CN106339965A - Learning situation analysis method - Google Patents
Learning situation analysis method Download PDFInfo
- Publication number
- CN106339965A CN106339965A CN201610662969.4A CN201610662969A CN106339965A CN 106339965 A CN106339965 A CN 106339965A CN 201610662969 A CN201610662969 A CN 201610662969A CN 106339965 A CN106339965 A CN 106339965A
- Authority
- CN
- China
- Prior art keywords
- topic
- wrong
- mistake
- wrong topic
- similarity
- 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
Classifications
-
- 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—Systems or methods specially adapted for 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
- 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
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
Abstract
The invention discloses a learning situation analysis method. The method comprises the steps that the images of the wrongly answered questions are acquired; image binarization processing is performed on the images of the wrongly answered questions; corresponding question error information is set for the images of the wrongly answered questions; the images after image binarization processing and the corresponding question error information are transmitted to a data processing platform; the data processing platform performs character recognition processing on the received images and performs data classification on the recognized characters and the corresponding question error information; and dirty data processing is performed on the classified data and then the data are stored in a database, and similarity matching is performed on the question errors stored in the database according to the set matching conditions so that the high frequency question errors of all the question errors are obtained. With application of the learning situation analysis method, the frequent errors and the knowledge points which are not greatly mastered in daily learning of the students can be effectively mined according to the question errors of the students so that targeted extra tutoring can be performed.
Description
Technical field
The present invention relates to data analysis technique field, particularly to a kind of analysis of the students method.
Background technology
The enhancing of the ability processing with the development of intelligent terminal's (for example, smart mobile phone), data mining, big data, intelligence
More applications can be carried by mobile phone, therefore can meet study, the requirements of one's work of people, bring a lot of convenience.
For example, in the prior art, after user finishes exercise question, it is possible to use intelligent terminal sends and/or receives wrong
Topic information, analysis described mistake topic information simultaneously obtains analysis result.Wherein, mistake knowledge point and mistake can be comprised in analysis result
The information such as type.Therefore, user can generate study plan according to above-mentioned analysis result, is obtained in study according to study plan
Hold, service side can also be obtained according to study plan and push described study content to user.
But, general in prior art all do not clearly state the mode obtaining wrong topic information and content (for example, data
Content and implementation etc.), and the details of study content and study plan are not explicitly described, do not have simultaneously yet
There is the correlation function embodying data mining and calculating.
Content of the invention
In view of this, the present invention provides a kind of analysis of the students method, excavates such that it is able to the wrong topic according to student effectively
The mistake that student often makes in the daily study knowledge point bad with grasp.
Technical scheme is specifically achieved in that
A kind of analysis of the students method, the method includes:
Obtain the picture of wrong topic；
Image binaryzation process is carried out to the picture of described wrong topic；
Picture setting wrong topic information accordingly for described wrong topic；
Picture after image binaryzation is processed and accordingly wrong topic information transfer are to data processing platform (DPP)；
Data processing platform (DPP) carries out Text region process to the picture receiving, and to the word identifying and corresponding
Wrong topic information carries out data classification；
Data after sorting out is carried out being stored in data base after dirty data processing
According to the matching condition setting, similarity mode is carried out to the wrong topic of storage in data base, obtain in the wrong topic of institute
The wrong topic of high frequency.
Preferably, described mistake topic information includes:
Subject, knowledge point, topic type, errors number, type of error, complexity and significance level.
Preferably, described carry out data to the word identifying and accordingly wrong topic information and sort out including:
According to default classification condition, data classification is carried out to the word identifying and accordingly wrong topic information.
Preferably, the described matching condition according to setting, similarity mode is carried out to the wrong topic of storage in data base, obtains
The wrong topic of high frequency in wrong topic include:
Matching condition according to setting is inquired about in data base, obtains the wrong topic meeting matching condition；
Calculate each mistake topic that inquiry obtains and corresponding subject, grade wrong topic similarity, and according to similar
Degree judges whether between each mistake topic be similar topic；
Count the frequency of occurrences that each mistake topic occurs as similar topic；
Sequence according to the frequency of occurrences is ranked up to each mistake topic, and is owned according to default screening conditions
The wrong topic of high frequency in wrong topic.
