CN106934742A - A kind of Impoverished College Studentss assessment method - Google Patents
A kind of Impoverished College Studentss assessment method Download PDFInfo
- Publication number
- CN106934742A CN106934742A CN201710096553.5A CN201710096553A CN106934742A CN 106934742 A CN106934742 A CN 106934742A CN 201710096553 A CN201710096553 A CN 201710096553A CN 106934742 A CN106934742 A CN 106934742A
- Authority
- CN
- China
- Prior art keywords
- neural network
- college
- student
- studentss
- impoverished
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000013528 artificial neural network Methods 0.000 claims abstract description 11
- 230000036541 health Effects 0.000 claims abstract description 11
- 238000012360 testing method Methods 0.000 claims abstract description 7
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 claims abstract description 6
- 238000003062 neural network model Methods 0.000 claims description 15
- 210000002569 neuron Anatomy 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 7
- 230000007935 neutral effect Effects 0.000 claims description 6
- 238000002790 cross-validation Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 6
- 239000000463 material Substances 0.000 description 4
- 238000003066 decision tree Methods 0.000 description 3
- 208000017667 Chronic Disease Diseases 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 241000721047 Danaus plexippus Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001010 compromised effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000037213 diet Effects 0.000 description 1
- 235000005911 diet Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 230000001568 sexual effect Effects 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- 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)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Computational Linguistics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Primary Health Care (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a kind of Impoverished College Studentss assessment method, comprise the following steps:1. get parms:Obtain by evaluating and charge to ten metrics of index in the college student data of system, ten indexs be respectively family average monthly income FI, per capita the moon revenue and expenditure than FIOR, there is labour member to account for the ratio FMR of kinsfolk, special H/S FT, kinsfolk's health condition FH, tuition fee source ST, cost of living source SC, average daily messes consumption SE, class Democracy test and judge SS and extension section situation SCS;2. Model checking;3. result is obtained.The present invention is by using the preceding method to there is supervision neural network algorithm model, and more reasonably index for selection, so that the degree of accuracy can exceed that 93.3%, it is largely avoided the situation of over-fitting, accuracy rate is preferable, and then enables more true, fair school, convenience, expeditiously evaluates poor student.
Description
Technical field
The present invention relates to a kind of Impoverished College Studentss assessment method.
Background technology
For the financial burden of the family that alleviates poverty, the study for perplexing student because of economic problems is reduced as far as possible.Party and state
Family always payes attention to and implements such as to poverty-stricken mountains work《Subsidized on the especially difficult student that lived to academy
Notice》、《On further strengthening the notice that colleges and universities subsidize Poor students work》And《The Ministry of Finance of the Ministry of Education is on recognizing
The true instruction for carrying out institution of higher education's poor student identification》Poor student is benefited Deng some policies, makes him
Reduce the pressure of financial burden and then securely learn.Poor student is defined according to the Ministry of Education:Recruited in country
In ordinary higher learning school universities and colleges student, because household economy is difficult, education expenses are highly difficult or financial insolvency educational expenses
Student.But there is certain ambiguity in regulation, cause shortage of each colleges and universities in the practical operation evaluated to poor student
Unified module.The missing of standard causes that the sponsored mode of many colleges and universities is random stronger.The appearance of this phenomenon deviates from
Original intention and reduce the utilization benefit of poor fund that country is subsidized Impoverished College Studentss, while being also difficult to play country to height
Deng the subsidy function of education, fair, just and impartial right of the citizen to higher education is compromised.In order to avoid above-mentioned phenomenon
Generation, the method for necessary use unified standard.On the basis of investigation, using combination of qualitative and quantitative analysis
Poor student's identifying indexes setup, overcomes the simplification of evaluation work with random, the utilization benefit of the tired fund of continuous improvement Ji.
The unfair problem present in poor student's evaluation causes the concern of scholar, and as vast colleges and universities' financing work
Personnel and researcher's concern, various assessment methods are suggested solution fairness problem.Li Ming rivers et al.
