CN113408253A - Job review system and method - Google Patents
Job review system and method Download PDFInfo
- Publication number
- CN113408253A CN113408253A CN202110674243.3A CN202110674243A CN113408253A CN 113408253 A CN113408253 A CN 113408253A CN 202110674243 A CN202110674243 A CN 202110674243A CN 113408253 A CN113408253 A CN 113408253A
- Authority
- CN
- China
- Prior art keywords
- annotation
- semantic
- fuzzy
- word
- automatic
- 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
- 238000012552 review Methods 0.000 title claims abstract description 66
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000011156 evaluation Methods 0.000 claims abstract description 51
- 238000005516 engineering process Methods 0.000 claims abstract description 40
- 230000014509 gene expression Effects 0.000 claims abstract description 34
- 238000013135 deep learning Methods 0.000 claims abstract description 25
- 238000004891 communication Methods 0.000 claims abstract description 8
- 238000000605 extraction Methods 0.000 claims abstract description 4
- 238000012937 correction Methods 0.000 claims description 21
- 230000008901 benefit Effects 0.000 claims description 12
- 230000011218 segmentation Effects 0.000 claims description 8
- 230000007547 defect Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 230000001915 proofreading effect Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 abstract description 10
- 238000010586 diagram Methods 0.000 description 12
- 230000000694 effects Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/169—Annotation, e.g. comment data or footnotes
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
- G06F16/986—Document structures and storage, e.g. HTML extensions
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Machine Translation (AREA)
Abstract
The invention relates to an operation review system and method. The review system comprises: the operation extraction module is used for extracting the literal declarative operation by adopting a B/S architecture, an HTML5 technology and a COM automation technology; the automatic reading and amending analysis module is used for carrying out fuzzy semantic recognition on the word declarative operation according to fuzzy semantics in the reading and amending library and based on a fuzzy semantic locating recognition algorithm and a deep learning semantic vector similarity recognition algorithm of a regular expression to determine an analysis result; the automatic annotation module is used for automatically adding automatic annotation sentences in the review library to the word declarative operation according to the analysis result based on a regular expression fuzzy semantic positioning recognition algorithm and an Ajax asynchronous communication technology, and generating annotation categories according to the annotation sentences; and the automatic total evaluation module is used for generating a total evaluation report according to the annotation category by utilizing a deep learning semantic vector similarity recognition algorithm. The invention solves the problems of complicated process and difficult statistics of manual reading and amending.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to an operation review system and an operation review method.
Background
The correction of the post-lesson homework or the experimental report is the examination and evaluation of the teacher on the classroom theory or experimental learning condition of the students, and is an important learning feedback process. Teachers obtain teaching feedback information through homework correction, diagnose classroom teaching effects, know learning conditions of students, solve problems of the students at any time and lay a foundation for subsequent teaching work; students can correct wrong thinking ways or methods in time from returning the wholesale homework or report inspection. Therefore, the correction of post-school homework or experimental reports is an important link of school teaching work, but the conventional method has the common problems of long time consumption and difficult statistics.
With the acceleration of the networked teaching process, more and more schools adopt paperless operation and paperless experimental reports. Students submit post-lesson homework or experimental reports through the network, the mailbox and other modes, and the teacher downloads the reports and returns the reports to the students after manual correction, which improves the convenience of submitting the reports by the students but does not release the teachers from the heavy homework correction task. Especially, the operations mainly based on the text statements, such as brief answers, questions and answers, experimental reports, etc., must be reviewed manually, which is complicated in process and difficult in statistics.
Disclosure of Invention
The invention aims to provide an operation review system and an operation review method, which are used for solving the problems of complicated manual review process and difficult statistics.
