CN116610774B - High-efficiency intelligent online paper reading auxiliary method and system - Google Patents
High-efficiency intelligent online paper reading auxiliary method and system Download PDFInfo
- Publication number
- CN116610774B CN116610774B CN202310889711.8A CN202310889711A CN116610774B CN 116610774 B CN116610774 B CN 116610774B CN 202310889711 A CN202310889711 A CN 202310889711A CN 116610774 B CN116610774 B CN 116610774B
- Authority
- CN
- China
- Prior art keywords
- content
- score
- scoring
- answer
- teacher
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000000605 extraction Methods 0.000 claims description 15
- 238000012512 characterization method Methods 0.000 claims description 14
- 238000010276 construction Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 8
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- 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
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06398—Performance of employee with respect to a job function
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- General Engineering & Computer Science (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Computational Linguistics (AREA)
- Game Theory and Decision Science (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The application provides a high-efficiency intelligent online examination paper reading auxiliary method and a system, wherein the method comprises the following steps: step S1: obtaining answer contents of subjective questions in an answer sheet; step S2: selecting and scoring the answer content based on a preset standard answer corresponding to the subjective question, and obtaining a first score, unscored content and an unused standard answer; step S3: pushing the unscored content and the unused standard answer to an idle paper marking teacher for scoring, and obtaining a second score; step S4: a final score for the answer content is determined based on the first score and the second score. According to the application, the content with the ability to score the answer content of the subjective questions by self is scored according to the standard answers, and the remaining unscored content and the remaining unused standard answers are pushed to the scoring teacher for scoring, so that the scoring assistance is realized, the scoring teacher is not required to score all the answer content of the subjective questions, the labor cost of the scoring teacher is reduced, the online scoring efficiency is improved, and the method is more intelligent.
Description
Technical Field
The application relates to the technical field of computer data processing, in particular to a high-efficiency intelligent online examination paper reading auxiliary method and system.
Background
Currently, when implementing online examination, the objective question system with fixed standard answers can score according to the answer content of students, for example: the objective questions are selected questions, the answer content of the students is option A, the standard answer is option A, and the answer of the students is correct, and the objective questions are fully scored. However, the subjective question system without fixed standard answers cannot score the answer content of the students by itself, and the paper reader is required to score the answer content of the students. However, the implementation objects of online paper marking are mostly medium and large-sized exams, and students who need paper marking teachers to mark the exams have more answer contents, so that the labor cost of the paper marking teachers is increased, and the online paper marking efficiency is reduced.
Thus, a solution is needed.
Disclosure of Invention
The application aims at providing a high-efficiency intelligent online paper marking auxiliary method, which comprises the steps of automatically marking the content with the capability of marking the answer content of the subjective questions according to standard answers, pushing the rest unmarked content and the rest unused standard answers to a paper marking teacher for marking, realizing paper marking auxiliary, eliminating the need of the paper marking teacher to mark all the answer content of the subjective questions, reducing the labor cost of the paper marking teacher, greatly improving the online paper marking efficiency, and being more intelligent.
The embodiment of the application provides a high-efficiency intelligent online examination paper auxiliary method, which comprises the following steps:
step S1: obtaining answer contents of subjective questions in an answer sheet;
step S2: selecting and scoring the answer content based on a preset standard answer corresponding to the subjective question, and obtaining a first score, unscored content and an unused standard answer;
step S3: pushing the unscored content and the unused standard answer to an idle paper marking teacher for scoring, and obtaining a second score;
step S4: a final score for the answer content is determined based on the first score and the second score.
Preferably, step S2: selecting and scoring the answer content based on a preset standard answer corresponding to the subjective question to obtain a first score, unscored content and an unused standard answer, wherein the method comprises the following steps:
extracting a scoring standard set from the standard answers;
sequentially traversing the scoring criteria in the scoring criteria set;
each time of traversing, extracting keywords from the traversed scoring standard to obtain a first keyword set;
matching the first keyword set with a first trigger keyword set in a preset first trigger keyword set library;
when the matching is met, acquiring a preset content extraction rule, a content requirement and a local score corresponding to the matching met first trigger keyword set, and taking the traversed scoring standard as a used scoring standard;
attempting to extract first target content from the answer content based on the content extraction rule;
when the attempt is successful, the first target content is used as the scored content, and meanwhile, whether the first target content meets the content requirement or not is determined;
when yes, taking the local score as a valid score;
after traversing the scoring standard, accumulating and calculating the effective score to obtain a first score; taking the contents except the scored contents in the answer contents as non-scored contents; the scoring criteria other than the used scoring criteria in the scoring criteria set are used as the unused scoring criteria answers.