The evaluation work using the guide for method poor student of decision tree is proposed with Tao Shuanhong.For them to deliberated index indistinction pair
Treat, Chen Xiao etc. proposes method of the traditional decision-tree based on Weighted Constraint in poor student for the skewed popularity of deliberated index.Pay
Precious monarch is assert using the association rule mining based on FP-growth to poor student.Hu Lei and Liu Hongqi et al. are sharp respectively
The identification to Poor students merit is realized with Synthetic Grey assessment method.
The index that above-mentioned research is used is lower so that using higher than the practical operation of reality or the acquisition sexual valence of index
Method can not be well carried out and using decision tree there are problems that overfitting and Synthetic Grey evaluate to matrix
Consistency checking is without the guidance compared with science.And to the actual of poor student and be easily obtained deliberated index research it is less.
The content of the invention
In order to solve the above technical problems, the invention provides a kind of Impoverished College Studentss assessment method, the Impoverished College Studentss are commented
Method is determined by using the preceding method to there is supervision neural network algorithm model, and more reasonably index for selection, so that
The degree of accuracy can exceed that 93.3%, can be largely avoided the situation of over-fitting, and accuracy rate is preferable.
The present invention is achieved by the following technical programs.
A kind of Impoverished College Studentss assessment method that the present invention is provided, comprises the following steps:
1. get parms:Obtain by evaluating and charge to ten metrics of index, ten in the college student data of system
Individual index be respectively family average monthly income FI, per capita the moon revenue and expenditure than FIOR, have labour member account for kinsfolk ratio FMR,
Special H/S FT, kinsfolk's health condition FH, tuition fee source ST, cost of living source SC, average daily messes consumption SE, class
Democracy test and judge SS and extension section situation SCS;
2. Model checking:Ten indexs for obtaining are input into neural network model and are calculated, neural network model is
Three layers, three layers are respectively input layer, hidden layer, output layer, and wherein hidden layer neuron number uses Cross-validation
Calculate, neural network model is obtained using preceding to the neural network algorithm for having supervision;
3. result is obtained:Obtain the result that neural network model calculates output.
The neural network algorithm that the forward direction has supervision is LVQ neural network algorithms.
The neural network model is calculated using 300~500 samples as training set.
The special H/S FT, kinsfolk's health condition FH, tuition fee source ST, cost of living source SC, extension section feelings
Condition SCS is with the dummy variable of integer representation in the range of 0~9.
The beneficial effects of the present invention are:By using the preceding method to there is supervision neural network algorithm model, Yi Jigeng
Rational index for selection, so that the degree of accuracy can exceed that 93.3%, is largely avoided the situation of over-fitting, accuracy rate
Ideal, and then enable more true, fair school, convenience, expeditiously evaluate poor student.
Specific embodiment
Be described further below technical scheme, but claimed scope be not limited to it is described.
The invention provides a kind of Impoverished College Studentss assessment method, comprise the following steps:
1. get parms:Obtain by evaluating and charge to ten metrics of index, ten in the college student data of system
Individual index be respectively family average monthly income FI, per capita the moon revenue and expenditure than FIOR, have labour member account for kinsfolk ratio FMR,
Special H/S FT, kinsfolk's health condition FH, tuition fee source ST, cost of living source SC, average daily messes consumption SE, class
Democracy test and judge SS and extension section situation SCS;
2. Model checking:Ten indexs for obtaining are input into neural network model and are calculated, neural network model is
Three layers, three layers are respectively input layer, hidden layer, output layer, and wherein hidden layer neuron number uses Cross-validation
Calculate, neural network model is obtained using preceding to the neural network algorithm for having supervision;
3. result is obtained:Obtain the result that neural network model calculates output.
The neural network algorithm that the forward direction has supervision is LVQ neural network algorithms.
The neural network model is calculated using 300~500 samples as training set.
The special H/S FT, kinsfolk's health condition FH, tuition fee source ST, cost of living source SC, extension section feelings
Condition SCS is with the dummy variable of integer representation in the range of 0~9.
Specifically, it is 400 experimental results of sample according to training set, when hidden layer neuron number is 42, finally
Resultant error absolute value reaches minimum.
