CN110458737A - Method, apparatus, equipment and medium based on neural network modification University Educational Administration arrangement - Google Patents
Method, apparatus, equipment and medium based on neural network modification University Educational Administration arrangement Download PDFInfo
- Publication number
- CN110458737A CN110458737A CN201910766856.2A CN201910766856A CN110458737A CN 110458737 A CN110458737 A CN 110458737A CN 201910766856 A CN201910766856 A CN 201910766856A CN 110458737 A CN110458737 A CN 110458737A
- Authority
- CN
- China
- Prior art keywords
- educational administration
- error
- constraint condition
- educational
- calendar
- 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.)
- Granted
Links
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 76
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000004048 modification Effects 0.000 title claims abstract description 32
- PICOTJKHYPEGGN-UHFFFAOYSA-N 4-[nitroso(prop-2-enyl)amino]butanoic acid Chemical compound OC(=O)CCCN(N=O)CC=C PICOTJKHYPEGGN-UHFFFAOYSA-N 0.000 claims abstract description 77
- 238000004364 calculation method Methods 0.000 claims abstract description 72
- 238000012549 training Methods 0.000 claims abstract description 26
- 230000001537 neural effect Effects 0.000 claims abstract description 22
- 238000012545 processing Methods 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 10
- 238000012986 modification Methods 0.000 abstract description 10
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 239000002131 composite material Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000005859 cell recognition Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 235000015096 spirit Nutrition 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Educational Technology (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The present invention discloses method, apparatus, equipment and medium based on neural network modification University Educational Administration arrangement, this method comprises: arranging constraint condition to generate educational administration according to the educational administration that user uploads arranges error calculation formula;Constraint condition is arranged according to educational administration and/or the error training CPPN neural network of the calculated educational administration's calendar of error calculation formula is arranged according to educational administration;Go out educational administration's calendar using CPPN neural computing, and calculates the error of educational administration's calendar by educational administration's arrangement error calculation formula;In the case where error is not more than error threshold, the corresponding educational administration's calendar of the error is obtained.Method of the invention no longer needs cumbersome modification process, allows teaching and administrative staff and Educational Affairs Office to be capable of the process of largely Shangdi saving modification, the suggestion that the row's of being rapidly completed class row examines is submitted and modification process, improves the work efficiency in Educational Affairs Office.
Description
Technical field
The present invention relates to data processing fields, more particularly to the method based on neural network modification University Educational Administration arrangement, dress
It sets, equipment and medium.
Background technique
Educational administration arranges when be school according to teaching programme being each grade, the course of each profession and suitable arrangement of the tests
Between and suitable place;In now, educational administration arranges the course for being primarily referred to as attending class for College Teachers arrangement and arranges examination prison
It examines, therefore educational administration arranges work in the teaching management of school in very important status, is related to student and can teacher
Examination is normally attended class and is completed, once considering during arrangement not comprehensive, will lead to that work of normally imparting knowledge to students can not be unfolded
Make.Therefore, each term school requires to spend a large amount of man power and material that reply row's class row is gone to examine work, and with nowadays high
The subject and professional increasingly diversification, the quantity of class and the course quantity opened up that school is founded also correspondingly quickly increase, and
Original row's class row test method has been increasingly difficult to meet demand.Existing University Educational Administration arrangement is primarily present following problems: one
Be, due to consider it is improper cause course attend class or the conflict of arrangement of the tests time of occurrence either classroom conflict;Second is that for a certain
The adjustment of the time that subject row's class row examines either classroom, needs to take a substantial amount of time, influence whether a lot of other
Course arrangement;Third is that since row's class row examines, the constraint condition involved is more, and with the increase of course, artificial row's class row examines change
Must be more and more difficult, and the effect is unsatisfactory for current automation row's class examination arrangement system.
In existing correlative technology field, still lacks preferred technique scheme and solve the above problems.
Summary of the invention
The technical issues of solution of the invention, is to provide a kind of method based on neural network modification University Educational Administration arrangement, dress
It sets, equipment and medium, it is intended to when needing to modify to examination and course arrangement, it is no longer necessary to which cumbersome modification process allows religion
The process of largely Shangdi saving modification is capable of in worker and Educational Affairs Office, and the suggestion that the row's of being rapidly completed class row examines is submitted and repaired
It corrects one's mistakes journey, improves the work efficiency in Educational Affairs Office.
According to the first aspect of the invention, a kind of method based on neural network modification University Educational Administration arrangement is provided, it is described
Method includes:
It arranges constraint condition to generate educational administration according to the educational administration that user uploads and arranges error calculation formula;It generates educational administration and arranges error meter
Calculating formula is that indexization processing is carried out to constraint condition, and it includes initial educational administration's constraint condition and religion in real time that educational administration, which arranges constraint condition,
Business arranges constraint condition, and constraint condition is that user is unable to complete and/or preferentially completes educational administration's scheduled time section, educational administration's peace
Row includes attending class and invigilating;
Constraint condition is arranged according to educational administration and/or the error of the calculated educational administration's calendar of error calculation formula is arranged according to educational administration
Training CPPN neural network;The error is educational administration's calendar that CPPN neural computing goes out and the constraint condition that user fills in
The matching degree of corresponding educational administration's calendar;
Go out educational administration's calendar using CPPN neural computing, and arranges error calculation formula to calculate educational administration by educational administration and arrange
The error of table;
In the case where error is not more than error threshold, the corresponding educational administration's calendar of the error is obtained.