In order to achieve the purpose, the invention provides the following scheme:
a job review system comprising:
the operation extraction module is used for extracting the literal declarative operation by adopting a B/S architecture, an HTML5 technology and a COM automation technology;
the automatic reading and amending analysis module is used for carrying out fuzzy semantic recognition on the word declarative operation according to fuzzy semantics in the reading and amending library and based on a fuzzy semantic locating recognition algorithm and a deep learning semantic vector similarity recognition algorithm of a regular expression to determine an analysis result; the reading library comprises a plurality of fuzzy semantics, each fuzzy semantic corresponds to one or more automatic annotation sentences, and if one fuzzy semantic corresponds to a plurality of automatic annotation sentences, one of the automatic annotation sentences is randomly determined as an analysis result; the analysis results include errors, problems, advantages, and disadvantages in the literal declarative work;
the automatic annotation module is used for automatically adding automatic annotation sentences in the review library to the word declarative operation according to the analysis result based on a regular expression fuzzy semantic positioning recognition algorithm and an Ajax asynchronous communication technology, and generating annotation categories according to the annotation sentences; the annotation category comprises formats, contents and professional requirements corresponding to each annotation statement, such as format errors, content loss, content errors and non-compliance with professional requirements;
the automatic general evaluation module is used for generating a general evaluation report according to the annotation category by utilizing a deep learning semantic vector similarity recognition algorithm; the general evaluation report comprises job quality and defect evaluation, scores, teacher signature and review date.
Optionally, the automatic review analysis module specifically includes:
the reading database information acquisition unit is used for acquiring the area and the content corresponding to each fuzzy semantic in the reading database based on a fuzzy semantic locating and identifying algorithm of a regular expression;
and the analysis result determining unit is used for performing word segmentation, filtering and semantic comparison on the word declarative operation according to the region and content corresponding to each fuzzy semantic in the reading and amending library based on a deep learning semantic vector similarity recognition algorithm to determine an analysis result.
Optionally, the method further includes:
and the automatic duplicate checking module is used for comparing a plurality of total evaluation reports based on a fuzzy semantic locating and identifying algorithm of the regular expression and screening out the word declarative operation of which the word repetition rate is greater than or equal to a word repetition rate threshold value.
Optionally, the method further includes:
and the return module is used for returning the text declarative operation with the text repetition rate greater than or equal to the text repetition rate threshold value to the teacher client based on the B/S architecture, the HTML5 technology and the COM automation technology, and performing manual review, proofreading and correction.
Optionally, the method further includes:
and the personalized annotation module is used for manually adding personalized annotation sentences by the teacher client based on a fuzzy semantic location recognition algorithm of the regular expression, taking the personalized annotation sentences as automatic annotation sentences and updating the annotation library.
Optionally, the method further includes:
and the total evaluation report sending module is used for automatically sending the total evaluation report to the student client based on the B/S architecture, the HTML5 technology and the Ajax technology.
A job review method comprising:
extracting the literal declarative operation by adopting a B/S architecture, an HTML5 technology and a COM automation technology;
performing fuzzy semantic recognition on the word declarative operation based on a fuzzy semantic locating recognition algorithm and a deep learning semantic vector similarity recognition algorithm of a regular expression according to fuzzy semantics in a reading-in-batch library, and determining an analysis result; the reading library comprises a plurality of fuzzy semantics, each fuzzy semantic corresponds to one or more automatic annotation sentences, and if one fuzzy semantic corresponds to a plurality of automatic annotation sentences, one of the automatic annotation sentences is randomly determined as an analysis result; the analysis results include errors, problems, advantages, and disadvantages in the literal declarative work;
based on a fuzzy semantic locating recognition algorithm of a regular expression and an Ajax asynchronous communication technology, automatically adding automatic annotation sentences in the review library to the word declarative operation according to the analysis result, and generating annotation categories according to the annotation sentences; the annotation category comprises formats, contents and professional requirements corresponding to each annotation statement, such as format errors, content loss, content errors and non-compliance with professional requirements;
generating a general evaluation report according to the annotation category by utilizing a deep learning semantic vector similarity recognition algorithm; the general evaluation report comprises job quality and defect evaluation, scores, teacher signature and review date.
Optionally, the performing fuzzy semantic recognition on the word declarative operation according to fuzzy semantics in the reading-back library based on a regular expression fuzzy semantic locating recognition algorithm and a deep learning semantic vector similarity recognition algorithm to determine an analysis result, specifically including:
based on a fuzzy semantic locating and identifying algorithm of a regular expression, acquiring a region and content corresponding to each fuzzy semantic in the reading and amending library;
based on a deep learning semantic vector similarity recognition algorithm, performing word segmentation, filtering and semantic comparison on the word declarative operation according to the region and content corresponding to each fuzzy semantic in the reading and amending library, and determining an analysis result.
