CN107562918A - A kind of mathematical problem knowledge point discovery and batch label acquisition method - Google Patents
A kind of mathematical problem knowledge point discovery and batch label acquisition method Download PDFInfo
- Publication number
- CN107562918A CN107562918A CN201710818970.6A CN201710818970A CN107562918A CN 107562918 A CN107562918 A CN 107562918A CN 201710818970 A CN201710818970 A CN 201710818970A CN 107562918 A CN107562918 A CN 107562918A
- Authority
- CN
- China
- Prior art keywords
- label
- knowledge point
- keyword
- mathematical problem
- knowledge
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Mathematics Discipline knowledge point and subject vocabulary are collected, forms subject knowledge collection of illustrative plates；An important supplement source using the subject vocabulary as label as, the stem of label to be obtained is write to the text of reference format；Extract the keyword in the text, and the subject vocabulary according to belonging to the incidence relation of the keyword and the knowledge mapping determines the mathematical problem and knowledge point；The label of the corresponding exam pool is established, the label includes：Mathematics Discipline and specific knowledge point belonging to the keyword and the exam pool.Mathematical problem content is fully excavated, realizes that label obtains automatically, for the label of acquisition, system can provide recommendation grade.
Description
Technical field
The present invention relates to knowledge classification field, is that a kind of mathematical problem knowledge point discovery obtains with batch label specifically
Method.
Background technology
With the release of on-line study platform, the selection on-line study of more and more people.But as people are to education resource
Demand and requirement be on the increase, resource extreme expansion in network, this is that learner finds suitable education resource band
No small challenge is carried out.How the demand preferably according to learner searches out suitable resource from magnanimity education resource, from
And the utilization rate of education resource and the learning efficiency of learner are effectively improved, it is always the hot issue that everybody pays close attention to.Learn
In habit, either courseware or examination question, there are certain specific aim, certain knowledge point and adaptable colony.Take rationally
Classification, simple mark, i.e. label.Label is closely connected with resource, and gradually forms the recommendation machine of label on this basis
System, label are mutually tied with learning Content.
Teaching field, especially courseware and examination question labeling, label can be helped preferably in mining data storehouse in reality
Hold, user no longer needs the selection can of blindness to capture substantive content；Label can help selection and the mistake of huge volumes of content
Filter, and one of adaptive teaching core content.
The content of the invention
It is an object of the invention to provide a kind of mathematical problem knowledge point discovery and batch label acquisition method.The purpose of the present invention
It is to be achieved through the following technical solutions：
The present invention collects Mathematics Discipline knowledge point and subject vocabulary, forms subject knowledge collection of illustrative plates；By label to be obtained
Stem is write as the text of reference format；The keyword in the text is extracted, and according to the keyword and the knowledge mapping
Incidence relation determine subject vocabulary and knowledge point belonging to the mathematical problem；Establish the label of the corresponding exam pool, artificial inspection
Label to be verified is looked into, changes the information of label, and the admissible label of periodic check, it is ensured that the accuracy of label；This method is given birth to
Into label provide foundation for follow-up adaptive teaching, screening or filtering teaching resource provide reference frame.
Further, pending mathematical problem stem, examination question, answer, explanation and some annotation informations, conversion are included
For the text of reference format.
Further, mathematical knowledge point and mathematics vocabulary are gathered, forms Mathematics Discipline knowledge mapping, mathematics vocabulary is to meet
Extended in knowledge point and build up what is come, without strict specific standard and definition, it is equal with knowledge point, plays into one
The effect of step supplement knowledge point.
Further, clause in the text, knowledge point, keyword are extracted, according to the keyword and the knowledge
The incidence relation of collection of illustrative plates determines subject vocabulary and the knowledge point belonging to the mathematical problem.
Further, label recommendations grade, it is divided into three grades：It is completely credible, it is admissible, it is to be verified, manually only need to examine
Look into label to be verified.
Further, selection number of the counting user to label, it is added, deletes or replaces according to the selection number
Label.