Preferably, it is described according to user upload educational administration arrange constraint condition generate educational administration arrange error calculation formula it
Before, comprising:
It obtains initial educational administration and arranges constraint condition;
In the case where arranging constraint condition that can be matched to the first CPPN neural network according to initial educational administration, in the first CPPN
Gauss number is inputted in neural network and calculates educational administration's calendar, and the first CPPN neural network is based on other users
The educational administration of upload arranges constraint condition and trained CPPN neural network.
Preferably, the educational administration uploaded according to user arranges constraint condition to generate educational administration and arranges error calculation formula packet
It includes:
It arranges constraint condition to generate initial educational administration according to the initial educational administration that user fills in and arranges poor calculation formula;
It arranges constraint condition to generate new educational administration according to the new educational administration of user's addition and arranges error calculation formula.
Preferably, described that constraint condition is arranged according to educational administration and/or arranges error calculation formula to calculate according to educational administration
Educational administration's calendar error training CPPN neural network include:
The calculating factor for arranging error calculation formula according to the educational administration that educational administration arranges constraint condition to generate is obtained, and/or is obtained anti-
Corresponding educational administration arranges the calculating factor of error calculation formula after to conduction eror;
According to the weight for the node for calculating factor setting CPPN neural network and complete to train.
Preferably, the utilization CPPN neural computing goes out educational administration's calendar, and arranges error calculation by educational administration
The error that formula calculates educational administration's calendar includes:
Gauss number is inputted in CPPN neural network and obtains calculated educational administration's calendar;
Count calculated educational administration's calendar and constraint condition that user fills in corresponding to match in educational administration's calendar
Educational administration arrange number and the educational administration misfitted to arrange number;
Arrange number and the educational administration misfitted that number input educational administration is arranged to arrange error calculation formula the identical educational administration of statistics,
Obtain the error of calculated educational administration's calendar.
Preferably, religion corresponding to the constraint condition that statistics calculated educational administration's calendar and user fill in
The educational administration to match in business calendar arranges number and the educational administration misfitted arrangement number includes:
Counting user is unable to complete educational administration and the number for not arranging educational administration to arrange in the period, and/or user is arranged preferentially to complete to teach
Business arranges that the preferential number completing educational administration and arranging is scheduled in the period;
Counting user is unable to complete educational administration and the number for arranging educational administration to arrange in the period, and/or user is arranged preferentially to complete educational administration
Arrange the number for not arranging educational administration to arrange in the period.
Preferably, in the case where error is greater than error threshold, the described method includes:
Error described in the local derviation of error calculation formula and the error update of calculated educational administration's calendar is arranged using educational administration;
The error of update is subjected to reverse conduction and obtains educational administration arranging the matched calculating factor in error calculation formula;
Based on the matched calculating factor, the weight of the node of the CPPN neural network set and trains CPPN net
Network.
According to another aspect of the present invention, a kind of device based on neural network modification University Educational Administration arrangement is provided, including
Module is obtained, the educational administration for uploading according to user arranges constraint condition to generate educational administration and arranges error calculation formula;It generates
Educational administration arrange error calculation formula be to constraint condition carry out indexization processing, educational administration arrange constraint condition include initial educational administration about
Beam condition and real-time educational administration arrange constraint condition, constraint condition be user be unable to complete and/or preferentially complete educational administration's arrangement when
Between section, the educational administration arranges to include attending class and invigilating;
Training module, for arranging constraint condition according to educational administration and/or arranging the calculated religion of error calculation formula according to educational administration
The error training CPPN neural network of business calendar;The error is the educational administration's calendar and user that CPPN neural computing goes out
The matching degree of educational administration's calendar corresponding to the constraint condition filled in;
Processing module for going out educational administration's calendar using CPPN neural computing, and arranges error calculation formula by educational administration
Calculate the error of educational administration's calendar;
Planning module, for obtaining the corresponding educational administration's calendar of the error in the case where error is not more than error threshold.
The third aspect includes: at least one processor, at least one the embodiment of the invention provides a kind of computer equipment
A memory and computer program instructions stored in memory, the realization when computer program instructions are executed by processor
Such as the method for first aspect in above embodiment.
Fourth aspect, the embodiment of the invention provides a kind of computer readable storage mediums, are stored thereon with computer journey
The method such as first aspect in above embodiment is realized in sequence instruction when computer program instructions are executed by processor.
Compared with prior art, the beneficial effects of the present invention are: the present invention, and Educational Affairs Office personnel can be made very simple fast
The row's of acquisition class arranges the scheme examined promptly, and can also easily modify to scheme in follow-up work.Educational Affairs Office only needs
All kinds of constraint conditions are inputted, and checks and judges whether the scheme of output has met the requirements.The present invention solves existing
There is the mistake occurred in row's class row's examination process the various problems such as arrange, omit in printing, largely Shangdi improves efficiency, maximumlly saves
Human resources sheet, and reduce due to consider the problems of it is improper caused by classroom or arrangement of the tests conflict.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes part of this application, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is the flow chart of the method based on neural network modification University Educational Administration arrangement of the embodiment of the present invention;
Fig. 2 is the structural schematic diagram of the device according to an embodiment of the present invention based on neural network modification University Educational Administration arrangement.
