CN113887193A - Academic thesis evaluation method, academic thesis evaluation system, academic thesis evaluation medium and electronic equipment - Google Patents
Academic thesis evaluation method, academic thesis evaluation system, academic thesis evaluation medium and electronic equipment Download PDFInfo
- Publication number
- CN113887193A CN113887193A CN202111076357.4A CN202111076357A CN113887193A CN 113887193 A CN113887193 A CN 113887193A CN 202111076357 A CN202111076357 A CN 202111076357A CN 113887193 A CN113887193 A CN 113887193A
- Authority
- CN
- China
- Prior art keywords
- evaluation
- expert
- academic
- score
- thesis
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 111
- 238000012552 review Methods 0.000 claims abstract description 48
- 238000000034 method Methods 0.000 claims abstract description 30
- 230000011218 segmentation Effects 0.000 claims abstract description 21
- 238000003860 storage Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 abstract description 7
- 238000011160 research Methods 0.000 description 17
- 238000010586 diagram Methods 0.000 description 12
- 238000010606 normalization Methods 0.000 description 12
- 238000004590 computer program Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000013441 quality evaluation Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000005056 compaction Methods 0.000 description 2
- 239000002131 composite material Substances 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
-
- 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
- G06F16/355—Class or cluster creation or modification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Engineering & Computer Science (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Databases & Information Systems (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
Abstract
The invention provides a academic thesis evaluation method, a system, a medium and electronic equipment, belonging to the technical field of text data processing, wherein the method comprises the following steps: obtaining each evaluation index score and expert comment in the academic paper review data; carrying out word segmentation on the expert comment, removing stop words, and carrying out serialization on the expert comment; classifying the serialized expert comments according to a preset model; performing evaluation and scoring of expert comments according to the classification result; obtaining a final academic paper evaluation result according to the weighted sum of the evaluation attribution and each evaluation index score; the invention realizes more accurate and more comprehensive evaluation of the quality of the thesis by clustering or classifying the expert comments and combining the overall scores of other dimensions.
Description
Technical Field
The invention relates to the technical field of text data processing, in particular to a academic dissertation evaluation method, a system, a medium and electronic equipment.
Background
The statements in this section merely provide background information related to the present disclosure and may not constitute prior art.
The assessment of the academic thesis is carried out by assessment experts for assessing and scoring the thesis from four dimensions of topic selection and review, novelty, thesis value, scientific research capability, basic knowledge and thesis normalization, and expert assessment is attached. The paper is evaluated by integrating the four-dimensional scores and the expert comments, so that the quality of the academic paper can be better distinguished.
The quality of the academic paper is an important means for measuring the academic level, and the academic paper is concerned with the acquisition of the academic degree. Therefore, evaluation of the academic thesis is particularly important. Scientific evaluation of the academic paper can judge the research ability of students, the mastery of scientific knowledge and the achievement of scientific spirit, and can also screen problem papers and excellent papers more effectively. Therefore, scientific evaluation methods of academic papers are very important.
The inventor finds that the following technical problems exist in the prior art:
the existing academic paper evaluation method evaluates the academic paper based on the overall scores of four dimensions of the topic selection and review, the innovation, the value of the paper, the scientific research capability and basic knowledge and the normalization of the paper, but the expert evaluation mainly provides the shortcomings of the paper, and has important reference value for the quality evaluation of the paper, but the expert evaluation is not considered in the existing evaluation system, so that the accuracy and the reliability of the final evaluation result are low.
Disclosure of Invention
In order to solve the defects of the prior art, the invention provides a academic dissertation evaluation method, a system, a medium and electronic equipment, which realize more accurate and more comprehensive thesis quality evaluation by clustering or classifying expert comments and combining the overall scores of other dimensions.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention provides a academic dissertation evaluation method.
A academic thesis evaluation method comprises the following processes:
obtaining each evaluation index score and expert comment in the academic paper review data;
carrying out word segmentation on the expert comment, removing stop words, and carrying out serialization on the expert comment;
classifying the serialized expert comments according to a preset model;
performing evaluation and scoring of expert comments according to the classification result;
and obtaining a final academic thesis evaluation result according to the weighted sum of the evaluation assignment and each evaluation index score.