Preferably, described judge between each mistake topic whether be that similar topic includes according to similarity:
One first threshold of setting；
For the wrong topic of any two between each mistake topic, the similarity between two wrong topics is more than or equal to described the
During one threshold value, judge the entitled similar topic of described two mistakes；When similarity between two wrong topics is less than described first threshold, sentence
The disconnected entitled non-similar topic of described two mistakes.
Preferably, the method may further comprise:
According to each Similarity Measure and classification results, the value of first threshold is adjusted.
Preferably, the frequency that each mistake topic of described statistics occurs as similar topic includes:
For any one mistake topic a in each mistake topic, when wrong topic a is similar topic to another one wrong topic b, by wrong topic
The frequency of occurrences of a and wrong topic b all adds one.
Preferably, described screening conditions are: the frequency of occurrences is more than or equal to the wrong topic of the entitled high frequency of mistake of Second Threshold.
As above visible, analysis of the students method provided by the present invention, can be collected by intelligent terminal and arrange student's
Mistake is inscribed, and excavates the student normal mistake made knowledge point bad with grasp in daily study according to the mistake topic of student, thus can
To carry out targetedly make-up lessons.
Brief description
Fig. 1 is the schematic flow sheet of the analysis of the students method in the embodiment of the present invention.
Specific embodiment
For making the objects, technical solutions and advantages of the present invention become more apparent, develop simultaneously embodiment referring to the drawings, right
The present invention further describes.
Present embodiments provide a kind of analysis of the students method.
Fig. 1 is the schematic flow sheet of the analysis of the students method in the embodiment of the present invention.As shown in figure 1, the embodiment of the present invention
In analysis of the students method mainly include step as described below:
Step 101, obtains the picture of wrong topic.
In the inventive solutions, by firstly the need of the picture obtaining wrong topic, the step then carrying out follow-up v again.
For example, preferably, in a particular embodiment of the present invention, it is possible to use (for example, camera, intelligence is eventually for filming apparatus
End etc.) exercise question (i.e. wrong topic) doing wrong is shot, obtain the picture of wrong topic.
Further, in the preferred embodiment, also acquired picture can be edited accordingly.Example
As the size of the acquired picture of adjustment；Or, wipe the answer item on picture using functions such as paintbrush, erasing rubbers；Or
Person, carries out adjustment or upset of position etc. to picture.
Step 102, carries out image binaryzation process to the picture of described wrong topic.
In this step, need to carry out image binaryzation process to the picture of described wrong topic.
Described image binary conversion treatment is exactly that the gray value of the pixel on image is set to 0 or 255, so that whole
Individual image presents obvious black and white effect.
Image binaryzation process is carried out to the picture of wrong topic, can be in order to carry out to the word on picture in subsequent process
Identification.
Step 103, is the picture setting wrong topic information accordingly of described wrong topic.
In addition it is also necessary to be that its corresponding picture setting is corresponding according to the wrong topic content in picture after obtaining the picture of wrong topic
Wrong topic information.
For example, preferably, in a particular embodiment of the present invention, described mistake topic information may include that subject, knowledge point,
The information such as topic type, errors number, type of error, complexity and significance level, thus be conducive to the data in subsequent step to know
Not and classification.
Step 104, the picture after image binaryzation is processed and accordingly wrong topic information transfer are to data processing platform (DPP).
Step 105, data processing platform (DPP) carries out Text region process to the picture receiving, and to the word identifying with
And wrong topic information carries out data classification accordingly.
For example, preferably, in a particular embodiment of the present invention, can be according to the needs of practical situations, according to pre-
If classification condition data classification is carried out to the word identifying and accordingly wrong topic information.
For example, data classification can be carried out according to complexity, or data classification is carried out according to topic type, or root
Carry out data classification etc. according to subject.
Step 106, carries out being stored in data base after dirty data processing to the data after sorting out.
Due to when carrying out Text region process, being sometimes difficult to all words that 100% ground identifies in picture, therefore having
Mess code etc. may occur in recognition result can not read symbol.Therefore, in this step, also the data after sorting out will be carried out
Dirty data processing, removes the symbols of can not reading such as mess code, thus avoid above-mentioned symbol of can not reading to the data in subsequent process as far as possible
Excavate and analysis has undesirable effect, then will carry out the data storage after dirty data processing in data base again, as the later stage
Data mining and the basic data of analysis.
