CN115564606A - Intelligent marking method suitable for judicial examination subjective questions - Google Patents
Intelligent marking method suitable for judicial examination subjective questions Download PDFInfo
- Publication number
- CN115564606A CN115564606A CN202211016577.2A CN202211016577A CN115564606A CN 115564606 A CN115564606 A CN 115564606A CN 202211016577 A CN202211016577 A CN 202211016577A CN 115564606 A CN115564606 A CN 115564606A
- Authority
- CN
- China
- Prior art keywords
- score
- scoring
- standard
- answers
- question
- 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 33
- 238000004140 cleaning Methods 0.000 claims abstract description 4
- 238000004364 calculation method Methods 0.000 claims description 23
- 238000010276 construction Methods 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000014509 gene expression Effects 0.000 description 2
- 235000019580 granularity Nutrition 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Images
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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Technology Law (AREA)
- Mathematical Physics (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention relates to an intelligent examination paper reading method suitable for judicial examination subjective questions, which comprises the following steps: the standard answers of each subjective question are input into a database of an automatic paper marking system, then the answers of the test papers are imported into the system in batches, after the automatic paper marking system collects text information of the test papers, a scoring unit carries out data cleaning on the text information and then compares the text information with the standard answers in the database, and therefore the total score of each scoring point is obtained, and intelligent paper marking is achieved. The automatic scoring system is used for extracting the keywords on the answer sheet, the keywords are compared with the standard answers in the database through the scoring unit, and therefore the total score of each score point of different questions is calculated.
Description
Technical Field
The invention relates to the technical field of computer-aided paper marking, in particular to an intelligent paper marking method suitable for judicial examination subjective questions.
Background
In the prior art, when examination papers of subjective questions of judicial examinations are reviewed, a manual examination paper reviewing mode is generally adopted. Before reading the examination paper, a plurality of teachers are summoned to judge the examination paper, the examination paper of the subjective questions of the examinees is read one by one after the examination paper is referred to the standard answers, and the score is given according to the similarity degree of the standard answers. However, the manual paper marking mode has strong subjective awareness, different answer scores of subjective test papers are different due to different professional abilities of teachers, so that the final score is unreasonable, time and labor are wasted, and the efficiency is extremely low.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide an intelligent marking method suitable for judicial examination subjective questions, which utilizes an automatic marking system to extract key words on an answer sheet and compares the key words with standard answers in a database through a scoring unit so as to calculate the total score of each score point of different questions.
The above object of the present invention is achieved by the following technical solutions:
an intelligent marking method suitable for judicial examination subjective questions comprises the following steps: the standard answers of each subjective question are input into a database of an automatic paper marking system, then the answers of the test papers are imported into the system in batches, after the automatic paper marking system collects text information of the test papers, a marking unit carries out data cleaning on the text information and then compares the text information with the standard answers in the database, and therefore the total score of each point is obtained, and intelligent paper marking is achieved.
The present invention in a preferred example may be further configured to: the scoring unit comprises a scoring standard library and a similarity calculation module, the scoring standard library is connected with the database and is used for calculating the similarity between an answer text of an examinee and an answer text of a test question standard;
the similarity calculation module is connected with the scoring standard library and used for performing strip matching on the answers of the examinees and the scoring points, calculating and accumulating scores to obtain a final scoring result.
The present invention in a preferred example may be further configured to: the design method of the scoring standard library comprises the following steps:
a1, giving a plurality of different answers aiming at a specific question, wherein the number of each standard answer is respectively marked as al, a2, … … at, and the standard answer can be a standard answer provided by a question giving teacher or a full-mark answer of an examinee in an existing question bank;
a2, summarizing a plurality of score main points aiming at a standard answer at, wherein the number of each score main point is respectively marked as al1, al2, … at-n, if only the at-n is equivalently stated, the score main points are numbered in the forms of at-n-1, at-n2, … … at-n-s (s is more than or equal to 1);
a3, extracting a plurality of keywords aiming at a certain score principal point at-n, wherein the number of each keyword is at-n.1, at-n.2 … … at-n.m (m is more than or equal to 1), and the keyword number of the score principal point at-n-s expressed equivalently is in the form of at-n-s.1 and at-n-s.2 … ….
