CN110472929A - One kind aspiration neural network based makes a report on method, system, device and medium - Google Patents
One kind aspiration neural network based makes a report on method, system, device and medium Download PDFInfo
- Publication number
- CN110472929A CN110472929A CN201910643756.0A CN201910643756A CN110472929A CN 110472929 A CN110472929 A CN 110472929A CN 201910643756 A CN201910643756 A CN 201910643756A CN 110472929 A CN110472929 A CN 110472929A
- Authority
- CN
- China
- Prior art keywords
- information
- aspiration
- report
- entrance examination
- achievement
- 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 72
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 66
- 239000002245 particle Substances 0.000 claims abstract description 35
- 238000005457 optimization Methods 0.000 claims abstract description 23
- 230000001537 neural effect Effects 0.000 claims abstract description 15
- 230000000977 initiatory effect Effects 0.000 claims description 23
- 210000005036 nerve Anatomy 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 10
- 238000011156 evaluation Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 235000013399 edible fruits Nutrition 0.000 claims 4
- 238000012360 testing method Methods 0.000 claims 3
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 210000004218 nerve net Anatomy 0.000 description 2
- 238000013480 data collection Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000001755 vocal effect Effects 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
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
- G06N3/08—Learning methods
-
- 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
- G06Q10/10—Office automation; Time management
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Operations Research (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- General Business, Economics & Management (AREA)
- Biomedical Technology (AREA)
- Tourism & Hospitality (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Molecular Biology (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to a kind of aspirations neural network based to make a report on method, system, device and medium, and method includes obtaining college entrance examination big data information；User identity is verified, if being verified, the Entrance Examination information for obtaining user's upload analyzes the Entrance Examination information according to the college entrance examination big data information, generates achievement and analyzes result；Using the neural net prediction method based on particle group optimizing, result is analyzed according to the achievement, the Entrance Examination information is predicted, obtain filing prediction result；The aspiration information that user uploads is obtained, prediction result is filed according to described, the aspiration information is assessed, generates aspiration assessment report.The present invention is based on neural networks and particle group optimizing method, and professional Analysis Service is provided for examinee, and helping parent and examinee, rationally and scientifically aspiration is made a report on, and reduce the fault rate that aspiration is made a report on, the quality and efficiency that optimization aspiration is made a report on.
Description
Technical field
The present invention relates to aspirations to make a report on technical field, more particularly to a kind of aspiration neural network based makes a report on method, is
System, device and medium.
Background technique
After new college entrance examination reform in 2017, candidates' aspiration is made of " vocational school ", and admission in batches, it is parallel not carry out profession
It files, and clearly filing ratio is 1:1.That is, traditional college admission score line may disappear, enrollment
" school+profession (class) " can all have one corresponding to file score line.
But professional parallel wish, which is filed, to be not free from risk, and aspiration, which is made a report on, improper still may bring two kinds of risks: first is that filling out
Lack backing aspiration in report aspiration, causes successfully to file；Second is that aspiration make a report on sequence it is improper, cause high score low just.Currently,
Number examinees big absolutely are often according to the experience or personal subjective analysis of teacher and parent during really making a report on, but parent or
Personal experience is not comprehensive, be easy to cause selection improper.Major selection is improper, and gently then high score is low just, and school's profession is undesirable, weight
It then " loses rank ", loses the chance of current aspiration admission, or even miss the chance being educated in the university.Profession is undesirable to will have a direct impact on student
In the learning state of university stage, less serious case generates mood of being weary of studying, and severe one exchanges profession and even leaves school.It is aobvious according to authoritative department investigation
Show have 42.1% university student dissatisfied to profession is learned, if profession can be reselected, there is 65.5% university student to indicate
It will be optionally professional.
Therefore, in face of the puzzlement of parent and examinee, such as " volunteering how this fills out ", " how school and professional this select ", " height
School former years admission fractional data how to analyze ", " how colleges and universities enroll ", " enrollment office, province is how to file again " and " how
Treat whether profession in aspiration submits to assignment ", it requires scientific, efficient, reasonable college entrance will and makes a report on method and system to come pair
The aspiration of parent and examinee's college entrance examination makes a report on carry out decision assistant.
In order to help college entrance examination examinee to make a report on before aspiration is made a report on according to the flowsheeting that college entrance examination is made a report on, reduce what aspiration was made a report on
Fault rate, foundation meet market reality, scientific and rational recommender system, design with realize college entrance examination simulation aspiration make a report on it is non-often with
There is use value.
Summary of the invention
The technical problem to be solved by the present invention is to solve the above shortcomings of the prior art and to provide one kind to be based on neural network
Aspiration make a report on method, system, device and medium, be capable of providing professional Analysis Service, help parent and examinee rationally and
Scientifically aspiration is made a report on, and reduces the fault rate that aspiration is made a report on, the quality and efficiency that optimization aspiration is made a report on.