It is operating procedure of the present invention below：
Mathematical knowledge point and mathematics vocabulary are gathered, Mathematics Discipline knowledge mapping is formed, to elaborate here, mathematics
Vocabulary, the extension of Mathematics Discipline knowledge point and progressively accumulating and enriching are satisfied with, without strict standard and specific boundary
Limit, itself and knowledge point phase same-action play a part of further supplementing knowledge point, this vocabulary knowledge point is different from notional
Knowledge point, interim closer in learning process, the knowledge point for feature of having the ability.
The pending mathematical problem stem, comprising contents such as examination question, answer, explanations, is converted to reference format text.
Clause in the text, knowledge point, keyword are extracted, and according to the pass of the keyword and the knowledge mapping
Connection relation determines subject vocabulary and the knowledge point belonging to the mathematical problem.
The label of the corresponding mathematical problem is established, the label includes：The keyword and mathematical problem institute
The subject of category, knowledge point.
Preferably, the keyword has one or more.
Preferably, the keyword in the extraction text includes：
Word2vec participles are carried out to the text, and (word2vec is that Google is proposed based on context of co-text the word that obtains
Vector), obtain each sub- word；
Calculate each sub- word, including clause, knowledge point, keyword, the TF-IDF values of subject vocabulary；
The TF-IDF values, wherein TF are word frequency, and IDF is inverse document frequency；Two values are multiplied, and just obtain the described of word
TF-IDF values；The importance of one word is higher, and the TF-IDF values described in it are bigger；Before keyword is the TF-IDF maximum
Several, further processing forms knowledge point.
The participle semantic processes, in word2vec, each word is a vector in examination question, hash algorithm,
Word2vec, hash break up word, while are defined as vector, and term vector adds up determination, and it is credible；In word2vec understandings
The lower semantic accuracy for recognizing statement sequence up and down simultaneously, realizing sentence participle and semanteme.Each word has one in examination question
Individual value, bow algorithms and word weight, LDA themes and word matrix, both have progressive relationship, and bow evolves to LDA, realizes and divides
The accurate calculating of value.Label is obtained in patent of the present invention recommendation grade is provided, be divided into third rank：It is completely credible, it is admissible, treat
Checking.Manually only need to check label to be verified.
Using the TF-IDF values higher than given threshold related content as keyword, or according to the TF-IDF values by
High to Low order chooses the related content of above setting number as keyword.
Preferably, the incidence relation of the keyword and knowledge mapping includes：The keyword is in the knowledge mapping
The position of appearance and number.
Preferably, methods described also includes：
Selection number of the counting user to label, label is added, deletes or replaces according to the selection number.
A kind of mathematical problem label extraction method, including：
Handling module, for capturing each subject knowledge point and subject vocabulary in advance；
Map construction module, for building the subject knowledge collection of illustrative plates of corresponding the subject knowledge point and subject vocabulary；
Transcription module, for the contents of test question transcription that extracts the mathematical problem for treating labeling into text, during transcription, with
The subject vocabulary is as label keyword；
Keyword extracting module, for extracting the keyword in the text；
Information determination module, for determining the mathematical problem according to the incidence relation of the keyword and the knowledge mapping
Subject vocabulary and knowledge point belonging to mesh；
Label establishes module, and for establishing the label of the corresponding mathematical problem, the label includes：The keyword
And subject belonging to the mathematical problem, knowledge point.
Preferably, the keyword has one or more.
Preferably, the keyword extracting module includes：
Participle unit, for being segmented to the text, obtain each sub- word；
Computing unit, for calculating the related content TF-IDF values；
Extraction unit, for related content of the TF-IDF values higher than given threshold to be extracted as into keyword, Huo Zheyi
The related content that above setting number is chosen according to the order of the TF-IDF values from high to low is extracted as keyword.
Preferably, the incidence relation of the keyword and knowledge mapping includes：The keyword is in the knowledge mapping
The position of appearance and number.
Preferably, the system also includes：
Optimization module, for selection number of the counting user to label, be added according to the selection number, delete or
Replace label.