Further, clustering of the serialized expert comments is carried out by using the DBSCAN model, and evaluation and scoring of the expert comments are carried out according to comparison of the average value of the total scores of all papers in the clustered classes with a preset score threshold.
Furthermore, by using the DBSCAN model, the optimal hyper-parameter is searched by a grid search method, and the clustering of expert comments is performed.
Furthermore, it is excellent that the average score of all the papers in the class is greater than or equal to the first score threshold, it is good that the average score of all the papers in the class is less than the second score threshold and greater than or equal to the second threshold, and it is passing that the average score of all the papers in the class is less than the second threshold.
Further, the overall score of all papers within a class is divided equally into: the weighted sum of the individual evaluation index scores of all papers is then quotient to the number of papers.
Further, the trained TextCNN is used for carrying out the classification of the serialized expert comments, and the evaluation and the scoring of the expert comments are carried out according to the classification result.
Further, the word segmentation includes: and recombining the expert comments represented by the continuous word sequences into the word sequences according to a preset specification.
Further, stop words at least include: the Chinese characters include the Chinese characters of the Chinese characters, the adverbs, the prepositions, the conjunctions and the unique nouns of the disciplines.
Further, the serialization of the expert comments is performed, which includes: and constructing a bag-of-words model, and serializing the expert comments by using TF-IDF.
The invention provides a academic dissertation evaluation system in a second aspect.
A academic thesis evaluation system, comprising:
an information acquisition module configured to: obtaining each evaluation index score and expert comment in the academic paper review data;
a pre-processing module configured to: carrying out word segmentation on the expert comment, removing stop words, and carrying out serialization on the expert comment;
a comment classification module configured to: classifying the serialized expert comments according to a preset model;
a classification evaluation module configured to: performing evaluation and scoring of expert comments according to the classification result; (ii) a
A paper evaluation module configured to: and obtaining a final academic thesis evaluation result according to the weighted sum of the evaluation assignment and each evaluation index score.
A third aspect of the present invention provides a computer-readable storage medium on which a program is stored, the program, when executed by a processor, implementing the steps in the academic dissertation evaluation method according to the first aspect of the present invention.
A fourth aspect of the present invention provides an electronic device, including a memory, a processor, and a program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps in the academic thesis evaluation method according to the first aspect of the present invention.
Compared with the prior art, the invention has the beneficial effects that:
1. the method, the system, the medium or the electronic equipment realizes more accurate and more comprehensive evaluation of the quality of the thesis by clustering the expert comments and combining the overall scores of other dimensions.
2. The method, the system, the medium or the electronic equipment provided by the invention can be used for clustering or classifying the review comments of the academic paper to obtain papers with similar characteristics, acquiring respective typical characteristics of papers with different levels, introducing the paper comments to evaluate the quality of the papers, so that the evaluation of the paper level is more scientific, and searching the papers with typical characteristics by adjusting the scoring weight of the paper comments.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
Fig. 1 is a schematic flow chart of a academic dissertation evaluation method provided in embodiment 1 of the present invention.
Fig. 2 is a schematic flow chart of the academic dissertation evaluation method provided in embodiment 2 of the present invention.
Fig. 3 is a diagram illustrating four dimensional scores of a paper provided in embodiment 1 or 2 of the present invention.
FIG. 4 is a diagram illustrating a thesis review provided in embodiment 1 or 2 of the present invention.
Fig. 5 shows the word segmentation result provided in embodiment 1 or 2 of the present invention.
FIG. 6 shows the stop word removal results provided in embodiments 1 or 2 of the present invention.
Fig. 7 is a cloud chart of different levels of articles provided in embodiment 1 or 2 of the present invention.
FIG. 8 is a comparison graph of the total score of four-dimensional scores of papers and the combined score of the associated comments provided in example 1 or 2 of the present invention.