The technical scheme to solve the above technical problems is that
One kind aspiration neural network based makes a report on method, comprising the following steps:
Step 1: obtaining college entrance examination big data information；
Step 2: user identity being verified, if being verified, executes step 3, if verifying does not pass through, terminates process；
Step 3: obtain the Entrance Examination information that user uploads, according to the college entrance examination big data information, to the college entrance examination at
Achievement information is analyzed, and is generated achievement and is analyzed result；
Step 4: using the neural net prediction method based on particle group optimizing, result is analyzed to described according to the achievement
Entrance Examination information is predicted, obtains filing prediction result；
Step 5: obtaining the aspiration information that user uploads, file prediction result according to described, the aspiration information is carried out
Assessment generates aspiration assessment report.
The beneficial effects of the present invention are: by obtain college entrance examination big data information, on the one hand the statistics based on big data and point
Analysis is analyzed convenient for the subsequent Entrance Examination information uploaded to user, improves results and analyze the reliability of result, on the other hand
Entrance Examination information is predicted using the neural net prediction method based on particle group optimizing convenient for subsequent, guarantees nerve net
The reliability of the sample data of network prediction model；By verifying to user identity, guarantee safety and conjunction that aspiration is made a report on
Method；By analyzing Entrance Examination information, the achievement analysis result of generation facilitates examinee and parent understands examinee's
The details of Entrance Examination information knows close examinee's whereabouts distributed intelligence, for examinee aspiration make a report on provide it is more professional
Reference and guidance；Entrance Examination information is predicted by using the neural net prediction method based on particle group optimizing,
Obtained prediction result of filing facilitates examinee and parent and understands the Entrance Examination information of examinee in different colleges and universities and profession
Universities and colleges file score line and corresponding admission probability, further help to be that the aspiration of examinee makes a report on and carries out decision and auxiliary；
Aspiration information is assessed in conjunction with prediction result is filed finally by the aspiration information that user uploads, obtained aspiration assessment
Report helps examinee and parent understand whether the aspiration information that examinee is uploaded is suitable, provides risk and suggestion that aspiration is made a report on；
The present invention makes a report on method by above-mentioned aspiration, is based on neural network and particle group optimizing method, provides specially for examinee
The Analysis Service of industry grade, helping parent and examinee, rationally and scientifically aspiration is made a report on, and reduces the fault rate that aspiration is made a report on, and optimizes will
It is willing to the quality and efficiency made a report on.
Based on the above technical solution, the present invention can also be improved as follows:
Further, the college entrance examination big data information includes former years whole nation college entrance examination information, former years University Enrollment, former years height
School admission information, current year national college entrance examination information, current year University Enrollment and current year achievement distributed intelligence；
The specific implementation of the step 1 are as follows:
Using the method for web crawlers, the former years whole nation college entrance examination information, the former years University Enrollment, described is acquired
Former years colleges and universities' admission information, the current year whole nation college entrance examination information, the current year University Enrollment and current year achievement distribution
Information.
Further, the specific implementation of the step 2 are as follows:
Acquisition subscriber identity information in advance, and user name and user password are generated according to the subscriber identity information；
According to the user name and the user password, the logon name and login password of user's input are verified,
If being verified, step 3 is executed, if verifying does not pass through, terminates process.
Further, the Entrance Examination information includes examinee information and overall scores corresponding with the examinee information, examines
Try subject, branch achievement, bonus point information and rare foreign languages information；
The achievement analysis result includes achievement ranking distributed intelligence and close examinee's whereabouts distributed intelligence.
Further, it is described file prediction result include multiple universities and colleges file score line and admission probability；
The specific implementation of the step 4 are as follows:
It is pre- that original neural network is established according to achievement ranking distributed intelligence and close examinee's whereabouts distributed intelligence
Survey model；
It is optimized, is obtained using initiation parameter of the particle group optimizing method to the original neural network prediction model
Optimize initiation parameter；
The original neural network prediction model is trained according to the optimization initiation parameter, obtains target nerve
Network Prediction Model；
The Entrance Examination information is predicted according to the target nerve Network Prediction Model, obtain it is described file it is pre-
Survey result.
Further, the aspiration information includes school region, types of schools, property of running a school, tuition fee, major field and goes abroad
Intention.
Another aspect according to the present invention provides one kind aspiration neural network based and makes a report on system, including obtains mould
Block, authentication module, analysis module, prediction module and evaluation module:
The acquisition module, for obtaining college entrance examination big data information；
The authentication module, for being verified to user identity；
The acquisition module is also used to after the subscriber authentication passes through, and obtains the Entrance Examination letter that user uploads
Breath；
The analysis module, it is raw for analyzing the Entrance Examination information according to the college entrance examination big data information
Result is analyzed at achievement；
The prediction module, for using the neural net prediction method based on particle group optimizing, according to the achievement point
Analysis result predicts the Entrance Examination information, obtains filing prediction result；
The evaluation module files prediction result according to described, to the will for obtaining the aspiration information of user's upload
It is willing to that information is assessed, generates aspiration assessment report.
