CN109509123A - College entrance will based on general aspect analysis model makes a report on recommender system and its method - Google Patents
College entrance will based on general aspect analysis model makes a report on recommender system and its method Download PDFInfo
- Publication number
- CN109509123A CN109509123A CN201811204270.9A CN201811204270A CN109509123A CN 109509123 A CN109509123 A CN 109509123A CN 201811204270 A CN201811204270 A CN 201811204270A CN 109509123 A CN109509123 A CN 109509123A
- Authority
- CN
- China
- Prior art keywords
- examinee
- profession
- aspiration
- university
- program module
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000007405 data analysis Methods 0.000 claims abstract description 6
- 238000012545 processing Methods 0.000 claims abstract description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000013208 measuring procedure Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 abstract description 3
- 238000013139 quantization Methods 0.000 abstract description 3
- 238000007726 management method Methods 0.000 description 18
- 239000003814 drug Substances 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000013178 mathematical model Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 3
- IMNFDUFMRHMDMM-UHFFFAOYSA-N N-Heptane Chemical compound CCCCCCC IMNFDUFMRHMDMM-UHFFFAOYSA-N 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 125000001400 nonyl group Chemical group [H]C([*])([H])C([H])([H])C([H])([H])C([H])([H])C([H])([H])C([H])([H])C([H])([H])C([H])([H])C([H])([H])[H] 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009223 counseling Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000004080 punching Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000002747 voluntary effect Effects 0.000 description 1
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
- 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
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
- G06Q50/2057—Career enhancement or continuing education service
Abstract
The invention discloses a kind of college entrance wills based on general aspect analysis model to make a report on recommender system and its method, comprising: parameter recording program module calculates the university for meeting examinee's situation and profession for inputting examinee's parameter by parameter recording program interface；Admission divides Prediction program module, and the current year acceptance cut-off point of each profession of each university of specified province enrollment are predicted according to college entrance examination data over the years；Volunteer recommended program module, the algorithm model of mode and built-in a variety of data processings is made a report on for the aspiration according to target province, the universities and colleges and profession that each aspiration column is recommended, and the information such as general safety index Jing Guo the calculated recommended university of data analysis process and tailored index are calculated；Program module as the result is shown, for showing the aspiration recommendation results information of the aspiration recommended program module output.Using the present invention, can be provided for college entrance examination examinee once every year science, intelligence, quantization college entrance will make a report on rapid evaluation service.
Description
Technical field
The present invention relates to data analysis and application technologies more particularly to a kind of college entrance examination will based on general aspect analysis model
Hope makes a report on recommender system and its method.
Background technique
College entrance examination examinee often relies on teacher, parent, relatives and friends and other people experience to carry out when aspiration is made a report on
Selection often feels confused and feels at a loss when in face of thousands of a universities and colleges and hundreds of professions.College entrance examination money currently on the market
It interrogates website and universities and colleges and specialized query is provided, also provide some college entrance will auxiliary tools, but often function is fairly simple, and exist
Following multiple problems:
1) personal interest is not considered.Many examinees, only to prepare for the college entrance examination and effort, lack to life, occupation in previous decade
The thinking or planning of carry out system.There are investigation statistics, nearly seventy percent student does not know about entered oneself for the examination profession, nearly there are four one-tenth university students
It does not like and learns profession, obtain employment unrelated with profession.Be difficult in aspiration selection and career planing selection will be personal emerging by examinee at present
Interest hobby is taken into account.
2) big data technology is not deep enough.Voluntary service product currently on the market, greatly all in the starting stage, substantially
Be be in collect data and simple statistics stage, mathematical modeling and machine learning ability it is more weak.It can only be gone through mostly to examinee
The function of history data query not can be carried out the big data modeling analysis of real meaning.
3) applications for university consulting is main by rule of thumb.It is to rely on " Senior Expert " that college entrance will, which makes a report on counseling services mostly, at present
It assumes personal, relies on expertise, guidance examinee buys expensive one-to-one expert service, this is only that tradition aspiration expert answers questions meeting
Reprint on the line of mode, bad adaptability, efficiency are also very low.
It would therefore be highly desirable to a Internet application system made a report on for solution college entrance examination candidates' aspiration.
Summary of the invention
In view of this, the main purpose of the present invention is to provide a kind of college entrance wills based on general aspect analysis model to fill out
Recommender system and its method are reported, by the data founding mathematical models to national college entrance examination over the years, in conjunction with the examination announced after college entrance examination
The admission point that school report one divides one grade of table and acceptance cut-off point precisely to predict each profession in each school, and utilize general aspect parser
With big data assist multiple attribute decision making (MADM) algorithm for college entrance examination examinee once every year provide science, intelligence, quantization college entrance will fill out
Report rapid evaluation service.
