CN113962444A - Student quality literacy prediction system based on reinforcement learning - Google Patents
Student quality literacy prediction system based on reinforcement learning Download PDFInfo
- Publication number
- CN113962444A CN113962444A CN202111153574.9A CN202111153574A CN113962444A CN 113962444 A CN113962444 A CN 113962444A CN 202111153574 A CN202111153574 A CN 202111153574A CN 113962444 A CN113962444 A CN 113962444A
- Authority
- CN
- China
- Prior art keywords
- literacy
- student
- index
- data
- hidden
- 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
- 230000002787 reinforcement Effects 0.000 title claims abstract description 18
- 238000011156 evaluation Methods 0.000 claims abstract description 44
- 238000000034 method Methods 0.000 claims abstract description 44
- 230000008569 process Effects 0.000 claims abstract description 15
- 230000008859 change Effects 0.000 claims abstract description 8
- 239000011159 matrix material Substances 0.000 claims description 30
- 230000007704 transition Effects 0.000 claims description 14
- 238000004891 communication Methods 0.000 claims description 9
- 238000009825 accumulation Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 3
- 230000008520 organization Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 239000013598 vector Substances 0.000 claims description 3
- 238000011161 development Methods 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000008685 targeting Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/219—Managing data history or versioning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Game Theory and Decision Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Educational Technology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a student quality literacy prediction method and system based on reinforcement learning, wherein the method comprises the following steps: initializing and setting the literacy index of the student, constructing a student literacy evaluation system, and analyzing the weight of the literacy index of the student by an analytic hierarchy process; acquiring historical literacy index data of students, and evaluating the historical literacy index data through a student literacy evaluation system to construct a data set; and constructing a hidden Markov model through the data set, and predicting the literacy index of the student based on the hidden Markov model. According to the method, potential time sequence change rules and hidden parameters of the historical literacy observation data of the students are mined through the hidden Markov model, the change trend of the literacy of the students can be analyzed in advance according to the historical data, and the real-time performance and the accuracy are higher.
Description
Technical Field
The invention belongs to the technical field of student quality, and particularly relates to a student quality literacy prediction system based on reinforcement learning.
Background
In the traditional teaching practice, except that students are supervised to complete various teaching tasks, in order to ensure that the students can develop healthily and comprehensively, the development of various literacy indexes of the moral and intelligent overworks of the students needs to be tracked irregularly, and the respective development conditions of the students are mastered by analyzing the indexes of the students, so that the goal of targeting, simplicity and high efficiency are realized.
The traditional diathesis index is usually set manually, so the diathesis index is generally greatly influenced by subjective factors of people; once the setting of the indexes is finished, even if some indexes are found to be unreasonable subsequently, the indexes are not suitable to be changed in the whole evaluation period in order to ensure the integrity of the evaluation; in order to accurately master the development conditions of students, the indexes are frequently tracked and predicted irregularly, and the indexes are very complicated to count and analyze and a large amount of manpower is consumed.
Disclosure of Invention
In view of the above, the invention provides a student literacy prediction method and system based on reinforcement learning, which are used for solving the problem that dynamic tracking prediction cannot be effectively performed on student literacy.
In a first aspect of the present invention, a student quality literacy prediction method based on reinforcement learning is disclosed, the method comprising:
initializing and setting the literacy index of the student, constructing a student literacy evaluation system, and analyzing the weight of the literacy index of the student by an analytic hierarchy process;
acquiring historical literacy index data of students, and evaluating the historical literacy index data through a student literacy evaluation system to construct a data set;
and constructing a hidden Markov model through the data set, and predicting the literacy index of the student based on the hidden Markov model.
Preferably, the diathesis literacy index of the student comprises:
the first-level index and a second-level index corresponding to the first-level index; primary indicators include, but are not limited to, culture, competency, diathesis; the secondary index layer comprises, but is not limited to, classroom knowledge mastering, extraclass knowledge accumulation, cross-learning scientific knowledge accumulation and self-learning initiative corresponding to culture dimensions, social ability, organization coordination ability and engineering practice ability corresponding to ability dimensions, moral literacy, physical literacy and psychological literacy under the literacy dimensions.
