CN108985300A - A kind of automatic marking papers system based on Wunsch algorithm - Google Patents
A kind of automatic marking papers system based on Wunsch algorithm Download PDFInfo
- Publication number
- CN108985300A CN108985300A CN201810704559.0A CN201810704559A CN108985300A CN 108985300 A CN108985300 A CN 108985300A CN 201810704559 A CN201810704559 A CN 201810704559A CN 108985300 A CN108985300 A CN 108985300A
- Authority
- CN
- China
- Prior art keywords
- answer
- module
- syntagma
- answer module
- wunsch algorithm
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Abstract
The present invention relates to field of computer technology, especially a kind of automatic marking papers system based on Wunsch algorithm.Including answer module, answer module and identification module, the syntagma of answer module and answer module is identified by the NPL character recognition tools of identification module；The answer module and answer module include syntagma and separate punctuate, and syntagma carries out number of words by separation sign point and level separates setting.Syntagma is convenient for examinee's answer and NPL character recognition after separating, and the compartmentation for separating punctuate is particularly suitable for Chinese context, convenient for examinee with reference to answer after the paragraph of font complexity, semantic multiplicity is separated.
Description
Technical field
The present invention relates to field of computer technology, especially a kind of automatic marking papers system based on Wunsch algorithm.
Technical background
With the fast development of information technology, the automatic scoring advantage of computer is outstanding day by day, and computer subjective item is automatic
Scoring can reduce the investment consumption of the huge manpower financial capacity of tradition examination, save human cost, computer reads and appraises subjective item automatically
Effort analysis caused by due to the subjective factor for the people that gos over examination papers can also be avoided, artificial nature's Language Processing (NLP) technology is sent out at present
Exhibition is swift and violent, and more and more Language Processing schemes are applied to Domestic News, e-commerce, community's product, Internet advertising, search
Using etc., but since Chinese font is complicated, semantic various, natural language processing technique is applied to traditional large-scale examination and is still deposited
In some problems.
Summary of the invention
The present invention solve prior art deficiency provide a kind of recognition efficiency it is high, it is convenient to carry out based on Wunsch algorithm from
Dynamic marking system.
The technical solution adopted by the present invention to solve the technical problems are as follows:
A kind of automatic marking papers system based on wunsch algorithm, including answer module, answer module and identification module, answer module
It is identified with the syntagma of answer module by the NPL character recognition tools of identification module；The answer module and answer module include
Syntagma and separation punctuate, syntagma carries out number of words by separation sign point and level separates setting.
Setting prompt keyword and blank answer word in the syntagma of the answer module.
A kind of application method of the automatic marking papers system based on wunsch algorithm, includes the following steps:
A, the syntagma of answer module and answer module carries out number of words by separation sign point and level separates；
B, the syntagma of answer module and answer module is identified by the NPL character recognition tools of identification module, answer module
It is compared with the character of answer module identification；
C, calculating is compared to answer character and answer character by wunsch algorithm, calculates character percent similarity；
D, percent similarity obtains the topic final score multiplied by topic score value.
Setting prompt keyword in the syntagma of answer module in the step A.
The invention has the benefit that
1, a kind of automatic marking papers system based on wunsch algorithm, including answer module, answer module and identification module, answer mould
The syntagma of block and answer module is identified by the NPL character recognition tools of identification module；The answer module and answer module packet
It includes syntagma and separates punctuate, syntagma carries out number of words by separation sign point and level separates setting.Syntagma is answered after separating convenient for examinee
Topic and NPL character recognition, the compartmentation for separating punctuate are particularly suitable for Chinese context, the paragraph of font is complicated, semantic multiplicity
Answer is referred to after separation convenient for examinee.
2, setting prompt keyword and blank answer word in the syntagma of the answer module.Prompt is set in long section syntagma
Keyword prompts keyword to be interspersed in prompt answer specification in paragraph.Examinee answers on blank answer word.The present invention realizes
The approximate scoring of subjective item, can fast implement the approximate evaluation of answer.Reduce the subjectivity artificially goed over examination papers, it can be quick
The systems of going over examination papers such as on probation and paper self-test assessment.
Specific embodiment
A kind of automatic marking papers system based on wunsch algorithm, including answer module, answer module and identification module, answer
The syntagma of module and answer module is identified by the NPL character recognition tools of identification module；The answer module and answer module
Including syntagma and separate punctuate, syntagma carries out number of words by separation sign point and level separates setting.
Setting prompt keyword and blank answer word in the syntagma of the answer module.
A kind of application method of the automatic marking papers system based on wunsch algorithm, includes the following steps:
A, the syntagma of answer module and answer module carries out number of words by separation sign point and level separates；
B, the syntagma of answer module and answer module is identified by the NPL character recognition tools of identification module, answer module
It is compared with the character of answer module identification；
C, calculating is compared to answer character and answer character by wunsch algorithm, calculates character percent similarity；
D, percent similarity obtains the topic final score multiplied by topic score value.
Setting prompt keyword in the syntagma of answer module in the step A.
Embodiment 1
Answer module is that double knee joint group skeletonization has no obvious fracture and dislocation.Answer is separated by " ", " " is
Separator is one of, and general symbol can be used.Score value is 10 points.Answer module is answered to be had no for double knee joint formation bone
Significant fracture and dislocation.Due to reading and making comments quantity and subjective human factor when group signature, wherein organizing skeletonization and forming bone, have no
It is obvious and have no and significantly will appear the inconsistent situation of score.Answer character and answer character are compared by wunsch algorithm
To calculating, character percent similarity is calculated, 16 word of answer number of words answers questions 13 words, character percent similarity 0.8125, this subject score
8.125 point.Retain scale according to traditional marking mode or rounds up.
Embodiment 2
Answer module is that left elbow joint group skeletonization has no that obvious fracture and the dislocation left ruler of scratch bone and have no the left wrist joint of sclerotin change
Group skeletonization has no that obvious fracture and dislocation are separated answer by " ", and " " is that separator is one of, general symbol
It can be used.Score value is 10 points.Answer module is left elbow jointObviously.Have no sclerotin changeIt has no.
The specification answer by way of setting prompt keyword and separator.Answer is left elbow jointBone is formed not seeObviouslyIt fractures and de- Position.Left ruler scratches boneHave no sclerotin changeLeft wrist joint group skeletonizationIt has no obvious fracture and dislocation 21 word of answer number of words, answers questions 19
Word, character percent similarity 0.9047, this subject score 9.047 are divided.Automatic marking assessment subjective item score function is applicable to
A large amount of paper can reduce the heavier workload of going over examination papers of teacher, can also be generalized to other from survey and subjective item scoring test
Type is goed over examination papers and is checked and rated in test.The subjectivity goed over examination papers is greatly reduced, the objectivity of subjective question marking is improved, is reduced
Artificial subjectivity.
Claims (4)
1. a kind of automatic marking papers system based on wunsch algorithm, including answer module, answer module and identification module, answer mould
The syntagma of block and answer module is identified by the NPL character recognition tools of identification module；It is characterized in that the answer module and
Answer module includes syntagma and separates punctuate, and syntagma carries out number of words by separation sign point and level separates setting.
2. a kind of automatic marking papers system based on wunsch algorithm according to claim 1, it is characterised in that the answer
Setting prompt keyword and blank answer word in the syntagma of module.
3. a kind of application method of automatic marking papers system based on wunsch algorithm according to claim 1 or 2, feature
It is to include the following steps:
A, the syntagma of answer module and answer module carries out number of words by separation sign point and level separates；
B, the syntagma of answer module and answer module is identified by the NPL character recognition tools of identification module, answer module
It is compared with the character of answer module identification；
C, calculating is compared to answer character and answer character by wunsch algorithm, calculates character percent similarity；
D, percent similarity obtains the topic final score multiplied by topic score value.
4. a kind of application method of automatic marking papers system based on wunsch algorithm according to claim 3, feature exist
The setting prompt keyword in the syntagma of answer module in the step A.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810704559.0A CN108985300A (en) | 2018-07-01 | 2018-07-01 | A kind of automatic marking papers system based on Wunsch algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810704559.0A CN108985300A (en) | 2018-07-01 | 2018-07-01 | A kind of automatic marking papers system based on Wunsch algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108985300A true CN108985300A (en) | 2018-12-11 |
Family
ID=64539168
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810704559.0A Pending CN108985300A (en) | 2018-07-01 | 2018-07-01 | A kind of automatic marking papers system based on Wunsch algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108985300A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112036343A (en) * | 2020-09-04 | 2020-12-04 | 北京字节跳动网络技术有限公司 | Answer extraction method and device, computer readable medium and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140199676A1 (en) * | 2013-01-11 | 2014-07-17 | Educational Testing Service | Systems and Methods for Natural Language Processing for Speech Content Scoring |
| CN103955874A (en) * | 2014-03-31 | 2014-07-30 | 西南林业大学 | Automatic subjective-question scoring system and method based on semantic similarity interval |
| CN104268603A (en) * | 2014-09-16 | 2015-01-07 | 科大讯飞股份有限公司 | Intelligent marking method and system for text objective questions |
| US9767094B1 (en) * | 2016-07-07 | 2017-09-19 | International Business Machines Corporation | User interface for supplementing an answer key of a question answering system using semantically equivalent variants of natural language expressions |
| CN107977637A (en) * | 2017-12-11 | 2018-05-01 | 上海启思教育科技服务有限公司 | A kind of intelligently reading system of more topic types |
-
2018
- 2018-07-01 CN CN201810704559.0A patent/CN108985300A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140199676A1 (en) * | 2013-01-11 | 2014-07-17 | Educational Testing Service | Systems and Methods for Natural Language Processing for Speech Content Scoring |
| CN103955874A (en) * | 2014-03-31 | 2014-07-30 | 西南林业大学 | Automatic subjective-question scoring system and method based on semantic similarity interval |
| CN104268603A (en) * | 2014-09-16 | 2015-01-07 | 科大讯飞股份有限公司 | Intelligent marking method and system for text objective questions |
| US9767094B1 (en) * | 2016-07-07 | 2017-09-19 | International Business Machines Corporation | User interface for supplementing an answer key of a question answering system using semantically equivalent variants of natural language expressions |
| CN107977637A (en) * | 2017-12-11 | 2018-05-01 | 上海启思教育科技服务有限公司 | A kind of intelligently reading system of more topic types |
Non-Patent Citations (2)
| Title |
|---|
| 刘伟 等: "主观题自动测评研究", 《北京邮电大学学报( 社会科学版)》 * |
| 孙润志: "基于语义理解的文本相似度计算研究与实现", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112036343A (en) * | 2020-09-04 | 2020-12-04 | 北京字节跳动网络技术有限公司 | Answer extraction method and device, computer readable medium and electronic equipment |
| CN112036343B (en) * | 2020-09-04 | 2022-02-08 | 北京字节跳动网络技术有限公司 | Answer extraction method and device, computer readable medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107562918A (en) | A kind of mathematical problem knowledge point discovery and batch label acquisition method | |
| CN108121702B (en) | Method and system for evaluating and reading mathematical subjective questions | |
| CN106503255A (en) | Based on the method and system that description text automatically generates article | |
| CN109299480A (en) | Terminology Translation method and device based on context of co-text | |
| CN106815194A (en) | Model training method and device and keyword recognition method and device | |
| CN103955874A (en) | Automatic subjective-question scoring system and method based on semantic similarity interval | |
| CN109388700A (en) | A kind of intension recognizing method and system | |
| CN106205609A (en) | A kind of based on audio event and the audio scene recognition method of topic model and device | |
| CN110427609A (en) | One kind writing people's composition structure of an article reasonability method for automatically evaluating | |
| CN103336832A (en) | Video classifier construction method based on quality metadata | |
| CN101980210A (en) | Marked word classifying and grading method and system | |
| CN111309891B (en) | System for reading robot to automatically ask and answer questions and application method thereof | |
| CN106096609A (en) | A kind of merchandise query keyword automatic generation method based on OCR | |
| CN106227836B (en) | Unsupervised joint visual concept learning system and unsupervised joint visual concept learning method based on images and characters | |
| CN105183808A (en) | Problem classification method and apparatus | |
| CN104347071B (en) | Method and system for generating reference answers of spoken language test | |
| CN104966075A (en) | Face recognition method and system based on two-dimensional discriminant features | |
| CN108985300A (en) | A kind of automatic marking papers system based on Wunsch algorithm | |
| CN109346108A (en) | A kind of review of operations method and system | |
| Wiza et al. | Classification Analysis Using C4. 5 Algorithm To Predict The Level of Graduation of Nurul Falah Pekanbaru High School Students | |
| CN111079582A (en) | Image recognition English composition running question judgment method | |
| CN108932289A (en) | One kind being based on the problem of information extraction and deep learning answer treatment method and system | |
| CN112163768A (en) | Chinese reading scoring method and system | |
| Chiranjeevi et al. | Finding and classifying the deceptive spam reviews using LIWC dictionary variables and decision tree classifier | |
| CN109460447A (en) | A kind of soft literary recognition methods of marketing |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181211 |