The mathematical problem batch tag extraction method that the present invention is implemented, utilize speech transcription technology and abundant interconnection netting index
According to being standardized text-processing, keyword extraction to mathematical problem, and determine belonging to examination question according to keyword and knowledge mapping
Subject and knowledge point, realize label automated tag, reduce artificial participation amount, while can be follow-up resource supplying etc.
Service provides good foundation, is more beneficial for teacher, student and finds high-quality teaching resource in time.
Brief description of the drawings
Fig. 1 is recommending module operating procedure schematic diagram of the present invention.
Embodiment
The embodiment of the present invention is described in further detail with reference to Fig. 1.
As shown in figure 1, a kind of mathematical problem knowledge point discovery designed by the present invention actually should with batch label acquisition method
Among process, specifically comprise the following steps：
Step 101, Mathematics Discipline knowledge point and subject vocabulary are gathered in advance, form corresponding subject knowledge collection of illustrative plates.
Knowledge mapping, alternatively referred to as knowledge polar plot, it is using scientific knowledge point as node, with knowledge point and structural relation
A series of a variety of connections, it can use annexation indicate knowledge point and its examination question between connecting each other.
In the embodiment of the present invention, the subject knowledge collection of illustrative plates, including specific to each knowledge point of subject and its correlation.Subject knowledge
In the correlation of each vocabulary in this subject is shown, the filtering of examination question or selection link are extremely important for the effect of collection of illustrative plates.
In practical application, instrument collection subject knowledge point and subject vocabulary can be first passed through, for example, trigonometric function knowledge
Point, positive angle, negative angle, zero angle and quadrant angle etc., all it is the knowledge point of trigonometric function.Subject knowledge point is handled first, next,
The word lists of Knowledge Relation are obtained using other modes.To each vocabulary, to judge whether the vocabulary is the subject word
Converge, constantly vocabulary is cleaned, form the knowledge mapping of corresponding subject.
Step 102, one kind using the subject vocabulary as label, will treat that examination question extracts received text.
The examination question for treating labeling is extracted into received text.But due to the complexity of mathematics examination question, particularly with comprising
In the processing of a large amount of specialized vocabularies.Therefore, in embodiments of the present invention, using the specialized vocabulary that collects as label resources it
One, carry out labeling identification, it can be ensured that the accuracy rate of tag match is greatly enhanced.
Step 103, extract the keyword in the text, and pass is associated according to the keyword and the knowledge mapping
System determines the subject vocabulary and knowledge point belonging to the examination question.
Specifically, in the keyword in extracting the text, first have to segment the text, obtain each sub- word,
Then the TF-IDF values of related content are calculated, finally judge that can the word be used as the text according to the TF-IDF values of related content
Keyword.
In the present embodiment, when determining the keyword of text according to related content TF-IDF values, there can be following a variety of determinations
Method, such as：
1. given threshold method：The method sets TF-IDF threshold values first, then by TF-IDF values in text higher than setting threshold
The related content of value is defined as keyword；For different texts, under same given threshold, the keyword number extracted can
Can be different.
2. set number method：The method sets keyword number to be extracted first, then according to related content in text
The order of TF-IDF values from high to low chooses the related content of setting number as keyword.
The dependence very little for the accuracy that the keyword accuracy extracted using TF-IDF technologies is handled item colibrationization, makes
Accurate key word information still can be extracted with TF-IDF technologies.
It should be noted that one or more keyword of sub- word as text in text, keyword can be extracted
Number can be set according to user's request.
After the keyword of text is determined, the examination question is determined according to the incidence relation of keyword and subject knowledge collection of illustrative plates
Affiliated subject and knowledge point.Such as if the keyword extracted in Mathematics Discipline knowledge mapping equation solution this know
Know the number highest occurred at point, then can determine that the subject belonging to the examination question corresponding to the keyword and knowledge point are mathematics
The equation solution of section.
Step 104, the label of the corresponding examination question is established, the label includes：The keyword and examination question institute
The subject of category, knowledge point.