The beneficial effects of the present invention are: college entrance examination big data information is obtained by obtaining module, on the one hand based on big data
Statistics and analysis is analyzed convenient for the subsequent Entrance Examination information uploaded to user, improves results and analyze the reliability of result,
On the other hand Entrance Examination information is predicted using the neural net prediction method based on particle group optimizing convenient for subsequent, is protected
Demonstrate,prove the reliability of the sample data of neural network prediction model；User identity is verified by authentication module, guarantees aspiration
The safety and legitimacy made a report on；Entrance Examination information is analyzed by analysis module, the achievement analysis result of generation has
The details for helping the Entrance Examination information of examinee and parent understanding examinee, knows close examinee's whereabouts distributed intelligence, to examine
Raw aspiration, which is made a report on, provides more professional reference and guidance；The neural network based on particle group optimizing is used by prediction module
Prediction technique predicts that Entrance Examination information, what is obtained files the height that prediction result facilitates examinee and parent understands examinee
It examines universities and colleges of the performance information in different colleges and universities and profession and files score line and corresponding admission probability, further help is
The aspiration of examinee, which is made a report on, carries out decision and auxiliary；The aspiration information that user uploads is obtained finally by evaluation module, in conjunction with filing
Prediction result assesses aspiration information, and obtained aspiration assessment report helps examinee and parent to understand what examinee was uploaded
Volunteer whether information is suitable, risk and suggestion that aspiration is made a report on are provided；
Aspiration neural network based of the invention makes a report on system, neural network and particle group optimizing method is based on, to examine
Raw to provide professional Analysis Service, helping parent and examinee, rationally and scientifically aspiration is made a report on, and reduces the fault that aspiration is made a report on
Rate, the quality and efficiency that optimization aspiration is made a report on.
Based on the above technical solution, the present invention can also be improved as follows:
Further, the Entrance Examination information includes examinee information and overall scores corresponding with the examinee information, examines
Try subject, branch achievement, bonus point information and rare foreign languages information；
The achievement analysis result includes achievement ranking distributed intelligence and close examinee's whereabouts distributed intelligence；
The prediction module is specifically used for:
It is pre- that original neural network is established according to achievement ranking distributed intelligence and close examinee's whereabouts distributed intelligence
Survey model；
It is optimized, is obtained using initiation parameter of the particle group optimizing method to the original neural network prediction model
Optimize initiation parameter；
The original neural network prediction model is trained according to the optimization initiation parameter, obtains target nerve
Network Prediction Model；
The Entrance Examination information is predicted according to the target nerve Network Prediction Model, obtain it is described file it is pre-
Survey result.
Another aspect according to the present invention provides a kind of aspiration neural network based and makes a report on device, including processor,
Memory is transported with storing in the memory and may operate at the computer program on the processor, the computer program
Realize that one kind of the invention aspiration neural network based makes a report on the step in method when row.
The beneficial effects of the present invention are: the computer program by storage on a memory, and run on a processor, it is real
Existing aspiration of the invention is made a report on, and is based on neural network and particle group optimizing method, professional Analysis Service is provided for examinee, is helped
Helping parent and examinee, rationally and scientifically aspiration is made a report on, and reduces the fault rate that aspiration is made a report on, the quality and effect that optimization aspiration is made a report on
Rate.
Another aspect according to the present invention, provides a kind of computer storage medium, and the computer storage medium includes:
At least one instruction is performed in described instruction and realizes that one kind of the invention aspiration neural network based is made a report in method
Step.
The beneficial effects of the present invention are: realizing this hair by executing the computer storage medium comprising at least one instruction
Bright aspiration is made a report on, and neural network and particle group optimizing method are based on, and professional Analysis Service is provided for examinee, helps parent
Rationally and scientifically aspiration is made a report on examinee, reduces the fault rate that aspiration is made a report on, the quality and efficiency that optimization aspiration is made a report on.
Detailed description of the invention
Fig. 1 is the flow diagram neural network based for volunteering to make a report on method in the embodiment of the present invention one；
Fig. 2 is the flow diagram for obtaining filing prediction result in the embodiment of the present invention one；
Fig. 3 is to obtain the process signal of optimization initiation parameter using particle group optimizing method in the embodiment of the present invention one
Figure；
Fig. 4 is the structural schematic diagram neural network based for volunteering to make a report on system in the embodiment of the present invention two.
Specific embodiment
The principle and features of the present invention will be described below with reference to the accompanying drawings, and the given examples are served only to explain the present invention, and
It is non-to be used to limit the scope of the invention.
With reference to the accompanying drawing, the present invention will be described.
Embodiment one, as shown in Figure 1, a kind of aspiration neural network based makes a report on method, comprising the following steps:
S1: college entrance examination big data information is obtained；
S2: verifying user identity, if being verified, executes step 3, if verifying does not pass through, terminates process；
S3: obtaining the Entrance Examination information that user uploads, and according to the college entrance examination big data information, believes the Entrance Examination
Breath is analyzed, and is generated achievement and is analyzed result；
S4: using the neural net prediction method based on particle group optimizing, analyzes result to the height according to the achievement
It examines performance information to be predicted, obtains filing prediction result；
S5: the aspiration information that user uploads is obtained, prediction result is filed according to described, the aspiration information is commented
Estimate, generates aspiration assessment report.