Using colleges and universities' data to poor student's assessment of data over the years, when training set is 400 samples, final result is accurate
Rate is 96.9%, and when training set is 300 samples, final result accuracy rate is 93.3%, when training set is less than 300,
Accuracy rate is difficult to ensure that, and easily the situation of over-fitting occurs.
Thus, the present invention to student carries out overall merit and assumes height for the deficiency of existing method using deliberated index
There is specific functional relation between the existing a large amount of assessment of data in school and poor student's classification, this specific function relation is available such as
Lower form description:
C=f (indicator1, indicator2, indicator3 ..., indicatorK)
Wherein, C represents types of poverty;Indicatork represents k-th evaluation index;F represents that poor student's type is commented with K
Certain number mapping relations between valency index.In the specific function relation that mass data is contained is excavated, neutral net need not
Set up expression formula just can extract potential, valuable knowledge, model or rule from substantial amounts of data.LVQ networks are
The a kind of of neutral net can obtain accurate result by the study to input pattern.Therefore, have selected LVQ nerve nets herein
Network is used as the f function in model.By carrying out Comprehensive Assessment to each student under evaluation index, and then obtain more considerable public affairs
Positive evaluation result.The method of the evaluation modeling based on student assessment index is divided into following 5 steps:
(1) assume there is specific functional relation between college student assessment of data and poor student's classification;
(2) enter row index to Impoverished College Studentss assessment of data to extract to objectively respond student's poverty classification;
(3) structure of LVQ networks, input layer number, competition layer neuron number and output layer neuron are determined
Number;
(4) already present a large amount of poor student's data learnt by LVQ neutral nets, train and dived with excavating them
Functional relation;
(5) using evaluation index as function f input, function f is output as the poor classification of student;By LVQ nerves
Network draws poor classification C.The result drawn by LVQ neutral nets is contrasted with concrete class, verifies the reasonable of model
Property.
The selection of index is closely bound up with the poverty degree of student.Unified Impoverished College Studentss there is no to recognize at present due to China
Determine index, therefore, the present invention from current conditions screened 2 major class 10 easily obtain and concentrated expression student's family situation and
The index of student's self-condition.From the point of view of reality, the material conditions of family directly determine the poverty degree of student;And it is big
Part poor student is consistent in the material conditions that the daily performance of school also can bear in its family.Therefore, from home background
The major class index of situation 2 with student itself is just capable of the poverty degree of concentrated expression student.Below by the major class index of comprehensive analysis 2
And its measure.
First, family's class index
A. family's average monthly income:The average moon total income of student's family, can reflect family's funds source in 1 year
Width, is represented with FI.Refer to that target value can be obtained from the proof that village of counties and townships issues;
B. the equal moon revenue and expenditure ratio of people:The ratio of average monthly income (FI) and monthly average expenditure (FO), energy in student's family 1 year
The balance between revenue and expenditure degree of enough concentrated expression one families, is represented with FIOR.Its value is obtained with equation below:
FIOR=FI/FO
C. labour member accounts for the ratio of kinsfolk:Member has labour capacity to account for the ratio of kinsfolk in student's family
Example, can reflect the Main Economic source of one family, be represented with FMR.Refer to that target value can be from the proof that village of counties and townships issues
Obtain;
D. special H/S:Can not resistance if family meets with, then the poverty degree of family can be caused to increase.
Special H/S is represented whether there is special circumstances, foster home, martyr family, minimum living and single-parent family 5 respectively with FT herein
Type;They are replaced with numerical value 0,1,2,3,4 respectively in model.The judgement of special H/S needs related testimonial material
Corresponding judgement can just be given.
E. kinsfolk's health condition:Kinsfolk's health status can affect to the poverty degree of family,
Therefore kinsfolk's health condition is that model considers object.Kinsfolk's health condition represents with FH, unsoundness, grave illness, single parent
7 classes such as chronic disease, parents' chronic disease, one-level deformity family, two grades of disabled families, itself illness;Use numerical value respectively in a model
0,1,2,3,4,5,6 substitutes.The health condition of kinsfolk is other kinds of in addition to healthy type to be judged to need related card
Bright material can just give corresponding judgement.