Preferably, the step of constructing the student quality literacy evaluation system, wherein the step of analyzing the weight of the student quality literacy index by an analytic hierarchy process specifically comprises the following steps:
constructing a three-level student quality literacy evaluation system according to a secondary index corresponding to the primary index and a total target;
and respectively scoring the importance of each index item of the first level and the second level of the student quality literacy evaluation system by an analytic hierarchy process, calculating a fuzzy judgment consistent matrix and each weight of the two levels, and calculating the comprehensive weight of each second level index relative to the total target.
Preferably, the acquiring of the historical literacy index data of the student, the evaluating of the historical literacy index data by the student literacy evaluation system, and the constructing of the data set specifically include:
extracting feature vectors as sample data from historical literacy index data of students;
evaluating the historical literacy index data through a student literacy evaluation system to obtain a result score;
and grading the result scores, and constructing a data set by taking the grading results as corresponding sample data labels.
Preferably, the constructing of the hidden markov model by the data set specifically includes:
grade interval division is carried out on the student quality literacy indexes, the grade intervals of the divided student quality literacy indexes are expressed as hidden states of a hidden Markov model, and the number of the grade intervals is the number of the hidden states;
dividing the observation value of the student quality literacy index into a plurality of observation intervals as the observation states of the hidden Markov model, wherein the number of the observation intervals is the number of the observation states;
arranging samples in the data set according to the time sequence of the historical data, and constructing a state transition matrix according to transition probabilities among all hidden states;
constructing an observation state confusion matrix according to the occurrence probability of each index observation state and the weight of each diathesis literacy index; the initial state probabilities are set to be the same.
Preferably, the predicting the literacy index of the student based on the hidden markov model specifically comprises:
multiplying the state transition matrix P by the initial state probability to obtain an expected hidden state at the next moment;
and multiplying the expected hidden state at the next moment by the forward probability, and taking the hidden state corresponding to the maximum hidden state probability obtained after normalization processing of the multiplication result as the grade interval of the literacy prediction of the student.
Calculating to obtain a forward probability value based on the literacy index of the student to be evaluated;
and obtaining the probability of the expected hidden state as a setting parameter of the forward probability according to the state transition matrix and the initial state probability, and taking the hidden state corresponding to the maximum hidden state probability obtained after setting as a predicted level interval.
Preferably, the method further comprises:
and evaluating the student literacy for multiple times according to the time sequence through a hidden Markov model, and analyzing the time sequence change trend of the student literacy.
In a second aspect of the present invention, a student literacy prediction system based on reinforcement learning is disclosed, the system comprising:
initializing and setting the literacy index of the student, constructing a student literacy evaluation system, and analyzing the weight of the literacy index of the student by an analytic hierarchy process;
acquiring historical literacy index data of students, and evaluating the historical literacy index data through a student literacy evaluation system to construct a data set;
and constructing a hidden Markov model through the data set, and predicting the literacy of the student through the hidden Markov model.
In a third aspect of the present invention, an electronic device is disclosed, comprising: at least one processor, at least one memory, a communication interface, and a bus;
the processor, the memory and the communication interface complete mutual communication through the bus;
the memory stores program instructions executable by the processor, which program instructions are invoked by the processor to implement the method according to the first aspect of the invention.
In a fourth aspect of the invention, a computer-readable storage medium is disclosed, which stores computer instructions for causing a computer to implement the method of the first aspect of the invention.
Compared with the prior art, the invention has the following beneficial effects:
1) the method analyzes the weight of the diathesis literacy index of the student through an analytic hierarchy process, further excavates the potential time sequence change rule and hidden parameters of the historical diathesis observation data of the student through a hidden Markov model based on the weight of the diathesis literacy index of the student, predicts the change trend of the diathesis literacy index of the student, can dynamically track the diathesis literacy of the student, can predict the change trend of the diathesis literacy of the student in advance according to the historical data, and has real-time performance and forward-looking performance.