By obtaining college entrance examination big data information, on the one hand based on the statistics and analysis of big data, convenient for subsequent on user
The Entrance Examination information of biography is analyzed, and is improved results and is analyzed the reliability of result, on the other hand convenient for subsequent using based on grain
The neural net prediction method of subgroup optimization predicts Entrance Examination information, guarantees the sample number of neural network prediction model
According to reliability；By verifying to user identity, guarantee safety and legitimacy that aspiration is made a report on；By to Entrance Examination
Information is analyzed, and the achievement analysis result of generation facilitates the detailed feelings of the Entrance Examination information of examinee and parent understanding examinee
Condition knows close examinee's whereabouts distributed intelligence, for examinee aspiration make a report on provide more profession reference and guidance；By using
Entrance Examination information is predicted based on the neural net prediction method of particle group optimizing, obtained prediction result of filing helps
Universities and colleges of the Entrance Examination information of examinee in different colleges and universities and profession, which are understood, in examinee and parent files score line and right
The admission probability answered further helps the aspiration for examinee to make a report on and carries out decision and auxiliary；The aspiration uploaded finally by user
Information assesses aspiration information in conjunction with prediction result is filed, and obtained aspiration assessment report helps examinee and parent to understand
Whether the aspiration information that examinee is uploaded is suitable, provides risk and suggestion that aspiration is made a report on；
The present embodiment makes a report on method by above-mentioned aspiration, is based on neural network and particle group optimizing method, provides for examinee
Professional Analysis Service, helping parent and examinee, rationally and scientifically aspiration is made a report on, and reduces the fault rate that aspiration is made a report on, optimization
Volunteer the quality and efficiency made a report on.
Preferably, the college entrance examination big data information includes former years whole nation college entrance examination information, former years University Enrollment, former years height
School admission information, current year national college entrance examination information, current year University Enrollment and current year achievement distributed intelligence；
The specific implementation of S1 are as follows:
Using the method for web crawlers, the former years whole nation college entrance examination information, the former years University Enrollment, described is acquired
Former years colleges and universities' admission information, the current year whole nation college entrance examination information, the current year University Enrollment and current year achievement distribution
Information.
Above-mentioned college entrance examination big data information is acquired by the method for web crawlers, it is convenient and efficient, it is based on big data, can guarantee
The comprehensive and reliability of data, convenient for the subsequent statistics and analysis based on big data；Meanwhile convenient for subsequent using based on particle
The neural net prediction method of group's optimization predicts Entrance Examination information, guarantees the sample data of neural network prediction model
Reliability.
Specifically, the present embodiment can also obtain college entrance examination big data information by the method for hand data collection.
Preferably, the specific implementation of S2 are as follows:
Acquisition subscriber identity information in advance, and user name and user password are generated according to the subscriber identity information；
According to the user name and the user password, the logon name and login password of user's input are verified,
If being verified, step 3 is executed, if verifying does not pass through, terminates process.
By acquiring subscriber identity information in advance, convenient for generating use corresponding and with uniqueness with subscriber identity information
Name in an account book and user password, convenient for the identity of the unique user name of subsequent basis and user password verifying user, to guarantee to volunteer
The safety and legitimacy made a report on.
Specifically, there are two database in the present embodiment, one of database is college entrance examination database, and it is big to be stored with college entrance examination
Data information, including former years whole nation college entrance examination information, former years University Enrollment, former years colleges and universities' admission information, current year national college entrance examination
Information, current year University Enrollment and current year achievement distributed intelligence；Another database is CMS database, is stored with user's body
Part information and customer management information etc..
Preferably, the Entrance Examination information includes examinee information and overall scores corresponding with the examinee information, examines
Try subject, branch achievement, bonus point information and rare foreign languages information；
The achievement analysis result includes achievement ranking distributed intelligence and close examinee's whereabouts distributed intelligence.
It can more comprehensively and objectively be analyzed by the Entrance Examination information of above-mentioned upload in conjunction with college entrance examination big data information
The achievement situation of examinee to obtain the ranking distributed intelligence of achievement corresponding to the achievement of examinee, and obtains the achievement with examinee
Similar examinee's whereabouts (close achievement includes that overall scores is close, the close and special achievement of branch achievement is close, wherein it is special at
Achievement refers to corresponding achievement in bonus point information and/or rare foreign languages information), most including admission similar in former years and examinee's achievement
Result is analyzed in colleges and universities, profession and city, i.e. achievement；It is analyzed by above-mentioned achievement as a result, examinee and parent is facilitated to slap in more detail
Hold the achievement situation of examinee, for examinee aspiration make a report on provide more profession reference and guidance；Wherein, achievement ranking distribution letter
Breath includes the ranking of overall scores province, the coordination of the overall scores whole nation, branch achievement saves ranking, the branch achievement whole nation ranks, special achievement saves
Ranking and the ranking of the special achievement whole nation etc.；Due to close close, the close and special achievement phase of branch achievement including overall scores of achievement
Closely, therefore close examinee's whereabouts distributed intelligence includes former years close overall scores admission colleges and universities ranking data, former years close overall scores
Admission profession ranking data, former years close overall scores admission city ranking data, the ranking of former years close branch achievement admission colleges and universities
Data, former years close branch achievement admission profession ranking data, former years close branch achievement admission city rank data, former years phase
Nearly special achievement admission colleges and universities ranking data, former years close special achievement admission profession ranking data, former years close special achievement
It enrolls city and ranks data.