Optionally, the generating a general review report according to the annotation category by using a deep learning semantic vector similarity recognition algorithm further includes:
and comparing a plurality of total evaluation reports based on a fuzzy semantic locating and identifying algorithm of the regular expression, and screening out the word declarative operation with the word repetition rate more than or equal to the word repetition rate threshold.
Optionally, the regular expression-based fuzzy semantic locating and identifying algorithm compares multiple total evaluation reports, and screens out a text declarative operation with a text repetition rate greater than or equal to a text repetition rate threshold, and then further includes:
based on the B/S architecture, the HTML5 technology and the COM automation technology, the text declarative operation with the text repetition rate larger than or equal to the text repetition rate threshold value is returned to the teacher client side for manual review, proofreading and correction.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects: the invention discloses an operation review system and method.A automatic review analysis module positions fuzzy semantics in advance according to the structural characteristics of an electronic character statement type operation or an experimental report and an automatic commenting module carries out automatic amending according to the fuzzy semantics to generate a general review report so as to achieve the effect of completely intelligently reviewing student character statement type operations or experimental reports. The operation review system or the method disclosed by the invention can realize automatic intellectualization of heavy operation review, score statistics (including classification scores) and other works, and effectively reduce the workload of teachers.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a block diagram of a job review system provided by the present invention;
FIG. 2 is a diagram of a job review system architecture provided by the present invention;
FIG. 3 is a flow chart of the intelligent training and modifying process of the homework review system provided by the present invention;
FIG. 4 is a flowchart of a job review method provided by the present invention;
FIG. 5 is a diagram of a card faceplate interface provided by the present invention;
FIG. 6 is a diagram of an automatic correction selection interface provided by the present invention;
FIG. 7 is a diagram of an artificial comment and a standard interface thereof according to the present invention;
FIG. 8 is a diagram of a new standard interface provided by the present invention;
FIG. 9 is a diagram of a manual summary interface provided by the present invention;
FIG. 10 is a diagram illustrating an analysis of the cause of error provided by the present invention;
FIG. 11 is another analysis diagram of the cause of error according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Fig. 1 is a block diagram of a job review system provided by the present invention, fig. 2 is an architecture diagram of the job review system provided by the present invention, fig. 3 is a flow diagram of intelligent training and modification of the job review system provided by the present invention, as shown in fig. 1-3, a job review system includes:
the job extraction module 101 extracts the literal declarative job by using browser/Server architecture (browser/Server, B/S), HTML5 technology, and COM automation technology.
The automatic reading and amending analysis module 102 is used for performing fuzzy semantic recognition on the word declarative operation according to fuzzy semantics in the reading and amending library and based on a fuzzy semantic locating recognition algorithm and a deep learning semantic vector similarity recognition algorithm of a regular expression to determine an analysis result; the reading library comprises a plurality of fuzzy semantics, each fuzzy semantic corresponds to one or more automatic annotation sentences, and if one fuzzy semantic corresponds to a plurality of automatic annotation sentences, one of the automatic annotation sentences is randomly determined as an analysis result; the analysis results include errors, problems, advantages, and disadvantages in the literal declarative work.
The automatic annotation module 103 is used for automatically adding automatic annotation sentences in the review library to the word declarative operation according to the analysis result based on a regular expression fuzzy semantic localization recognition algorithm and an Ajax asynchronous communication technology, and generating annotation categories according to the annotation sentences; the annotation category comprises formats, contents and professional requirements corresponding to each annotation statement, such as format errors, content loss, content errors and non-professional requirements.
The automatic overall evaluation module 104 is used for generating an overall evaluation report according to the annotation category by utilizing a deep learning semantic vector similarity recognition algorithm; the general evaluation report comprises job quality and defect evaluation, scores, teacher signature and review date.
In practical applications, the automatic review analysis module 102 specifically includes: the reading database information acquisition unit is used for acquiring the area and the content corresponding to each fuzzy semantic in the reading database based on a fuzzy semantic locating and identifying algorithm of a regular expression; and the analysis result determining unit is used for performing word segmentation, filtering and semantic comparison on the word declarative operation according to the region and content corresponding to each fuzzy semantic in the reading and amending library based on a deep learning semantic vector similarity recognition algorithm to determine an analysis result.