In order to achieve the above objectives, the technical scheme of the present invention is realized as follows:
A kind of college entrance will based on general aspect analysis model makes a report on recommender system, including parameter recording program module,
Admission divides Prediction program module, aspiration recommended program module and program module as the result is shown；Wherein:
The parameter recording program module, for inputting examination mark, occupational planning, profession happiness by parameter recording program interface
Good, region hobby examinee's parameter, calculates the university for meeting examinee's situation and profession；
The admission divides Prediction program module, predicts that each university of specified province enrollment is each special according to college entrance examination data over the years
The current year acceptance cut-off point of industry；
The aspiration recommended program module makes a report on mode according to the aspiration in target province for storing the data calculated
With the algorithm model of built-in a variety of data processings, universities and colleges and profession that each aspiration column is recommended are calculated, and pass through data
The general safety index and tailored index of the calculated recommended university of analytic process are recommended all to meet examinee's interest in university
Each of hobby profession provides the admission number of prediction, admission threshold point and admission safety and divides information；
The program module as the result is shown for showing the parameter inputted through the parameter recording program module, and is used for
Show the aspiration recommendation results information of the aspiration recommended program module output.
Wherein, the parameter recording program module, the requirement for also supporting that according to target province aspiration makes a report on mode are pushed away to examinee
Recommend the profession relevant to the interest of examinee of profession set by university and the university and admission information.
Wherein, the aspiration recommended program module further include:
Personalized measuring procedure module is configured each index according to oneself personalized preference for examinee, formulates
Completely personalized model out；With,
General aspect analyzes program module, and the prediction model for being established according to college entrance examination data over the years utilizes the prediction mould
The type enrollment plan in province and examinee's individualized selection in conjunction with where each profession of current year each university in examinee, are analyzed with GMA and are calculated
Method quickly calculates all universities for meeting examinee's situation and profession matching according to the college entrance examination score and individualized selection of examinee, is used in combination
Multiple attribute decision making (MADM) algorithm recommends school and profession for each aspiration column in parallel wish or the aspiration columns at different levels preferentially volunteered, and calculates
The general safety index and tailored index of system recommendation university.
The aspiration recommended program module is also used to export the record in the past period by program module as the result is shown
Take historical data.
A kind of college entrance will based on general aspect analysis model makes a report on recommended method, and this method comprises the following steps:
A, the step of setting model index；The index includes professional preference degree, region preference degree, occupational planning, employment
The model index of situation；
B, setting personalized the step of measuring；Specifically include: examinee passes through system interface pair according to the personal preference of oneself
The index of profession hobby, region hobby and occupational planning is configured marking, makes the model of complete personalization；
C, the step of data analysis is carried out；In conjunction with current year enrollment plan and examinee's individualized selection, general aspect is used
It analyzes GMA algorithm and carries out data analytical calculation；
D, in a manner of parallel wish, the tailored index of universities and colleges' profession is shown to examinee, the higher selection of tailored index is more
It is suitble to the reality of examination.
Wherein, the step C is specifically included:
According to the prediction model that college entrance examination data over the years are established, the province in conjunction with where each profession of current year each university in examinee
Enrollment plan and examinee's individualized selection are quickly calculated with GMA parser according to the college entrance examination score and individualized selection of examinee
Meet all universities and the profession matching of examinee's situation, and is each aspiration column recommendation in parallel wish with multiple attribute decision making (MADM) algorithm
School and profession, computing system recommend university general safety index and tailored index, and to recommend university in it is all meet examine
Each of raw hobby profession provides the admission number of prediction, admission threshold point and admission safety point.
College entrance will based on general aspect analysis model of the invention makes a report on recommender system and its method, and have has as follows
Beneficial effect:
Recommender system is made a report on using the college entrance will of the invention based on general aspect analysis model, it can be to the whole nation over the years
The data founding mathematical models of college entrance examination, one point of one grade of table and acceptance cut-off point in conjunction with the examinee's achievement announced after college entrance examination are precisely pre-
The admission point of each profession in each school is surveyed, and is annual one using general aspect parser and big data auxiliary multiple attributive decision making method
The college entrance examination examinee of degree provide science, intelligence, quantization college entrance will make a report on rapid evaluation service.It is only provided with similar product single
Data are different, which makes a report on recommender system and pass through each profession of the mathematical model high-precision forecast Chu Ge universities and colleges of science
" safety is divided to " of current year admission and " threshold is divided to " two class data.With the mathematical model, identical data are inputted, can obtain phase
Same conclusion, therefore the directive significance that there is science to make a report on college entrance will.
Detailed description of the invention
Fig. 1 is the Score on Prediction that the embodiment of the present invention makes a report on recommender system based on the college entrance will of general aspect analysis model
Model schematic；
Fig. 2 is the structure composed that the embodiment of the present invention makes a report on recommender system based on the college entrance will of general aspect analysis model
Schematic diagram；
Fig. 3 is the process schematic that college entrance will shown in Fig. 2 of the present invention makes a report on that recommender system uses general aspect to analyze.
Specific embodiment
With reference to the accompanying drawing and the embodiment of the present invention the present invention is described in further detail.
Fig. 1 is the Score on Prediction that the embodiment of the present invention makes a report on recommender system based on the college entrance will of general aspect analysis model
Model schematic.