Preferably, it is described file prediction result include multiple universities and colleges file score line and admission probability；
As shown in Fig. 2, the specific implementation of S4 are as follows:
S4.1: distributed intelligence is ranked according to the achievement and original nerve net is established in close examinee's whereabouts distributed intelligence
Network prediction model；
S4.2: it is carried out using initiation parameter of the particle group optimizing method to the original neural network prediction model excellent
Change, obtains optimization initiation parameter；
S4.3: the original neural network prediction model is trained according to the optimization initiation parameter, obtains mesh
Mark neural network prediction model；
S4.4: predicting the Entrance Examination information according to the target nerve Network Prediction Model, obtains described
File prediction result.
Since former years admission data and current year admission result have the characteristics that nonlinearity, it is ranked based on achievement
Distributed intelligence and close examinee's whereabouts distributed intelligence, the primitive network prediction model of foundation can more comprehensively, it is more professional and more objective
Ground predicts the Entrance Examination information of examinee, makes a report on to provide and more instructs rationally and objectively for the aspiration of examinee；Using grain
Subgroup, which optimizes, carries out the initiation parameter of original neural network prediction model, can guarantee to obtain the higher target of predictablity rate
Neural network prediction model, further helping parent and examinee, rationally and scientifically aspiration is made a report on, and reduces the fault that aspiration is made a report on
Rate, the quality and efficiency that optimization aspiration is made a report on.
Specifically, in the present embodiment S4.2, using particle group optimizing method to the initial of original neural network prediction model
Change the process that parameter optimizes as shown in figure 3, including following procedure:
(1) initiation parameter of original neural network prediction model, including weight w are determinedijAnd threshold θi, while defining mind
Through network input layer, hidden layer and output layer number of nodes Sin、ShAnd Sout；
(2) particle group optimizing method is to weight wijAnd threshold θiIt is encoded, while defining population dimension S=SinSh+
ShSout+SinSout；
(3) training sample obtains error and using error as fitness valueWherein, YiFor training
The real output value of i-th of sample, y in sampleiFor the desired output of i-th of sample in training sample；
(4) after finding the initial extreme value of individual and global initial extreme value, particle group optimizing iteration, the position and speed of population
It is updated iteration, and calculates the fitness value in each iterative process, individual extreme value and global pole are carried out according to fitness value
The update of value；
(5) it verifies whether to meet population termination condition, if satisfied, it is original to get arriving then to obtain optimization initiation parameter
The best initial weights and threshold value of neural network prediction model；If not satisfied, repeating step (4).
After above-mentioned steps, best initial weights and threshold value are inputted in original neural network prediction model, to original mind
It is trained through Network Prediction Model, target nerve Network Prediction Model can be obtained；Trained concrete operation step is existing
Technology, details are not described herein again.
Preferably, the aspiration information includes school region, types of schools, property of running a school, tuition fee, major field and goes abroad
Intention.
File that the universities and colleges that prediction result includes different universities and colleges file score line and examinee's achievement is corresponding not obtained in S4
Same admission probability, therefore the above-mentioned aspiration information uploaded according to user, file prediction result in conjunction with above-mentioned, can mention for examinee
For whether suitably assessing, the suggestion pricked and push away the indicating risk made a report on and adjustment school's profession is provided, parent and examinee is helped to close
Reason is made a report on scientifically aspiration, reduces the fault rate that aspiration is made a report on, and the quality and efficiency made a report on are volunteered in optimization.
Specifically, during generating aspiration assessment report, the reasonable of sequence is made a report on using isSortOK function inspection
Property, i.e., the data acquisition system of solution layer is constructed by volunteering proposed algorithm, then the data acquisition system inspection of layer is used with this solution
Whether the aspiration information that family uploads, which meets, is made a report on sequence；More specifically, the reasonability for making a report on sequence mainly passes through the number of solution layer
Can impact, can guarantee the minimum and safer three types according to whether he exists simultaneously in set, wherein can impact-type prediction score
Within 3 points, the prediction score of safer type is 3~5 points, and the prediction score for the type that can guarantee the minimum is 5 points or more.
Embodiment two, as shown in figure 4, a kind of aspiration neural network based makes a report on system, including obtain module, verifying mould
Block, analysis module, prediction module and evaluation module:
The acquisition module, for obtaining college entrance examination big data information；
The authentication module, for being verified to user identity；
The acquisition module is also used to after the subscriber authentication passes through, and obtains the Entrance Examination letter that user uploads
Breath；
The analysis module, it is raw for analyzing the Entrance Examination information according to the college entrance examination big data information
Result is analyzed at achievement；
The prediction module, for using the neural net prediction method based on particle group optimizing, according to the achievement point
Analysis result predicts the Entrance Examination information, obtains filing prediction result；
The evaluation module files prediction result according to described, to the will for obtaining the aspiration information of user's upload
It is willing to that information is assessed, generates aspiration assessment report.
College entrance examination big data information is obtained by obtaining module, on the one hand based on the statistics and analysis of big data, convenient for subsequent
The Entrance Examination information uploaded to user is analyzed, and is improved results and is analyzed the reliability of result, is on the other hand adopted convenient for subsequent
Entrance Examination information is predicted with the neural net prediction method based on particle group optimizing, guarantees neural network prediction model
Sample data reliability；User identity is verified by authentication module, guarantees the safety made a report on of aspiration and legal
Property；Entrance Examination information is analyzed by analysis module, the achievement analysis result of generation facilitates examinee and parent understands
The details of the Entrance Examination information of examinee knows close examinee's whereabouts distributed intelligence, for examinee aspiration make a report on provide compared with
For the reference and guidance of profession；By prediction module using the neural net prediction method based on particle group optimizing to Entrance Examination
Information is predicted that obtained prediction result of filing facilitates the Entrance Examination information of examinee and parent understanding examinee different
Universities and colleges in colleges and universities and profession file score line and corresponding admission probability, further help to make a report on progress for the aspiration of examinee
Decision and auxiliary；The aspiration information that user uploads is obtained finally by evaluation module, in conjunction with prediction result is filed, to aspiration information
It is assessed, whether the aspiration information that obtained aspiration assessment report helps examinee and parent understanding examinee to be uploaded is suitable, mentions
For the risk and suggestion for volunteering to make a report on；
The aspiration neural network based of the present embodiment makes a report on system, is based on neural network and particle group optimizing method, is
Examinee provides professional Analysis Service, and helping parent and examinee, rationally and scientifically aspiration is made a report on, and reduces the mistake that aspiration is made a report on
Accidentally rate, the quality and efficiency that optimization aspiration is made a report on.
Preferably, the Entrance Examination information includes examinee information and overall scores corresponding with the examinee information, examines
Try subject, branch achievement, bonus point information and rare foreign languages information；
The achievement analysis result includes achievement ranking distributed intelligence and close examinee's whereabouts distributed intelligence；
The prediction module is specifically used for:
It is pre- that original neural network is established according to achievement ranking distributed intelligence and close examinee's whereabouts distributed intelligence
Survey model；
It is optimized, is obtained using initiation parameter of the particle group optimizing method to the original neural network prediction model
Optimize initiation parameter；
The original neural network prediction model is trained according to the optimization initiation parameter, obtains target nerve
Network Prediction Model；
The Entrance Examination information is predicted according to the target nerve Network Prediction Model, obtain it is described file it is pre-
Survey result.
By above-mentioned Entrance Examination information and achievement analysis as a result, facilitate examinee and parent grasp in more detail examinee at
Achievement situation, for examinee aspiration make a report on provide more profession reference and guidance；Prediction module through this embodiment, based at
Achievement ranks distributed intelligence and close examinee's whereabouts distributed intelligence, the primitive network prediction model of foundation can more comprehensively, it is more professional and
More objectively the Entrance Examination information of examinee is predicted, for examinee aspiration make a report on provide more rationally and objectively instruct；
The initiation parameter of original neural network prediction model is carried out using particle group optimizing, can guarantee to obtain predictablity rate higher
Target nerve Network Prediction Model, further helping parent and examinee, rationally and scientifically aspiration is made a report on, and is reduced aspiration and is made a report on
Fault rate, optimization the aspiration quality and efficiency made a report on.
Specifically, the aspiration system of making a report on neural network based of the present embodiment further includes memory module, more specifically, depositing
Storage module includes college entrance examination database and CMS database, and college entrance examination database purchase has college entrance examination big data information, including former years whole nation height
Examine information, former years University Enrollment, former years colleges and universities' admission information, current year national college entrance examination information, current year University Enrollment and
Current year achievement distributed intelligence；CMS database is stored with subscriber identity information and customer management information etc..
Specifically, the aspiration neural network based of the present embodiment make a report on system exploitation environment it is as follows:
Operating system: Windows10；
Python version: Python3.7；
Python Web frame: Flask；
Virtual environment: virtualenv；
Database: CMS database and college entrance examination database；
Developing instrument: wechat developer's tool+PyCharm etc.；
Interface debugging tool: Postman.
Embodiment three is based on embodiment one and embodiment two, and the present embodiment also discloses a kind of will neural network based
Hope makes a report on device, including processor, memory and stores in the memory and may operate at the calculating on the processor
Machine program, the computer program realize the specific steps of S1 to S5 as shown in Figure 1 when running.
It by storing computer program on a memory, and runs on a processor, realizes that aspiration of the invention is made a report on,
Based on neural network and particle group optimizing method, professional Analysis Service is provided for examinee, help parent and examinee rationally and
Scientifically aspiration is made a report on, and reduces the fault rate that aspiration is made a report on, the quality and efficiency that optimization aspiration is made a report on.
The present embodiment also provides a kind of computer storage medium, is stored at least one in the computer storage medium and refers to
It enables, described instruction is performed the specific steps for realizing the S1 to S5.