Fig. 3 is the hardware structural diagram of computer equipment provided in an embodiment of the present invention.
Specific embodiment
The invention will now be described in further detail with reference to the accompanying drawings.
It is exemplary by reference to the embodiment that attached drawing describes, it is intended to for explaining the application, and should not be understood as pair
The limitation of the application.Hereinafter, the present invention will be described in detail with reference to the accompanying drawings and in combination with Examples.It should be noted that not rushing
In the case where prominent, the features in the embodiments and the embodiments of the present application be can be combined with each other.
It should be noted that description and claims of this specification and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.
Embodiment 1
The present invention provides a kind of method based on neural network modification University Educational Administration arrangement, and Fig. 1 is that the present invention is based on neural networks
The flow chart for modifying the method for University Educational Administration arrangement, as shown in Figure 1, the step of this method includes:
Step S101. arranges constraint condition to generate educational administration and arranges error calculation formula according to the educational administration that user uploads;Generate educational administration
Arranging error calculation formula is that indexization processing is carried out to constraint condition, and it includes initial educational administration's constraint item that educational administration, which arranges constraint condition,
Part and real-time educational administration arrange constraint condition, and constraint condition is that user is unable to complete and/or preferentially completes educational administration's scheduled time section,
The educational administration arranges to include attending class and invigilating;
Step S102. arranges constraint condition according to educational administration and/or arranges the calculated educational administration of error calculation formula to pacify according to educational administration
Arrange the error training CPPN neural network of table;The error is that educational administration's calendar that CPPN neural computing goes out is filled in user
Constraint condition corresponding to educational administration's calendar matching degree;
Step S103. goes out educational administration's calendar using CPPN neural computing, and arranges error calculation formula to calculate by educational administration
The error of educational administration's calendar out;
Step S104. obtains the corresponding educational administration's calendar of the error in the case where error is not more than error threshold.
In step S101-S104, educational administration arranges error calculation formula to be constraint condition according to upload and real-time change
's;Training CPPN neural network in step S102 is divided into two kinds of situations, first is that according to the constraint condition of upload to CPPN nerve
Network is trained, and another kind is, when the error of the educational administration's calendar gone out based on CPPN neural computing is too big, at this point, right
The error carries out reverse conduction (including arranging error calculation formula to carry out derivative operation and pacify to the educational administration of derivative operation educational administration
Row's error calculation formula and the error carry out convolution) and error calculation formula adjusted is obtained, according to error meter adjusted
It calculates formula to be trained CPPN neural network, such repetition training adjusts and obtains the error that the educational administration calculated can be made to arrange and exist
Within the scope of energy is received;In step S102: arranging the mistake of the calculated educational administration's calendar of error calculation formula according to educational administration
Difference training CPPN neural network, really executes the CPPN neural computing to initializing constraint training in step s 103
After educational administration's calendar;And in the case where error is greater than error threshold, in step S103 and step S102 according to educational administration
The error training CPPN neural network for arranging the calculated educational administration's calendar of error calculation formula is that circulation carries out;And execute step
Before rapid S104, error is needed (to be set as being 0.1 in practice, it is, passing through CPPN neural computing no more than error threshold
Educational administration's calendar educational administration's calendar corresponding with constraint condition need to reach 90% or more the goodness of fit).
It should be noted that CPPN(Compositional Pattern-Producing Network, composite mode is raw
At network) it is a kind of production model based on Genetic Algorithm Evolution neural network structure, by after training, for input
Gauss number can export corresponding educational administration by encoder and decoder and arrange scheme;And execute what modification educational administration arranged
Main body is server, and constraint condition is the constraint for being uploaded to server using module (user terminal) by user, and uploading
Condition includes that user's (execute educational administration arrange teacher) can not attend class which at school in week (during student learns) period
And take an examination all (term Mo) which period can not course invigilated, further include it is desired preferentially select attend class/invigilate
Period;When executing step S101- step S104 in practice, server can first receive user and fill in constraint condition, according to constraint
Condition initialization error calculation formula and to CPPN composite mode generate network carry out initialize and neural network is trained,
Go out preferably educational administration according to trained CPPN neural computing and arrange scheme, and return to user, asks the user whether
Need to change educational administration's arrangement, if it does, then request and receive the constraint condition that user continues to fill in, server according to user again
The constraint condition of upload adjusts the error calculation mode of neural network and re-starts training to network, until training user
Satisfied scheme just terminates.
Meanwhile it should be explained that, error is to pass through the educational administration that CPPN neural computing obtains to arrange scheme and user
The corresponding educational administration of the constraint condition filled in arranges whether scheme matches, if had in the scheme that CPPN neural computing obtains
Course or examination be arranged at user can not scheduled time, error is just very big, if there is multiple course arrangement are being used
Family is wanted in scheduled time section, then the goodness of fit is high, and error is small;
Initialization is exactly that the constraint condition filled in user carries out indexization processing and is created that the formula compared, and row's class row is examined
The arrangement of each period is compared with user's constraint condition in arrangement, such as: user fills on Monday one or two section in morning
It can not arrange, but have the class of bis- section of Zhou Yiyi inside calculated scheme, the calculated value of error formula will be big;And if
User fills in that on Monday morning, one or two section was given priority in arranging for, and has the class of bis- section of Zhou Yiyi inside calculated scheme, and error is just
It can be small;
For CPPN neural network, input can be arbitrary content, thus using Gauss number come it is random generate one it is defeated
The number entered can export the side of educational administration's arrangement for arbitrarily inputting after CPPN neural network and coding decoder
Case;
Training to CPPN neural network is exactly to continuously adjust the weight of each node inside CPPN neural network so as to any
Input can access preferable educational administration and arrange scheme, the mode of the training of CPPN neural network is exactly to be determined by constraint condition
The educational administration of justice arranges error calculation formula, its error is all calculated after calculating educational administration's arrangement scheme every time, then to accidentally
Poor result carries out reverse conduction, modifies the weight of neural network interior joint.
Preferably, the educational administration uploaded according to user in step S101 arranges constraint condition to generate educational administration and arranges mistake
Before poor calculation formula, the method is also executed the following steps:
Step S105. obtains initial educational administration and arranges constraint condition;
Step S106. according to initial educational administration in the case where arranging constraint condition that can be matched to the first CPPN neural network, in institute
It states and inputs Gauss number in the first CPPN neural network and calculate educational administration's calendar, the first CPPN neural network is base
Constraint condition and trained CPPN neural network are arranged in the educational administration that other users upload.
It should be noted that it is so-called can matching be filled according to user can not arrange time and preferential selection time and take
The be engaged in educational administration filled in of middle other users of device arranges to be compared, and the period different in one week is carried out label, to can not
Arranging the time to attend class ,/invigilate and preferentially the selection time attends class/invigilates and distinguishes the identical quantity of statistical labeling, then sum it up, quantity
To represent matching accuracy rate higher more;Specifically, it will be unable to arrange to attend class/invigilate to be denoted as a, giving priority in arranging for attend class/invigilate is denoted as
B, it is 1,2,3 that then the period each in one week, which numbers in order, and if first-half in morning Monday is 1, rear two section is 2, afternoon
First-half is 3 ... can not arrange to attend class for user's selection, and/time invigilated and the arrangement preferentially selected are attended class/invigilates
Time is numbered, as on Monday one or two section in morning is busy by user, but wants to be arranged in three or four sections, is just denoted as a1, b2, will
The constraint condition that user fills in is converted into after label, and the constraint condition of the other users with storing in server is compared,
If there is also the labels by the user compared, then number of matches adds 1, finally find out number of matches it is highest that, exactly match
Accuracy rate is highest, that is, trained CPPN neural network.
Preferably, the educational administration uploaded according to user in step S1O1 arranges constraint condition to generate educational administration and arranges mistake
Poor calculation formula can be achieved by the steps of:
Step S1O1-1 arranges constraint condition to generate initial educational administration and arranges poor calculation formula according to the initial educational administration that user fills in;
Step S1O1-2 arranges constraint condition to generate new educational administration and arranges error calculation formula according to the new educational administration of user's addition.
Preferably, described according to educational administration's arrangement constraint condition and/or according to educational administration's arrangement error meter in step S102
The error training CPPN neural network for calculating the calculated educational administration's calendar of formula is achieved by the steps of:
Step S102-1. obtains the calculating factor that error calculation formula is arranged according to the educational administration that educational administration arranges constraint condition to generate,
And/or obtain the calculating factor of corresponding educational administration's arrangement error calculation formula after reverse conduction error;
Step S102-2. according to calculate the factor setting CPPN neural network node weight and complete to train.
Preferably, the utilization CPPN neural computing in step S103 goes out educational administration's calendar, and passes through educational administration
The error for arranging error calculation formula to calculate educational administration's calendar can be achieved by the steps of:
Step S103-1. inputs Gauss number in CPPN neural network and obtains calculated educational administration's calendar;
Educational administration corresponding to the constraint condition that step S103-2. counts calculated educational administration's calendar and user fills in arranges
The educational administration to match in table arranges number and the educational administration misfitted to arrange number (indexization constraint condition);
The identical educational administration of statistics is arranged number and the educational administration misfitted that number input educational administration is arranged to arrange to miss by step S103-3.
Poor calculation formula obtains the error of calculated educational administration's calendar.
Preferably, in the case where error is greater than error threshold, the method also includes following steps:
Step S107. is arranged using educational administration described in the local derviation of error calculation formula and the error update of calculated educational administration's calendar
Error;
The error of update is carried out reverse conduction and obtains matched meter in educational administration's arrangement error calculation formula by step 108.
Calculate the factor;
Step S109. is based on the matched calculating factor, is set simultaneously to the weight of the node of the CPPN neural network
Training CPPN network.
Through the above description of the embodiments, those skilled in the art can be understood that according to above-mentioned implementation
The method of example can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but it is very much
In the case of the former be more preferably embodiment.Based on this understanding, technical solution of the present invention is substantially in other words to existing
The part that technology contributes can be embodied in the form of software products, which is stored in a storage
In medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that a terminal device (can be mobile phone, calculate
Machine, server, or the network equipment etc.) method that executes each embodiment of the present invention.