As shown in Figure 1, it is somebody's turn to do the analysis prediction model that the college entrance will based on general aspect analysis model makes a report on recommender system,
It is based primarily upon college entrance examination data over the years (at least collecting the data such as 5 years or more each universities and colleges' profession acceptance cut-off point, admission numbers),
In conjunction with the enrollment plan data of current year each each profession of universities and colleges and using relevant data algorithm (for example, utilizing big data technology
Multiple attribute decision making (MADM) algorithm, including DEA, SAW, AHP, TOPSIS etc.) it is calculated, so that the admission door of each universities and colleges be calculated
Sill are divided to and safety is divided to two class data and safety index and tailored index.
Here, the safety point is the higher fractional predicted in admission score section, there is very big once meeting or exceeding
Hold admission；The threshold point is then the lower score predicted in admission score section, and that is enrolled if the score is not achieved can
Can property by very little.
Fig. 2 is the structure composed that the embodiment of the present invention makes a report on recommender system based on the college entrance will of general aspect analysis model
Schematic diagram.
As shown in Fig. 2, being somebody's turn to do the college entrance will based on general aspect analysis model makes a report on recommender system, it mainly include that parameter is recorded
Enter program module, admission point Prediction program module, volunteer recommended program module and as the result is shown program module.The aspiration is recommended
Program module further includes personalized measuring procedure module and general aspect analysis program module.Wherein:
The parameter recording program module, for inputting examination mark, occupational planning, profession happiness by parameter recording program interface
Examinees' parameters such as good, region hobby, calculate the university for meeting examinee's situation and profession, and according to target province aspiration makes a report on mode
It is required that recommending the profession relevant to the interest of examinee of profession set by university and the university and admission information to examinee.
The admission divides Prediction program module, predicts that each university of specified province enrollment is each special according to college entrance examination data over the years
The current year acceptance cut-off point of industry, including threshold point and safety point.
With reference to Fig. 1, for the example schematic predicted using the Score on Prediction model current year acceptance cut-off point.
Example 1: following table is the prediction mould with Jiangsu Province 2013 and 2 years 2014 first college admission data with us
The threshold point for each profession of a collection of university in Jiangsu Province's enrollment in 2015 that type calculates exists with each profession of 2015 Nian Ge universities
The reality of Jiangsu Province's enrollment really enrolls the minimum point of percentage compared.
Illustrate: the identical profession of different universities being considered as difference in table, i.e., using school's name as the prefix of profession, such as
There are mathematics major in Tsinghua University and Peking University, are considered as " Tsinghua University's mathematics major " and " Peking University in model calculating
Two different professions of mathematics major ".The threshold point for each profession of current year each university that prediction model calculates is according to prediction
The variance of the admission average mark of each profession and minimum point of the admission of prediction and average mark is calculated by the parameter of model specification
's；Similarly, the prediction admission safety point of each profession of each university is admission average mark and the prediction of each profession according to prediction
The variance of best result and average mark is calculated by the parameter of model specification.
Example 2: following table is the prediction model with the 2013 and 2 years 2014 a collection of college admission data in Jiangsu Province with us
Admission average mark and 2015 Nian Ge university each professions of 2015 calculated in each profession of a collection of university of Jiangsu Province's enrollment
The percentage that the true admission average mark of enrollment compares in Jiangsu.
The target for making a report on recommender system the present invention is based on the college entrance will of general aspect analysis model is to establish science, intelligence
The college entrance will that can, quantify makes a report on assessment online service, constructs comprehensive universities and colleges' specialized information for examinee, personalized aspiration pushes away
Assessment report is recommended, college admission examination user group is obtained, provides college entrance examination relevant data analysis professional service.Further, the college entrance examination
Aspiration makes a report on recommender system can also accumulate college entrance examination data and user data in service process, be done step-by-step based on big data
Deep learning and analytical technology, establish examinee individual portrait, for student provide for individual individual character interaction go to school community, choose a job
Select and study abroad the service such as selection.
The data calculated are stored in the aspiration recommended program module, the will by the aspiration recommended program module
Be willing to recommended program module, the aspiration comprising target province make a report on mode (parallel wish or preferential aspiration) and a variety of data processings and
The algorithm model of analysis, the algorithm model include general aspect analysis (GMA) algorithm, more attribute aid decision algorithms, safety
Exponentiation algorithm and tailored index algorithm etc..
Preferably, the embodiment of the present invention emphasis, which uses general aspect, analyzes (GMA) algorithm.
So-called general aspect analyzes (GMA), is Switzerland's astrophysics and aerodynamics scientist doctor Zwicky in 1960
A kind of modeling method proposed during California Institute of Technology (Caltech) work at the beginning of age end to the 1970's, to containing higher-dimension
Data and be difficult to the challenge quantified carry out global analysis it is effective.Zwicky carries out astrophysics object with this method
Classification, and it is used successfully to the development of jet engine and rocket moving system, and solve the law of space travelling and celestial body immigrant
Problem.
In recent years, general aspect analysis method is successfully used for policy analysis and future by the researcher of US and European
Learn the research in terms of (future studies), Switzerland's national defence research center (Swedish especially headed by Ritchey
National Defence Research Agency) scientist successfully use computer science and technology, make general aspect
Analysis method can quickly calculate complicated big data decision problem optimal under the auxiliary of computer from a large amount of scheme
Answer.