2) According to the method, the student quality literacy historical time sequence data is used as a training sample, so that hidden Markov model parameters are determined, hidden parameters in student quality literacy evaluation can be determined through the hidden Markov model, the problem that evaluation indexes are uncertain in the process of student quality literacy prediction can be solved, and compared with an evaluation mode based on artificially set evaluation indexes, the method is higher in evaluation accuracy and closer to the actual state of students.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of the student literacy prediction method based on reinforcement learning of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
As shown in fig. 1, the present invention relates to a student literacy prediction method based on reinforcement learning, which comprises:
s1, initializing and setting the literacy index of the student, constructing a student literacy evaluation system, and analyzing the weight of the literacy index of the student by an analytic hierarchy process;
s11, setting the diathesis and literacy index of the student;
the initially set literacy index follows the principles of being as extensive and comprehensive as possible. For example, setting the literacy index of the student comprises: the first-level index and a second-level index corresponding to the first-level index; primary indicators include, but are not limited to, culture, competency, diathesis; the secondary index layer includes, but is not limited to, classroom knowledge mastering, extraclass knowledge accumulation, cross-learning scientific knowledge accumulation, self-learning initiative corresponding to cultural dimensionality, interplay ability, organization coordination ability, engineering practice ability corresponding to competence dimensionality, moral literacy, physical literacy, psychological literacy and the like in literacy dimensionality.
S12, constructing a student literacy evaluation system;
and constructing a three-level student quality literacy evaluation system according to a secondary index corresponding to the primary index and the total target, wherein the primary index is a standard test layer, and the corresponding secondary index is a decision layer.
S13, analyzing the weight of the quality literacy index of the student by an analytic hierarchy process;
specifically, importance of each index item of the first level and the second level of the student quality literacy evaluation system is respectively scored through an analytic hierarchy process, a fuzzy judgment consistent matrix and each weight of the two levels are calculated, and the comprehensive weight of each second level index relative to the total target is calculated.
S2, acquiring historical literacy index data of students, and storing the activity data of each time of the students in an HDFS (Hadoop distributed File System), so that irregular tracking and prediction are facilitated; evaluating the historical literacy index data through a student literacy evaluation system to construct a data set;
s21, obtaining historical diathesis literacy index data of students, and extracting feature vectors as sample data;
s22, evaluating the historical literacy index data through a student literacy evaluation system to obtain result scores;
and S23, grading the result scores, and constructing a data set by taking the grading results as corresponding sample data labels.
S3, constructing a hidden Markov model through the data set, and predicting the literacy of the student based on the hidden Markov model.
S31, constructing a hidden Markov model;
s311, arranging samples in the data set according to the time sequence of the historical data;
specifically, historical parameter data of the evaluation index is obtained, and averaging processing is performed on a certain sampling duration to obtain an average sequence of the evaluation index parameters; for each average sequence, subtracting the value of the previous moment from the value of the next moment, and calculating the difference value in pairs to obtain a residual sequence of the index;
s312, carrying out grade interval division on the student literacy index, representing the grade interval of the divided student literacy index as a hidden state of a hidden Markov model, and constructing a hidden state matrix A, wherein the number of the grade intervals is the number of the hidden states; specifically, the residual sequence is subjected to state division to obtain different grade intervals, and the number and the size of the grade intervals are determined.
S313, dividing the student quality literacy index observed value into a plurality of observation intervals as the observation states of the hidden Markov model, wherein the number of the observation intervals is the number of the observation states;
s314, constructing a state transition matrix P according to transition probabilities among all hidden states;
s315, an observation state confusion matrix is constructed according to the probability of the observation state of each index and the weight of each diathesis literacy index. In the invention, the initial state probabilities are set to be the same.
Specifically, an observation state occurrence probability matrix is constructed according to a training set, the observation state occurrence probability matrix is weighted by adopting each index weight obtained by hierarchical analysis, and an observation state confusion matrix B is obtained after addition, wherein elements in the observation state confusion matrix B represent the occurrence probability of each observation interval in each hidden state.
And S32, predicting the literacy of the student based on the hidden Markov model.
Specifically, the probability of the hidden state is defined as a forward probability, a forward matrix C is formed by the forward probability, and the confusion matrix B is multiplied by the hidden state matrix a and the forward matrix C to obtain an observation interval D corresponding to the actually observed student literacy.