Extracting the keyword of examination question, it is determined that, can be by the pass after the subject and knowledge point corresponding to the examination question
Keyword, affiliated subject, knowledge point carry out automated tag as the label of the examination question.Such as：It is N to extract keyword number, then
The label of examination question includes corresponding to the keyword：N number of keyword, affiliated subject, knowledge point, altogether N+2 label.
Mathematical problem batch label acquisition method of the embodiment of the present invention, using natural language processing technique, enters to contents of test question
The processing of row text standardization, keyword extraction, foundation knowledge mapping determine subject and knowledge point, can fully excavate the mark of examination question
Label, find high-quality examination question in time, or the service such as follow-up examination question push provides good foundation.
What is finally illustrated is：Above-described embodiments are merely to illustrate the technical scheme, rather than it is limited
System；Although the present invention is described in detail with reference to the foregoing embodiments, it will be understood by those within the art that：Its
The technical scheme described in previous embodiment can still be modified, or which part or all technical characteristic are carried out
Equivalent substitution；And these modifications or substitutions, the essence of appropriate technical solution is departed from various embodiments of the present invention technical scheme
Scope.
Claims (6)
1. a kind of mathematical problem knowledge point discovery and batch label acquisition method, it is characterised in that：Collect Mathematics Discipline knowledge point with
And subject vocabulary, form subject knowledge collection of illustrative plates；The stem of label to be obtained is write as to the text of reference format；Extract the text
In keyword, and the subject word according to belonging to the incidence relation of the keyword and the knowledge mapping determines the mathematical problem
Remittance and knowledge point；Establish the label of the corresponding exam pool, hand inspection label to be verified, change the information of label, and periodically
Verify admissible label, it is ensured that the accuracy of label；The label of this method generation provides foundation for follow-up adaptive teaching, sieves
Choosing or filtering teaching resource provide reference frame.
2. a kind of mathematical problem knowledge point discovery according to claim 1 and batch label acquisition method, it is characterised in that：Treat
The mathematical problem stem of processing, comprising examination question, answer, explanation and some annotation informations, be converted to the text of reference format.
3. a kind of mathematical problem knowledge point discovery according to claim 1 and batch label acquisition method, it is characterised in that：Adopt
Collect mathematical knowledge point and mathematics vocabulary, form Mathematics Discipline knowledge mapping, mathematics vocabulary be satisfied with knowledge point extension and progressively
Accumulate, without strict specific standard and definition, it is equal with knowledge point, plays the work of further supplement knowledge point
With.
4. a kind of mathematical problem knowledge point discovery according to claim 1 and batch label acquisition method, it is characterised in that：Carry
Clause in the text, knowledge point, keyword are taken, institute is determined according to the incidence relation of the keyword and the knowledge mapping
State subject vocabulary and the knowledge point belonging to mathematical problem.
5. a kind of mathematical problem knowledge point discovery according to claim 1 and batch label acquisition method, it is characterised in that：Mark
Recommendation grade is signed, is divided into three grades：It is completely credible, it is admissible, it is to be verified, manually only need to check label to be verified.