2nd, student's oneself factor class index
A. tuition fee is originated:Loan payment its tuition fee is generally required for underprivileged home, therefore the source situation of tuition fee also can
It is enough to illustrate H/S to a certain extent.In a model, tuition fee is originated and is represented with ST, is divided into loan and normal two types difference
Represented with 1 and 0.The acquisition of tuition fee source-information can subsidize center and obtain from school;
B. the cost of living is originated:It is identical with the implication that tuition fee is originated.Represented with SC, be divided into family and pay, take a part-time job while studying at school, provide a loan
With and take a part-time job while studying at school and three classifications of loan portfolio mode, be indicated with 0,1,2,3 respectively in a model;The index is obtained
Obtain identical with tuition fee source;
C. average daily messes consumption:In student's current consumption, saving is often compared in the personal lifestyle consumption of poor student, very
I haven't seen you for ages there is situation about spending freely.In today of the consumption diversification, the consumption data that student is set up comprehensively is often relatively difficult, and learns
The raw diet consumption situation in school can reflect by school's grasp and to a certain extent the overall consumption of student again.Cause
This using the overall consumption of monthly messes consumption reflection student, is represented with SE in a model.In a practical situation, due to family
In emergency case, sick, extracurricular practice situations such as students' union ask for leave, therefore SE is using effective feelings of number of days consumption in an academic year
Condition.Its value is obtained with following formula, and wherein n represents effective number of days, and Bi, Li, Si are the consumption in i-th day.The index can
Obtained with from logistics center.
D. class's Democracy test and judge:Class classmate everybody there is a steelyard to pass through daily behavior, personal consumption at heart to weigh
Each student of class.Therefore, class's Democracy test and judge can grade this student from another angle.In a model, class
Democracy test and judge represents that its value is obtained using formula below, and APPROVEi represents that class member agrees with situation with SS.N-1 is represented
The sum of other classmates in addition to oneself.The specific value of the index can be voted by class and be obtained.
E. extension section situation:The student that national poverty-stricken mountains policy is mainly to aid in underprivileged home finishes school, either
Poor student is also that non-poor student should try to learn during school.And if student's extension section, learned in national policy and student
Main task is practised to run counter to.So if student's extension section, just accordingly cancels the poor subsidy in the year.In a model, student's extension section
Situation represents with SCS, is divided into nothing and has and is represented with 0 and 1 respectively.
Interaction of the LVQ network structures simply and by internal element can just complete sufficiently complex classification treatment,
Also in being easy to for the various numerous and diverse scattered design condition in design domain to converge to conclusion.And LVQ is without to input pattern
Carry out the pretreatment works such as normalization, orthogonalization, it is only necessary to which entering the calculating of row distance just can realize the identification of pattern, simply
It is easy.
LVQ networks constitute respectively input layer, competition layer and output layer and constitute as typical neutral net, by 3 layers,
Wherein input layer uses part mutual contact mode with competition layer using full mutual contact mode, competition layer and output layer.
The learning rules of LVQ networks are that the connection weight between input layer and competition layer is carried out in the state of having supervision
Update, network more can be fully reflected a kind of algorithm of feature of existing data after weights are updated.The step of learning rules
It is rapid as follows:
STEP1:Connection weight Wij and learning rate η between input layer and competition layer is initialized;
STEP2:Calculate the distance between competition layer neuron and input vector x (x1, x2, x3 ..., xn):
STEP3:The selection competition layer neuron minimum with input vector distance, if di is minimum, remembers the line being attached thereto
Property output layer neuron class label be Ci;
STEP4:CX is the corresponding class label of input vector, if Ci=CX, weights is adjusted with following method:
wij_new=wij_current+η(x-wij_current)
Otherwise, it is adjusted as follows:
wij_new=wij_current-η(x-wij_current)。
Claims (4)
1. a kind of Impoverished College Studentss assessment method, it is characterised in that:Comprise the following steps:
1. get parms:Obtain by evaluating and charge to ten metrics of index in the college student data of system, ten fingers
Mark be respectively family average monthly income FI, per capita the moon revenue and expenditure than FIOR, there is labour member to account for the ratio FMR of kinsfolk, special
H/S FT, kinsfolk's health condition FH, tuition fee source ST, cost of living source SC, average daily messes consumption SE, class's democracy
Test and appraisal SS and extension section situation SCS;
2. Model checking:Ten indexs for obtaining are input into neural network model and are calculated, neural network model is three layers,
Three layers are respectively input layer, hidden layer, output layer, and wherein hidden layer neuron number is calculated using Cross-validation,
Neural network model is obtained using preceding to the neural network algorithm for having supervision;
3. result is obtained:Obtain the result that neural network model calculates output.