In practical application, the method further comprises the following steps: and the automatic duplicate checking module is used for comparing a plurality of total evaluation reports based on a fuzzy semantic locating and identifying algorithm of the regular expression and screening out the word declarative operation of which the word repetition rate is greater than or equal to a word repetition rate threshold value.
In practical application, the method further comprises the following steps: and the return module is used for returning the text declarative operation with the text repetition rate greater than or equal to the text repetition rate threshold value to the teacher client based on the B/S architecture, the HTML5 technology and the COM automation technology, and performing manual review, proofreading and correction.
In practical application, the method further comprises the following steps: and the personalized annotation module is used for manually adding personalized annotation sentences by the teacher client based on a fuzzy semantic location recognition algorithm of the regular expression, taking the personalized annotation sentences as automatic annotation sentences and updating the annotation library.
In practical application, the method further comprises the following steps: and the total evaluation report sending module is used for automatically sending the total evaluation report to the student client.
The invention is developed based on B/S architecture and HTML5 technology, com automation technology, ajax asynchronous communication technology, fuzzy semantic-based positioning recognition algorithm and deep learning semantic vector similarity recognition algorithm, solves the problem of automatically reading statement type operation or experimental report (hereinafter referred to as operation for short), and has the following specific flows:
after the homework is submitted, the computer program carries out intelligent positioning according to fuzzy semantic positioning identification in the reading and amending library by utilizing the fact that the homework of students generally has 'fixed format or content requirement'; the automatic reading and amending analysis module identifies through fuzzy semantics, compares the fuzzy semantics with the semantics of the reading and amending library, and analyzes and correspondingly scores errors, problems or advantages in the operation according to the judgment semantics in the reading and amending library; the automatic annotation processing module automatically adds annotations at corresponding modules or contents of the operation according to the analysis result; the automatic general evaluation module analyzes and arranges the contents of the automatic annotations to give general evaluation and scores; meanwhile, the online duplicate checking processing platform automatically checks the submitted jobs, finds that the jobs with a large number of repeated contents are returned to the teacher as the duplicate jobs to be processed, and avoids the problem that the duplicate jobs can be high-grade. The system has the functions of adding automatic or personalized reading sentences at any time and converting the personalized reading sentences into the automatic reading sentences in the reading and amending operation process. The automatic reading sentences can be updated to the automatic reading library in real time and are used for automatic reading operation. When the personalized reading and amending sentences are used for manually reading and amending the homework, only the relevant reading and amending sentences at the current reading and amending part are displayed for selection, so that the speed of amending the homework can be increased.
Fig. 4 is a flowchart of the job review method provided by the present invention, and as shown in fig. 4, a job review method includes:
step 401: B/S architecture, HTML5 technology and COM automation technology are adopted to extract literal declarative operation.
Step 402: performing fuzzy semantic recognition on the word declarative operation based on a fuzzy semantic locating recognition algorithm and a deep learning semantic vector similarity recognition algorithm of a regular expression according to fuzzy semantics in a reading-in-batch library, and determining an analysis result; the reading library comprises a plurality of fuzzy semantics, each fuzzy semantic corresponds to one or more automatic annotation sentences, and if one fuzzy semantic corresponds to a plurality of automatic annotation sentences, one of the automatic annotation sentences is randomly determined as an analysis result; the analysis results include errors, problems, advantages, and disadvantages in the literal declarative work.
The step 402 specifically includes: based on a fuzzy semantic locating and identifying algorithm of a regular expression, acquiring a region and content corresponding to each fuzzy semantic in the reading and amending library; based on a deep learning semantic vector similarity recognition algorithm, performing word segmentation, filtering and semantic comparison on the word declarative operation according to the region and content corresponding to each fuzzy semantic in the reading and amending library, and determining an analysis result.
Step 403: based on a fuzzy semantic locating recognition algorithm of a regular expression and an Ajax asynchronous communication technology, automatically adding automatic annotation sentences in the review library to the word declarative operation according to the analysis result, and generating annotation categories according to the annotation sentences; the annotation category comprises formats, contents and professional requirements corresponding to each annotation statement, such as format errors, content loss, content errors and non-professional requirements.
Step 404: generating a general evaluation report according to the annotation category by utilizing a deep learning semantic vector similarity recognition algorithm; the general evaluation report comprises job quality and defect evaluation, scores, teacher signature and review date.