People complicated policy is analyzed and to the future may appear the case where predict when often encounter
Following three classes problem: the first, certain key factors are difficult to quantitative description, for example, those be related in terms of society and policy it is artificial because
Element and the consciousness centered on self are all not easy to carry out quantitative description.The second, certain factors be it is non-deterministic, do not have also usually
There is complete description.Third, specific solution procedure are dependent on the assurance to the correlation between each factor.
Different from traditional operation research method, the analysis of area of computer aided general aspect handles decision problem from another angle,
This method makes correctly those factors for being difficult to quantitative description on the basis of using the method for quantitative analysis as far as possible
Judgement, in Preserving problems consistency.
The various possible cloth of big data will report of college entrance are analyzed using general aspect parser in the embodiment of the present invention
Office can calculate all possible university for meeting examinee's score and interest and profession, with multiple attribute decision making (MADM) algorithm to examinee
Best one-to-one aspiration is provided and makes a report on recommendation and risk assessment (detailed process refers to Fig. 3).In addition, in the embodiment of the present invention,
It additionally uses more attribute aid decision algorithms to calculate for school recommendation and index, refer to safely using the progress of safety index algorithm
Several calculating is used to calculate tailored index using tailored index algorithm.
The program module as the result is shown, the applications for university mode taken according to the target province that examinee selects are (i.e. parallel
Aspiration or preferential aspiration), each universities and colleges for volunteering column recommendation are shown to examinee and are calculated in profession and data analysis program module
The general safety index and tailored index of recommended university out recommend all each of examinee's hobbies that meet in university special
Industry provides the admission number of prediction, admission threshold point and admission safety point and the admission history of the past period (such as 2 years)
Data.
Shown as shown in figure 3, making a report on recommender system for college entrance will of the embodiment of the present invention using the process that general aspect is analyzed
It is intended to.
The embodiment of the present invention is analyzed using general aspect, is asked professional preference degree, the region preference degree etc. in aspiration selection
Topic is modeled, and examinee is from largely selecting decision in embankment case to go out optimal case for auxiliary.The process specifically includes that
Step 31: the step of setting model index.The index includes: professional preference degree, region preference degree, occupation rule
It draws, the models index such as employment situation.
These indexs are the partial parameters of model, wherein profession hobby, region hobby and the parameter values such as occupational planning by
Examinee provides, but system of the invention by inquiring the hobby of examinee and providing can suggest that examinee is helped to determine these parameters.
The information and system that the numerical value of employment situation parameter is provided by system according to examinee are by analyzing each profession employment tendency and market
Demand is calculated and is obtained.The other parameters of model further include major popularity, ranking, Graduate Employment situation, place city
Academic atmosphere and the level of economic development, place university relevant speciality number, quasi- enrollment etc., the numerical value of these parameters is by model
Module calculating is collected and analyzed according to back-end data and is obtained.
Step 32: the step of setting personalization is measured.Examinee is configured each index according to oneself personalized preference,
Make the model of complete personalization.Detailed process include: according to oneself personalized preference by system interface to profession hobby,
The indexs such as region hobby and occupational planning are configured marking, make the model of complete personalization.
Step 33: the step of carrying out data analysis.In conjunction with current year enrollment plan and examinee's individualized selection, use is general
Morphological analysis (GMA) algorithm carries out data analytical calculation.
It specifically includes: the prediction model established according to college entrance examination data over the years, in conjunction with each profession of current year each university in examinee
The enrollment plan (prediction) in place province and examinee's individualized selection, with GMA parser according to the college entrance examination score of examinee and
Propertyization selection quickly calculates all universities for meeting examinee's situation and profession matching, and is parallel wish with multiple attribute decision making (MADM) algorithm
In each aspiration column (or the aspiration columns at different levels preferentially volunteered) recommend school and profession, computing system recommend university general safety
Index and tailored index, and the admission people of prediction are provided to each of examinee's hobby professions that meet all in recommendation university
Number, admission threshold point and admission safety point, and 2 years admission historical datas in the past, including admission number, minimum point of admission and
Enroll best result.
The chance that the higher selection of safety index obtains admission is bigger, and equally, the higher selection of tailored index is more suitable
The situation of examinee individual.
Step 34: in a manner of parallel wish, the tailored index of universities and colleges' profession, the higher choosing of tailored index are shown to examinee
Select the reality of more suitable examination.
The will of recommender system is made a report on the college entrance will that Henan Province's prediction data in 2016 illustrates the present invention below
It is willing to that recommendation process, these examples give the practical admission data in Henan Province in 2016 as comparison simultaneously.
Mode is made a report on using 6 parallel wishs by Henan Province, be denoted as respectively A aspiration, B aspiration, C aspiration, D aspiration, E aspiration and
F volunteers six aspiration columns.Examinee make a report on strategy it is as follows: A aspiration university be can " punching " university, expression examinee's achievement
Meet or the admission of the slightly below university is offline, but still has admission may.It is " guaranteeing the minimum " university that F, which volunteers university, indicates examinee point
Number is higher by certain amount than the college admission best result, unless something unexpected happened, admission will have full assurance.B aspiration, C will
It is willing to, D aspiration and E aspiration university are volunteered between university and F aspiration university somewhere between A by different level.