2. Impoverished College Studentss assessment method as claimed in claim 1, it is characterised in that:The forward direction has the neutral net of supervision
Algorithm is LVQ neural network algorithms.
3. Impoverished College Studentss assessment method as claimed in claim 1, it is characterised in that:The neural network model uses 300
~500 samples are calculated as training set.
4. Impoverished College Studentss assessment method as claimed in claim 1, it is characterised in that:The special H/S FT, family
Member's health condition FH, tuition fee source ST, the cost of living source SC, extension section situation SCS are with integer representation in the range of 0~9
Dummy variable.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710096553.5A CN106934742A (en) | 2017-02-22 | 2017-02-22 | A kind of Impoverished College Studentss assessment method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710096553.5A CN106934742A (en) | 2017-02-22 | 2017-02-22 | A kind of Impoverished College Studentss assessment method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106934742A true CN106934742A (en) | 2017-07-07 |
Family
ID=59423732
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710096553.5A Pending CN106934742A (en) | 2017-02-22 | 2017-02-22 | A kind of Impoverished College Studentss assessment method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106934742A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108074208A (en) * | 2017-11-27 | 2018-05-25 | 同帅科技(天津)有限公司 | Disadvantaged group's auxiliary system and its method based on dining room data |
CN108170765A (en) * | 2017-12-25 | 2018-06-15 | 合肥城市云数据中心股份有限公司 | Recommend method based on the poverty-stricken mountains in school behavioral data multidimensional analysis |
CN108197657A (en) * | 2018-01-04 | 2018-06-22 | 成都寻道科技有限公司 | A kind of student's economic situation Forecasting Methodology based on campus data |
CN108876409A (en) * | 2018-06-28 | 2018-11-23 | 深信服科技股份有限公司 | Authentication method, system and relevant device are subsidized in a kind of colleges and universities' poverty |
CN108960273A (en) * | 2018-05-03 | 2018-12-07 | 淮阴工学院 | A kind of poor student's identification based on deep learning |
CN109145113A (en) * | 2018-08-24 | 2019-01-04 | 北京桃花岛信息技术有限公司 | A kind of student's poverty degree prediction technique based on machine learning |
CN110210815A (en) * | 2019-04-04 | 2019-09-06 | 安徽汇迈信息科技有限公司 | A kind of poor student based on big data precisely subsidizes system |
CN112215385A (en) * | 2020-03-24 | 2021-01-12 | 北京桃花岛信息技术有限公司 | Student difficulty degree prediction method based on greedy selection strategy |
-
2017
- 2017-02-22 CN CN201710096553.5A patent/CN106934742A/en active Pending
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108074208A (en) * | 2017-11-27 | 2018-05-25 | 同帅科技(天津)有限公司 | Disadvantaged group's auxiliary system and its method based on dining room data |
CN108170765A (en) * | 2017-12-25 | 2018-06-15 | 合肥城市云数据中心股份有限公司 | Recommend method based on the poverty-stricken mountains in school behavioral data multidimensional analysis |
CN108170765B (en) * | 2017-12-25 | 2021-11-12 | 合肥城市云数据中心股份有限公司 | Poverty-stricken and living fund assisting recommendation method based on multidimensional analysis of on-school behavior data |
CN108197657A (en) * | 2018-01-04 | 2018-06-22 | 成都寻道科技有限公司 | A kind of student's economic situation Forecasting Methodology based on campus data |
CN108197657B (en) * | 2018-01-04 | 2022-04-19 | 成都寻道科技有限公司 | Student economic condition prediction method based on campus data |
CN108960273A (en) * | 2018-05-03 | 2018-12-07 | 淮阴工学院 | A kind of poor student's identification based on deep learning |
CN108876409A (en) * | 2018-06-28 | 2018-11-23 | 深信服科技股份有限公司 | Authentication method, system and relevant device are subsidized in a kind of colleges and universities' poverty |