The method for recognizing the similarity of the semantic vector by deep learning is characterized in that a general comment report is generated according to the comment categories, and then the method further comprises the following steps: and the automatic duplicate checking module is used for comparing a plurality of total evaluation reports based on a fuzzy semantic locating and identifying algorithm of the regular expression and screening out the word declarative operation of which the word repetition rate is greater than or equal to a word repetition rate threshold value.
And the return module is used for returning the text declarative operation with the text repetition rate more than or equal to the text repetition rate threshold value to the teacher client based on the B/S architecture, the HTML5 technology and the COM automation technology, and performing manual review, proofreading and correction.
The invention has the following beneficial effects:
the method can carry out automatic and intelligent correction and evaluation on the traditional character statement type operation highly dependent on manual correction, greatly shortens the correction time, lightens the workload of the teacher correction operation, and simultaneously obtains the same effect of manual correction of the teacher.
The method can automatically classify, count and summarize the scoring condition of each part of knowledge points of the approved work, is favorable for formative evaluation of learning, and can effectively promote teaching effect and teaching feedback.
The functions of adding automatic or personalized reading sentences at any time and converting the personalized reading sentences into the automatic reading sentences are simultaneously possessed for the contents which are not related in the new operation or the reading library in the reading process, so that the intelligent learning and the final full automatic reading of the system can be realized.
The automatic intelligent word segmentation and sentence segmentation can form a duplicate checking library for the homework after reading in a wholesale manner, the repeated condition of each homework is automatically compared, the found contents can be pushed to a teacher for processing, and the problem that the student copy report can be highly scored is avoided.
The invention can be applied to the identification, annotation and analysis of all the literal statement contents, and can effectively obtain information based on a certain established standard from the personalized Chinese expression, and summarize and count the information.
The following is the operation flow of the operation of the invention applied to practice:
1. and logging in the online teaching platform, if no account number is registered in advance, and an account number is input and a password point is submitted, the online teaching platform can be logged in.
2. The student end: and opening a corresponding course by using the student account, selecting a corresponding class, selecting a corresponding experimental project and submitting a corresponding homework (note: the teacher can log in to assist in submitting homework).
3. Before the teacher corrects the homework, the teacher can click the 'my scale' menu through the teaching platform, and the existing personalized reading library or reading sentences and the scores thereof are imported, so that the accuracy of automatic reading is improved.
4. And (3) operation correction: opening an 'electronic operation intelligent reading system' plug-in, entering 'website, user name and password', then clicking '(logging in)' and entering an electronic operation reading interface (figure 5), clicking '(automatic correction)' to select corresponding experimental items and classes, and directly clicking '(batch opening)' to carry out automatic batch correction on the whole selected class operation; if a single job in the list is selected (fig. 6), then the selected job can be automatically batched independently. For the operation only with a basic reviewing library or an incomplete reviewing library, the intelligent training and upgrading of the reviewing library are required to be carried out after the plug-in is automatically reviewed.
5. The specific method of manual reading comprises the following steps: clicking (manual reading) on the plug-in panel, selecting corresponding experimental items and classes in the called menu bar, then selecting a job to be read in the right list of the student, and clicking (opening) to open the word document of the selected job to enter the manual checking or reading process. The specific operation is as follows:
A) in the manual review process, if the fact that some place needs to be modified or added with the comment content is found, the current review part of the operation is clicked, then the option activation (figure 7) in the plug-in is clicked, and the plug-in can display all the self-added personalized comments of the current part and the scores of the selected comments through the automatic positioning library;
B) and selecting the contents of errors, problems or advantages to be added with labels in the operation, selecting the comments in the plug-in, and then clicking (adding comments) to automatically label the comments selected in the plug-in to the corresponding contents in the operation. If no corresponding comment exists in the plug-in at the position to which the label is to be added in the operation, contents such as standard content, score, weight, teacher comment, total comment and the like are input in a dialog box appearing later by clicking (newly added standard) (figure 8), the error type is selected, a new comment can be added by clicking (saving), and the comment is automatically added into the plug-in comment library list. If a new label is added into the automatic review library, the column of the relation selects related information such as 'not including, or including and must include', and the like, the system automatically generates a standard code, and the comment can be automatically pushed into the automatic review library through the point of the relation.