College entrance will of the present invention is made a report on recommender system and is divided using the safety index that it is calculated as index, and A volunteers the peace of universities and colleges
For total index number between 54 to 62, B volunteers the safety index of universities and colleges between 63 to 71, and the safety index of C aspiration universities and colleges is arrived 72
Between 80, D volunteers the safety index of universities and colleges between 81 to 89, and E volunteers the safety index of universities and colleges between 90 to 94, F aspiration
Safety index between 95 to 100.Safety index is enrolled gap and the enrollment etc. in middle section point by examinee's examination mark and prediction
Factor determines that the universities and colleges' safety index of same class the high, and it is bigger to enroll possibility.
3~example of example 8 is the example of Henan Province's literal arts examinee's applications for university in 2016, and 9~example of example 14 is Henan Province 2016 years
The example of natural sciences examinee's applications for university.The parameter that examinee inputs in following Examples is virtual value.
Example 3: being the parameter of Henan Province's literal arts examinee's first in 2016 input below:
Examination mark and type: 619 literal arts；
Batch: 1；
Professional preference degree (arranging from high to low):
Want to learn: management, economy
It is not desired to learn: philosophy, pedagogy, literature, medicine
Region preference degree (arranges) from high to low:
Want to go to: Beijing, Henan, Shandong
Do not want to go to: Shanxi, Hebei, Liaoning, Heilungkiang, Shanghai
Occupational planning: it is engaged in management work.
Following table is the study under 1 university and the university in the A aspiration that recommender system is recommended to examinee's first with the examinee
The relevant profession of interest (be only listed in the relevant speciality for meeting examinee's score under the aspiration column, other admission scores it is excessively high or
Too low relevant speciality is not listed):
Example 4: being the parameter of Henan Province's literal arts examinee's second in 2016 input below:
Examination mark and type: 577 literal arts；
Batch: 1；
Professional preference degree (arranging from high to low):
Want to learn: management, economy；
It is not desired to learn: philosophy, pedagogy, literature, medicine；
Region preference degree (arranges) from high to low:
Want to go to: Beijing, Henan, Shandong；
Do not want to go to: Shanxi, Hebei, Liaoning, Heilungkiang, Shanghai；
Occupational planning: it is engaged in management work.
Following table is the study under 1 university and the university in the C aspiration that recommender system is recommended to examinee's second with the examinee
The relevant profession of interest (be only listed in the relevant speciality for meeting examinee's score under the aspiration column, other admission scores it is excessively high or
Too low relevant speciality is not listed):
Example 5: being the parameter of Henan Province literal arts examinee third in 2016 input below:
Examination mark and type: 541 literal arts；
Batch: 1；
Professional preference degree (arranging from high to low):
Want to learn: management, economy；
It is not desired to learn: philosophy, pedagogy, literature, medicine；
Region preference degree (arranges) from high to low:
Want to go to: Beijing, Henan, Shandong；
Do not want to go to: Shanxi, Hebei, Liaoning, Heilungkiang, Shanghai；
Occupational planning: it is engaged in management work.
Following table is the study under 1 university and the university in the E aspiration that recommender system is recommended to examinee third with the examinee
The relevant profession of interest (be only listed in the relevant speciality for meeting examinee's score under the aspiration column, other admission scores it is excessively high or
Too low relevant speciality is not listed):
Example 6: being the parameter of Henan Province's literal arts examinee's fourth in 2016 input below:
Examination mark and type: 515 literal arts；
Batch: 2；
Professional preference degree (arranging from high to low):
Want to learn: management, economy；
It is not desired to learn: philosophy, pedagogy, literature, medicine；
Region preference degree (arranges) from high to low:
Want to go to: Beijing, Henan, Shandong；
Do not want to go to: Shanxi, Hebei, Liaoning, Heilungkiang, Shanghai；
Occupational planning: it is engaged in management work.
Following table is the study under 1 university and the university in the B aspiration that recommender system is recommended to examinee's fourth with the examinee
The relevant profession of interest (be only listed in the relevant speciality for meeting examinee's score under the aspiration column, other admission scores it is excessively high or
Too low relevant speciality is not listed):
Example 7: being the parameter of Henan Province literal arts examinee penta in 2016 input below:
Examination mark and type: 499 literal arts；
Batch: 2；
Professional preference degree (arranging from high to low):
Want to learn: management, economy；
It is not desired to learn: philosophy, pedagogy, literature, medicine；
Region preference degree (arranges) from high to low:
Want to go to: Beijing, Henan, Shandong；
Do not want to go to: Shanxi, Hebei, Liaoning, Heilungkiang, Shanghai
Occupational planning: it is engaged in management work.