6. a kind of mathematical problem knowledge point discovery according to claim 1 and batch label acquisition method, it is characterised in that：System
Selection number of the user to label is counted, label is added, deletes or replaces according to the selection number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710818970.6A CN107562918A (en) | 2017-09-12 | 2017-09-12 | A kind of mathematical problem knowledge point discovery and batch label acquisition method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710818970.6A CN107562918A (en) | 2017-09-12 | 2017-09-12 | A kind of mathematical problem knowledge point discovery and batch label acquisition method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107562918A true CN107562918A (en) | 2018-01-09 |
Family
ID=60980733
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710818970.6A Pending CN107562918A (en) | 2017-09-12 | 2017-09-12 | A kind of mathematical problem knowledge point discovery and batch label acquisition method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107562918A (en) |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109214445A (en) * | 2018-08-27 | 2019-01-15 | 陆柒（北京）科技有限公司 | A kind of multi-tag classification method based on artificial intelligence |
| CN109255031A (en) * | 2018-09-20 | 2019-01-22 | 苏州友教习亦教育科技有限公司 | The data processing method of knowledge based map |
| CN109359290A (en) * | 2018-08-20 | 2019-02-19 | 国政通科技有限公司 | The knowledge point of examination question text determines method, electronic equipment and storage medium |
| CN109635100A (en) * | 2018-12-24 | 2019-04-16 | 上海仁静信息技术有限公司 | A kind of recommended method, device, electronic equipment and the storage medium of similar topic |
| CN109783693A (en) * | 2019-01-18 | 2019-05-21 | 广东小天才科技有限公司 | Method and system for determining video semantics and knowledge points |
| CN110096692A (en) * | 2018-01-29 | 2019-08-06 | 亿度慧达教育科技（北京）有限公司 | A kind of Semantic Information Processing method and apparatus |
| CN110134945A (en) * | 2019-04-15 | 2019-08-16 | 平安科技（深圳）有限公司 | The recognition methods of exercise examination point, device, equipment and storage medium |
| CN110223206A (en) * | 2019-06-11 | 2019-09-10 | 广州蓝鸽软件有限公司 | Text major field determines method and system and parsing courseware matching process and system |
| CN110222125A (en) * | 2019-05-13 | 2019-09-10 | 厦门无常师教育科技有限公司 | Education individualization method for pushing and system on a kind of line of knowledge based map |
| CN110309363A (en) * | 2018-03-02 | 2019-10-08 | 广州润沁教育科技有限公司 | A kind of instructional video segment method of commerce of knowledge based point |
| CN110362688A (en) * | 2019-06-14 | 2019-10-22 | 北京百度网讯科技有限公司 | Examination question mask method, device, equipment and computer readable storage medium |
| CN110599377A (en) * | 2019-09-16 | 2019-12-20 | 中国人民解放军国防科技大学 | Knowledge point ordering method and device for online learning |
| CN110909533A (en) * | 2019-11-19 | 2020-03-24 | 浙江蓝鸽科技有限公司 | Resource theme judgment method and system |
| CN111324730A (en) * | 2018-11-29 | 2020-06-23 | 东莞市七宝树教育科技有限公司 | Test question label classification method |
| CN111966834A (en) * | 2020-07-29 | 2020-11-20 | 深圳市元征科技股份有限公司 | File generation method, file generation device and server |
| CN112216161A (en) * | 2020-10-23 | 2021-01-12 | 新维畅想数字科技（北京）有限公司 | Digital work teaching method and device |
| CN112487183A (en) * | 2020-11-10 | 2021-03-12 | 江苏乐易学教育科技有限公司 | Labeled test question knowledge point classification method and system |
| CN112711663A (en) * | 2019-10-24 | 2021-04-27 | 北京一起教育信息咨询有限责任公司 | Method and device for determining label, electronic equipment and storage medium |
| CN112784062A (en) * | 2019-03-15 | 2021-05-11 | 北京金山数字娱乐科技有限公司 | Idiom knowledge graph construction method and device |
| CN112948650A (en) * | 2021-03-31 | 2021-06-11 | 北京大米科技有限公司 | Learning effect display method and device and computer storage medium |
| CN113268563A (en) * | 2021-05-24 | 2021-08-17 | 平安科技（深圳）有限公司 | Semantic recall method, device, equipment and medium based on graph neural network |