C) In the comment in the plug-in list area, if an error occurs or other reasons need to be modified, the comment needing to be modified is selected, and then the comment can be edited [ editing standard ]. If the comment needs to be deleted, the comment to be deleted is clicked, and then the [ deletion standard ] is clicked in the editing area.
6. Overall evaluation: after the manual reviewing operation is finished, the total comment in the plug-in is clicked, and the total comment, the teacher signature and the date can be automatically added at the end of the operation. If the total evaluation is not satisfactory, clicking a button of the manual total evaluation in the plug-in, entering an interface shown in fig. 9, selecting the total evaluation in the advantage library or the disadvantage library list to insert into the automatic comment, and correcting or changing the automatic comment; if no corresponding comment exists in the total evaluation library, clicking the 'advantage library' or 'disadvantage library', inputting a related comment at a comment place, and clicking the 'new addition', and adding the total evaluation sentence of the advantage library or the disadvantage library. And selecting the comment to be changed or corrected in the operation, selecting the total evaluation sentence (or a plurality of sentences) in the total evaluation sentence list in the plug-in, clicking the [ insert ] button, and replacing the selected comment with the selected total evaluation sentence in the plug-in.
7. Storing and uploading: clicking the button of 'upload review' in the tool to submit the review report, the system automatically saves the current document (all information such as rating, deduction, comment, time, teacher, etc.) and checks the document in the background.
8. Clicking an insert (automatic correction) button and clicking a batch export button, selecting a certain folder, and exporting the corrected student homework under the experimental project in batch. And when the student enters the teaching platform, the teacher can authorize the student to return to the homework.
In practical application, as shown in fig. 10 to 11, teaching big data generated according to the error types of the automatic statistical jobs or reports of the program is convenient for teachers to intensively explain contents of common errors, and a basis is provided for further improving teaching methods.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (10)
1. A job review system, comprising:
the operation extraction module is used for extracting the literal declarative operation by adopting a B/S architecture, an HTML5 technology and a COM automation technology;
the automatic reading and amending analysis module is used for carrying out fuzzy semantic recognition on the word declarative operation according to fuzzy semantics in the reading and amending library and based on a fuzzy semantic locating recognition algorithm and a deep learning semantic vector similarity recognition algorithm of a regular expression to determine an analysis result; the reading library comprises a plurality of fuzzy semantics, each fuzzy semantic corresponds to one or more automatic annotation sentences, and if one fuzzy semantic corresponds to a plurality of automatic annotation sentences, one of the automatic annotation sentences is randomly determined as an analysis result; the analysis results include errors, problems, advantages, and disadvantages in the literal declarative work;
the automatic annotation module is used for automatically adding automatic annotation sentences in the review library to the word declarative operation according to the analysis result based on a regular expression fuzzy semantic positioning recognition algorithm and an Ajax asynchronous communication technology, and generating annotation categories according to the annotation sentences; the annotation category comprises formats, contents and professional requirements corresponding to each annotation statement, such as format errors, content loss, content errors and non-compliance with professional requirements;
the automatic general evaluation module is used for generating a general evaluation report according to the annotation category by utilizing a deep learning semantic vector similarity recognition algorithm; the general evaluation report comprises job quality and defect evaluation, scores, teacher signature and review date.
2. The homework review system of claim 1, wherein the automated review analysis module comprises:
the reading database information acquisition unit is used for acquiring the area and the content corresponding to each fuzzy semantic in the reading database based on a fuzzy semantic locating and identifying algorithm of a regular expression;
and the analysis result determining unit is used for performing word segmentation, filtering and semantic comparison on the word declarative operation according to the region and content corresponding to each fuzzy semantic in the reading and amending library based on a deep learning semantic vector similarity recognition algorithm to determine an analysis result.
3. The task review system of claim 1, further comprising:
and the automatic duplicate checking module is used for comparing a plurality of total evaluation reports based on a fuzzy semantic locating and identifying algorithm of the regular expression and screening out the word declarative operation of which the word repetition rate is greater than or equal to a word repetition rate threshold value.
4. The task review system of claim 3, further comprising:
and the return module is used for returning the text declarative operation with the text repetition rate greater than or equal to the text repetition rate threshold value to the teacher client based on the B/S architecture, the HTML5 technology and the COM automation technology, and performing manual review, proofreading and correction.
5. The task review system of claim 4, further comprising:
and the personalized annotation module is used for manually adding personalized annotation sentences by the teacher client based on a fuzzy semantic location recognition algorithm of the regular expression, taking the personalized annotation sentences as automatic annotation sentences and updating the annotation library.
6. The task review system of claim 1, further comprising:
and the total evaluation report sending module is used for automatically sending the total evaluation report to the student client based on the B/S architecture, the HTML5 technology and the Ajax technology.
7. A job review method, comprising:
extracting the literal declarative operation by adopting a B/S architecture, an HTML5 technology and a COM automation technology;
performing fuzzy semantic recognition on the word declarative operation based on a fuzzy semantic locating recognition algorithm and a deep learning semantic vector similarity recognition algorithm of a regular expression according to fuzzy semantics in a reading-in-batch library, and determining an analysis result; the reading library comprises a plurality of fuzzy semantics, each fuzzy semantic corresponds to one or more automatic annotation sentences, and if one fuzzy semantic corresponds to a plurality of automatic annotation sentences, one of the automatic annotation sentences is randomly determined as an analysis result; the analysis results include errors, problems, advantages, and disadvantages in the literal declarative work;
based on a fuzzy semantic locating recognition algorithm of a regular expression and an Ajax asynchronous communication technology, automatically adding automatic annotation sentences in the review library to the word declarative operation according to the analysis result, and generating annotation categories according to the annotation sentences; the annotation category comprises formats, contents and professional requirements corresponding to each annotation statement, such as format errors, content loss, content errors and non-compliance with professional requirements;
generating a general evaluation report according to the annotation category by utilizing a deep learning semantic vector similarity recognition algorithm; the general evaluation report comprises job quality and defect evaluation, scores, teacher signature and review date.
8. The homework review method according to claim 7, wherein the fuzzy semantic recognition is performed on the word declarative homework according to fuzzy semantics in the review library and a fuzzy semantic locating recognition algorithm and a deep learning semantic vector similarity recognition algorithm based on regular expressions, and an analysis result is determined, specifically comprising:
based on a fuzzy semantic locating and identifying algorithm of a regular expression, acquiring a region and content corresponding to each fuzzy semantic in the reading and amending library;
based on a deep learning semantic vector similarity recognition algorithm, performing word segmentation, filtering and semantic comparison on the word declarative operation according to the region and content corresponding to each fuzzy semantic in the reading and amending library, and determining an analysis result.
9. The job review method of claim 7, wherein generating a summary report according to the annotation category further comprises:
and comparing a plurality of total evaluation reports based on a fuzzy semantic locating and identifying algorithm of the regular expression, and screening out the word declarative operation with the word repetition rate being greater than or equal to the word repetition rate threshold.
10. The task review method according to claim 9, wherein the regular expression based fuzzy semantic locating recognition algorithm compares a plurality of the general evaluation reports to screen out the word declarative task with a word repetition rate greater than or equal to a word repetition rate threshold, and then further comprises:
based on the B/S architecture, the HTML5 technology and the COM automation technology, the text declarative operation with the text repetition rate larger than or equal to the text repetition rate threshold value is returned to the teacher client side for manual review, proofreading and correction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110674243.3A CN113408253A (en) | 2021-06-17 | 2021-06-17 | Job review system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110674243.3A CN113408253A (en) | 2021-06-17 | 2021-06-17 | Job review system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113408253A true CN113408253A (en) | 2021-09-17 |
Family
ID=77684919
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110674243.3A Pending CN113408253A (en) | 2021-06-17 | 2021-06-17 | Job review system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113408253A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113778454A (en) * | 2021-09-22 | 2021-12-10 | 重庆海云捷迅科技有限公司 | Automatic evaluation method and system for artificial intelligence experiment platform |