Calculating to obtain a forward probability value based on the literacy index of the student to be evaluated;
and multiplying the state transition matrix P by the initial state probability to obtain an expected hidden state at the next moment, multiplying the expected hidden state at the next moment by the forward probability, and taking the hidden state corresponding to the maximum hidden state probability obtained after normalization processing of the multiplication result as the grade interval of the literacy prediction of the student.
And S4, predicting the student literacy for multiple times according to the time sequence through a hidden Markov model, and analyzing the time sequence change trend of the student literacy.
Specifically, the hidden state probability obtained by the evaluation is used as the initial hidden state probability in the next prediction, corresponding data is updated into a state transition matrix and a confusion matrix, and multiple predictions are performed on the student quality literacy.
Counting the state transition matrix and the prediction result of the two adjacent predictions, calculating the variation of the parameter trend of the evaluation index according to the state transition matrix of the two adjacent predictions, and calculating the prediction value of the evaluation index at the next moment, wherein the specific mode is as follows: calculating the variable quantity of the index parameter in the two adjacent predictions by the state transition matrix of the multiple prediction data; counting the variation of the two adjacent predictions in the multiple predictions and the variation trend of the prediction result, calculating the mean value of the variation of the N closest predictions, adding the current value of the evaluation index parameter and the obtained variation mean value, predicting to obtain the predicted value of the evaluation index at the next moment, and predicting the quality literacy of the student at the next moment by using the hidden Markov model according to the predicted value of the evaluation index at the next moment. And the next time is a next prediction period which is a time node.
Corresponding to the embodiment of the method, the invention discloses a student quality literacy prediction system based on reinforcement learning, which comprises:
initializing and setting the literacy index of the student, constructing a student literacy evaluation system, and analyzing the weight of the literacy index of the student by an analytic hierarchy process;
acquiring historical literacy index data of students, and evaluating the historical literacy index data through a student literacy evaluation system to construct a data set;
and constructing a hidden Markov model through the data set, wherein the hidden Markov model predicts the literacy index of the student.
The above system embodiments and method embodiments are corresponding, and please refer to the method embodiments for brief description of the system embodiments.
The present invention also discloses an electronic device, comprising: at least one processor, at least one memory, a communication interface, and a bus; the processor, the memory and the communication interface complete mutual communication through the bus; the memory stores program instructions executable by the processor, which invokes the program instructions to implement the methods of the invention described above.
The invention also discloses a computer readable storage medium which stores computer instructions for causing the computer to implement all or part of the steps of the method of the embodiment of the invention. The storage medium includes: u disk, removable hard disk, ROM, RAM, magnetic disk or optical disk, etc.
The above-described system embodiments are merely illustrative, wherein the units described as separate parts may or may not be physically separate, and the parts shown as units may or may not be physical units, i.e. may be distributed over a plurality of network units. Without creative labor, a person skilled in the art can select some or all of the modules according to actual needs to achieve the purpose of the solution of the embodiment.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A student literacy prediction method based on reinforcement learning, the method comprising:
initializing and setting the literacy index of the student, constructing a student literacy evaluation system, and analyzing the weight of the literacy index of the student by an analytic hierarchy process;
acquiring historical literacy index data of students, and evaluating the historical literacy index data through a student literacy evaluation system to construct a data set;
and training a hidden Markov model through a data set, and predicting the literacy of the student based on the hidden Markov model.
2. The reinforcement learning-based student literacy prediction method of claim 1, wherein the student's literacy indicators comprise:
the first-level index and a second-level index corresponding to the first-level index; primary indicators include, but are not limited to, culture, competency, diathesis; the secondary index layer comprises, but is not limited to, classroom knowledge mastering, extraclass knowledge accumulation, cross-learning scientific knowledge accumulation and self-learning initiative corresponding to culture dimensions, social ability, organization coordination ability and engineering practice ability corresponding to ability dimensions, moral literacy, physical literacy and psychological literacy under the literacy dimensions.
3. The reinforcement learning-based student literacy prediction method according to claim 2, wherein the step of constructing a student literacy evaluation system, wherein the step of analyzing the weight of the student literacy index by an analytic hierarchy process specifically comprises the steps of:
constructing a three-level student quality literacy evaluation system according to a secondary index corresponding to the primary index and a total target;
and respectively scoring the importance of each index item of the first level and the second level of the student quality literacy evaluation system by an analytic hierarchy process, calculating a fuzzy judgment consistent matrix and each weight of the two levels, and calculating the comprehensive weight of each second level index relative to the total target.