Preferably, step S3: pushing the unscored content and the unused standard answer to an idle paper reader for scoring, and obtaining a second score, wherein the method comprises the following steps:
acquiring a paper reading terminal used by a paper reading teacher;
pushing the unscored content and the unused standard answer to the paper marking terminal;
when the paper marking teacher browses unscored content and unused standard answers through the paper marking terminal, starting timing;
when the timing duration is greater than or equal to a preset first time duration threshold, carrying out characterization processing on unscored content and unqualified answers based on a preset characterization template to obtain target features;
generating a template based on a preset search requirement corresponding to the feature type of the target feature, and generating a search requirement according to the target feature;
searching out a target teacher from a preset teacher examination paper history library based on the search requirement;
selecting an idle target teacher as a partner teacher;
accessing a conference teacher to a paper reading terminal;
acquiring a teacher speaking text of a conference teacher;
extracting keywords from the speaking text of the teacher to obtain a second keyword set;
matching the second keyword set with a second trigger keyword set in a preset second trigger keyword set library;
when the matching is met, acquiring a preset content circling rule corresponding to the matched second trigger keyword set;
based on the content circling rules, temporarily circling second target content from unscored content in the paper marking terminal;
pushing a preset scoring column to the paper marking terminal when the timing time length is greater than or equal to a preset second time length threshold;
and obtaining a second score input by the paper marking teacher based on the scoring column.
Preferably, searching a target teacher from a preset teacher's paper history library based on a search requirement includes:
constructing a search requirement set according to the search requirement based on the search requirement set construction condition;
searching a target teacher meeting all search requirements in the search requirement set from a teacher examination paper history library;
wherein the search requirement set construction conditions include:
the sum of the weights of all the search requirements in the search requirement set is greater than or equal to a preset weight and threshold;
at least M search requirements in the search requirement set are located in the first N search requirements in the search requirement sequence; the search requirement sequence is formed by arranging search requirements according to the requirement weight from big to small.
Preferably, step S4: determining a final score for the answer content based on the first score and the second score, comprising:
accumulating and calculating a first score and a second score to obtain a final score;
or alternatively, the first and second heat exchangers may be,
giving a first score a preset error coefficient to obtain a target value;
and accumulating the calculated target value and the second score to obtain a final score.
The embodiment of the application provides a high-efficiency intelligent online examination paper reading auxiliary system, which comprises the following components:
the acquisition module is used for acquiring answer contents of subjective questions in the answer sheet;
the first scoring module is used for selecting and scoring the answer content based on a preset standard answer corresponding to the subjective question, and obtaining a first score, unscored content and an unused standard answer;
the second scoring module is used for pushing the unscored content and the unused standard answer to an idle paper marking teacher for scoring, and obtaining a second score;
a determining module, configured to step S4: a final score for the answer content is determined based on the first score and the second score.
Preferably, the first scoring module performs selection scoring on answer content based on a preset standard answer corresponding to the subjective question, obtains a first score, unscored content and an unused standard answer, and performs the following operations:
extracting a scoring standard set from the standard answers;
sequentially traversing the scoring criteria in the scoring criteria set;
each time of traversing, extracting keywords from the traversed scoring standard to obtain a first keyword set;
matching the first keyword set with a first trigger keyword set in a preset first trigger keyword set library;
when the matching is met, acquiring a preset content extraction rule, a content requirement and a local score corresponding to the matching met first trigger keyword set, and taking the traversed scoring standard as a used scoring standard;
attempting to extract first target content from the answer content based on the content extraction rule;
when the attempt is successful, the first target content is used as the scored content, and meanwhile, whether the first target content meets the content requirement or not is determined;
when yes, taking the local score as a valid score;
after traversing the scoring standard, accumulating and calculating the effective score to obtain a first score; taking the contents except the scored contents in the answer contents as non-scored contents; the scoring criteria other than the used scoring criteria in the scoring criteria set are used as the unused scoring criteria answers.
Preferably, the second scoring module pushes the unscored content and the unqualified answer to an idle paper marking teacher for scoring, obtains a second score, and performs the following operations:
acquiring a paper reading terminal used by a paper reading teacher;
pushing the unscored content and the unused standard answer to the paper marking terminal;
when the paper marking teacher browses unscored content and unused standard answers through the paper marking terminal, starting timing;
when the timing duration is greater than or equal to a preset first time duration threshold, carrying out characterization processing on unscored content and unqualified answers based on a preset characterization template to obtain target features;
generating a template based on a preset search requirement corresponding to the feature type of the target feature, and generating a search requirement according to the target feature;
searching out a target teacher from a preset teacher examination paper history library based on the search requirement;
selecting an idle target teacher as a partner teacher;
accessing a conference teacher to a paper reading terminal;
acquiring a teacher speaking text of a conference teacher;
extracting keywords from the speaking text of the teacher to obtain a second keyword set;
matching the second keyword set with a second trigger keyword set in a preset second trigger keyword set library;
when the matching is met, acquiring a preset content circling rule corresponding to the matched second trigger keyword set;
based on the content circling rules, temporarily circling second target content from unscored content in the paper marking terminal;
pushing a preset scoring column to the paper marking terminal when the timing time length is greater than or equal to a preset second time length threshold;
and obtaining a second score input by the paper marking teacher based on the scoring column.
Preferably, the second scoring module searches out a target teacher from a preset teacher's paper reading history base based on the search requirement, and performs the following operations:
constructing a search requirement set according to the search requirement based on the search requirement set construction condition;
searching a target teacher meeting all search requirements in the search requirement set from a teacher examination paper history library;
wherein the search requirement set construction conditions include:
the sum of the weights of all the search requirements in the search requirement set is greater than or equal to a preset weight and threshold;
at least M search requirements in the search requirement set are located in the first N search requirements in the search requirement sequence; the search requirement sequence is formed by arranging search requirements according to the requirement weight from big to small.