The present invention in a preferred example may be further configured to: in step a2, the corresponding score proportion is given for the importance degree of each scoring point, the score proportion of all the scoring points is less than or equal to 100%, and the scoring points provided by the scoring teacher are equivalent statements of a certain existing scoring point.
The present invention in a preferred example may be further configured to: the construction method of the scoring standard library comprises the following steps:
s1, artificial construction: marking standard answers and answers of full-scale examinees in a question bank in an artificial marking mode in an initial stage of building a scoring standard bank, wherein standard contents comprise scoring key points, weights of the scoring key points and scoring key words;
s2, semi-automatic construction: when the scoring standard library is accumulated to a certain scale, the scoring standard library is expanded by manually marking the historical question library in a machine-assisted manner in a semi-automatic manner;
s3, automatic construction: when the scale of the answer key point library is large enough, and the accuracy of the recommendation of the score key points and the score keywords meets the requirements of an automatic marking system, a mode of automatically constructing the answer key point library without manual intervention is adopted;
and giving a question according to the structure of the automatic scoring standard library, and scoring according to the t standard answers by using an automatic scoring algorithm respectively to select the highest score in the t scoring results as an automatic scoring result.
The invention in a preferred example may be further configured to: the similarity calculation module is connected with a score coefficient calculation module, the score coefficient calculation module is connected with a final score calculation module, and the score coefficient calculation module is used for calculating the score coefficient of the subjective question by using a basic score equation corresponding to the question stem data and the semantic similarity value;
and the final score calculating module is used for calculating a final score, and the final score is the product of the score coefficient and the total score of the subjective questions.
The invention in a preferred example may be further configured to: if the similarity value is [0.9,1], the score of the title is full score;
if the similarity value is [0.7,0.9 ], the title score is 80% of full score;
if the similarity value is [0.3,0.7 ], the score of the title is 50% of full score;
if the similarity is vertical [0,0.3), the title is given a score of zero.
In summary, the invention includes at least one of the following beneficial technical effects:
1. the invention discloses an intelligent marking method suitable for subjective questions of judicial examinations, which utilizes an automatic marking system to extract key words on an answer sheet and compares the key words with standard answers in a database through a scoring unit so as to calculate the total score of each score point of different questions, compared with a manual marking mode, the intelligent marking method not only improves the marking efficiency, but also ensures that the judged score is more reasonable and accurate, and avoids the problem that the marking is inaccurate and unreasonable due to the subjective consciousness of a marking teacher;
the intelligent marking method combines a short text similarity calculation method for manually establishing text similarity standards, term sets, term sequences and synonyms, designs and realizes a corresponding text subjective question marking system, establishes a test question manual marking standard library, achieves the same text automatic marking result as compared with a manual marking result by 59 percent, and achieves the accuracy rate of about 85 percent.
Drawings
FIG. 1 is a schematic flow diagram of the present invention.
FIG. 2 is a logical relationship diagram showing the design of a scoring criteria library according to the present invention.
FIG. 3 is a logical relationship diagram showing the construction of a scoring criteria library according to the present invention.
Detailed Description
The technical solution in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application; it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all embodiments, and all other embodiments obtained by those of ordinary skill in the art without any inventive work based on the embodiments in the present application belong to the protection scope of the present application.
In the description of the present application, it should be noted that the terms "upper", "lower", "inner", "outer", "top/bottom", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplification of description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus should not be construed as limiting the present application. Furthermore, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present application, it is to be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "disposed," "sleeved/connected," "connected," and the like are to be construed broadly, e.g., "connected," which may be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in this application will be understood to be a specific case for those of ordinary skill in the art.