4. The reinforcement learning-based student literacy prediction method of claim 3, wherein the obtaining of the historical literacy index data of the student, and the evaluation of the historical literacy index data by a student literacy evaluation system, the constructing of the data set specifically comprises:
extracting feature vectors as sample data from historical literacy index data of students;
evaluating the historical literacy index data through a student literacy evaluation system to obtain a result score;
and grading the result scores, and constructing a data set by taking the grading results as corresponding sample data labels.
5. The reinforcement learning-based student literacy prediction method of claim 1, wherein the constructing of the hidden markov model from the dataset specifically comprises:
arranging samples in the data set according to the time sequence of the historical data;
grade interval division is carried out on the student quality literacy indexes, the grade intervals of the divided student quality literacy indexes are expressed as hidden states of a hidden Markov model, a hidden state matrix is constructed, and the number of the grade intervals is the number of the hidden states;
dividing the observed value of the student quality literacy index in the sample into a plurality of observation intervals as the observation states of the hidden Markov model, wherein the number of the observation intervals is the number of the observation states;
constructing a state transition matrix according to transition probabilities among all hidden states;
and constructing a confusion matrix according to the probability of the observation state of each index and the weight of each diathesis literacy index.
6. The reinforcement learning-based student literacy prediction method of claim 5, wherein the predicting the student's literacy based on the hidden Markov model specifically comprises:
defining the probability of the hidden state as a forward probability, and multiplying the confusion matrix with the hidden state matrix and the forward probability to obtain an observation interval corresponding to the actually observed student literacy;
calculating to obtain a forward probability value based on the literacy index of the student to be evaluated;
multiplying the state transition matrix P by the initial state probability to obtain an expected hidden state at the next moment;
and multiplying the expected hidden state at the next moment by the forward probability, and taking the hidden state corresponding to the maximum hidden state probability obtained after normalization processing of the multiplication result as the grade interval of the literacy prediction of the student.
7. The reinforcement learning-based student literacy prediction method of claim 6, further comprising:
and evaluating the student literacy for multiple times according to the time sequence through a hidden Markov model, and analyzing the time sequence change trend of the student literacy.
8. A student literacy prediction system based on reinforcement learning, the system comprising:
initializing and setting the literacy index of the student, constructing a student literacy evaluation system, and analyzing the weight of the literacy index of the student by an analytic hierarchy process;
acquiring historical literacy index data of students, and evaluating the historical literacy index data through a student literacy evaluation system to construct a data set;
and constructing a hidden Markov model through the data set, and predicting the literacy index of the student based on the hidden Markov model.
9. An electronic device, comprising: at least one processor, at least one memory, a communication interface, and a bus;
the processor, the memory and the communication interface complete mutual communication through the bus;
the memory stores program instructions executable by the processor, the processor invoking the program instructions to implement the method of any one of claims 1-7.