Preferably, the determining module determines a final score of the answer content based on the first score and the second score, and performs the following operations:
accumulating and calculating a first score and a second score to obtain a final score;
or alternatively, the first and second heat exchangers may be,
giving a first score a preset error coefficient to obtain a target value;
and accumulating the calculated target value and the second score to obtain a final score.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application. The objectives and other advantages of the application will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
The technical scheme of the application is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate the application and together with the embodiments of the application, serve to explain the application. In the drawings:
FIG. 1 is a schematic diagram of an intelligent online examination paper supporting method with high efficiency according to an embodiment of the present application;
fig. 2 is a schematic diagram of an intelligent online examination paper reading auxiliary system with high efficiency according to an embodiment of the present application.
Detailed Description
The preferred embodiments of the present application will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present application only, and are not intended to limit the present application.
The embodiment of the application provides a high-efficiency intelligent online examination paper auxiliary method, which is shown in fig. 1 and comprises the following steps:
step S1: obtaining answer contents of subjective questions in an answer sheet; the answer content can be obtained from the answer area of the subjective questions in the answer sheet;
step S2: selecting and scoring the answer content based on a preset standard answer corresponding to the subjective question, and obtaining a first score, unscored content and an unused standard answer; standard answers of subjective questions are preset and can be provided by a test paper question-setting party; when scoring is selected, the system scores the content with the ability to score by oneself in the answer content according to the standard answer, so as to obtain a first score, wherein the content which is not scored by oneself in the answer content, namely the content which is not scored by oneself in the answer content is not scored, and the unused content in the standard answer is an unused standard answer when the system scores by oneself;
step S3: pushing the unscored content and the unused standard answer to an idle paper marking teacher for scoring, and obtaining a second score; after receiving the push, the paper reading teacher scores the unscored content based on the unused standard answer, and gives a second score;
step S4: a final score for the answer content is determined based on the first score and the second score.
The working principle and the beneficial effects of the technical scheme are as follows:
the system of the application scores the content which has the ability to score the answer content of the subjective questions by oneself according to the standard answer, pushes the residual unscored content and the residual unused standard answer to the scoring teacher for scoring, realizes the assistance of scoring, does not need the scoring teacher to score all the answer content of the subjective questions, reduces the labor cost of the scoring teacher, greatly improves the online scoring efficiency, and is more intelligent.
When the method is applied specifically, a paper reader waits for unscored content and unused standard answers which are pushed by the system by using a computer, and when the paper reader receives the pushing, the unscored content is analyzed and scored by comparing with the unused standard answers.
In one embodiment, step S2: selecting and scoring the answer content based on a preset standard answer corresponding to the subjective question to obtain a first score, unscored content and an unused standard answer, wherein the method comprises the following steps:
extracting a scoring standard set from the standard answers; the scoring criteria set has a plurality of scoring criteria, and in general, the scoring criteria are scores of what requirements the answer content meets, for example: "the beginning description does not agree with the stem point of view, and gets a score of 2";
sequentially traversing the scoring criteria in the scoring criteria set;
each time of traversing, extracting keywords from the traversed scoring standard to obtain a first keyword set;
matching the first keyword set with a first trigger keyword set in a preset first trigger keyword set library; the first trigger keyword set is a set of keywords that represent the system's ability to score the answer content according to the scoring criteria, e.g., the first trigger keyword set includes "beginning", "description", "disagreement", "stem point of view" and "score 2";
when the matching is met, acquiring a preset content extraction rule, a content requirement and a local score corresponding to the matching met first trigger keyword set, and taking the traversed scoring standard as a used scoring standard;
attempting to extract first target content from the answer content based on the content extraction rule; when the matching is met, the description system has the capability of scoring the answer content according to the scoring standard, the content extraction rule is a rule for extracting answer content (namely, first target content) corresponding to the scoring standard from the answer content, the content requirement is a requirement to be met when the answer content is correct, and the local score is a score obtained locally after the answer content is correct, for example: matching the first triggering keyword set to contain 'beginning', 'description', 'disagreement', 'stem viewpoint' and 'score 2', wherein the content extraction rule is to extract sentence segments within 10 words of the beginning in the answer content, the content requirement is to explain the disagreement stem viewpoint, and the local score is 2 score;
when the attempt is successful, the first target content is used as the scored content, and meanwhile, whether the first target content meets the content requirement or not is determined;
when yes, taking the local score as a valid score; when the first target content accords with the local score, the first target content is correctly answered, and the corresponding local score is valid and is used as the valid score;
after traversing the scoring standard, accumulating and calculating the effective score to obtain a first score; taking the contents except the scored contents in the answer contents as non-scored contents; the scoring criteria other than the used scoring criteria in the scoring criteria set are used as the unused scoring criteria answers.
The working principle and the beneficial effects of the technical scheme are as follows:
according to the embodiment of the application, the first trigger keyword set library is introduced, the scoring standard which can represent that the system has the capability of scoring the answer content according to the scoring standard is rapidly selected from the scoring standard set, then the content extraction rule, the content requirement and the local score are introduced, the first target content which has the capability of scoring the answer content according to the scoring standard is rapidly scored, and the scoring efficiency and the scoring accuracy of the answer content in selection are improved.