| CN113704450A (en) * | 2021-08-30 | 2021-11-26 | 广东艾檬电子科技有限公司 | Weak knowledge point identification method and system, intelligent device and storage medium |
| CN113722506A (en) * | 2021-08-31 | 2021-11-30 | 广东艾檬电子科技有限公司 | Intelligent knowledge point identification method, system, intelligent equipment and storage medium |
-
2017
- 2017-09-12 CN CN201710818970.6A patent/CN107562918A/en active Pending
Cited By (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110096692A (en) * | 2018-01-29 | 2019-08-06 | 亿度慧达教育科技（北京）有限公司 | A kind of Semantic Information Processing method and apparatus |
| CN110096692B (en) * | 2018-01-29 | 2021-04-09 | 亿度慧达教育科技（北京）有限公司 | Semantic information processing method and device |
| CN110309363A (en) * | 2018-03-02 | 2019-10-08 | 广州润沁教育科技有限公司 | A kind of instructional video segment method of commerce of knowledge based point |
| CN109359290A (en) * | 2018-08-20 | 2019-02-19 | 国政通科技有限公司 | The knowledge point of examination question text determines method, electronic equipment and storage medium |
| CN109359290B (en) * | 2018-08-20 | 2023-05-05 | 国政通科技有限公司 | Knowledge point determining method of test question text, electronic equipment and storage medium |
| CN109214445A (en) * | 2018-08-27 | 2019-01-15 | 陆柒（北京）科技有限公司 | A kind of multi-tag classification method based on artificial intelligence |
| CN109255031A (en) * | 2018-09-20 | 2019-01-22 | 苏州友教习亦教育科技有限公司 | The data processing method of knowledge based map |
| CN109255031B (en) * | 2018-09-20 | 2022-02-11 | 苏州友教习亦教育科技有限公司 | Data processing method based on knowledge graph |
| CN111324730B (en) * | 2018-11-29 | 2023-03-14 | 东莞市七宝树教育科技有限公司 | Test question label classification method |
| CN111324730A (en) * | 2018-11-29 | 2020-06-23 | 东莞市七宝树教育科技有限公司 | Test question label classification method |
| CN109635100A (en) * | 2018-12-24 | 2019-04-16 | 上海仁静信息技术有限公司 | A kind of recommended method, device, electronic equipment and the storage medium of similar topic |
| CN109783693A (en) * | 2019-01-18 | 2019-05-21 | 广东小天才科技有限公司 | Method and system for determining video semantics and knowledge points |
| CN109783693B (en) * | 2019-01-18 | 2021-05-18 | 广东小天才科技有限公司 | Method and system for determining video semantics and knowledge points |
| CN112784062B (en) * | 2019-03-15 | 2024-06-04 | 北京金山数字娱乐科技有限公司 | Idiom knowledge graph construction method and device |
| CN112784062A (en) * | 2019-03-15 | 2021-05-11 | 北京金山数字娱乐科技有限公司 | Idiom knowledge graph construction method and device |
| CN110134945B (en) * | 2019-04-15 | 2024-04-23 | 平安科技（深圳）有限公司 | Method, device, equipment and storage medium for identifying examination points of exercise |
| CN110134945A (en) * | 2019-04-15 | 2019-08-16 | 平安科技（深圳）有限公司 | The recognition methods of exercise examination point, device, equipment and storage medium |
| CN110222125A (en) * | 2019-05-13 | 2019-09-10 | 厦门无常师教育科技有限公司 | Education individualization method for pushing and system on a kind of line of knowledge based map |
| CN110223206B (en) * | 2019-06-11 | 2023-12-08 | 广州蓝鸽软件有限公司 | Lesson specialty direction determining method and system and lesson matching method and system for analysis |
| CN110223206A (en) * | 2019-06-11 | 2019-09-10 | 广州蓝鸽软件有限公司 | Text major field determines method and system and parsing courseware matching process and system |
| CN110362688A (en) * | 2019-06-14 | 2019-10-22 | 北京百度网讯科技有限公司 | Examination question mask method, device, equipment and computer readable storage medium |
| CN110362688B (en) * | 2019-06-14 | 2022-03-25 | 北京百度网讯科技有限公司 | Test question labeling method, device and equipment and computer readable storage medium |
| CN110599377A (en) * | 2019-09-16 | 2019-12-20 | 中国人民解放军国防科技大学 | Knowledge point ordering method and device for online learning |
| CN112711663A (en) * | 2019-10-24 | 2021-04-27 | 北京一起教育信息咨询有限责任公司 | Method and device for determining label, electronic equipment and storage medium |
| CN110909533B (en) * | 2019-11-19 | 2023-07-18 | 浙江蓝鸽科技有限公司 | Resource theme judging method and system |
| CN110909533A (en) * | 2019-11-19 | 2020-03-24 | 浙江蓝鸽科技有限公司 | Resource theme judgment method and system |