Following table is the study under 1 university and the university in the D aspiration that recommender system is recommended to examinee penta with the examinee
The relevant profession of interest (be only listed in the relevant speciality for meeting examinee's score under the aspiration column, other admission scores it is excessively high or
Too low relevant speciality is not listed):
Example 8: being the parameter of the own input of Henan Province literal arts examinee in 2016 below:
Examination mark and type: 479 literal arts；
Batch: 2；
Professional preference degree (arranging from high to low):
Want to learn: management, economy；
It is not desired to learn: philosophy, pedagogy, literature, medicine；
Region preference degree (arranges) from high to low:
Want to go to: Beijing, Henan, Shandong；
Do not want to go to: Shanxi, Hebei, Liaoning, Heilungkiang, Shanghai；
Occupational planning: it is engaged in management work.
Following table is the study under 1 university and the university in the recommender system F aspiration that oneself recommends to examinee with the examinee
The relevant profession of interest (be only listed in the relevant speciality for meeting examinee's score under the aspiration column, other admission scores it is excessively high or
Too low relevant speciality is not listed):
Example 9: being the parameter that Henan Province natural sciences examinee in 2016 inputs heptan below:
Examination mark and type: 614 natural sciences；
Batch: 1；
Professional preference degree (arranging from high to low):
Want to learn: machinery, electronic information, chemical industry；
It is not desired to learn: management, geology, bioscience；
Region preference degree (arranges) from high to low:
Want to go to: Shanxi, Hebei, Liaoning, Heilungkiang, Shanghai；
Do not want to go to: Beijing, Henan, Shandong；
Occupational planning: engineer.
Following table is the study under 1 university and the university in the A aspiration that service system is recommended heptan to examinee with the examinee
The relevant profession of interest (be only listed in the relevant speciality for meeting examinee's score under the aspiration column, other admission scores it is excessively high or
Too low relevant speciality is not listed):
Example 10: being the parameter of Henan Province's pungent input of natural sciences examinee in 2016 below:
Examination mark and type: 582 natural sciences；
Batch: 1；
Professional preference degree (arranging from high to low):
Want to learn: machinery, electronic information, chemistry；
It is not desired to learn: management, geology, bioscience；
Region preference degree (arranges) from high to low:
Want to go to: Shanxi, Hebei, Liaoning, Heilungkiang, Shanghai；
Do not want to go to: Beijing, Henan, Shandong；
Occupational planning: engineer.
Following table is recommender system to the study under 1 university and the university in the C aspiration of the pungent recommendation of examinee with the examinee
The relevant profession of interest (be only listed in the relevant speciality for meeting examinee's score under the aspiration column, other admission scores it is excessively high or
Too low relevant speciality is not listed):
Example 11: being the parameter of Henan Province's natural sciences examinee's nonyl in 2016 input below:
Examination mark and type: 570 natural sciences；
Batch: 1；
Professional preference degree (arranging from high to low):
Want to learn: machinery, electronic information, chemistry；
It is not desired to learn: management, geology, bioscience；
Region preference degree (arranges) from high to low:
Want to go to: Shanxi, Hebei, Liaoning, Heilungkiang, Shanghai；
Do not want to go to: Beijing, Henan, Shandong；
Occupational planning: engineer.
Following table is the study under 1 university and the university in the E aspiration that recommender system is recommended to examinee's nonyl with the examinee
The relevant profession of interest (be only listed in the relevant speciality for meeting examinee's score under the aspiration column, other admission scores it is excessively high or
Too low relevant speciality is not listed):
Example 12: being the parameter that Henan Province inputs natural sciences examinee's last of the ten Heavenly stems in 2016 below:
Examination mark and type: 510 natural sciences；
Batch: 2；
Professional preference degree (arranging from high to low):
Want to learn: machinery, electronic information, chemistry；
It is not desired to learn: management, geology, bioscience；
Region preference degree (arranges) from high to low:
Want to go to: Shanxi, Hebei, Liaoning, Heilungkiang, Shanghai；
Do not want to go to: Beijing, Henan, Shandong；
Occupational planning: engineer.
Following table is the study under 1 university and the university in the B aspiration that recommender system is recommended to examinee's last of the ten Heavenly stems with the examinee
The relevant profession of interest (be only listed in the relevant speciality for meeting examinee's score under the aspiration column, other admission scores it is excessively high or
Too low relevant speciality is not listed):
Example 13: being the parameter that Henan Province inputs natural sciences examinee's third of the twelve Earthly Branches in 2016 below:
Examination mark and type: 480 natural sciences；
Batch: 2；
Professional preference degree (arranging from high to low):
Want to learn: machinery, electronic information, chemistry；
It is not desired to learn: management, geology, bioscience；
Region preference degree (arranges) from high to low:
Want to go to: Shanxi, Hebei, Liaoning, Heilungkiang, Shanghai；
Do not want to go to: Beijing, Henan, Shandong；
Occupational planning: engineer.