For example, preferably, in a particular embodiment of the present invention, above-mentioned method also can further include:
Step 107, according to the matching condition setting, carries out similarity mode to the wrong topic of storage in data base, obtains institute
The wrong topic of high frequency in wrong topic.
In the inventive solutions, can according to stored in data base above-mentioned carried out sort out process and dirty
Data after data processing, and relevant matches condition set in advance (for example, by grade, or pressing subject etc.) is to corresponding
Qualified wrong topic carries out similarity mode, and generates in units of student, class or even school according to matching result
Feelings analysis report.
For example, preferably, in a particular embodiment of the present invention, in described step 107 according to the matching condition setting,
Similarity mode is carried out to the wrong topic of storage in data base, the wrong topic of high frequency obtaining in the wrong topic of institute may include that
Step 21, the matching condition according to setting is inquired about in data base, obtains the wrong topic meeting matching condition.
For example, in a preferred embodiment of the present invention, described matching condition can be set to related to this student
Information (for example, grade, subject etc.), then inquired about in data base according to this matching condition, thus obtaining corresponding
Wrong topic, that is, meet the wrong topic of matching condition.
Step 22, calculate each mistake topic that inquiry obtains and corresponding subject, grade wrong topic similarity, and root
Judge whether between each mistake topic be similar topic according to similarity.
In the inventive solutions, by the similarity of each mistake topic calculated, you can judged which wrong topic
It is similar topic each other.
For example, preferably, in a particular embodiment of the present invention, described whether judge between each mistake topic according to similarity
May include that for similar topic
Step 31, arranges a first threshold.
In the inventive solutions, described first threshold can be according to actual needs or experience pre-set one
Individual threshold value is it is also possible to can be by the threshold value that dynamic mode is adjusted, for example, according to each Similarity Measure
And classification results are adjusted to the value of first threshold, thus reaching required effect the most satisfied；First threshold now
An actually experiment value.
Step 32, for the wrong topic of any two between each mistake topic, the similarity between two wrong topics is more than or waits
When described first threshold, judge the entitled similar topic of described two mistakes；Similarity between two wrong topics is less than described first
During threshold value, judge the entitled non-similar topic of described two mistakes.
By above-mentioned step 31 and 32, you can judge whether between each mistake topic be similar topic.
Step 23, counts the frequency of occurrences that each mistake topic occurs as similar topic.
In the inventive solutions, due to having been judged according to similarity in above-mentioned steps 22 between each mistake topic
Whether it is similar topic, therefore, in this step, the frequency that each mistake topic occurs as similar topic can be counted.
In the inventive solutions, it is possible to use various ways come to count each mistake topic as similar topic occur frequency
Rate.Hereinafter will taking a kind of specific implementation therein as a example technical scheme be described in detail.
For example, preferably, in a particular embodiment of the present invention, the frequency that each mistake topic of described statistics occurs as similar topic
Rate includes:
For any one mistake topic a in each mistake topic, when wrong topic a is similar topic to another one wrong topic b, by wrong topic
The frequency of occurrences of a and wrong topic b all adds one.
The rest may be inferred, after topic wrong to any two all calculates similarity, you can statistics obtains each mistake topic
The frequency of occurrences occurring as similar topic.
For example, the wrong topic of oneself can be uploaded to system by different students.System is after contrast and identification, permissible
Calculating these mistake topic similarities between any two. the similarity between two wrong topics is higher than certain value (for example, above-mentioned first
Threshold value) when be exactly to think that this two wrong topics are same type of topics, belong to similar topic, now can give this two wrong topics respectively
The frequency of occurrences all adds one.When wrong topic between similarity all calculated after, you can obtain each mistake topic as similar topic
The frequency of occurrences occurring.
Step 24, the sequence according to the frequency of occurrences is ranked up to each mistake topic, and according to default screening conditions
Obtain the wrong topic of high frequency in wrong topic, that is, students be easiest to the wrong topic doing wrong.
After the frequency of occurrences that each mistake topic occurs as similar topic being obtained by statistics in above-mentioned steps 23, you can root
Sequence according to the frequency of occurrences is ranked up to each mistake topic；After being ranked up, you can obtained according to default screening conditions
To the wrong topic of high frequency in wrong topic.
In the inventive solutions, above-mentioned screening conditions can according to the needs of practical situations in advance or dynamically
Setting.
For example, preferably, in a particular embodiment of the present invention, described screening conditions are: the frequency of occurrences is more than or equal to
The wrong topic of the entitled high frequency of mistake of Second Threshold.
According to this screening conditions, the wrong topic that all frequencies of occurrences can be more than or equal to Second Threshold is all wrong as high frequency
Topic.
For example, when described Second Threshold is n, then the wrong topic that the frequency of occurrences is more than or equal to n is all the wrong topic of high frequency, also
It is most similar topic that students upload, that is, students are easiest to the wrong topic doing wrong.
By above-mentioned step 21～24, you can similarity mode is carried out to the wrong topic of storage in data base, is owned
The wrong topic of high frequency in wrong topic, that is, obtain matching result.
In summary, by using the analysis of the students method in the present invention, can be collected by intelligent terminal and arrange
Raw mistake is inscribed, and excavates the student normal mistake made knowledge point bad with grasp in daily study according to the mistake topic of student, from
And targetedly make-up lessons can be carried out.
The foregoing is only presently preferred embodiments of the present invention, not in order to limit the present invention, all essences in the present invention
Within god and principle, any modification, equivalent substitution and improvement done etc., should be included within the scope of protection of the invention.
Claims (8)
1. a kind of analysis of the students method is it is characterised in that the method includes:
Obtain the picture of wrong topic；
Image binaryzation process is carried out to the picture of described wrong topic；
Picture setting wrong topic information accordingly for described wrong topic；
Picture after image binaryzation is processed and accordingly wrong topic information transfer are to data processing platform (DPP)；
Data processing platform (DPP) carries out Text region process to the picture receiving, and the word identifying and accordingly mistake are inscribed
Information carries out data classification；
Data after sorting out is carried out being stored in data base after dirty data processing
According to the matching condition setting, similarity mode is carried out to the wrong topic of storage in data base, the height in obtaining that institute is wrong and inscribing
The wrong topic of frequency.
2. method according to claim 1 is it is characterised in that described mistake topic information includes:
Subject, knowledge point, topic type, errors number, type of error, complexity and significance level.
3. method according to claim 1 it is characterised in that described to the word identifying and wrong topic information accordingly
Carry out data classification to include:
According to default classification condition, data classification is carried out to the word identifying and accordingly wrong topic information.
4. method according to claim 1, it is characterised in that the described matching condition according to setting, is deposited in data base
The wrong topic of storage carries out similarity mode, obtains the high frequency wrong topic inclusion in the wrong topic of institute:
Matching condition according to setting is inquired about in data base, obtains the wrong topic meeting matching condition；
Calculate each mistake topic that inquiry obtains and corresponding subject, grade wrong topic similarity, and sentenced according to similarity
Whether break between each mistake topic is similar topic；
Count the frequency of occurrences that each mistake topic occurs as similar topic；
Sequence according to the frequency of occurrences is ranked up to each mistake topic, and obtains the wrong topic of institute according to default screening conditions
In the wrong topic of high frequency.
5. method according to claim 4 it is characterised in that described judged according to similarity between each mistake topic be whether
Similar topic includes:
One first threshold of setting；
For the wrong topic of any two between each mistake topic, the similarity between two wrong topics is more than or equal to described first threshold
During value, judge the entitled similar topic of described two mistakes；When similarity between two wrong topics is less than described first threshold, judge institute
State the entitled non-similar topic of two mistakes.
6. method according to claim 5 is it is characterised in that the method may further comprise:
According to each Similarity Measure and classification results, the value of first threshold is adjusted.
7. method according to claim 6 is it is characterised in that each mistake topic of described statistics is as the similar frequency inscribed and occur
Including:
For any one mistake topic a in each mistake topic, when wrong topic a is similar topic with another one wrong topic b, by wrong topic a with
The frequency of occurrences of wrong topic b all adds one.
8. method according to claim 4 is it is characterised in that described screening conditions are:
The frequency of occurrences is more than or equal to the wrong topic of the entitled high frequency of mistake of Second Threshold.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610662969.4A CN106339965A (en) | 2016-08-12 | 2016-08-12 | Learning situation analysis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610662969.4A CN106339965A (en) | 2016-08-12 | 2016-08-12 | Learning situation analysis method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106339965A true CN106339965A (en) | 2017-01-18 |
Family
ID=57824719
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610662969.4A Pending CN106339965A (en) | 2016-08-12 | 2016-08-12 | Learning situation analysis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106339965A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106897767A (en) * | 2017-03-03 | 2017-06-27 | 盐城工学院 | Automatic volume group method and device |
| CN108280184A (en) * | 2018-01-23 | 2018-07-13 | 广东小天才科技有限公司 | A kind of examination question extracts method, system and smart pen based on smart pen |
| CN110348757A (en) * | 2019-07-18 | 2019-10-18 | 广东爱贝佳科技有限公司 | A kind of the Assessment of Learning Effect method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102360419A (en) * | 2011-09-28 | 2012-02-22 | 广东启明科技发展有限公司 | Method and system for computer scanning reading management |
| CN105224665A (en) * | 2015-09-30 | 2016-01-06 | 广东小天才科技有限公司 | A kind of wrong topic management method and system |
| CN105354775A (en) * | 2015-10-28 | 2016-02-24 | 广东小天才科技有限公司 | Error analyzing method and system |
-
2016
- 2016-08-12 CN CN201610662969.4A patent/CN106339965A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102360419A (en) * | 2011-09-28 | 2012-02-22 | 广东启明科技发展有限公司 | Method and system for computer scanning reading management |
| CN105224665A (en) * | 2015-09-30 | 2016-01-06 | 广东小天才科技有限公司 | A kind of wrong topic management method and system |
| CN105354775A (en) * | 2015-10-28 | 2016-02-24 | 广东小天才科技有限公司 | Error analyzing method and system |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106897767A (en) * | 2017-03-03 | 2017-06-27 | 盐城工学院 | Automatic volume group method and device |
| CN108280184A (en) * | 2018-01-23 | 2018-07-13 | 广东小天才科技有限公司 | A kind of examination question extracts method, system and smart pen based on smart pen |
| CN108280184B (en) * | 2018-01-23 | 2021-06-01 | 广东小天才科技有限公司 | Test question extracting method and system based on intelligent pen and intelligent pen |
| CN110348757A (en) * | 2019-07-18 | 2019-10-18 | 广东爱贝佳科技有限公司 | A kind of the Assessment of Learning Effect method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11790641B2 (en) | Answer evaluation method, answer evaluation system, electronic device, and medium | |
| US11410407B2 (en) | Method and device for generating collection of incorrectly-answered questions | |
| CN108304793B (en) | Online learning analysis system and method | |
| CN109697905A (en) | A kind of exam paper marking system | |
| CN110097094B (en) | Multiple semantic fusion few-sample classification method for character interaction | |
| CN112115736B (en) | Job correction method and system based on image recognition and intelligent terminal | |
| CN111046819B (en) | Behavior recognition processing method and device | |
| CN106909682A (en) | Test library design method and system | |
| CN105224665A (en) | A kind of wrong topic management method and system | |
| CN111144079B (en) | Method and device for intelligently acquiring learning resources, printer and storage medium | |
| CN108234610A (en) | A kind of classroom interaction and reponse system | |
| US20240005813A1 (en) | Method and apparatus of diagnostic test | |
| CN105427696A (en) | Method for distinguishing answer to target question | |
| CN106898173A (en) | The online review system in real time of students' work | |
| CN107016022A (en) | Teaching difficulty big data analysis system | |
| CN105225563A (en) | A kind of learning data recommend method, device and Wearable facility for study | |
| CN113537801B (en) | Blackboard writing processing method, blackboard writing processing device, terminal and storage medium | |
| KR20170021101A (en) | A smart studying apparatus, a method, and a computer readable storage medium for providing an user with scoring and studying information | |
| CN106339965A (en) | Learning situation analysis method | |
| CN112580503A (en) | Operation correction method, device, equipment and storage medium | |
| CN111932418B (en) | Student learning condition identification method and system, teaching terminal and storage medium | |
| CN113159014A (en) | Objective question reading method, device, equipment and storage medium based on handwritten question numbers | |
| CN112116840B (en) | Job correction method and system based on image recognition and intelligent terminal | |
| KR101996247B1 (en) | Method and apparatus of diagnostic test | |
| CN114443898B (en) | Video big data pushing method for Internet intelligent education |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170118 |