| CN113807308A (en) * | 2021-09-28 | 2021-12-17 | 腾讯科技（深圳）有限公司 | Job correction method, device, equipment, storage medium and computer program product |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005128837A (en) * | 2003-10-24 | 2005-05-19 | Kuriputon:Kk | Course participation management system, teaching material server, mail server, correction server, and learning support program |
| CN109285404A (en) * | 2018-10-25 | 2019-01-29 | 安徽创见未来教育科技有限公司 | A kind of English composition automatic scoring system |
| CN110245640A (en) * | 2019-06-21 | 2019-09-17 | 深圳市采集科技有限公司 | For being automatically positioned the method and work correction method, system and storage medium of topic in work correction |
| CN111753767A (en) * | 2020-06-29 | 2020-10-09 | 广东小天才科技有限公司 | Method and device for automatically correcting operation, electronic equipment and storage medium |
| CN112634689A (en) * | 2020-12-24 | 2021-04-09 | 广州奇大教育科技有限公司 | Application method of regular expression in automatic subjective question changing in computer teaching |
-
2021
- 2021-06-17 CN CN202110674243.3A patent/CN113408253A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005128837A (en) * | 2003-10-24 | 2005-05-19 | Kuriputon:Kk | Course participation management system, teaching material server, mail server, correction server, and learning support program |
| CN109285404A (en) * | 2018-10-25 | 2019-01-29 | 安徽创见未来教育科技有限公司 | A kind of English composition automatic scoring system |
| CN110245640A (en) * | 2019-06-21 | 2019-09-17 | 深圳市采集科技有限公司 | For being automatically positioned the method and work correction method, system and storage medium of topic in work correction |
| CN111753767A (en) * | 2020-06-29 | 2020-10-09 | 广东小天才科技有限公司 | Method and device for automatically correcting operation, electronic equipment and storage medium |
| CN112634689A (en) * | 2020-12-24 | 2021-04-09 | 广州奇大教育科技有限公司 | Application method of regular expression in automatic subjective question changing in computer teaching |
Non-Patent Citations (2)
| Title |
|---|
| 张翠翠等: "基于MVC的试卷生成及主观题判卷算法研究", 《系统仿真学报》 * |
| 李玉红等: "结合分词技术与语句相似度的主观题自动判分算法", 《计算机工程与设计》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113778454A (en) * | 2021-09-22 | 2021-12-10 | 重庆海云捷迅科技有限公司 | Automatic evaluation method and system for artificial intelligence experiment platform |
| CN113778454B (en) * | 2021-09-22 | 2024-02-20 | 重庆海云捷迅科技有限公司 | Automatic evaluation method and system for artificial intelligent experiment platform |
| CN113807308A (en) * | 2021-09-28 | 2021-12-17 | 腾讯科技（深圳）有限公司 | Job correction method, device, equipment, storage medium and computer program product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109947836B (en) | English test paper structuring method and device | |
| WO2018094925A1 (en) | Method and system for generating blank filling question and grading | |
| CN104199871B (en) | A kind of high speed examination question introduction method for wisdom teaching | |
| CN110991163B (en) | Document comparison and analysis method and device, electronic equipment and storage medium | |
| CN113255614A (en) | RPA flow automatic generation method and system based on video analysis | |
| CN107301164B (en) | Semantic analysis method and device for mathematical formula | |
| CN113408253A (en) | Job review system and method | |
| CN114913729B (en) | Question selecting method, device, computer equipment and storage medium | |
| Zhang et al. | Argrewrite: A web-based revision assistant for argumentative writings | |
| CN110837793A (en) | Intelligent recognition handwriting mathematical formula reading and amending system | |
| CN113902009A (en) | Resume analysis method and device, electronic equipment, medium and product | |
| CN113779345B (en) | Teaching material generation method and device, computer equipment and storage medium | |
| CN112528011B (en) | Open type mathematic operation correction method, system and equipment driven by multiple data sources | |
| CN110390032B (en) | Method and system for reading handwritten composition | |
| CN116934278A (en) | Method and device for auditing construction scheme | |
| CN109684395B (en) | Visual data interface universal analysis method based on natural language processing | |
| CN115017271B (en) | Method and system for intelligently generating RPA flow component block | |
| CN116451646A (en) | Standard draft detection method, system, electronic equipment and storage medium | |
| CN115357700A (en) | Event map-based compressor fault diagnosis method | |
| US10261993B1 (en) | Adaptable text analytics platform | |
| CN113408290A (en) | Intelligent marking method and system for Chinese text | |
| Rüdian et al. | Automatic Feedback for Open Writing Tasks: Is this text appropriate for this lecture? | |
| KR101207375B1 (en) | System and method for managing mathematical contents | |
| CN111563162A (en) | MOOC comment analysis system and method based on text emotion analysis | |
| Iwashokun et al. | Structural vetting of academic proposals |
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 |