Following table is the study under 1 university and the university in the D aspiration that recommender system is recommended to examinee's third of the twelve Earthly Branches with the examinee
The relevant profession of interest (be only listed in the relevant speciality for meeting examinee's score under the aspiration column, other admission scores it is excessively high or
Too low relevant speciality is not listed):
Example 14: being the parameter of the Henan Province natural sciences examinee fourth of the twelve Earthly Branches in 2016 input below:
Examination mark and type: 469 natural sciences；
Batch: 2；
Professional preference degree (arranging from high to low):
Want to learn: machinery, electronic information, chemistry；
It is not desired to learn: management, geology, bioscience；
Region preference degree (arranges) from high to low:
Want to go to: Shanxi, Hebei, Liaoning, Heilungkiang, Shanghai；
Do not want to go to: Beijing, Henan, Shandong；
Occupational planning: engineer.
Following table is the study under 1 university and the university in the F aspiration that recommender system is recommended to the examinee fourth of the twelve Earthly Branches with the examinee
The relevant profession of interest (be only listed in the relevant speciality for meeting examinee's score under the aspiration column, other admission scores it is excessively high or
Too low relevant speciality is not listed):
The foregoing is only a preferred embodiment of the present invention, is not intended to limit the scope of the present invention.
Claims (6)
1. a kind of college entrance will based on general aspect analysis model makes a report on recommender system, which is characterized in that including parameter typing
Program module, admission divide Prediction program module, aspiration recommended program module and program module as the result is shown；Wherein:
The parameter recording program module, for being liked by parameter recording program interface input examination mark, occupational planning, profession,
Examinee's parameter of region hobby, calculates the university for meeting examinee's situation and profession；
The admission divides Prediction program module, predicts each profession of each university of specified province enrollment according to college entrance examination data over the years
Current year acceptance cut-off point；
The aspiration recommended program module makes a report on mode and interior according to the aspiration in target province for storing the data calculated
The algorithm model for a variety of data processings set is calculated universities and colleges and profession that each aspiration column is recommended, and analyzes by data
The general safety index and tailored index of the calculated recommended university of process are recommended all to meet examinee's hobby in university
Each of profession admission number, admission threshold point and the admission safety of prediction are provided divide information；
The program module as the result is shown, for showing the parameter inputted through the parameter recording program module, and for showing
The aspiration recommendation results information of the aspiration recommended program module output.
2. the college entrance will according to claim 1 based on general aspect analysis model makes a report on recommender system, which is characterized in that
The parameter recording program module, the requirement for also supporting that according to target province aspiration makes a report on mode recommend university and the university to examinee
Set profession professional and admission information relevant to the interest of examinee.
3. the college entrance will according to claim 1 based on general aspect analysis model makes a report on recommender system, which is characterized in that
The aspiration recommended program module further include:
Personalized measuring procedure module is configured each index according to oneself personalized preference for examinee, has made
Complete personalized model；With,
General aspect analyzes program module, and the prediction model for being established according to college entrance examination data over the years utilizes the prediction model knot
Current year each university each the profession enrollment plan in province and examinee's individualized selection where examinee are closed, with GMA parser root
All universities for meeting examinee's situation and profession matching are quickly calculated according to the college entrance examination score and individualized selection of examinee, and are belonged to morely with
Property decision making algorithm be that school and profession, computing system are recommended in each aspiration column or the aspiration columns at different levels preferentially volunteered in parallel wish
Recommend the general safety index and tailored index of university.
4. according to claim 1 or 3 college entrance wills based on general aspect analysis model make a report on recommender system, feature exists
In the aspiration recommended program module is also used to export the admission in the past period by program module as the result is shown and go through
History data.
5. a kind of college entrance will based on general aspect analysis model makes a report on recommended method, which is characterized in that this method includes such as
Lower step:
A, the step of setting model index；The index includes professional preference degree, region preference degree, occupational planning, employment situation
Model index；
B, setting personalized the step of measuring；Specifically include: examinee is according to the personal preference of oneself by system interface to profession
The index of hobby, region hobby and occupational planning is configured marking, makes the model of complete personalization；
C, the step of data analysis is carried out；In conjunction with current year enrollment plan and examinee's individualized selection, analyzed using general aspect
GMA algorithm carries out data analytical calculation；
D, in a manner of parallel wish, the tailored index of universities and colleges' profession is shown to examinee, the higher selection of tailored index is more suitable
The reality of examination.
6. the college entrance will according to claim 5 based on general aspect analysis model makes a report on recommended method, which is characterized in that
The step C is specifically included:
According to the prediction model that college entrance examination data over the years are established, the enrollment in province in conjunction with where each profession of current year each university in examinee
Plan and examinee's individualized selection, are quickly calculated according to the college entrance examination score and individualized selection of examinee with GMA parser and are met
All universities of examinee's situation and profession matching, and be each aspiration column recommendation school in parallel wish with multiple attribute decision making (MADM) algorithm
With profession, computing system recommends the general safety index and tailored index of university, and all in university to meet examinee emerging to recommending
Each of interest hobby profession provides the admission number of prediction, admission threshold point and admission safety point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811204270.9A CN109509123A (en) | 2018-10-16 | 2018-10-16 | College entrance will based on general aspect analysis model makes a report on recommender system and its method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811204270.9A CN109509123A (en) | 2018-10-16 | 2018-10-16 | College entrance will based on general aspect analysis model makes a report on recommender system and its method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109509123A true CN109509123A (en) | 2019-03-22 |
Family
ID=65746664
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811204270.9A Pending CN109509123A (en) | 2018-10-16 | 2018-10-16 | College entrance will based on general aspect analysis model makes a report on recommender system and its method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109509123A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110751408A (en) * | 2019-10-28 | 2020-02-04 | 清华大学 | Novel interactive multidimensional university ranking method and system |
| CN110796576A (en) * | 2019-10-16 | 2020-02-14 | 湖北美和易思教育科技有限公司 | High vocational education enrollment consultation management platform |
| CN112069407A (en) * | 2020-09-07 | 2020-12-11 | 南京松数科技有限公司 | Examinee college entrance examination voluntary reporting recommendation system based on historical data |
| CN112330506A (en) * | 2020-09-29 | 2021-02-05 | 黑龙江未来桥教育科技有限公司 | College entrance examination aspiration filling and selection assisting system |
| CN112951378A (en) * | 2021-03-05 | 2021-06-11 | 中国科学院心理研究所 | Method for automatically recommending psychological consultants for visitors |
| CN113487106A (en) * | 2021-07-27 | 2021-10-08 | 南京红尘风云数字科技有限公司 | College entrance examination voluntary reporting method and system based on artificial intelligence algorithm |
-
2018
- 2018-10-16 CN CN201811204270.9A patent/CN109509123A/en active Pending
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110796576A (en) * | 2019-10-16 | 2020-02-14 | 湖北美和易思教育科技有限公司 | High vocational education enrollment consultation management platform |
| CN110751408A (en) * | 2019-10-28 | 2020-02-04 | 清华大学 | Novel interactive multidimensional university ranking method and system |
| CN110751408B (en) * | 2019-10-28 | 2022-03-08 | 清华大学 | Novel interactive multidimensional university ranking method and system |
| CN112069407A (en) * | 2020-09-07 | 2020-12-11 | 南京松数科技有限公司 | Examinee college entrance examination voluntary reporting recommendation system based on historical data |
| CN112330506A (en) * | 2020-09-29 | 2021-02-05 | 黑龙江未来桥教育科技有限公司 | College entrance examination aspiration filling and selection assisting system |
| CN112951378A (en) * | 2021-03-05 | 2021-06-11 | 中国科学院心理研究所 | Method for automatically recommending psychological consultants for visitors |
| CN112951378B (en) * | 2021-03-05 | 2023-11-21 | 中国科学院心理研究所 | Method for automatically recommending psychological consultants for visitor |
| CN113487106A (en) * | 2021-07-27 | 2021-10-08 | 南京红尘风云数字科技有限公司 | College entrance examination voluntary reporting method and system based on artificial intelligence algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109509123A (en) | College entrance will based on general aspect analysis model makes a report on recommender system and its method | |
| Kabra et al. | Performance prediction of engineering students using decision trees | |
| WO2017167069A1 (en) | Resume assessment method and apparatus | |
| Panik | Advanced statistics from an elementary point of view | |
| Chmielewska et al. | Educational context of mathability | |
| Asanbe et al. | Teachers’ performance evaluation in higher educational institution using data mining technique | |
| CN107274020B (en) | Learner subject total measured result prediction system and method based on collaborative filtering thought | |
| CN112184500A (en) | Extraclass learning tutoring system based on deep learning and knowledge graph and implementation method | |
| CN108629713A (en) | A kind of method that artificial intelligence formulation college entrance will makes a report on scheme | |
| CN112287037A (en) | Multi-entity mixed knowledge graph construction method and device and storage medium | |
| CN113886567A (en) | Teaching method and system based on knowledge graph | |
| Grewal et al. | Developing an intelligent recommendation system for course selection by students for graduate courses | |
| Peng | Research on online learning behavior analysis model in big data environment | |
| CN112069329A (en) | Text corpus processing method, device, equipment and storage medium | |
| Kortum et al. | Dissection of AI job advertisements: A text mining-based analysis of employee skills in the disciplines computer vision and natural language processing | |
| Herlambang et al. | Intelligent computing system to predict vocational high school student learning achievement using Naï ve Bayes algorithm | |
| Aji et al. | An implementation of C4. 5 classification algorithm to analyze student’s performance | |
| Gallardo et al. | Assessing understanding in mathematics: steps towards an operative model | |
| Koubek et al. | Toward a Model of Knowledge Structure and a Comparative Analysis of Knowledge Structure Measurement Techniques. | |
| Tulha et al. | Leda: A learning analytics based framework to analyze remote labs interaction | |
| Koubek et al. | The use of protocol analysis for determining ability requirements for personnel selection on a computer-based task | |
| Hosseinpour et al. | The relationship between structure and performance organizational from emergency staff viewpoints | |
| Imbar et al. | Development of an instrument to measure smart campus levels in Indonesian institutions of higher education | |
| Asanbe et al. | DATA MINING TECHNIQUE AS A TOOL FOR INSTRUCTORS’PERFORMANCE EVALUATION IN HIGHER EDUCATIONAL INSTITUTION | |
| Canedo et al. | How the academics qualification influence the students learning development |
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: 20190322 |
|
| RJ01 | Rejection of invention patent application after publication |