In one embodiment, step S3: pushing the unscored content and the unused standard answer to an idle paper reader for scoring, and obtaining a second score, wherein the method comprises the following steps:
acquiring a paper reading terminal used by a paper reading teacher; the paper marking terminal can be a computer, a tablet and the like used by a paper marking teacher in paper marking;
pushing the unscored content and the unused standard answer to the paper marking terminal;
when the paper marking teacher browses unscored content and unused standard answers through the paper marking terminal, starting timing;
when the timing duration is greater than or equal to a preset first time duration threshold, carrying out characterization processing on unscored content and unqualified answers based on a preset characterization template to obtain target features; the first time length threshold may be, for example: 30 seconds; the target features include: the position distribution of unscored content in answer content, answer sequence number of unused standard answer, etc., and the characterization template is a template for the system to compare with the characterization processing to obtain the target characteristics;
generating a template based on a preset search requirement corresponding to the feature type of the target feature, and generating a search requirement according to the target feature; the search requirement is a requirement of other paper reading teachers which search out the answer content of other students which are similar to the unscored content and are scored by using the same standard answer as the unscored content; such as: the target feature is that the position distribution of unscored content in the answer content is a middle section, and then the generated search requirement is "a teacher who scores answer content located in the middle section in the student answer content of subjective questions in search history", and then, for example: the target feature is that the answer serial number of the unused standard answer is 20C, then the generation search requirement is "the teacher who uses the standard answer with the answer serial number of 20C to score the answer content of the student in the search history", the search requirement generation template is a template for generating the search requirement by the system contrast;
searching out a target teacher from a preset teacher examination paper history library based on the search requirement; the teacher's history of going over the paper history in having different paper histories of going over the paper teacher's history, for example: answer content for scoring, standard answer to use, etc.;
selecting an idle target teacher as a partner teacher;
accessing a conference teacher to a paper reading terminal; after the paper reading terminal is accessed, the conference teacher can talk with the paper reading teacher;
acquiring a teacher speaking text of a conference teacher; when a conference teacher carries out dialogue with a paper reader, the generated speaking content is converted into a text, and the speaking text of the teacher is obtained;
extracting keywords from the speaking text of the teacher to obtain a second keyword set;
matching the second keyword set with a second trigger keyword set in a preset second trigger keyword set library; the second trigger keyword set is a set composed of keywords representing the content which needs to be checked by the paper reader in the unscored content pointed out by the counselor, for example, the second trigger keyword set comprises 'you see "," his' and 'second section answer content', etc.;
when the matching is met, acquiring a preset content circling rule corresponding to the matched second trigger keyword set; the content circle selection rule is a rule for circling and selecting a content which needs to be checked by a paper reader in un-scored content, for example: the second triggering keyword set comprises 'you watch', 'his' and 'second section answer content', and the content circling rule is to circling the second section of content in the unscored content;
based on the content circling rules, temporarily circling second target content from unscored content in the paper marking terminal; after the temporary circle selection, after a certain period of time, the circle selection is cancelled;
pushing a preset scoring column to the paper marking terminal when the timing time length is greater than or equal to a preset second time length threshold; the second duration threshold may be, for example: 100 seconds; the scoring column is provided with an information input column for a paper marking teacher to input scoring;
and obtaining a second score input by the paper marking teacher based on the scoring column.
The working principle and the beneficial effects of the technical scheme are as follows:
generally, when a scoring teacher uses a standard answer to score unscored content, the scoring uncertainty may occur, and at this time, the scoring teacher needs to communicate with other scoring teachers online to confirm the scoring. This is cumbersome. When the time length is larger than or equal to the first time length threshold, the embodiment of the application indicates that the paper marking teacher is hesitant to score, and the paper marking teacher is connected with the protocol teacher to assist the paper marking teacher to communicate with other paper marking teachers. In addition, the search requirement is introduced, and the rationality of access of the rationality teacher is improved by screening out the rationality teacher which can give correct scoring guidance to the paper reader. And secondly, when the contract teacher carries out scoring guidance on the paper reader, a content circling rule is introduced, so that the paper reader can conveniently and quickly find the second target content in the unscored content, the scoring guidance efficiency is improved, and the method has particular applicability.
In one embodiment, searching a target teacher from a preset teacher's paper history library based on a search requirement includes:
constructing a search requirement set according to the search requirement based on the search requirement set construction condition;
searching a target teacher meeting all search requirements in the search requirement set from a teacher examination paper history library;
wherein the search requirement set construction conditions include:
the sum of the weights of all the search requirements in the search requirement set is greater than or equal to a preset weight and threshold; the greater the claim weight, the more the search requirement needs to be satisfied when representing a search, the more the target teacher in the search results can give the paper reader correct scoring guidance, such as: the requirement weight of the search requirement for a teacher scoring the student answer content by using the standard answer with the answer sequence number of 20C in the search history is 8, and the search requirement for a teacher scoring the answer content positioned in the middle section in the student answer content of the subjective questions in the search history is 5; the weights and thresholds may be, for example: 20, a step of;
at least M search requirements in the search requirement set are located in the first N search requirements in the search requirement sequence; the search requirement sequence is formed by arranging search requirements according to the requirement weight from big to small. M may be 2 and N may be 5;
when the two conditions are met, the target teacher which is searched out and meets all the searching requirements in the searching requirement set is ensured to give correct scoring guidance to the paper reader.