By executing the computer storage medium comprising at least one instruction, realize that aspiration of the invention is made a report on, based on mind
Through network and particle group optimizing method, professional Analysis Service is provided for examinee, helps parent and examinee rationally and scientifically
Aspiration is made a report on, and the fault rate that aspiration is made a report on, the quality and efficiency that optimization aspiration is made a report on are reduced.
S1 to S5 does not use up details in the present embodiment, and the content of detailed in Example one and Fig. 1 to Fig. 3 specifically repeats no more.
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all in spirit of the invention and
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of aspiration neural network based makes a report on method, which comprises the following steps:
Step 1: obtaining college entrance examination big data information；
Step 2: user identity being verified, if being verified, executes step 3, if verifying does not pass through, terminates process；
Step 3: obtaining the Entrance Examination information that user uploads, according to the college entrance examination big data information, the Entrance Examination is believed
Breath is analyzed, and is generated achievement and is analyzed result；
Step 4: using the neural net prediction method based on particle group optimizing, result is analyzed to the college entrance examination according to the achievement
Performance information is predicted, obtains filing prediction result；
Step 5: the aspiration information that user uploads is obtained, prediction result is filed according to described, the aspiration information is assessed,
Generate aspiration assessment report.
2. aspiration neural network based according to claim 1 makes a report on method, which is characterized in that the college entrance examination big data
Information include former years whole nation college entrance examination information, former years University Enrollment, former years colleges and universities' admission information, current year national college entrance examination information,
Current year University Enrollment and current year achievement distributed intelligence；
The specific implementation of the step 1 are as follows:
Using the method for web crawlers, the former years whole nation college entrance examination information, the former years University Enrollment, the former years are acquired
Colleges and universities' admission information, the current year whole nation college entrance examination information, the current year University Enrollment and the current year achievement distributed intelligence.
3. aspiration neural network based according to claim 1 makes a report on method, which is characterized in that the tool of the step 2
Body is realized are as follows:
Acquisition subscriber identity information in advance, and user name and user password are generated according to the subscriber identity information；
According to the user name and the user password, the logon name and login password of user's input are verified, if testing
Card passes through, and executes step 3, if verifying does not pass through, terminates process.
4. aspiration neural network based according to claim 1 makes a report on method, which is characterized in that the Entrance Examination letter
Breath includes examinee information and overall scores corresponding with the examinee information, test subject, branch achievement, bonus point information and small language
Kind information；
The achievement analysis result includes achievement ranking distributed intelligence and close examinee's whereabouts distributed intelligence.
5. aspiration neural network based according to claim 4 makes a report on method, which is characterized in that described to file prediction knot
Fruit include multiple universities and colleges file score line and admission probability；
The specific implementation of the step 4 are as follows:
Distributed intelligence is ranked according to the achievement and original neural network prediction mould is established in close examinee's whereabouts distributed intelligence
Type；
It is optimized, is optimized using initiation parameter of the particle group optimizing method to the original neural network prediction model
Initiation parameter；
The original neural network prediction model is trained according to the optimization initiation parameter, obtains target nerve network
Prediction model；
The Entrance Examination information is predicted according to the target nerve Network Prediction Model, described file is obtained and predicts knot
Fruit.
6. aspiration neural network based according to any one of claims 1 to 5 makes a report on method, which is characterized in that described
Volunteering information includes school region, types of schools, property of running a school, tuition fee, major field and intention of going abroad.
7. a kind of aspiration neural network based makes a report on system, which is characterized in that including obtaining module, authentication module, analysis mould
Block, prediction module and evaluation module:
The acquisition module, for obtaining college entrance examination big data information；
The authentication module, for being verified to user identity；
The acquisition module is also used to after the subscriber authentication passes through, and obtains the Entrance Examination information that user uploads；
The analysis module is analyzed the Entrance Examination information for according to the college entrance examination big data information, generate at
Achievement analyzes result；
The prediction module is analyzed according to the achievement and is tied for using the neural net prediction method based on particle group optimizing
Fruit predicts the Entrance Examination information, obtains filing prediction result；
The evaluation module is filed prediction result according to described, is believed the aspiration for obtaining the aspiration information of user's upload
Breath is assessed, and aspiration assessment report is generated.
8. aspiration neural network based according to claim 7 makes a report on system, which is characterized in that the Entrance Examination letter
Breath includes examinee information and overall scores corresponding with the examinee information, test subject, branch achievement, bonus point information and small language
Kind information；
The achievement analysis result includes achievement ranking distributed intelligence and close examinee's whereabouts distributed intelligence；
The prediction module is specifically used for:
Distributed intelligence is ranked according to the achievement and original neural network prediction mould is established in close examinee's whereabouts distributed intelligence
Type；
It is optimized, is optimized using initiation parameter of the particle group optimizing method to the original neural network prediction model
Initiation parameter；
The original neural network prediction model is trained according to the optimization initiation parameter, obtains target nerve network
Prediction model；
The Entrance Examination information is predicted according to the target nerve Network Prediction Model, described file is obtained and predicts knot
Fruit.
9. a kind of aspiration neural network based makes a report on device, which is characterized in that including processor, memory and be stored in described
It in memory and may operate at the computer program on the processor, such as claim realized when the computer program is run
Method and step described in any one of 1 to 6 claim.