The first embodiment is as follows:
referring to fig. 1, the intelligent examination paper reading method for the judicial examination subjective questions disclosed by the invention comprises the following steps: the standard answers of each subjective question are input into a database of an automatic paper marking system, then the answers of the test papers are led into the system in batches, after the automatic paper marking system collects text information of the test papers, a scoring unit carries out data cleaning on the text information and then compares the text information with the standard answers in the database, and therefore the total score of each scoring point is obtained, and intelligent paper marking is achieved.
In the text examination paper field, because text answers such as short-cut answers and discussion questions are short, how to calculate the similarity between the examinee answers and the standard answers is the key for determining automatic scoring. Natural language meaning has different granularities, such as words, phrases, sentences, segments, sections, chapters, documents, and so on.
A word/word may be viewed as the smallest unit of meaning in natural language-a phrase may be a combination of one or more words and a sentence is a unit of text that can convey a more complete meaning. A sentence is divided into many units of significance by punctuation marks such as commas and semicolons. In addition to spoken language, a sentence in written text is typically composed of a plurality of words and punctuation marks. Accordingly, there are different levels of similarity for natural language processing text units: the similarity between words and phrases may divide words into synonyms and antonyms; similarity exists between two documents and the similarity between the documents is the basis of text classification and clustering; the similarity of sentences is between the similarity of words and the similarity of documents. The similarity of texts with different granularities can be calculated in different ways.
The scoring unit comprises a scoring standard library and a similarity calculation module, the scoring standard library is connected with the database, and the scoring standard library is used for calculating the similarity between the answer text of the examinee and the answer text of the test question standard. The similarity calculation module is connected with the scoring standard library and used for carrying out segmentation matching on the examinee answers and the score points, calculating and accumulating scores and obtaining the final scoring result.
If the similarity value is [0.9,1], the score of the title is full score;
if the similarity value is [0.7,0.9 ], the title score is 80% of full score;
if the similarity value is [0.3,0.7 ], the score of the title is 50% of full score;
if the similarity is vertical [0,0.3), the title is given a score of zero.
If the answer text of the examinee is the same as the answer text of the test question standard, the similarity is 1; if the answer of the examinee is not coherent with the standard answer of the test question, the similarity is 0; generally, the similarity between the answers of the examinees and the answer of the test question standard is between 0 and 1, and the higher the similarity between the answers and the answer of the test question standard is, the higher the score of the examinees is.
Since a plurality of answers to a question may be presented in a text test question, the scoring of a plurality of standard answers is considered in text scoring. When a text test is scored, a question master is generally required to give scoring standards, and each scoring standard can have various different representations due to the diversity of language expressions. And matching and calculating the answer of the test taker with the score standard to obtain the score of the test taker. Therefore, the design method of the scoring standard library comprises the following steps:
a1, giving a plurality of different answers aiming at a specific question, wherein the number of each standard answer is respectively marked as al, a2, … … at, and the standard answer can be a standard answer provided by a question giving teacher or a full-mark answer of an examinee in an existing question bank;
a2, summarizing a plurality of scoring main points aiming at a standard answer at, wherein the number of each scoring main point is respectively marked as al1, al2, … at-n, if at-n is equivalently stated, the scoring main points are numbered in the forms of at-n-1, at-n2, … … at-n-s (s is more than or equal to 1) to represent the equivalence with at-n, and referring to fig. 2, the scoring main points a1-1-1 of the answer a1 are equivalent expressions of a 1-1;
a3, extracting a plurality of keywords aiming at a certain score principal point at-n, wherein the number of each keyword is at-n.1, at-n.2 … … at-n.m (m is more than or equal to 1), and the keyword number of the score principal point at-n-s expressed equivalently is in the form of at-n-s.1 and at-n-s.2 … ….
In step a2, the corresponding score proportion is given for the importance degree of each scoring point, the score proportion of all the scoring points is less than or equal to 100%, and the scoring points provided by the scoring teacher are equivalent statements of a certain existing scoring point.