CN109145113A (en) * | 2018-08-24 | 2019-01-04 | 北京桃花岛信息技术有限公司 | A kind of student's poverty degree prediction technique based on machine learning |
CN109145113B (en) * | 2018-08-24 | 2021-12-21 | 北京桃花岛信息技术有限公司 | Student poverty degree prediction method based on machine learning |
CN110210815A (en) * | 2019-04-04 | 2019-09-06 | 安徽汇迈信息科技有限公司 | A kind of poor student based on big data precisely subsidizes system |
CN112215385A (en) * | 2020-03-24 | 2021-01-12 | 北京桃花岛信息技术有限公司 | Student difficulty degree prediction method based on greedy selection strategy |
CN112215385B (en) * | 2020-03-24 | 2024-03-19 | 北京桃花岛信息技术有限公司 | Student difficulty degree prediction method based on greedy selection strategy |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106934742A (en) | A kind of Impoverished College Studentss assessment method | |
Nikolova et al. | In transit: The well-being of migrants from transition and post-transition countries | |
Allah Pitchay et al. | Factors influencing the behavioral intentions of muslim employees to contribute to cash-waqf through salary deductions | |
Varghese | Challenges of massification of higher education in India | |
Rahman et al. | The effect of remittance on energy consumption: Panel cointegration and dynamic causality analysis for South Asian countries | |
Mehrotra | Realising the demographic dividend: Policies to achieve inclusive growth in India | |
Lim et al. | Income inequality, trade and financial openness | |
Wei et al. | An approach to multiple attribute group decision making with interval intuitionistic trapezoidal fuzzy information | |
Buera et al. | From micro to macro development | |
Johnston et al. | Financial decision-making in the household: Exploring the importance of survey respondent, health, cognitive ability and personality | |
Reber | From separate and unequal to integrated and equal? School desegregation and school finance in Louisiana | |
Yun et al. | Analysis of the teaching quality on deep learning-based innovative ideological political education platform | |
Kupets | The development and the side effects of remittances in the CIS countries: The case of Ukraine | |
Białowolski et al. | Decomposition of the financial capability construct: A structural model of debt knowledge, skills, confidence, attitudes, and behavior | |
CN107564391A (en) | Public administration method and training platform based on simulation sand table | |
Bau | School competition and product differentiation | |
Hannaford et al. | Predicting nursing baccalaureate program graduates using machine learning models: A quantitative research study | |
Yao et al. | Schooling returns for migrant workers in China: Estimations from the perspective of the institutional environment in a rural setting | |
Nepal | Remittances and livelihood strategies: A case study in Eastern Nepal | |
Kimani et al. | The effects of pupil-teacher ratio and expenditure per pupil on educational attainment in South Africa | |
Yang et al. | Urban economic resilience within the Yangtze River Delta urban agglomeration: Exploring spatially correlated network and spatial heterogeneity | |
Brun et al. | Effect of central transfers on municipalities' own revenue mobilization: Do conflict and local revenue management matter? | |
Andrews et al. | An estimation of the aggregate educational production function for public schools in Louisiana | |
Shi | Determination of real estate price based on principal component analysis and artificial neural networks | |
Duan et al. | Multi-Index and Hierarchical Comprehensive Evaluation System for Training Quality of Science and Engineering Postgraduates. |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170707 |
|
RJ01 | Rejection of invention patent application after publication |