10. a kind of computer storage medium, which is characterized in that the computer storage medium includes: at least one instruction, in institute
It states instruction and is performed realization such as method and step as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910643756.0A CN110472929A (en) | 2019-07-17 | 2019-07-17 | One kind aspiration neural network based makes a report on method, system, device and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910643756.0A CN110472929A (en) | 2019-07-17 | 2019-07-17 | One kind aspiration neural network based makes a report on method, system, device and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110472929A true CN110472929A (en) | 2019-11-19 |
Family
ID=68509664
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910643756.0A Pending CN110472929A (en) | 2019-07-17 | 2019-07-17 | One kind aspiration neural network based makes a report on method, system, device and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110472929A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111667389A (en) * | 2020-06-16 | 2020-09-15 | 衢州量智科技有限公司 | Assessment method and assessment device for college entrance examination probability based on big data |
| 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 |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105956968A (en) * | 2016-05-26 | 2016-09-21 | 程欧亚 | Artificial intelligent college entrance examination voluntary reporting system and method |
| CN107609711A (en) * | 2017-09-27 | 2018-01-19 | 百度在线网络技术（北京）有限公司 | A kind of offer method, apparatus, equipment and storage medium for entering oneself for the examination information |
| CN108629713A (en) * | 2018-05-04 | 2018-10-09 | 上饶市普适科技有限公司 | A kind of method that artificial intelligence formulation college entrance will makes a report on scheme |
| CN108764718A (en) * | 2018-05-28 | 2018-11-06 | 王春宁 | Selection method, system are estimated and volunteered to college entrance examination score based on deep learning algorithm |
-
2019
- 2019-07-17 CN CN201910643756.0A patent/CN110472929A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105956968A (en) * | 2016-05-26 | 2016-09-21 | 程欧亚 | Artificial intelligent college entrance examination voluntary reporting system and method |
| CN107609711A (en) * | 2017-09-27 | 2018-01-19 | 百度在线网络技术（北京）有限公司 | A kind of offer method, apparatus, equipment and storage medium for entering oneself for the examination information |
| CN108629713A (en) * | 2018-05-04 | 2018-10-09 | 上饶市普适科技有限公司 | A kind of method that artificial intelligence formulation college entrance will makes a report on scheme |
| CN108764718A (en) * | 2018-05-28 | 2018-11-06 | 王春宁 | Selection method, system are estimated and volunteered to college entrance examination score based on deep learning algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 刘宏: "基于PSO-BP神经网络的电子政务绩效评价模型", 《电子商务》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111667389A (en) * | 2020-06-16 | 2020-09-15 | 衢州量智科技有限公司 | Assessment method and assessment device for college entrance examination probability based on big data |
| 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 |
|---|---|---|
| CN104008453A (en) | Vocational ability evaluation simulation system | |
| CN116541538B (en) | Intelligent learning knowledge point mining method and system based on big data | |
| CN110472929A (en) | One kind aspiration neural network based makes a report on method, system, device and medium | |
| Siraj et al. | Uncovering hidden information within university's student enrollment data using data mining | |
| CN107301497A (en) | The method and system of working memory ability evaluation | |
| CN110288878A (en) | Adaptive learning method and device | |
| Duan | Automatic generation and evolution of personalized curriculum based on genetic algorithm | |
| Hu et al. | An intelligent testing system embedded with an ant-colony-optimization-based test composition method | |
| Jiang | Online English teaching course score analysis based on decision tree mining algorithm | |
| Lepers et al. | Inference with selection, varying population size, and evolving population structure: application of ABC to a forward–backward coalescent process with interactions | |
| Seki et al. | An adaptive sequencing method of the learning objects for the e‐learning environment | |
| Abeyrathna et al. | Analyzing and predicting player performance in a quantum cryptography serious game | |
| CN114971425B (en) | Database information monitoring method, device, equipment and storage medium | |
| Lupton | Pokémon in the midst: Collecting and using data from within the Pokémon GO ecosystem to facilitate ecology and wildlife biology education | |
| Georgiadis et al. | Reinforcing stealth assessment in serious games | |
| CN115511670A (en) | Online education method and online education platform | |
| CN113919983A (en) | Test question portrait method, device, electronic equipment and storage medium | |
| Keuchel | Arts Education Development Index (AEDI)–A Comparative International Empirical Research Approach in Arts Education | |
| CN110334353A (en) | Analysis method, device, equipment and the storage medium of word order recognition performance | |
| Wendlinger et al. | Evofficient: reproducing a cartesian genetic programming method | |
| Deepika et al. | Analyze and predicting the student academic performance using data mining tools | |
| Liang et al. | Inferring how novice students learn to code: Integrating automated program repair with cognitive model | |
| Laureano et al. | Affinity propagation SMOTE approach for imbalanced dataset used in predicting student at risk of low performance | |
| Milinković et al. | Using decision tree classifier for analyzing students’ activities | |
| Yu et al. | A transfer learning based interpretable user experience model on small samples |
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: 20191119 |
|
| RJ01 | Rejection of invention patent application after publication |