In one embodiment, step S4: determining a final score for the answer content based on the first score and the second score, comprising:
accumulating and calculating a first score and a second score to obtain a final score; the first score may be directly added to the second score to obtain a final score;
or alternatively, the first and second heat exchangers may be,
giving a first score a preset error coefficient to obtain a target value; the error coefficient is, for example: 1.001, etc.; errors may exist in the systematic scoring, so that error coefficients are introduced, and the accuracy of final score determination is improved;
and accumulating the calculated target value and the second score to obtain a final score.
The embodiment of the application provides a high-efficiency intelligent online examination paper reading auxiliary system, which is shown in fig. 2 and comprises the following steps:
the acquisition module 1 is used for acquiring answer contents of subjective questions in the answer sheet;
the first scoring module 2 is used for selecting and scoring the answer content based on a preset standard answer corresponding to the subjective question, and obtaining a first score, unscored content and an unused standard answer;
the second scoring module 3 is used for pushing the unscored content and the unused standard answer to an idle paper marking teacher for scoring, and obtaining a second score;
a determining module 4, configured to step S4: a final score for the answer content is determined based on the first score and the second score.
The first scoring module 2 performs selection scoring on answer content based on preset standard answers corresponding to subjective questions, obtains first scores, unscored content and unused standard answers, and performs the following operations:
extracting a scoring standard set from the standard answers;
sequentially traversing the scoring criteria in the scoring criteria set;
each time of traversing, extracting keywords from the traversed scoring standard to obtain a first keyword set;
matching the first keyword set with a first trigger keyword set in a preset first trigger keyword set library;
when the matching is met, acquiring a preset content extraction rule, a content requirement and a local score corresponding to the matching met first trigger keyword set, and taking the traversed scoring standard as a used scoring standard;
attempting to extract first target content from the answer content based on the content extraction rule;
when the attempt is successful, the first target content is used as the scored content, and meanwhile, whether the first target content meets the content requirement or not is determined;
when yes, taking the local score as a valid score;
after traversing the scoring standard, accumulating and calculating the effective score to obtain a first score; taking the contents except the scored contents in the answer contents as non-scored contents; the scoring criteria other than the used scoring criteria in the scoring criteria set are used as the unused scoring criteria answers.
The second scoring module 3 pushes the unscored content and the unused standard answer to an idle paper marking teacher for scoring, obtains a second score, and executes the following operations:
acquiring a paper reading terminal used by a paper reading teacher;
pushing the unscored content and the unused standard answer to the paper marking terminal;
when the paper marking teacher browses unscored content and unused standard answers through the paper marking terminal, starting timing;
when the timing duration is greater than or equal to a preset first time duration threshold, carrying out characterization processing on unscored content and unqualified answers based on a preset characterization template to obtain target features;
generating a template based on a preset search requirement corresponding to the feature type of the target feature, and generating a search requirement according to the target feature;
searching out a target teacher from a preset teacher examination paper history library based on the search requirement;
selecting an idle target teacher as a partner teacher;
accessing a conference teacher to a paper reading terminal;
acquiring a teacher speaking text of a conference teacher;
extracting keywords from the speaking text of the teacher to obtain a second keyword set;
matching the second keyword set with a second trigger keyword set in a preset second trigger keyword set library;
when the matching is met, acquiring a preset content circling rule corresponding to the matched second trigger keyword set;
based on the content circling rules, temporarily circling second target content from unscored content in the paper marking terminal;
pushing a preset scoring column to the paper marking terminal when the timing time length is greater than or equal to a preset second time length threshold;
and obtaining a second score input by the paper marking teacher based on the scoring column.
The second scoring module 3 searches out a target teacher from a preset teacher's paper reading history base based on the search requirement, and executes the following operations:
constructing a search requirement set according to the search requirement based on the search requirement set construction condition;
searching a target teacher meeting all search requirements in the search requirement set from a teacher examination paper history library;
wherein the search requirement set construction conditions include:
the sum of the weights of all the search requirements in the search requirement set is greater than or equal to a preset weight and threshold;
at least M search requirements in the search requirement set are located in the first N search requirements in the search requirement sequence; the search requirement sequence is formed by arranging search requirements according to the requirement weight from big to small.
The determining module 4 determines a final score of the answer content based on the first score and the second score, and performs the following operations:
accumulating and calculating a first score and a second score to obtain a final score;
or alternatively, the first and second heat exchangers may be,
giving a first score a preset error coefficient to obtain a target value;
and accumulating the calculated target value and the second score to obtain a final score.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (6)
1. A high-efficiency intelligent online paper reading auxiliary method is characterized by comprising the following steps:
step S1: obtaining answer contents of subjective questions in an answer sheet;
step S2: selecting and scoring the answer content based on a preset standard answer corresponding to the subjective question, and obtaining a first score, unscored content and an unused standard answer;
step S3: pushing the unscored content and the unqualified answer to an idle paper marking teacher for scoring, and obtaining a second score;
step S4: determining a final score of the answer content based on the first score and the second score;
the step S2: selecting and scoring the answer content based on a preset standard answer corresponding to the subjective question, and obtaining a first score, unscored content and an unused standard answer, wherein the method comprises the following steps:
extracting a scoring standard set from the standard answers;
sequentially traversing the scoring criteria in the scoring criteria set;
each time of traversing, extracting keywords from the traversed scoring standard to obtain a first keyword set;
matching the first keyword set with a first trigger keyword set in a preset first trigger keyword set library;
when the matching is met, acquiring a preset content extraction rule, a content requirement and a local score corresponding to the first trigger keyword set, and taking the traversed scoring standard as a used scoring standard;
attempting to extract first target content from the answer content based on the content extraction rule;
when the attempt is successful, taking the first target content as scored content, and simultaneously determining whether the first target content meets the content requirement;
when yes, taking the local score as a valid score;
after traversing the scoring standard, accumulating and calculating the effective score to obtain the first score; taking the contents except the scored contents in the answer contents as the unscored contents; setting the scoring criteria other than the used scoring criteria in the scoring criteria set as answers to the unused criteria;
the step S3: pushing the unscored content and the unqualified answer to an idle paper reader for scoring, and obtaining a second score, including:
acquiring a paper reading terminal used by the paper reading teacher;
pushing the unscored content and the unqualified answer to the paper marking terminal;
when the paper marking teacher browses the unscored content and the unused standard answer through the paper marking terminal, starting timing;
when the timing duration is greater than or equal to a preset first time duration threshold, carrying out characterization processing on the unscored content and the unused standard answer based on a preset characterization template to obtain target features;
generating a template based on a preset search requirement corresponding to the feature type of the target feature, and generating a search requirement according to the target feature;
searching out a target teacher from a preset teacher examination paper history base based on the search requirement;
selecting an idle target teacher as a partner teacher;
accessing the conference teacher into the paper reading terminal;
acquiring a teacher speaking text of the conference teacher;
extracting keywords from the speech text of the teacher to obtain a second keyword set;
matching the second keyword set with a second trigger keyword set in a preset second trigger keyword set library;
when the matching is met, acquiring a preset content circling rule corresponding to the matched second trigger keyword set;
temporarily circling second target content from the unscored content in the scoring terminal based on the content circling rule;
pushing a preset scoring column to the paper marking terminal when the timing time length is greater than or equal to a preset second time length threshold;
and acquiring the second score input by the paper marking teacher based on the scoring column.
2. The high-efficiency online intelligent examination paper supporting method as claimed in claim 1, wherein searching out the target teacher from the history of examination paper of the preset teacher based on the search requirement comprises:
constructing a search requirement set based on a search requirement set construction condition according to the search requirement;
searching out the target teacher meeting all the searching requirements in the searching requirement set from a teacher examination paper history library;
wherein the search requirement set construction conditions include:
the sum of the weights of all the search requirements in the search requirement set is greater than or equal to a preset weight and threshold;
at least M of the search requirements in the search requirement set are located in the first N of the search requirements in the search requirement sequence; the search requirement sequence is formed by arranging the search requirements according to the requirement weight from large to small.
3. The high-efficiency intelligent online examination paper supporting method as claimed in claim 1, wherein the step S4: determining a final score for the answer content based on the first score and the second score, comprising:
accumulating and calculating the first score and the second score to obtain the final score;
or alternatively, the first and second heat exchangers may be,
giving the first score a preset error coefficient to obtain a target value;
and accumulating and calculating the target value and the second score to obtain the final score.
4. An efficient intelligent online paper marking auxiliary system is characterized by comprising:
the acquisition module is used for acquiring answer contents of subjective questions in the answer sheet;
the first scoring module is used for selecting and scoring the answer content based on a preset standard answer corresponding to the subjective question, and obtaining a first score, unscored content and an unused standard answer;
the second scoring module is used for pushing the unscored content and the unused standard answer to an idle paper marking teacher for scoring, and obtaining a second score;
a determining module, configured to step S4: determining a final score of the answer content based on the first score and the second score;
the first scoring module performs selection scoring on the answer content based on a preset standard answer corresponding to the subjective question, obtains a first score, unscored content and an unused standard answer, and performs the following operations:
extracting a scoring standard set from the standard answers;
sequentially traversing the scoring criteria in the scoring criteria set;
each time of traversing, extracting keywords from the traversed scoring standard to obtain a first keyword set;
matching the first keyword set with a first trigger keyword set in a preset first trigger keyword set library;
when the matching is met, acquiring a preset content extraction rule, a content requirement and a local score corresponding to the first trigger keyword set, and taking the traversed scoring standard as a used scoring standard;
attempting to extract first target content from the answer content based on the content extraction rule;
when the attempt is successful, taking the first target content as scored content, and simultaneously determining whether the first target content meets the content requirement;
when yes, taking the local score as a valid score;
after traversing the scoring standard, accumulating and calculating the effective score to obtain the first score; taking the contents except the scored contents in the answer contents as the unscored contents; setting the scoring criteria other than the used scoring criteria in the scoring criteria set as answers to the unused criteria;
the second scoring module pushes the unscored content and the unused standard answer to an idle paper marking teacher for scoring, obtains a second score, and executes the following operations:
acquiring a paper reading terminal used by the paper reading teacher;
pushing the unscored content and the unqualified answer to the paper marking terminal;
when the paper marking teacher browses the unscored content and the unused standard answer through the paper marking terminal, starting timing;
when the timing duration is greater than or equal to a preset first time duration threshold, carrying out characterization processing on the unscored content and the unused standard answer based on a preset characterization template to obtain target features;
generating a template based on a preset search requirement corresponding to the feature type of the target feature, and generating a search requirement according to the target feature;
searching out a target teacher from a preset teacher examination paper history base based on the search requirement;
selecting an idle target teacher as a partner teacher;
accessing the conference teacher into the paper reading terminal;
acquiring a teacher speaking text of the conference teacher;
extracting keywords from the speech text of the teacher to obtain a second keyword set;
matching the second keyword set with a second trigger keyword set in a preset second trigger keyword set library;
when the matching is met, acquiring a preset content circling rule corresponding to the matched second trigger keyword set;
temporarily circling second target content from the unscored content in the scoring terminal based on the content circling rule;
pushing a preset scoring column to the paper marking terminal when the timing time length is greater than or equal to a preset second time length threshold;
and acquiring the second score input by the paper marking teacher based on the scoring column.
5. The system of claim 4, wherein the second scoring module searches out a target teacher from a history of teacher's scoring based on the search requirement, and performs the following operations:
constructing a search requirement set based on a search requirement set construction condition according to the search requirement;
searching out the target teacher meeting all the searching requirements in the searching requirement set from a teacher examination paper history library;
wherein the search requirement set construction conditions include:
the sum of the weights of all the search requirements in the search requirement set is greater than or equal to a preset weight and threshold;
at least M of the search requirements in the search requirement set are located in the first N of the search requirements in the search requirement sequence; the search requirement sequence is formed by arranging the search requirements according to the requirement weight from large to small.
6. The efficient online intelligent scoring assistance system of claim 4, wherein the determining module determines a final score for the answer content based on the first score and the second score by:
accumulating and calculating the first score and the second score to obtain the final score;
or alternatively, the first and second heat exchangers may be,
giving the first score a preset error coefficient to obtain a target value;
and accumulating and calculating the target value and the second score to obtain the final score.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310889711.8A CN116610774B (en) | 2023-07-20 | 2023-07-20 | High-efficiency intelligent online paper reading auxiliary method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310889711.8A CN116610774B (en) | 2023-07-20 | 2023-07-20 | High-efficiency intelligent online paper reading auxiliary method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116610774A CN116610774A (en) | 2023-08-18 |
| CN116610774B true CN116610774B (en) | 2023-09-26 |
Family
ID=87683960
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310889711.8A Active CN116610774B (en) | 2023-07-20 | 2023-07-20 | High-efficiency intelligent online paper reading auxiliary method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116610774B (en) |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105469662A (en) * | 2016-01-18 | 2016-04-06 | 黄道成 | Student answer information real-time collection and efficient and intelligent correcting system and use method in teaching process |
| CN105516356A (en) * | 2016-01-13 | 2016-04-20 | 广东小天才科技有限公司 | Test question correcting method, communication terminal and server |
| CN106548674A (en) * | 2016-09-12 | 2017-03-29 | 广东德诚网络科技有限公司 | For the method for dynamically processing and system of net marking |
| CN107705231A (en) * | 2017-11-07 | 2018-02-16 | 语联网（武汉）信息技术有限公司 | A kind of computer assisted method to go over files, device and computer-readable recording medium |
| CN109033046A (en) * | 2018-06-25 | 2018-12-18 | 陕西师范大学 | Structuring visible document snap information input system and method |
| CN109165877A (en) * | 2018-10-11 | 2019-01-08 | 四川生学教育科技有限公司 | A kind of method and system promoting network scoring speed |
| CN109697905A (en) * | 2017-10-20 | 2019-04-30 | 深圳市鹰硕技术有限公司 | A kind of exam paper marking system |
| CN110390616A (en) * | 2019-07-15 | 2019-10-29 | 北京成长教育科技有限公司 | Work correction method, electronic equipment and storage medium |
| CN110705905A (en) * | 2019-10-15 | 2020-01-17 | 李晚华 | High-accuracy intelligent online paper marking method |
| CN112088391A (en) * | 2018-07-06 | 2020-12-15 | 道鑛有限公司 | Examination and selection system, examination and selection device and examination and selection method |
| CN112115736A (en) * | 2019-06-19 | 2020-12-22 | 广东小天才科技有限公司 | Job correction method and system based on image recognition and intelligent terminal |
| CN113160005A (en) * | 2021-02-24 | 2021-07-23 | 山东智多分教育科技有限公司 | Online examination paper marking method for subjective questions |
| CN114860881A (en) * | 2022-05-13 | 2022-08-05 | 北京举个例子科技有限公司 | Subjective question marking method and device, storage medium and electronic equipment |
| CN115423663A (en) * | 2022-11-04 | 2022-12-02 | 广州宏途数字科技有限公司 | Intelligent management method, system, equipment and storage medium for home operation |
| CN115564606A (en) * | 2022-08-24 | 2023-01-03 | 湖南沐高信息科技有限公司 | Intelligent marking method suitable for judicial examination subjective questions |
| CN115759031A (en) * | 2022-11-14 | 2023-03-07 | 上海凌立健康管理股份有限公司 | Method and system for automatically scoring subjective questions |
-
2023
- 2023-07-20 CN CN202310889711.8A patent/CN116610774B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105516356A (en) * | 2016-01-13 | 2016-04-20 | 广东小天才科技有限公司 | Test question correcting method, communication terminal and server |
| CN105469662A (en) * | 2016-01-18 | 2016-04-06 | 黄道成 | Student answer information real-time collection and efficient and intelligent correcting system and use method in teaching process |
| CN106548674A (en) * | 2016-09-12 | 2017-03-29 | 广东德诚网络科技有限公司 | For the method for dynamically processing and system of net marking |
| CN109697905A (en) * | 2017-10-20 | 2019-04-30 | 深圳市鹰硕技术有限公司 | A kind of exam paper marking system |
| CN107705231A (en) * | 2017-11-07 | 2018-02-16 | 语联网（武汉）信息技术有限公司 | A kind of computer assisted method to go over files, device and computer-readable recording medium |
| CN109033046A (en) * | 2018-06-25 | 2018-12-18 | 陕西师范大学 | Structuring visible document snap information input system and method |
| CN112088391A (en) * | 2018-07-06 | 2020-12-15 | 道鑛有限公司 | Examination and selection system, examination and selection device and examination and selection method |
| CN109165877A (en) * | 2018-10-11 | 2019-01-08 | 四川生学教育科技有限公司 | A kind of method and system promoting network scoring speed |
| CN112115736A (en) * | 2019-06-19 | 2020-12-22 | 广东小天才科技有限公司 | Job correction method and system based on image recognition and intelligent terminal |
| CN110390616A (en) * | 2019-07-15 | 2019-10-29 | 北京成长教育科技有限公司 | Work correction method, electronic equipment and storage medium |
| CN110705905A (en) * | 2019-10-15 | 2020-01-17 | 李晚华 | High-accuracy intelligent online paper marking method |
| CN113160005A (en) * | 2021-02-24 | 2021-07-23 | 山东智多分教育科技有限公司 | Online examination paper marking method for subjective questions |
| CN114860881A (en) * | 2022-05-13 | 2022-08-05 | 北京举个例子科技有限公司 | Subjective question marking method and device, storage medium and electronic equipment |
| CN115564606A (en) * | 2022-08-24 | 2023-01-03 | 湖南沐高信息科技有限公司 | Intelligent marking method suitable for judicial examination subjective questions |
| CN115423663A (en) * | 2022-11-04 | 2022-12-02 | 广州宏途数字科技有限公司 | Intelligent management method, system, equipment and storage medium for home operation |
| CN115759031A (en) * | 2022-11-14 | 2023-03-07 | 上海凌立健康管理股份有限公司 | Method and system for automatically scoring subjective questions |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116610774A (en) | 2023-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117033608B (en) | Knowledge graph generation type question-answering method and system based on large language model | |
| CN108304437B (en) | automatic question answering method, device and storage medium | |
| CN110147436B (en) | Education knowledge map and text-based hybrid automatic question-answering method | |
| CN109815491B (en) | Answer scoring method, device, computer equipment and storage medium | |
| KR100932141B1 (en) | Sentence Evaluation Device and Sentence Evaluation Program | |
| KR20050005523A (en) | Word association method and apparatus | |
| CN112287069B (en) | Information retrieval method and device based on voice semantics and computer equipment | |
| CN110853422A (en) | Immersive language learning system and learning method thereof | |
| CN114416942A (en) | Automatic question-answering method based on deep learning | |
| CN117149984B (en) | Customization training method and device based on large model thinking chain | |
| CN112685550B (en) | Intelligent question-answering method, intelligent question-answering device, intelligent question-answering server and computer readable storage medium | |
| CN110796911A (en) | Language learning system capable of automatically generating test questions and language learning method thereof | |
| Dumal et al. | Adaptive and automated online assessment evaluation system | |
| CN116610774B (en) | High-efficiency intelligent online paper reading auxiliary method and system | |
| JP6942759B2 (en) | Information processing equipment, programs and information processing methods | |
| JP2008090117A (en) | Learning system, similar question retrieval method, and program | |
| CN116401344A (en) | Method and device for searching table according to question | |
| CN113553416A (en) | Question answering method, system and readable storage medium based on semantic similarity | |
| CN112818102A (en) | Context-based fast question answering method for FAQ (failure of expert knowledge) knowledge base | |
| CN113342953A (en) | Government affair question and answer method based on multi-model integration | |
| CN111159360A (en) | Method and device for obtaining query topic classification model and query topic classification | |
| Harrak et al. | Categorizing students' questions using an ensemble hybrid approach | |
| CN112131889A (en) | Intelligent Chinese subjective question scoring method and system based on big data | |
| CN113569022B (en) | Method for realizing dialogue robot response engine based on cascade search | |
| CN111813919B (en) | MOOC course evaluation method based on syntactic analysis and keyword detection |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |