司 | Image information processing method and system |
| JP2019212002A (en) * | 2018-06-05 | 2019-12-12 | 公益財団法人大学セミナーハウス | Examination management device |
| CN109583401A (en) * | 2018-12-05 | 2019-04-05 | 广东小天才科技有限公司 | It is a kind of automatically generate answer search topic method and user equipment |
| CN111914068A (en) * | 2020-08-21 | 2020-11-10 | 广州云蝶科技有限公司 | Method for extracting knowledge points of test questions |
| CN112860845A (en) * | 2020-12-24 | 2021-05-28 | 北京高途云集教育科技有限公司 | Test question retrieval method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 黄建年: "古籍计算机自动断句标点与自动分词标引研究", 安徽师范大学出版社, pages: 92 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Marsh et al. | The digital expansion of the mind: Implications of internet usage for memory and cognition | |
| CN109359215B (en) | Video intelligent pushing method and system | |
| CN108648757B (en) | Analysis method based on multi-dimensional classroom information | |
| CN110209897B (en) | Intelligent dialogue method, device, storage medium and equipment | |
| WO2022095380A1 (en) | Ai-based virtual interaction model generation method and apparatus, computer device and storage medium | |
| CN108281052A (en) | A kind of on-line teaching system and online teaching method | |
| CN111507097B (en) | Title text processing method and device, electronic equipment and storage medium | |
| CN107133303A (en) | Method and apparatus for output information | |
| Cetinkaya et al. | Students’ success in English vocabulary acquisition through multimedia annotations sent via WhatsApp | |
| CN113254708A (en) | Video searching method and device, computer equipment and storage medium | |
| Alfaify et al. | Cultural references in films: an audience reception study of subtitling into Arabic | |
| CN113657509B (en) | Teaching training lifting method, device, terminal and storage medium | |
| US9547995B1 (en) | Dynamic instructional course | |
| CN111339809A (en) | Classroom behavior analysis method and device and electronic equipment | |
| CN113673475A (en) | Answering method based on image information | |
| US11704585B2 (en) | System and method to determine outcome probability of an event based on videos | |
| CN112528790A (en) | Teaching management method and device based on behavior recognition and server | |
| CN112800177A (en) | FAQ knowledge base automatic generation method and device based on complex data types | |
| KR101011773B1 (en) | An education management system by ability using education-content development and classification and a method thereof | |
| CN111209817A (en) | Assessment method, device and equipment based on artificial intelligence and readable storage medium | |
| CN110781322A (en) | Multimedia courseware generation method and device, storage medium and terminal equipment | |
| CN111914068B (en) | Method for extracting test question knowledge points | |
| CN110807094A (en) | Big data analysis, prediction and data visualization system and device for legal document | |
| US11810132B1 (en) | Method of collating, abstracting, and delivering worldwide viewpoints | |
| Wanasinghe et al. | Hastha: online learning platform for hearing impaired |
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 | ||
| CB02 | Change of applicant information |
Address after: Room 1002, floor 10, block B, No. 18, Zhongguancun Street, Haidian District, Beijing 100044 Applicant after: Beijing Biyun shuchuang Technology Co.,Ltd. Address before: Room 1002, floor 10, block B, No. 18, Zhongguancun Street, Haidian District, Beijing 100044 Applicant before: Beijing yundie Zhixue Technology Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211119 |