A large amount of examination questions and answer information of examinees are accumulated in a question bank of an existing examination system, a grading standard bank can be established by utilizing historical data, standard answers provided by a question teacher and full-mark answers of the examinees are used as standard answers to be processed, and therefore a large-scale grading standard bank is established.
Referring to fig. 3, the method for constructing the scoring criteria library includes the following steps:
s1, artificial construction: marking standard answers and answers of full-scale examinees in a question bank in an artificial marking mode in an initial stage of building a scoring standard bank, wherein standard contents comprise scoring key points, weights of the scoring key points and scoring key words;
s2, semi-automatic construction: when the scoring standard library is accumulated to a certain scale, the scoring standard library is expanded by manually marking the historical question library in a machine-assisted manner in a semi-automatic manner;
further, the semi-automatic construction of the scoring standard library comprises the following steps:
and calculating the weight of each keyword by using a statistical method for the scoring keywords in the existing scoring standard library. The weights of the words can be calculated for different levels of a certain field, a single topic or a certain knowledge point topic. And counting the frequency of the specific word appearing in the standard answers of the whole question bank and the frequency of the specific word appearing in the text test questions according to a certain field, and calculating the weight of the word by using TFIDF.
And counting the frequency and the occurrence times of related keywords in different standard answers aiming at a single question, and calculating the word weight by using TFIDF. If several test questions are around one knowledge point, the association degree of the words and the knowledge point can be calculated around the knowledge point and then is normalized to be used as the word weight. One method is to use TF-IDF; and the other method is that the correlation degree of the key words and the knowledge points is calculated by utilizing mutual information, and then normalization is carried out to be used as the weight of the key words.
And performing score principal point and score keyword recommendation on the answers in the historical question bank by using the keyword weight.
And manually selecting score key points and score keywords, and submitting the score key points and the score keywords to a score standard library. The recommendation scheme for scoring the main points is as follows: the point of score is typically a sentence. Firstly, word segmentation and keyword recognition are carried out on a sentence, and the weight of the sentence is calculated by utilizing the weight of the keyword. After the weight of each sentence in the standard answers is calculated, one or more sentences with the highest weight are selected from all the sentences to be recommended as key points of answer, and the recommended weight (calculated according to the condition of the keywords in the sentences) of the key points in the recommended key points is given.
For the answer key point information submitted to the scoring standard library, the answer key point information can be used for updating the weight of the keyword so as to improve the accuracy of scoring key points and scoring keyword recommendation.
S3, automatic construction: when the scale of the answer key point library is large enough, and the accuracy of the recommendation of the score key points and the score keywords meets the requirements of an automatic marking system, a mode of automatically constructing the answer key point library without manual intervention is adopted;
and giving a question according to the structure of the automatic scoring standard library, and scoring according to the t standard answers by using an automatic scoring algorithm respectively to select the highest score in the t scoring results as an automatic scoring result.
The similarity calculation module is connected with a score coefficient calculation module, the score coefficient calculation module is connected with a final score calculation module, and the score coefficient calculation module is used for calculating the score coefficient of the subjective question by using a basic score equation and a semantic similarity value corresponding to the question stem data. And the final score calculating module is used for calculating a final score, and the final score is the product of the score coefficient and the total score of the subjective questions.
The implementation principle of the embodiment is as follows: the invention discloses an intelligent marking method suitable for subjective questions of judicial examinations, which utilizes an automatic marking system to extract key words on an answer sheet and compares the key words with standard answers in a database through a scoring unit so as to calculate the total score of each score point of different questions, compared with a manual marking mode, the intelligent marking method not only improves the marking efficiency, but also ensures that the judged score is more reasonable and accurate, and avoids the problem that the marking is inaccurate and unreasonable due to the subjective consciousness of a marking teacher;
the intelligent marking method combines a short text similarity calculation method for manually establishing text similarity standards, term sets, term sequences and synonyms, designs and realizes a corresponding text subjective question marking system, establishes a test question manual marking standard library, achieves the same text automatic marking result as compared with a manual marking result by 59 percent, and achieves the accuracy rate of about 85 percent.