Fig. 9 is a functional block diagram of a system according to embodiment 3 of the present invention.
Fig. 10 is a functional block diagram of a system according to embodiment 4 of the present invention.
Detailed Description
The invention is further described with reference to the following figures and examples.
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
Example 1:
as shown in fig. 1 and fig. 3 to 8, embodiment 1 of the present invention provides a method for evaluating a academic dissertation based on DBSCAN clustering, including:
s1: acquiring academic thesis review information; obtaining each evaluation index score and expert comment from the review information;
s2: performing word segmentation on the expert comment: recombining the expert comments represented by the continuous word sequences into word sequences according to a certain standard;
removing stop words from the obtained word segmentation result: removing words which have high frequency in comments but have little practical meaning on the quality evaluation of the thesis, wherein the words mainly comprise tone words, adverbs, prepositions, conjunctions and unique nouns of various disciplines, namely the discipline terms are treated as stop words;
and constructing a bag-of-words model, and performing text serialization by using TF-IDF.
S3: searching for an optimal hyper-parameter by a grid search method by using a DBSCAN model, and clustering the thesis comments;
s4: establishing corresponding evaluation indexes for the clustered results, and performing comprehensive evaluation on various clustered papers to obtain a paper score based on paper comment;
s5: and the overall scores of four dimensions of topic selection and review, innovation, topic value, scientific research capability and basic knowledge, and the normative thesis score are combined to comprehensively evaluate the thesis, so that a more scientific academic thesis score is obtained.
The academic paper review information scores the evaluation of the papers in four dimensions, namely question selection and review, novelty, paper value, scientific research capability, basic knowledge and paper normalization of review experts. The evaluation elements of the questions and the reviews are the theoretical significance and the practicability of the research, and the understanding degree of the development conditions and the academic dynamics at home and abroad in the subject and the related subject fields. The innovation and the evaluation element of the thesis value are new insights provided for the thesis and the value of the new method; the influence or effect of the results of the thesis on scientific and technological progress, economic construction, national security and the like. The evaluation factors of scientific research capability and basic knowledge are the compaction degree of the theoretical basis embodied by the thesis; systematicness of expertise in this and related subject areas; ability to analyze problems, solve problems; the scientificity of the research method, whether advanced technology, equipment, information and the like are adopted for thesis research work. The evaluation elements of the normalization of the paper are the normalization of citation and the rigor of wind learning; the accuracy of the paper language expression, the logical tightness, the writing format and the normalization of the chart.
The expert comment mainly provides the shortcomings of the paper for evaluating the paper by the expert.
This example includes the review information of 1246 Master degree treatises covering 11 disciplinary categories. Tag refers to subject code, bm refers to paper numbers, each number corresponds to 1 master academic paper, each paper has 3 review expert evaluation information, and each subject paper is shown in table 1.
Table 1: subject paper counting
As one or more embodiments, in S1, the specific steps of obtaining the review information of the academic thesis, obtaining the scores of the evaluation indexes and the expert comments from the review information include:
first, the sum of the four-dimensional scores of all academic papers is calculated, and the review opinions of three review experts are merged.
As one or more embodiments, in S2, the specific steps of segmenting the review comment, removing stop words, constructing a bag-of-words model, and serializing the text include:
and performing word segmentation operation on the comment, and adopting a common word segmentation tool (jieba word segmentation).
And removing stop words, and constructing a common word dictionary which comprises the Chinese words, the adverbs, the prepositions, the conjunctions and the unique nouns of all disciplines. And removing the words in the common word dictionary from the evaluation comment after word segmentation.
And constructing a bag-of-words model by using a python toolkit, and performing text serialization by using TF-IDF.
As one or more embodiments, in S3, finding an optimal hyper-parameter by using a DBSCAN model and using a grid search method to cluster thesis comments, the specific steps include:
and building a DBSCAN model, finding out the hyper-parameters which enable the clustering effect to be optimal through a grid search method, and clustering the thesis review comments.
As one or more embodiments, in S4, the specific step of obtaining the score based on the paper comment includes:
and constructing an evaluation index, wherein the evaluation index is determined according to the average score of the total scores of the four dimensions of the clustered papers. Comprehensively analyzing the score distribution condition of each score section and the effect of multiple experiments, considering that the classification of students into excellent, good and passing 3 types is the best, and establishing the following evaluation indexes.
If the average score of all the papers in the clustered class is more than or equal to 90, the papers are classified as excellent, if the average score of all the papers is more than or equal to 80, the papers are classified as good, and the average score of all the papers is less than 80, the papers are classified as passing.
The total score average score calculation formula:
wherein, ScoreiThe total score in the clustered intra-class is averagely divided, n is the number of papers in the clustered intra-class, XijIs the total score of four dimensions of the paper.
Here, weighting individual dimension scores may be used to evaluate the clustered papers, rather than taking the sum of the four dimension scores directly. For example, the scoring weight of novelty and paper value can be increased, and the novelty of the paper is emphasized.
Evaluation formula:
wherein M _ S is the category.
The comment score was determined by its category, using excellent 25 points, good 20 points, and good 10 points.
Comment score calculation formula:
where M _ Score is a Score based on the comment.
As one or more embodiments, in S5, the specific step of calculating the paper composite score includes:
the comprehensive score is obtained by weighting the average total score and the score of the comment of three experts. Wherein the total score average score weight and the score weight of the comment of three review experts are respectively 0.8 and 0.2.
The comprehensive score calculation formula is as follows:
wherein, Score is the comprehensive Score, M _ Score is the Score of the comment, and X is the average Score of the total scores of three experts.
Example 2:
as shown in fig. 2 to 8, embodiment 2 of the present invention provides a academic dissertation evaluation method based on TextCNN text classification, including:
s1: acquiring academic thesis review information; obtaining each evaluation index score and expert comment from the review information;
s2: dividing the expert comments into words, and recombining the expert comments represented by the continuous word sequences into word sequences according to a certain specification; and removing stop words from the obtained word segmentation result, and removing words which have high frequency of occurrence in the comment but have little practical significance to the quality evaluation of the paper. The method mainly comprises the following steps of (1) processing the words of tone, adverbs, prepositions, conjunctions and unique nouns of various disciplines, namely the discipline terms as stop words; constructing a bag-of-words model, and performing text serialization by using TF-IDF;
s3: training a textCNN model, classifying the paper comments, and giving the classified paper scores of various papers based on the paper comments;
s4: and the overall scores of four dimensions of topic selection and review, innovation, topic value, scientific research capability and basic knowledge, and the normative thesis score are combined to comprehensively evaluate the thesis, so that a more scientific academic thesis score is obtained.
The academic paper review information scores the evaluation of the papers in four dimensions, namely question selection and review, novelty, paper value, scientific research capability, basic knowledge and paper normalization of review experts. The evaluation elements of the questions and the reviews are the theoretical significance and the practicability of the research, and the understanding degree of the development conditions and the academic dynamics at home and abroad in the subject and the related subject fields. The innovation and the evaluation element of the thesis value are new insights provided for the thesis and the value of the new method; the influence or effect of the results of the thesis on scientific and technological progress, economic construction, national security and the like. The evaluation factors of scientific research capability and basic knowledge are the compaction degree of the theoretical basis embodied by the thesis; systematicness of expertise in this and related subject areas; ability to analyze problems, solve problems; the scientificity of the research method, whether advanced technology, equipment, information and the like are adopted for thesis research work. The evaluation elements of the normalization of the paper are the normalization of citation and the rigor of wind learning; the accuracy of the paper language expression, the logical tightness, the writing format and the normalization of the chart.
The expert comment mainly provides the shortcomings of the paper for evaluating the paper by the expert.
This example includes the review information of 1246 Master degree treatises covering 11 disciplinary categories. Tag refers to subject code, bm refers to paper numbers, each number corresponds to 1 master academic paper, each paper has 3 review expert evaluation information, and each subject paper is shown in table 2.