10. A computer-readable storage medium storing computer instructions for causing a computer to implement the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111153574.9A CN113962444A (en) | 2021-09-29 | 2021-09-29 | Student quality literacy prediction system based on reinforcement learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111153574.9A CN113962444A (en) | 2021-09-29 | 2021-09-29 | Student quality literacy prediction system based on reinforcement learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113962444A true CN113962444A (en) | 2022-01-21 |
Family
ID=79463202
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111153574.9A Pending CN113962444A (en) | 2021-09-29 | 2021-09-29 | Student quality literacy prediction system based on reinforcement learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113962444A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117391902A (en) * | 2023-12-13 | 2024-01-12 | 北京师范大学珠海校区 | Evaluation method and device for Chinese core literacy education based on large language model |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109190895A (en) * | 2018-08-01 | 2019-01-11 | 上海电力学院 | A kind of new Engineering Undergraduate Students Comprehensive quality appraisal method |
| CN109272191A (en) * | 2018-08-09 | 2019-01-25 | 上海电力学院 | A kind of college-student complex appraisal procedure based on FAHP and PSO-SVM |
| CN109284921A (en) * | 2018-09-17 | 2019-01-29 | 北京工商大学 | Agricultural irrigation dynamic evaluation of water quality method based on Hidden Markov Model |
| CN110136832A (en) * | 2019-05-20 | 2019-08-16 | 合肥工业大学 | A kind of cognitive ability assessment system and method based on the elderly's daily behavior |
| CN113240222A (en) * | 2021-02-02 | 2021-08-10 | 广东国粒教育技术有限公司 | Student quality evaluation method, student quality evaluation system, electronic device and computer readable storage medium |
-
2021
- 2021-09-29 CN CN202111153574.9A patent/CN113962444A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109190895A (en) * | 2018-08-01 | 2019-01-11 | 上海电力学院 | A kind of new Engineering Undergraduate Students Comprehensive quality appraisal method |
| CN109272191A (en) * | 2018-08-09 | 2019-01-25 | 上海电力学院 | A kind of college-student complex appraisal procedure based on FAHP and PSO-SVM |
| CN109284921A (en) * | 2018-09-17 | 2019-01-29 | 北京工商大学 | Agricultural irrigation dynamic evaluation of water quality method based on Hidden Markov Model |
| CN110136832A (en) * | 2019-05-20 | 2019-08-16 | 合肥工业大学 | A kind of cognitive ability assessment system and method based on the elderly's daily behavior |
| CN113240222A (en) * | 2021-02-02 | 2021-08-10 | 广东国粒教育技术有限公司 | Student quality evaluation method, student quality evaluation system, electronic device and computer readable storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117391902A (en) * | 2023-12-13 | 2024-01-12 | 北京师范大学珠海校区 | Evaluation method and device for Chinese core literacy education based on large language model |
| CN117391902B (en) * | 2023-12-13 | 2024-04-26 | 北京师范大学珠海校区 | Evaluation method and device for Chinese core literacy education based on large language model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rammer et al. | Harnessing deep learning in ecology: An example predicting bark beetle outbreaks | |
| CN109598995A (en) | Intelligent tutoring system based on Bayes's knowledge trace model | |
| CN110263979A (en) | Method and device based on intensified learning model prediction sample label | |
| Orji et al. | Using machine learning to explore the relation between student engagement and student performance | |
| CN110059052A (en) | A kind of refinery scheduling case management method and computer readable storage medium | |
| CN112419029B (en) | Similar financial institution risk monitoring method, risk simulation system and storage medium | |
| CN112561320A (en) | Training method of mechanism risk prediction model, mechanism risk prediction method and device | |
| Adeyemo et al. | Effects of normalization techniques on logistic regression in data science | |
| CN115588161A (en) | Digital system based on digital twinning technology and construction method thereof | |
| Kaklauskas et al. | Crisis management model and recommended system for construction and real estate | |
| Deepika et al. | Relief-F and Budget Tree Random Forest Based Feature Selection for Student Academic Performance Prediction. | |
| Lynn et al. | Using data mining techniques to predict students’ performance. a review | |
| CN110084291B (en) | Student behavior analysis method and device based on big data extreme learning | |
| CN113962444A (en) | Student quality literacy prediction system based on reinforcement learning | |
| Popchev et al. | DataScience: Experience and Trends | |
| Lan et al. | Evaluation system of music art instructional quality based on convolutional neural networks and big data analysis | |
| Reddy et al. | Neural networks for prediction of loan default using attribute relevance analysis | |
| Kumari et al. | Analyzing the Factors Influencing the Waiting Time to First Citation and Long-Term Impact of Publications. | |
| Kumar et al. | Relevance of data mining techniques in edification sector | |
| Chen | Hotel management evaluation index system based on data mining and deep neural network | |
| CN115630732A (en) | City operation-oriented enterprise migration big data monitoring and early warning method and device | |
| Wang | Abnormal behavior identification of enterprise cloud platform financial system based on artificial neural network | |
| Khor et al. | A learning analytics approach to model and predict learners’ success in digital learning | |
| CN113837220A (en) | Robot target identification method, system and equipment based on online continuous learning | |
| Rahman et al. | Grading System Prediction of Educational Performance Analysis Using Data Mining Approach |
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 |