The embodiments of the present invention are preferred embodiments of the present invention, and the scope of the present invention is not limited by these embodiments, so: all equivalent changes made according to the structure, shape and principle of the invention are covered by the protection scope of the invention.
Claims (7)
1. An intelligent marking method suitable for judicial examination subjective questions is characterized in that: the method comprises the following steps: the standard answers of each subjective question are input into a database of an automatic paper marking system, then the answers of the test papers are imported into the system in batches, after the automatic paper marking system collects text information of the test papers, a marking unit carries out data cleaning on the text information and then compares the text information with the standard answers in the database, and therefore the total score of each point is obtained, and intelligent paper marking is achieved.
2. The intelligent examination paper reading method suitable for the judicial examination subjective questions according to claim 1, wherein the intelligent examination paper reading method comprises the following steps: the scoring unit comprises a scoring standard library and a similarity calculation module, the scoring standard library is connected with the database, and the scoring standard library is used for calculating the similarity between the answer text of the examinee and the answer text of the test question standard;
the similarity calculation module is connected with the scoring standard library and used for performing segmentation matching on the answers of the examinees and the scoring points, calculating and accumulating scores to obtain the final scoring result.
3. The intelligent examination paper reading method suitable for the judicial examination subjective questions according to claim 2, wherein the intelligent examination paper reading method comprises the following steps: the design method of the scoring standard library comprises the following steps:
a1, giving a plurality of different answers aiming at a specific question, wherein the number of each standard answer is respectively marked as al, a2, … … at, and the standard answer can be a standard answer provided by a question giving teacher or a full-mark answer of an examinee in an existing question bank;
a2, summarizing a plurality of score main points aiming at a standard answer at, wherein the number of each score main point is respectively marked as al1, al2, … at-n, if only the at-n is equivalently stated, the score main points are numbered in the forms of at-n-1, at-n2, … … at-n-s (s is more than or equal to 1);
a3, extracting a plurality of keywords aiming at a certain score principal point at-n, wherein the number of each keyword is at-n.1, at-n.2 … … at-n.m (m is more than or equal to 1), and the keyword number of the score principal point at-n-s expressed equivalently is in the form of at-n-s.1 and at-n-s.2 … ….
4. The intelligent examination paper reading method suitable for the judicial examination subjective questions according to claim 3, wherein the intelligent examination paper reading method comprises the following steps: in step a2, the corresponding score proportion is given for the importance degree of each scoring point, the score proportion of all the scoring points is less than or equal to 100%, and the scoring points provided by the scoring teacher are equivalent statements of a certain existing scoring point.
5. The intelligent examination paper reading method suitable for the judicial examination subjective questions according to claim 2, wherein the intelligent examination paper reading method comprises the following steps: the construction method of the scoring standard library comprises the following steps:
s1, artificial construction: marking standard answers and answers of full-scale examinees in a question bank in an artificial marking mode in an initial stage of building a scoring standard bank, wherein standard contents comprise scoring key points, weights of the scoring key points and scoring key words;
s2, semi-automatic construction: when the scoring standard library is accumulated to a certain scale, the scoring standard library is expanded by manually marking the historical question library in a machine-assisted manner in a semi-automatic manner;
s3, automatic construction: when the scale of the answer key point library is large enough, and the accuracy of the recommendation of the score key points and the score keywords meets the requirements of an automatic marking system, a mode of automatically constructing the answer key point library without manual intervention is adopted;
and giving a question according to the structure of the automatic scoring standard library, and scoring according to the t standard answers by using an automatic scoring algorithm respectively to select the highest score in the t scoring results as an automatic scoring result.
6. The intelligent examination paper reading method suitable for the judicial examination subjective questions according to claim 2, wherein the intelligent examination paper reading method comprises the following steps: the similarity calculation module is connected with a score coefficient calculation module, the score coefficient calculation module is connected with a final score calculation module, and the score coefficient calculation module is used for calculating the score coefficient of the subjective question by using a basic score equation corresponding to the question stem data and the semantic similarity value;
and the final score calculating module is used for calculating a final score, and the final score is the product of the score coefficient and the total score of the subjective questions.
7. The intelligent examination paper reading method suitable for the judicial examination subjective questions according to claim 2, wherein the intelligent examination paper reading method comprises the following steps: if the similarity value is [0.9,1], the score of the title is full score;
if the similarity value is [0.7,0.9 ], the title score is 80% of full score;
if the similarity value is [0.3,0.7 ], the score of the title is 50% of full score;
if the similarity is vertical [0,0.3), the title is given a score of zero.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211016577.2A CN115564606A (en) | 2022-08-24 | 2022-08-24 | Intelligent marking method suitable for judicial examination subjective questions |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211016577.2A CN115564606A (en) | 2022-08-24 | 2022-08-24 | Intelligent marking method suitable for judicial examination subjective questions |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115564606A true CN115564606A (en) | 2023-01-03 |
Family
ID=84738362
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211016577.2A Pending CN115564606A (en) | 2022-08-24 | 2022-08-24 | Intelligent marking method suitable for judicial examination subjective questions |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115564606A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116610774A (en) * | 2023-07-20 | 2023-08-18 | 河北鑫考科技股份有限公司 | High-efficiency intelligent online paper reading auxiliary method and system |
-
2022
- 2022-08-24 CN CN202211016577.2A patent/CN115564606A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116610774A (en) * | 2023-07-20 | 2023-08-18 | 河北鑫考科技股份有限公司 | High-efficiency intelligent online paper reading auxiliary method and system |
| CN116610774B (en) * | 2023-07-20 | 2023-09-26 | 河北鑫考科技股份有限公司 | High-efficiency intelligent online paper reading auxiliary method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110147436B (en) | Education knowledge map and text-based hybrid automatic question-answering method | |
| CN109213999B (en) | Subjective question scoring method | |
| CN110096702B (en) | Subjective question scoring method and device | |
| Sukkarieh et al. | Automarking: using computational linguistics to score short ‚free− text responses | |
| US9959776B1 (en) | System and method for automated scoring of texual responses to picture-based items | |
| US8301640B2 (en) | System and method for rating a written document | |
| CN106570109B (en) | Method for automatically generating question bank knowledge points through text analysis | |
| KR20080021017A (en) | Comparing text based documents | |
| CN111914532A (en) | Chinese composition scoring method | |
| CN110472203B (en) | Article duplicate checking and detecting method, device, equipment and storage medium | |
| KR102484007B1 (en) | Method and system for estimating a reading index using automatic analysis program for text of korean language | |
| CN115130465A (en) | Method and system for identifying knowledge graph entity annotation error on document data set | |
| CN115564606A (en) | Intelligent marking method suitable for judicial examination subjective questions | |
| CN111767743B (en) | Machine intelligent evaluation method and system for translation test questions | |
| CN113934814A (en) | Automatic scoring method for subjective questions of ancient poetry | |
| CN114004218A (en) | NLP (non line segment) identification method aiming at government work report | |
| Bannò et al. | Cross-corpora experiments of automatic proficiency assessment and error detection for spoken English | |
| KR100583174B1 (en) | A Readablilty Indexing System based on Lexical Difficulty and Thesaurus | |
| CN113918708B (en) | Abstract extraction method | |
| CN114118097A (en) | Online comment emotion evaluation method and system for urban public space | |
| CN110674871B (en) | Translation-oriented automatic scoring method and automatic scoring system | |
| Sen et al. | Chinese automatic text simplification based on unsupervised learning | |
| CN112163768A (en) | Chinese reading scoring method and system | |
| Kuyoro et al. | Intelligent Essay Grading System using Hybrid Text Processing Techniques | |
| KR20210026285A (en) | Essay Auto Correction System And Method |
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 |