Table 2: subject paper counting
As one or more embodiments, in S1, the specific steps of obtaining the review information of the academic thesis, obtaining the scores of the evaluation indexes and the expert comments from the review information include:
first, the sum of the four-dimensional scores of all academic papers is calculated, and the review opinions of three review experts are merged.
As one or more embodiments, in S2, the specific steps of segmenting the review comment, removing stop words, constructing a bag-of-words model, and serializing the text include:
and performing word segmentation operation on the comment, and adopting a common word segmentation tool (jieba word segmentation).
And removing stop words, and constructing a common word dictionary which comprises the Chinese words, the adverbs, the prepositions, the conjunctions and the unique nouns of all disciplines. And removing the words in the common word dictionary from the evaluation comment after word segmentation.
And constructing a bag-of-words model by using a python toolkit, and performing text serialization by using TF-IDF.
As one or more embodiments, in S3, the training of the TextCNN model and the classification of the paper comments, and the specific steps of giving the paper scores of the classified papers based on the paper comments include:
and acquiring a paper label based on four-dimensional scores of the paper, building and training a textCNN model, and classifying the paper review comments.
And obtaining a paper label, and determining the evaluation label according to the total score of the four-dimensional scores of the paper. Comprehensively analyzing the score distribution condition of each score section and the effect of multiple experiments, considering that the classification of students into excellent, good and passing 3 classes is the best, and the classification method is as follows.
The total score calculation formula is as follows:
wherein, ScoreiFor the general score of the article, 4 is four evaluation dimensions, XijScores were scored for four dimensions of the paper.
Evaluation formula:
wherein M _ S is the category.
The comment score was determined by its category, using excellent 25 points, good 20 points, and good 10 points.
Where M _ Score is a Score based on the comment.
As one or more embodiments, in S4, the specific step of calculating the paper composite score includes:
the comprehensive score is obtained by weighting the total score average and the comment score of three review experts, wherein the total score average and the comment score of the three review experts are respectively weighted by 0.8 and 0.2.
The comprehensive score calculation formula is as follows:
wherein, Score is the comprehensive Score, M _ Score is the Score of the comment, and X is the average Score of three experts in the paper.
Example 3:
as shown in fig. 9, embodiment 3 of the present invention provides a system for evaluating a academic dissertation based on DBSCAN clustering, including:
an information acquisition module configured to: acquiring academic thesis review information; obtaining each evaluation index score and expert comment from the review information;
a pre-processing module configured to: performing word segmentation on the expert comment; removing stop words; constructing a bag-of-words model, and performing text serialization by using TF-IDF;
a comment clustering module configured to: searching for an optimal hyper-parameter by a grid search method by using a DBSCAN model, and clustering the thesis comments;
a cluster evaluation module configured to: establishing corresponding evaluation indexes for the clustered results, and evaluating various clustered papers to obtain a paper score based on paper comment;
a paper evaluation module configured to: the method is characterized by comprehensively evaluating the thesis through the general scores of four dimensions of topic selection and review, innovation, thesis value, scientific research capability and basic knowledge, thesis normalization and thesis scoring based on thesis comments.
The working method of the system is the same as the academic thesis evaluation method based on DBSCAN clustering provided in embodiment 1, and is not described herein again.
Example 4:
as shown in fig. 10, embodiment 4 of the present invention provides a academic dissertation evaluation system based on TextCNN text classification, including:
an information acquisition module configured to: acquiring academic thesis review information; obtaining each evaluation index score and expert comment from the review information;
a pre-processing module configured to: performing word segmentation on the expert comment; removing stop words; constructing a bag-of-words model, and performing text serialization by using TF-IDF;
a classification evaluation module configured to: training a textCNN model, classifying the paper comments, and giving the classified paper scores of various papers based on the paper comments;
a comprehensive evaluation module configured to: the method is characterized by comprehensively evaluating the thesis through the general scores of four dimensions of topic selection and review, innovation, thesis value, scientific research capability and basic knowledge, thesis normalization and thesis scoring based on thesis comments.
The working method of the system is the same as the academic dissertation evaluation method based on TextCNN text classification provided in embodiment 2, and details are not repeated here.
Example 5:
embodiment 5 of the present invention provides a computer-readable storage medium on which a program is stored, the program implementing the steps in the academic dissertation evaluation method according to embodiment 1 or embodiment 2 of the present invention when executed by a processor.
Example 6:
embodiment 6 of the present invention provides an electronic device, which includes a memory, a processor, and a program stored in the memory and executable on the processor, and when the processor executes the program, the method implements the steps in the academic dissertation evaluation method according to embodiment 1 or embodiment 2 of the present invention.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A academic dissertation evaluation method is characterized by comprising the following processes:
obtaining each evaluation index score and expert comment in the academic paper review data;
carrying out word segmentation on the expert comment, removing stop words, and carrying out serialization on the expert comment;
classifying the serialized expert comments according to a preset model;
performing evaluation and scoring of expert comments according to the classification result;
and obtaining a final academic thesis evaluation result according to the weighted sum of the evaluation assignment and each evaluation index score.
2. The academic thesis evaluation method of claim 1, wherein,
and clustering the serialized expert comments by using the DBSCAN model, and evaluating and assigning the scores of the expert comments according to the comparison of the average value of the total scores of all papers in the clustered class and a preset score threshold.
3. The academic thesis evaluation method according to claim 2, wherein,
and searching for the optimal hyper-parameter by using a DBSCAN model through a grid search method, and clustering expert comments.
4. The academic thesis evaluation method according to claim 2, wherein,
the average score of all the papers in the class is superior if the average score is greater than or equal to the first score threshold, the average score of all the papers in the class is less than the second score threshold and is good if the average score is greater than or equal to the second threshold, and the average score of all the papers in the class is passing if the average score is less than the second threshold.
5. The academic thesis evaluation method according to claim 2, wherein,
the total score of all papers in a class is divided equally into: the weighted sum of the individual evaluation index scores of all papers is then quotient to the number of papers.
6. The academic thesis evaluation method of claim 1, wherein,
and carrying out serialized classification of the expert comments by using the trained textCNN, and carrying out evaluation and scoring of the expert comments according to a classification result.
7. The academic thesis evaluation method of claim 1, wherein,
the word segmentation comprises the following steps: and recombining the expert comments represented by the continuous word sequences into the word sequences according to a preset specification.
Alternatively, the first and second electrodes may be,
stop words, including at least: the Chinese characters include the Chinese characters, the adverbs, the prepositions, the conjunctions and the unique nouns of the disciplines;
alternatively, the first and second electrodes may be,
serializing the expert comments, comprising: and constructing a bag-of-words model, and serializing the expert comments by using TF-IDF.
8. A system for evaluating a academic thesis, comprising:
an information acquisition module configured to: obtaining each evaluation index score and expert comment in the academic paper review data;
a pre-processing module configured to: carrying out word segmentation on the expert comment, removing stop words, and carrying out serialization on the expert comment;
a comment classification module configured to: classifying the serialized expert comments according to a preset model;
a classification evaluation module configured to: performing evaluation and scoring of expert comments according to the classification result; (ii) a
A paper evaluation module configured to: and obtaining a final academic thesis evaluation result according to the weighted sum of the evaluation assignment and each evaluation index score.
9. A computer-readable storage medium, on which a program is stored, which, when being executed by a processor, carries out the steps of the academic dissertation evaluation method according to any one of claims 1 to 7.
10. An electronic device comprising a memory, a processor and a program stored on the memory and executable on the processor, wherein the processor implements the steps of the academic thesis evaluation method according to any one of claims 1 to 7 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111076357.4A CN113887193A (en) | 2021-09-14 | 2021-09-14 | Academic thesis evaluation method, academic thesis evaluation system, academic thesis evaluation medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111076357.4A CN113887193A (en) | 2021-09-14 | 2021-09-14 | Academic thesis evaluation method, academic thesis evaluation system, academic thesis evaluation medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113887193A true CN113887193A (en) | 2022-01-04 |
Family
ID=79009125
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111076357.4A Pending CN113887193A (en) | 2021-09-14 | 2021-09-14 | Academic thesis evaluation method, academic thesis evaluation system, academic thesis evaluation medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113887193A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107239900A (en) * | 2017-06-01 | 2017-10-10 | 陕西学前师范学院 | Based on the Undergraduate Thesis quality evaluating method of cloud model can be opened up |
| KR20180127840A (en) * | 2017-05-22 | 2018-11-30 | 주식회사 제오시스 | Method of evaluating paper and method of recommending expert |
| CN109857862A (en) * | 2019-01-04 | 2019-06-07 | 平安科技（深圳）有限公司 | File classification method, device, server and medium based on intelligent decision |
| CN112488507A (en) * | 2020-11-30 | 2021-03-12 | 广东电网有限责任公司 | Expert classification portrait method and device based on clustering and storage medium |
-
2021
- 2021-09-14 CN CN202111076357.4A patent/CN113887193A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20180127840A (en) * | 2017-05-22 | 2018-11-30 | 주식회사 제오시스 | Method of evaluating paper and method of recommending expert |
| CN107239900A (en) * | 2017-06-01 | 2017-10-10 | 陕西学前师范学院 | Based on the Undergraduate Thesis quality evaluating method of cloud model can be opened up |
| CN109857862A (en) * | 2019-01-04 | 2019-06-07 | 平安科技（深圳）有限公司 | File classification method, device, server and medium based on intelligent decision |
| CN112488507A (en) * | 2020-11-30 | 2021-03-12 | 广东电网有限责任公司 | Expert classification portrait method and device based on clustering and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 马莉萍;: "研究生学位论文质量评价体系的构建", 天津理工大学学报, no. 06, 30 December 2005 (2005-12-30) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112214610B (en) | Entity relationship joint extraction method based on span and knowledge enhancement | |
| JP7090936B2 (en) | ESG-based corporate evaluation execution device and its operation method | |
| CN103995876A (en) | Text classification method based on chi square statistics and SMO algorithm | |
| CN109522412B (en) | Text emotion analysis method, device and medium | |
| CN105389583A (en) | Image classifier generation method, and image classification method and device | |
| KR102105319B1 (en) | Esg based enterprise assessment device and operating method thereof | |
| CN106776672A (en) | Technology development grain figure determines method | |
| Verma et al. | An ensemble approach to identifying the student gender towards information and communication technology awareness in european schools using machine learning | |
| Salim et al. | Time series prediction on college graduation using kNN algorithm | |
| CN110134777A (en) | Problem De-weight method, device, electronic equipment and computer readable storage medium | |
| CN112651296A (en) | Method and system for automatically detecting data quality problem without prior knowledge | |
| CN110458600A (en) | Portrait model training method, device, computer equipment and storage medium | |
| Palani et al. | Clustering Techniques to Identify Low-engagement Student Levels. | |
| CN110310012B (en) | Data analysis method, device, equipment and computer readable storage medium | |
| CN115794803A (en) | Engineering audit problem monitoring method and system based on big data AI technology | |
| CN109241276B (en) | Word classification method in text, and speech creativity evaluation method and system | |
| CN116861358A (en) | BP neural network and multi-source data fusion-based computing thinking evaluation method | |
| CN113887193A (en) | Academic thesis evaluation method, academic thesis evaluation system, academic thesis evaluation medium and electronic equipment | |
| Nohuddin et al. | Monitoring students performance using self organizing map trend clustering | |
| CN111341404B (en) | Electronic medical record data set analysis method and system based on ernie model | |
| CN113888265A (en) | Product recommendation method, device, equipment and computer-readable storage medium | |
| CN110633466B (en) | Short message crime identification method and system based on semantic analysis and readable storage medium | |
| Razak et al. | Prediction of Secondary Students Performance: A Case Study | |
| Ogihara et al. | Student retention pattern prediction employing linguistic features extracted from admission application essays | |
| Zhao | College English Score Analysis Based on Data Mining Algorithm |
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 |