| CN111966834A (en) * | 2020-07-29 | 2020-11-20 | 深圳市元征科技股份有限公司 | File generation method, file generation device and server |
| CN112216161A (en) * | 2020-10-23 | 2021-01-12 | 新维畅想数字科技（北京）有限公司 | Digital work teaching method and device |
| CN112487183A (en) * | 2020-11-10 | 2021-03-12 | 江苏乐易学教育科技有限公司 | Labeled test question knowledge point classification method and system |
| CN112487183B (en) * | 2020-11-10 | 2024-08-02 | 江苏乐易学教育科技有限公司 | Method and system for classifying labeled test question knowledge points |
| CN112948650A (en) * | 2021-03-31 | 2021-06-11 | 北京大米科技有限公司 | Learning effect display method and device and computer storage medium |
| CN112948650B (en) * | 2021-03-31 | 2024-04-12 | 北京大米科技有限公司 | Learning effect display method and device and computer storage medium |
| CN113268563A (en) * | 2021-05-24 | 2021-08-17 | 平安科技（深圳）有限公司 | Semantic recall method, device, equipment and medium based on graph neural network |
| CN113268563B (en) * | 2021-05-24 | 2022-06-17 | 平安科技（深圳）有限公司 | Semantic recall method, device, equipment and medium based on graph neural network |
| CN113704450A (en) * | 2021-08-30 | 2021-11-26 | 广东艾檬电子科技有限公司 | Weak knowledge point identification method and system, intelligent device and storage medium |
| CN113722506A (en) * | 2021-08-31 | 2021-11-30 | 广东艾檬电子科技有限公司 | Intelligent knowledge point identification method, system, intelligent equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107562918A (en) | A kind of mathematical problem knowledge point discovery and batch label acquisition method | |
| CN107766371B (en) | Text information classification method and device | |
| CN109213999B (en) | Subjective question scoring method | |
| CN107563498B (en) | Image description method and system based on visual and semantic attention combined strategy | |
| CN107092596B (en) | Text emotion analysis method based on attention CNNs and CCR | |
| CN104298651B (en) | Biomedicine named entity recognition and protein interactive relationship extracting on-line method based on deep learning | |
| CN108121702B (en) | Method and system for evaluating and reading mathematical subjective questions | |
| CN110489755A (en) | Document creation method and device | |
| CN109388700A (en) | Intention identification method and system | |
| CN110825867B (en) | Similar text recommendation method and device, electronic equipment and storage medium | |
| CN104268603A (en) | Intelligent marking method and system for text objective questions | |
| CN110555206A (en) | named entity identification method, device, equipment and storage medium | |
| CN111914550B (en) | Knowledge graph updating method and system oriented to limited field | |
| CN110175229A (en) | A kind of method and system carrying out online training based on natural language | |
| CN106407482B (en) | A kind of network academic report category method based on multi-feature fusion | |
| CN107145573A (en) | The problem of artificial intelligence customer service robot, answers method and system | |
| CN106227836B (en) | Unsupervised joint visual concept learning system and unsupervised joint visual concept learning method based on images and characters | |
| CN112749556B (en) | Multi-language model training method and device, storage medium and electronic equipment | |
| CN111723870B (en) | Artificial intelligence-based data set acquisition method, apparatus, device and medium | |
| CN111159356A (en) | Knowledge graph construction method based on teaching content | |
| CN110489747A (en) | A kind of image processing method, device, storage medium and electronic equipment | |
| CN110287405A (en) | The method, apparatus and storage medium of sentiment analysis | |
| CN114265937A (en) | Intelligent classification analysis method and system of scientific and technological information, storage medium and server | |
| CN110516240A (en) | A kind of Semantic Similarity Measurement model DSSM technology based on Transformer | |
| CN118038139A (en) | Multi-mode small sample image classification method based on large model fine tuning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180109 |