Embodiment 2
Additionally provide in the present embodiment it is a kind of based on neural network modification University Educational Administration arrangement device, the device for realizing
Above-described embodiment and preferred embodiment, the descriptions that have already been made will not be repeated.As used below, term " module ",
" unit " can be the combination for realizing the software and/or hardware of predetermined function.Although device described in following embodiment is preferable
Ground is realized with software, but the realization of the combination of hardware or software and hardware is also that may and be contemplated.
Fig. 2 is the structural representation of the device according to an embodiment of the present invention based on neural network modification University Educational Administration arrangement
Figure, as described in Figure 2, which includes:
Module S21 is obtained, the educational administration for uploading according to user arranges constraint condition to generate educational administration and arranges error calculation formula;It is raw
Arranging error calculation formula at educational administration is that indexization processing is carried out to constraint condition, and it includes initial educational administration that educational administration, which arranges constraint condition,
Constraint condition and real-time educational administration arrange constraint condition, and constraint condition is that user is unable to complete and/or preferentially completes educational administration's arrangement
Period, the educational administration arrange to include attending class and invigilating;
Training module S22 is of coupled connections with module S21 and processing module S23 is obtained, for arranging constraint condition according to educational administration
And/or the error training CPPN neural network of the calculated educational administration's calendar of error calculation formula is arranged according to educational administration;The mistake
Difference is of educational administration's calendar corresponding to educational administration's calendar that CPPN neural computing goes out and the constraint condition that user fills in
With degree;
Processing module S23 is of coupled connections with training module S22, for going out educational administration's calendar using CPPN neural computing, and
The error of educational administration's calendar is calculated by educational administration's arrangement error calculation formula;
Planning module S24 is of coupled connections with processing module S23, in the case where error is not more than error threshold, obtaining should
The corresponding educational administration's calendar of error.
Preferably, involved device can also include: in the present embodiment
First obtains module S25, arranges constraint condition for obtaining initial educational administration;
First processing module S26 is of coupled connections with the first acquisition module S25, for arranging constraint condition according to initial educational administration
In the case where the first CPPN neural network can be matched to, Gauss number is inputted in the first CPPN neural network and is calculated
Educational administration's calendar out, the first CPPN neural network are that the educational administration uploaded based on other users is arranged constraint condition and trained
CPPN neural network.
Preferably, the acquisition module 21 of the present embodiment may include:
Generation unit S21-1, the initial educational administration by being filled according to user arrange constraint condition to generate based on initial educational administration's arrangement difference
It calculates formula and the new educational administration for being added according to user arranges constraint condition to generate new educational administration's arrangement error calculation formula.
Preferably, the training module S22 of the present embodiment may include:
First acquisition unit S22-1 arranges error calculation formula according to the educational administration that educational administration arranges constraint condition to generate for obtaining
The calculating factor, and/or obtain the calculating factor that corresponding educational administration after reverse conduction error arranges error calculation formula;
First processing units S22-2 is of coupled connections with first acquisition unit S22-1, for refreshing according to factor setting CPPN is calculated
The weight of node through network simultaneously is completed to train.
Preferably, the processing module S23 of the present embodiment may include:
First computing unit S23-1, for inputting Gauss number in CPPN neural network and obtaining calculated educational administration's peace
Arrange table;
First statistic unit S23-2 is of coupled connections with the first computing unit S23-1, for counting calculated educational administration's peace
The religion that the educational administration to match in educational administration's calendar corresponding to the constraint condition that row's table and user fill in arranges number and misfits
Business arranges number;
First processing units S23-3 is of coupled connections with the first statistic unit S23-2, and the identical educational administration for that will count arranges
Number and the educational administration misfitted arrange number input educational administration to arrange error calculation formula, obtain the mistake of calculated educational administration's calendar
Difference.
Preferably, the first statistic unit S23-2 in the present embodiment can also include:
First statistics subelement S23-21. is unable to complete educational administration for counting user and arranges not arranging educational administration to arrange in the period
Number, and/or user preferentially complete educational administration and arrange that the preferential number completing educational administration and arranging is scheduled in the period;
First statistics subelement S23-22. is unable to complete educational administration for counting user and arranges the number for arranging educational administration to arrange in the period
Mesh, and/or user preferentially complete educational administration and arrange the number for not arranging educational administration to arrange in the period.
Preferably, the device of the present embodiment can also include:
Second processing module S27, for arranging the local derviation and calculated educational administration's calendar of error calculation formula using educational administration
Error described in error update;
Third processing module S28, is of coupled connections with Second processing module S27, for reversely being passed the error updated
It leads and obtains educational administration and arrange the matched calculating factor in error calculation formula;
Fourth processing module S29 is of coupled connections with third processing module S28, for being based on the matched calculating factor, to institute
The weight for stating the node of CPPN neural network set and trains CPPN network.
It should be noted that above-mentioned modules, each unit can be realized by software or hardware, for rear
Person can be accomplished by the following way, but not limited to this: above-mentioned module is respectively positioned in same processor;Or above-mentioned module point
It Wei Yu not be in multiple processors.
In addition, the method based on neural network modification University Educational Administration arrangement in conjunction with Fig. 1 embodiment of the present invention described can
To be realized by computer equipment.Fig. 3 shows the hardware structural diagram of computer equipment provided in an embodiment of the present invention.
Computer equipment may include processor 401 and the memory 402 for being stored with computer program instructions.
Specifically, above-mentioned processor 401 may include central processing unit (CPU) or specific integrated circuit
(Application Specific Integrated Circuit, ASIC), or may be configured to implement implementation of the present invention
One or more integrated circuits of example.
Memory 402 may include the mass storage for data or instruction.For example it rather than limits, memory
402 may include hard disk drive (Hard Disk Drive, HDD), floppy disk drive, flash memory, CD, magneto-optic disk, tape or logical
With the combination of universal serial bus (Universal Serial Bus, USB) driver or two or more the above.It is closing
In the case where suitable, memory 402 may include the medium of removable or non-removable (or fixed).In a suitable case, it stores
Device 402 can be inside or outside data processing equipment.In a particular embodiment, memory 402 is nonvolatile solid state storage
Device.In a particular embodiment, memory 402 includes read-only memory (ROM).In a suitable case, which can be mask
ROM, programming ROM (PROM), erasable PROM (EPROM), the electric erasable PROM (EEPROM), electrically-alterable ROM of programming
(EAROM) or the combination of flash memory or two or more the above.
Processor 401 is by reading and executing the computer program instructions stored in memory 402, to realize above-mentioned implementation
The weak covering problem cell recognition method of LTE in example.
In one example, computer equipment may also include communication interface 403 and bus 410.As shown in Figure 3, wherein, locate
Reason device 401, memory 402, communication interface 403 connect by bus 410 and complete mutual communication.
Communication interface 403 is mainly used for realizing in the embodiment of the present invention between each module, device, unit and/or equipment
Communication.
Bus 410 includes hardware, software or both, and the component of computer equipment is coupled to each other together.For example
Rather than limit, bus may include accelerated graphics port (AGP) or other graphics bus, enhance Industry Standard Architecture (EISA) always
Line, front side bus (FSB), super transmission (HT) interconnection, the interconnection of Industry Standard Architecture (ISA) bus, infinite bandwidth, low pin count
(LPC) bus, memory bus, micro- channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express
(PCI-X) bus, Serial Advanced Technology Attachment (SATA) bus, Video Electronics Standards Association part (VLB) bus or other conjunctions
The combination of suitable bus or two or more the above.In a suitable case, bus 410 may include one or more
Bus.Although specific bus has been described and illustrated in the embodiment of the present invention, the present invention considers any suitable bus or interconnection.
The computer equipment can execute modifying in the embodiment of the present invention based on neural network based on the parameter got
The method of University Educational Administration arrangement.
In addition, in conjunction with the method based on neural network modification University Educational Administration arrangement in above-described embodiment, the present invention is implemented
Example can provide a kind of computer readable storage medium to realize.Computer program is stored on the computer readable storage medium to refer to
Enable: the computer program instructions realize in above-described embodiment when being executed by processor any one to be based on neural network modification high
The method that school educational administration arranges.
It should be clear that the invention is not limited to specific configuration described above and shown in figure and processing.
For brevity, it is omitted here the detailed description to known method.In the above-described embodiments, several tools have been described and illustrated
The step of body, is as example.But method process of the invention is not limited to described and illustrated specific steps, this field
Technical staff can be variously modified, modification and addition after understanding spirit of the invention, or suitable between changing the step
Sequence.
Functional block shown in structures described above block diagram can be implemented as hardware, software, firmware or their group
It closes.When realizing in hardware, it may, for example, be electronic circuit, specific integrated circuit (ASIC), firmware appropriate, insert
Part, function card etc..When being realized with software mode, element of the invention is used to execute program or the generation of required task
Code section.Perhaps code segment can store in machine readable media program or the data-signal by carrying in carrier wave is passing
Defeated medium or communication links are sent." machine readable media " may include any medium for capableing of storage or transmission information.
The example of machine readable media includes electronic circuit, semiconductor memory devices, ROM, flash memory, erasable ROM(EROM), it is soft
Disk, CD-ROM, CD, hard disk, fiber medium, radio frequency (RF) link, etc..Code segment can be via such as internet, inline
The computer network of net etc. is downloaded.
It should also be noted that, the exemplary embodiment referred in the present invention, is retouched based on a series of step or device
State certain methods or system.But the present invention is not limited to the sequence of above-mentioned steps, that is to say, that can be according in embodiment
The sequence referred to executes step, may also be distinct from that the sequence in embodiment or several steps are performed simultaneously.
It is not intended to limit the scope of the present invention above, all technical spirits according to the present invention are to above implementation
Any modification, equivalent variations and modification made by example, in the range of still falling within technical solution of the present invention.
Claims (10)
1. a kind of method based on neural network modification University Educational Administration arrangement, it is characterised in that, include:
It arranges constraint condition to generate educational administration according to the educational administration that user uploads and arranges error calculation formula;It generates educational administration and arranges error meter
Calculating formula is that indexization processing is carried out to constraint condition, and it includes initial educational administration's constraint condition and religion in real time that educational administration, which arranges constraint condition,
Business arranges constraint condition, and constraint condition is that user is unable to complete and/or preferentially completes educational administration's scheduled time section, educational administration's peace
Row includes attending class and invigilating;
Constraint condition is arranged according to educational administration and/or the error of the calculated educational administration's calendar of error calculation formula is arranged according to educational administration
Training CPPN neural network;The error is educational administration's calendar that CPPN neural computing goes out and the constraint condition that user fills in
The matching degree of corresponding educational administration's calendar;
Go out educational administration's calendar using CPPN neural computing, and arranges error calculation formula to calculate educational administration by educational administration and arrange
The error of table;
In the case where error is not more than error threshold, the corresponding educational administration's calendar of the error is obtained.
2. a kind of method based on neural network modification University Educational Administration arrangement according to claim 1, it is characterised in that, institute
Before the educational administration uploaded according to user stated arranges constraint condition to generate educational administration's arrangement error calculation formula, comprising:
It obtains initial educational administration and arranges constraint condition;
In the case where arranging constraint condition that can be matched to the first CPPN neural network according to initial educational administration, in the first CPPN
Gauss number is inputted in neural network and calculates educational administration's calendar, and the first CPPN neural network is based on other users
The educational administration of upload arranges constraint condition and trained CPPN neural network.
3. a kind of method based on neural network modification University Educational Administration arrangement according to claim 2, it is characterised in that, institute
The educational administration uploaded according to user stated arranges constraint condition to generate educational administration's arrangement error calculation formula
It arranges constraint condition to generate initial educational administration according to the initial educational administration that user fills in and arranges poor calculation formula;
It arranges constraint condition to generate new educational administration according to the new educational administration of user's addition and arranges error calculation formula.
4. a kind of method based on neural network modification University Educational Administration arrangement according to claim 2, it is characterised in that, institute
That states arranges constraint condition according to educational administration and/or according to the error of educational administration's arrangement calculated educational administration's calendar of error calculation formula
Training CPPN neural network include:
The calculating factor for arranging error calculation formula according to the educational administration that educational administration arranges constraint condition to generate is obtained, and/or is obtained anti-
Corresponding educational administration arranges the calculating factor of error calculation formula after to conduction eror;
According to the weight for the node for calculating factor setting CPPN neural network and complete to train.
5. a kind of method based on neural network modification University Educational Administration arrangement according to claim 4, it is characterised in that, institute
That states goes out educational administration's calendar using CPPN neural computing, and arranges error calculation formula to calculate educational administration by educational administration and arrange
The error of table includes:
Gauss number is inputted in CPPN neural network and obtains calculated educational administration's calendar;
Count calculated educational administration's calendar and constraint condition that user fills in corresponding to match in educational administration's calendar
Educational administration arrange number and the educational administration misfitted to arrange number;
Arrange number and the educational administration misfitted that number input educational administration is arranged to arrange error calculation formula the identical educational administration of statistics,
Obtain the error of calculated educational administration's calendar.
6. a kind of method based on neural network modification University Educational Administration arrangement according to claim 5, it is characterised in that, institute
It matches in educational administration's calendar corresponding to the constraint condition that the statistics calculated educational administration's calendar stated and user fill in
Educational administration arrange number and the educational administration misfitted to arrange the number to include:
Counting user is unable to complete educational administration and the number for not arranging educational administration to arrange in the period, and/or user is arranged preferentially to complete to teach
Business arranges that the preferential number completing educational administration and arranging is scheduled in the period;
Counting user is unable to complete educational administration and the number for arranging educational administration to arrange in the period, and/or user is arranged preferentially to complete educational administration
Arrange the number for not arranging educational administration to arrange in the period.
7. a kind of method based on neural network modification University Educational Administration arrangement according to claim 6, it is characterised in that,
In the case where error is greater than error threshold, the described method includes:
Error described in the local derviation of error calculation formula and the error update of calculated educational administration's calendar is arranged using educational administration;
The error of update is subjected to reverse conduction and obtains educational administration arranging the matched calculating factor in error calculation formula;
Based on the matched calculating factor, the weight of the node of the CPPN neural network set and trains CPPN net
Network.
8. a kind of device based on neural network modification University Educational Administration arrangement, it is characterised in that, include:
Module is obtained, the educational administration for uploading according to user arranges constraint condition to generate educational administration and arranges error calculation formula;It generates
Educational administration arrange error calculation formula be to constraint condition carry out indexization processing, educational administration arrange constraint condition include initial educational administration about
Beam condition and real-time educational administration arrange constraint condition, constraint condition be user be unable to complete and/or preferentially complete educational administration's arrangement when
Between section, the educational administration arranges to include attending class and invigilating;
Training module, for arranging constraint condition according to educational administration and/or arranging the calculated religion of error calculation formula according to educational administration
The error training CPPN neural network of business calendar;The error is the educational administration's calendar and user that CPPN neural computing goes out
The matching degree of educational administration's calendar corresponding to the constraint condition filled in;
Processing module for going out educational administration's calendar using CPPN neural computing, and arranges error calculation formula by educational administration
Calculate the error of educational administration's calendar;
Planning module, for obtaining the corresponding educational administration's calendar of the error in the case where error is not more than error threshold.
9. a kind of computer equipment, it is characterised in that, include: at least one processor, at least one processor and is stored in
Computer program instructions in the memory realize such as right when the computer program instructions are executed by the processor
It is required that method described in any one of 1-7.
10. a kind of computer readable storage medium, is stored thereon with computer program instructions, which is characterized in that when the calculating
Such as method of any of claims 1-7 is realized when machine program instruction is executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910766856.2A CN110458737B (en) | 2019-08-20 | 2019-08-20 | Method, device, equipment and medium for modifying college educational administration arrangement based on neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910766856.2A CN110458737B (en) | 2019-08-20 | 2019-08-20 | Method, device, equipment and medium for modifying college educational administration arrangement based on neural network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110458737A true CN110458737A (en) | 2019-11-15 |
CN110458737B CN110458737B (en) | 2023-09-26 |
Family
ID=68487829
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910766856.2A Active CN110458737B (en) | 2019-08-20 | 2019-08-20 | Method, device, equipment and medium for modifying college educational administration arrangement based on neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110458737B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107610012A (en) * | 2017-09-22 | 2018-01-19 | 皇晓琳 | A kind of curricula-variable and Course Arrangement and its curricula-variable and cource arrangement method |
CN109902371A (en) * | 2019-02-19 | 2019-06-18 | 校宝在线(杭州)科技股份有限公司 | A kind of Intelligent Course Scheduling method based on deeply study |
CN109961189A (en) * | 2019-03-29 | 2019-07-02 | 北京工业大学 | New college entrance examination timetabling algorithm based on genetic algorithm |
CN110020831A (en) * | 2019-03-29 | 2019-07-16 | 北京工业大学 | New college entrance examination timetabling algorithm based on particle swarm algorithm |
CN110047023A (en) * | 2019-03-29 | 2019-07-23 | 北京工业大学 | New college entrance examination timetabling algorithm based on simulated annealing |
-
2019
- 2019-08-20 CN CN201910766856.2A patent/CN110458737B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107610012A (en) * | 2017-09-22 | 2018-01-19 | 皇晓琳 | A kind of curricula-variable and Course Arrangement and its curricula-variable and cource arrangement method |
CN109902371A (en) * | 2019-02-19 | 2019-06-18 | 校宝在线(杭州)科技股份有限公司 | A kind of Intelligent Course Scheduling method based on deeply study |
CN109961189A (en) * | 2019-03-29 | 2019-07-02 | 北京工业大学 | New college entrance examination timetabling algorithm based on genetic algorithm |
CN110020831A (en) * | 2019-03-29 | 2019-07-16 | 北京工业大学 | New college entrance examination timetabling algorithm based on particle swarm algorithm |
CN110047023A (en) * | 2019-03-29 | 2019-07-23 | 北京工业大学 | New college entrance examination timetabling algorithm based on simulated annealing |
Non-Patent Citations (1)
Title |
---|
刘瑶;: "智能决策在教务管理系统中的应用", 韶关学院学报, no. 12, pages 17 - 20 * |
Also Published As
Publication number | Publication date |
---|---|
CN110458737B (en) | 2023-09-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11783227B2 (en) | Method, apparatus, device and readable medium for transfer learning in machine learning | |
CN109740657B (en) | Training method and device of neural network model for image data classification | |
CN110390108B (en) | Task type interaction method and system based on deep reinforcement learning | |
DE102018202497A1 (en) | Technologies for optimized machine learning training | |
CN109990790A (en) | A kind of unmanned plane paths planning method and device | |
CN108197652A (en) | For generating the method and apparatus of information | |
US20230394986A1 (en) | Test question generation method, apparatus and system, and computer storage medium and program product | |
CN107220916A (en) | Pushing learning resource method and device | |
CN112001609A (en) | Occupational training evaluation system and method thereof | |
DE112020002961T5 (en) | TRANSLATE A NATURAL LANGUAGE QUERY INTO A FORMAL DATA REQUEST | |
CN109086352A (en) | Consultation information feedback method, terminal and storage medium based on artificial intelligence | |
CN110162554A (en) | Data processing method, device, storage medium and electronic equipment | |
CN110399933A (en) | Data mark modification method, device, computer-readable medium and electronic equipment | |
JP7177294B2 (en) | Individual flight training scheme generation system, method and apparatus | |
CN110390110A (en) | The method and apparatus that pre-training for semantic matches generates sentence vector | |
KR102316070B1 (en) | Self-directed learning optimization system and method thereof | |
US11276005B2 (en) | Cognitive assessment based recommendations | |
CN107909164A (en) | O&M processing method, system, electronic equipment and computer-readable medium | |
CN110458737A (en) | Method, apparatus, equipment and medium based on neural network modification University Educational Administration arrangement | |
CN110033239B (en) | Greedy algorithm based examination scheduling method, device, equipment and medium | |
CN112883174A (en) | Automatic generation method and system for online programming test questions | |
CN111754370A (en) | Artificial intelligence-based online education course management method and system | |
CN115658928B (en) | Method, device, computer equipment and storage medium for assembling paper test paper | |
Reitinger | 4On the Nature and Empirical Accessibility of Inquiry Learning: The Criteria of Inquiry Learning Inventory (CILI) | |
US20140038161A1 (en) | Multi-layered cognitive tutor |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |