CN116468416A - Intelligent shift-walking course-arranging method based on genetic algorithm - Google Patents
Intelligent shift-walking course-arranging method based on genetic algorithm Download PDFInfo
- Publication number
- CN116468416A CN116468416A CN202310723576.XA CN202310723576A CN116468416A CN 116468416 A CN116468416 A CN 116468416A CN 202310723576 A CN202310723576 A CN 202310723576A CN 116468416 A CN116468416 A CN 116468416A
- Authority
- CN
- China
- Prior art keywords
- class
- constraint
- course
- representing
- arrangement
- 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 52
- 230000002068 genetic effect Effects 0.000 title claims abstract description 26
- 238000005457 optimization Methods 0.000 claims abstract description 7
- 238000011156 evaluation Methods 0.000 claims description 26
- 230000003442 weekly effect Effects 0.000 claims description 17
- 238000007599 discharging Methods 0.000 claims description 12
- 239000006185 dispersion Substances 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 6
- 108090000623 proteins and genes Proteins 0.000 claims description 6
- 239000012634 fragment Substances 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 abstract description 2
- 238000007418 data mining Methods 0.000 abstract description 2
- 238000010801 machine learning Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 44
- 230000000694 effects Effects 0.000 description 2
- 238000012248 genetic selection Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000008303 genetic mechanism Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/109—Time management, e.g. calendars, reminders, meetings or time accounting
- G06Q10/1093—Calendar-based scheduling for persons or groups
-
- 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
- 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
- G06Q10/109—Time management, e.g. calendars, reminders, meetings or time accounting
-
- 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
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Educational Technology (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Primary Health Care (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an intelligent shift-walking course-arranging method based on a genetic algorithm, which belongs to the field of intelligent course-arranging and comprises the following steps: s1, generating an initial class list by adopting an individual optimization mode, and performing binary coding on the initial class list to obtain an initial pre-arranged class list population; s2, calculating the fitness of the initial pre-arranged class list population by adopting a genetic algorithm, and selecting a class list with the minimum fitness value as an optimal class list; s3, judging whether the adaptability corresponding to the current optimal textbook reaches an expected value or not; if yes, outputting a current optimal class list; if not, the current optimal textlist is crossed and mutated, and then the step S2 is returned until the adaptability reaches the expected value, and the corresponding optimal textlist is output. The intelligent class walking and course arrangement method based on the genetic algorithm can meet constraint conditions in course arrangement to the greatest extent under the condition of limited teaching resources based on big data analysis, data mining and machine learning, and intelligent course arrangement is realized.
Description
Technical Field
The invention relates to the technical field of intelligent course arrangement, in particular to an intelligent course walking and course arrangement method based on a genetic algorithm.
Background
In the traditional administrative class teaching, courses, lessons, places of lessons and teachers of all students in one class are fixed, at this time, the 'one-class schedule' can solve the course arrangement of all students, and school educational departments only need to discharge the schedule according to requirements.
After the new college and university is reformed, courses are required to be arranged for students of different selected departments according to the student selected department conditions, and the students are encouraged to conduct personalized selection according to own characters, interests and special expertise and the requirements of the college and university specialized selected subjects. Taking a 3+1+2 mode as an example, except 3 college examination subjects in Chinese, mathematics and foreign languages, 1 subject is selected from 2 subjects in physics and history, 2 subjects in chemistry, biology, politics and geography are selected from 4 subjects, 12 selected combinations can be selected, the unselected subjects are taken as study courses to take part in the study level examination, and the college examination score consists of three subjects selected independently in Chinese, mathematics and foreign languages.
The new college entrance examination reform scheme improves the freedom degree of student selection, and can bring the special features of students into play to the greatest extent. At this time, the traditional class-dividing and course-arranging mode cannot meet the class-dividing and course-arranging mode of the new college entrance under the existing teaching resources, so that at the initial stage of the reform of the new college entrance, many schools have the problem of insufficient teacher resources, classroom resources and software and hardware resources, only a plurality of kinds of selection combinations are opened for students to select, instead of all twelve kinds of selection combinations, so that the freedom of selection of the students is limited.
Disclosure of Invention
In order to solve the problem that the traditional manual course arrangement and course arrangement tool can hardly meet the personalized requirements of course arrangement. The invention provides an intelligent class-walking class-arranging method based on a genetic algorithm, which is used for preferentially solving the problem of space constraint of teachers in pre-class arranging, and dispersing and arranging subjects into a weekly class list, and generating an initial class list population according to a pre-class-arranging result. And calculating the population fitness of the multiple tables by adopting a genetic algorithm, selecting the table with the minimum population fitness as the optimal initial table, outputting the table if the table meets the expected expectations, and if the table does not meet the expected expectations, intersecting and mutating the table population which does not meet the expected expectations, so that the genetic process advances towards the optimal table until the expected expectations are reached.
In order to achieve the above purpose, the invention provides an intelligent shift-walking course-arranging method based on a genetic algorithm, which comprises the following steps:
s1, generating an initial class list in an individual optimization mode, and binary coding the initial class list of each class week to obtain an initial pre-arranged class list population;
s2, calculating the fitness of the initial pre-arranged class list population by adopting a genetic algorithm, sorting the fitness, and selecting a class list with the minimum fitness value as an optimal class list;
s3, judging whether the adaptability corresponding to the current optimal textbook reaches an expected value or not; if yes, outputting a current optimal class list; if not, the current optimal textlist is crossed and mutated, and then the step S2 is returned until the adaptability reaches the expected value, and the corresponding optimal textlist is output.
Preferably, the step S1 specifically includes the following steps:
s11, acquiring the class time of each week of the Monday to Sunday, the time, the class division situation, the class path, the class arrangement constraint condition and the class time of each week of each grade;
s12, acquiring the course arrangement of each class week according to the class from monday to friday, the time, the amount of time of each week of each class and the class division condition;
s13, performing binary coding on the class scheduling list, and generating an initial pre-class scheduling list group according to the weekly course arrangement, the class path and the constraint conditions of each class.
Preferably, the step S13 specifically includes the following steps:
s131, coding according to the class-teacher-subject-class time sequence;
s132, generating an initial textbook gene fragment matrix:
assume that school is on class weeklyFestival, altogether->The class-arrangement task includes arrangement +.>Course matrix of individual gene segments:
（1）
s133, generating an initial class list in an individual optimization mode;
s134, copying the initial class list to generate an initial class list group.
Preferably, the fitness of the population in step S2 is calculated using the fitness function:
（2）
in the method, in the process of the invention,to take into account the number of constraints; />For the index taking into account constraints, the range is from 1 to +.>；/>A weight for each fitness function; />An evaluation function which is an fitness function;
（3）
in the method, in the process of the invention,to violate the number of course arrangement constraints +.>Is a penalty factor;
the lesson-discharging constraint conditions comprise a teacher space constraint condition, a fixed lesson-discharging constraint condition, a lesson-discharging constraint condition forbidden, a priority lesson-discharging constraint condition, a continuous lesson-discharging constraint condition, a teacher collective lesson-preparing constraint condition, a weekly dispersion lesson-discharging constraint condition and a shift-moving path constraint condition;
converting the fitness function into:
（4）
in the method, in the process of the invention,evaluation function of fitness function representing teacher space constraint +.>Representing the number of violations of the teacher space constraint, < +.>Penalty factors representing teacher space constraints; />Evaluation function of fitness function representing fixed class-arrangement constraints +.>Indicating the number of violations of the fixed rank condition, +.>Penalty factors representing fixed course scheduling constraints; />Evaluation function of fitness function representing forbidden class constraint>Representing the number of violations of the forbidden course arrangement constraint, < +.>A penalty factor representing a forbidden course arrangement constraint; />Evaluation function of fitness function representing priority class-ranking constraints +.>Indicating the number of violations of the priority class constraint,/>A penalty factor representing violation of a priority class-ordering constraint; />Evaluation function of fitness function representing continuous course arrangement constraint, +.>Representing the number of violations of the continuous course arrangement constraint, < +.>A penalty factor representing violating a continuous course arrangement constraint; />Evaluation function of fitness function representing constraint conditions of teacher collective lesson preparation, < ->Representing the number of violations of the teacher collective lesson preparation constraint,/-)>A penalty factor indicating violation of the teacher collective lesson preparation constraint; />An evaluation function of the fitness function representing weekly dispersion class-arrangement constraints, +.>Indicating the number of violations of the weekly dispersion class arrangement constraint,/->A penalty factor indicating violation of a weekly dispersion class-arrangement constraint; />Evaluation function of fitness function representing travel path constraints +.>Indicating the number of violations of the shift path constraints,and a penalty factor for violating the constraint condition of the shift path is represented.
Preferably, the intersecting in the step S3 is to adopt small granularity, and randomly select two classes of a class in a class list for exchanging;
the variation is as follows: two classes in the same class time period are randomly selected for exchange.
The invention has the following beneficial effects:
1. the problem of space constraint of teachers is preferentially solved, subjects are distributed and arranged into the weekly class list, an initial class list population is generated according to the pre-class arrangement result, the situation that the space constraint of the teachers is violated in the initial class list is reduced as much as possible, further iteration times are reduced, and class arrangement time is shortened.
2. And calculating the population fitness of a plurality of tables by adopting a genetic algorithm, selecting the table with the minimum population fitness as the optimal initial table, outputting the table if the table meets the expected expectations, and if the table does not meet the expected expectations, intersecting and mutating the table population which does not meet the expected expectations, so that the genetic process advances towards the optimal table until reaching the expected expectations, continuously converging, enabling fewer and fewer constraint conditions to be violated in the table, and finally achieving the effect of extremely few or even no constraint conditions to be violated.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
FIG. 1 is a flow chart of an intelligent shift course arrangement method based on a genetic algorithm.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the detailed description and specific examples, while indicating the embodiment of the invention, are intended for purposes of illustration only and are not intended to limit the scope of the invention. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present application based on the embodiments herein. Examples of the embodiments are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements throughout or elements having like or similar functionality.
It should be noted that the terms "comprises" and "comprising," along with any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
In the description of the present invention, it should be noted that, directions or positional relationships indicated by terms such as "upper", "lower", "inner", "outer", etc., are directions or positional relationships based on those shown in the drawings, or those that are conventionally put in use, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the apparatus or elements to be referred to must have a specific direction, be constructed and operated in a specific direction, and thus should not be construed as limiting the present invention.
In the description of the present invention, it should also be noted that, unless explicitly specified and limited otherwise, the terms "disposed," "mounted," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
As shown in FIG. 1, the intelligent shift-walking course-arranging method based on the genetic algorithm comprises the following steps:
s1, generating an initial class list in an individual optimization mode, and binary coding the initial class list of each class week to obtain an initial pre-arranged class list population;
preferably, the step S1 specifically includes the following steps:
s11, acquiring the class time of each week of the Monday to Sunday, the time, the class division situation, the class path, the class arrangement constraint condition and the class time of each week of each grade;
in this embodiment: the courseday to friday sections and the time are as follows: several lessons are arranged every day and at what time, respectively. The amount of lessons per week in each of the senior departments is: several classes are arranged in a week for each subject. Wherein the subjects are classified into selected subjects and unselected subjects. The selected subjects are subjects for taking college entrance examination results, and the unselected subjects are subjects for the academic level examination.
The shift situation is mainly divided into the following 4 types:
(1) 'fixed shift' mode
The school teaching resources are limited, the condition of the shift teaching cannot be met, and limited selection combinations are provided for students to select. Or the school teaching resources are sufficient, and all the selected combinations are provided for students to select. And finally, dividing the students with the same discipline combination into a class.
(2) Small shift mode
Students with the same selection combination or the same selection combination part are formed into fixed administrative shifts, and only part of students need to walk shifts. The method is specifically divided into two types: three families are preferred. Firstly, dividing as many students as possible in the same selection and combination into the same class, ensuring that the students do not need to walk, then dividing as many students in the same selection and combination into the same class, and finally dividing the students in the same selection or different selection into the same class; and (3) setting two times and one time. Students with the same selection of two departments are separated into the same class, and the rest students with different selection subjects walk through the class.
(3) 'big shift' mode
The subjects for the foreign language number examination are fixed on administrative shifts, and the rest subjects for the selected subjects walk shifts.
(4) 'full shift' mode
All subjects walk through the shifts.
The shift path is as follows: the class with a plurality of selected combinations has a fixed class subject, a walking class subject, and when the fixed class subject is in class, the walking class subject needs to go to the class of other classes containing the walking class subject, namely, the fixed class subject and the walking class subject are simultaneously in class with the corresponding class subject.
The class-arrangement constraint conditions also include student space constraint conditions (students can only play one course at the same time) and classroom constraint conditions (one classroom can only play one course at the same time).
S12, acquiring the course arrangement of each class week according to the class from monday to friday, the time, the amount of time of each week of each class and the class division condition;
in the embodiment, the number of the class hour of each class week is obtained according to the class hour of each class week, the time, the class hour of each class week and the class division condition;
s13, performing binary coding on the class scheduling list, and generating an initial pre-class scheduling list group according to the weekly course arrangement, the class path and the constraint conditions of each class.
Preferably, the step S13 specifically includes the following steps:
s131, coding according to the class-teacher-subject-class time sequence;
in this embodiment, the class 2 bit code length, the teacher 4 bit code length, the subject 2 bit code length, and the class time 2 bit code length. The time code of lesson is that if 8 lessons are arranged in each day of the school, the time code of lesson 09-18 indicates the first to eighth lessons on tuesday. If the codes 002-00026-01-01 indicate 002 class, 00026 teacher, 01 subject, and the teaching time is the first section of monday.
S132, generating an initial textbook gene fragment matrix:
assume that school is on class weeklyFestival, altogether->The class-arrangement task includes arrangement +.>Course matrix of individual gene segments:
（1）
s133, generating an initial class list in an individual optimization mode;
the generating step of the initial class list comprises the following steps:
the first step: starting from a first class, dispersedly arranging courses of each department downwards in sequence from a first class time period of each week according to a teaching plan, and finishing the class arrangement of the first class;
secondly, after the first class is arranged, the subsequent classes dispersedly arrange courses of each department downwards from the first class time period of each week from the non-class-arranging time period in sequence according to the teaching plan; meanwhile, judging whether the same class teacher appears in the same class time period or not in other classes, if so, indicating that the space constraint condition of the teacher is violated, and arranging the classes in the next class time period; if all the empty time periods violate the space constraint condition of the teacher, selecting the positions where lessons are arranged for replacement until the space constraint condition of the teacher is not violated;
s134, copying the initial class list to generate an initial class list group.
S2, calculating the fitness of the initial pre-arranged class list population by adopting a genetic algorithm, sorting the fitness, and selecting a class list with the minimum fitness value as an optimal class list;
it should be noted that the genetic algorithm source is designed and proposed according to the evolution rule of the organism in the nature. The method is a calculation model of the biological evolution process simulating the natural selection and genetic mechanism of the Darwin biological evolution theory, and is a method for searching the optimal solution by simulating the natural evolution process.
In the traditional genetic algorithm, the genetic selection operation is generally roulette, through practical tests, the roulette is adopted for genetic selection, if the fitness of each generation of population is not much, individuals with better fitness cannot be selected with high probability, and the genetic process tends to be unoriented. Therefore, the invention sorts the class list population of each generation according to the population fitness, and selects the class list with the smallest population fitness as the best class list. The smaller the population adaptability is, the fewer the violating constraint conditions are in the class list, the optimal class list of each iteration is reserved in the mode, after continuous selection, crossing and variation iteration, the fewer violating constraint conditions are in the class list, the class list is enabled to continuously converge, and finally the effect that the violating constraint conditions are very few or even none is achieved.
Preferably, the fitness of the population in step S2 is calculated using the fitness function:
（2）
in the method, in the process of the invention,to take into account the number of constraints; />For the index taking into account constraints, the range is from 1 to +.>；/>A weight for each fitness function; />An evaluation function which is an fitness function;
and has the following steps:
（3）
in the method, in the process of the invention,to violate the number of course arrangement constraints +.>Is a penalty factor;
the class arrangement constraint conditions include a teacher space constraint condition (a teacher can only take class in one class at the same section), a fixed class arrangement constraint condition (a class table is fixed in units of classes, the section does not support arrangement of other classes after fixing), a class arrangement prohibition constraint condition (a certain section is provided with a certain subject to prohibit class arrangement), a priority class arrangement constraint condition (a certain section is provided with a certain subject to prioritize class arrangement), a continuous class arrangement constraint condition (a certain subject is provided with a continuous class arrangement in a round), a teacher collective class preparation constraint condition (the class arrangement teachers of the same subject do not arrange teaching in the same teaching time period and do collective class preparation), a weekly dispersion class arrangement constraint condition (each day of the week should be dispersed in the class arrangement of each class), a class arrangement constraint condition (students should follow a reasonable road as much as possible between different time periods), and movement of the students between different classrooms is reduced);
converting the fitness function into:
（4）
in the method, in the process of the invention,evaluation function of fitness function representing teacher space constraint +.>Representing the number of violations of the teacher space constraint, < +.>Penalty factors representing teacher space constraints; />Evaluation function of fitness function representing fixed class-arrangement constraints +.>Indicating the number of violations of the fixed rank condition, +.>Penalty factors representing fixed course scheduling constraints; />Evaluation function of fitness function representing forbidden class constraint>Representing the number of violations of the forbidden course arrangement constraint, < +.>Penalty factor indicating constraint for forbidden course arrangementA seed; />Evaluation function of fitness function representing priority class-ranking constraints +.>Indicating the number of violations of the priority class constraint,/>A penalty factor representing violation of a priority class-ordering constraint; />Evaluation function of fitness function representing continuous course arrangement constraint, +.>Representing the number of violations of the continuous course arrangement constraint, < +.>A penalty factor representing violating a continuous course arrangement constraint; />Evaluation function of fitness function representing constraint conditions of teacher collective lesson preparation, < ->Representing the number of violations of the teacher collective lesson preparation constraint,/-)>A penalty factor indicating violation of the teacher collective lesson preparation constraint; />An evaluation function of the fitness function representing weekly dispersion class-arrangement constraints, +.>Indicating the number of violations of the weekly dispersion class arrangement constraint,/->A penalty factor indicating violation of a weekly dispersion class-arrangement constraint; />Evaluation function of fitness function representing travel path constraints +.>Indicating the number of violations of the shift path constraint, +.>And a penalty factor for violating the constraint condition of the shift path is represented.
It should be noted that, this embodiment is only to exemplify constraint conditions, and those skilled in the art may also replace or add other constraint conditions with actual demands, such as giving lessons to teachers at specified classes, giving lessons to teachers in a centralized manner, etc. And only the quantity which does not meet the conditions is counted in sequence, and the smaller the fitness function is, the closer the adaptability function is to the course arrangement requirement.
S3, judging whether the adaptability corresponding to the current optimal textbook reaches an expected value or not; if yes, outputting a current optimal class list; if not, the current optimal textlist is crossed and mutated, and then the step S2 is returned until the adaptability reaches the expected value, and the corresponding optimal textlist is output. Preferably, the intersecting in the step S3 is to adopt small granularity, and randomly select two classes of a class in a class list for exchanging;
the variation is as follows: two classes in the same class time period of the same year are randomly selected for exchange, for example, a first class and a second class of the annual class schedule are exchanged.
Therefore, the intelligent class-walking course-arranging method based on the genetic algorithm can meet constraint conditions in course-arranging to the greatest extent under the condition of limited teaching resources based on big data analysis, data mining and machine learning, and intelligent course-arranging is realized.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention and not for limiting it, and although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that: the technical scheme of the invention can be modified or replaced by the same, and the modified technical scheme cannot deviate from the spirit and scope of the technical scheme of the invention.
Claims (5)
1. An intelligent shift-walking course-arranging method based on a genetic algorithm is characterized in that: the method comprises the following steps:
s1, generating an initial class list in an individual optimization mode, and binary coding the initial class list of each class week to obtain an initial pre-arranged class list population;
s2, calculating the fitness of the initial pre-arranged class list population by adopting a genetic algorithm, sorting the fitness, and selecting a class list with the minimum fitness value as an optimal class list;
s3, judging whether the adaptability corresponding to the current optimal textbook reaches an expected value or not; if yes, outputting a current optimal class list; if not, the current optimal textlist is crossed and mutated, and then the step S2 is returned until the adaptability reaches the expected value, and the corresponding optimal textlist is output.
2. The intelligent shift-walking course-arranging method based on the genetic algorithm of claim 1, wherein the method comprises the following steps: the step S1 specifically comprises the following steps:
s11, acquiring the class time of each week of the Monday to Sunday, the time, the class division situation, the class path, the class arrangement constraint condition and the class time of each week of each grade;
s12, acquiring the course arrangement of each class week according to the class from monday to friday, the time, the amount of time of each week of each class and the class division condition;
s13, performing binary coding on the class scheduling list, and generating an initial pre-class scheduling list group according to the weekly course arrangement, the class path and the constraint conditions of each class.
3. The intelligent shift-walking course-arranging method based on the genetic algorithm of claim 2, wherein the method is characterized in that: the step S13 specifically includes the following steps:
s131, coding according to the class-teacher-subject-class time sequence;
s132, generating an initial textbook gene fragment matrix:
assume that school is on class weeklyFestival, altogether->The class-arrangement task includes arrangement +.>Course matrix of individual gene segments:
（1）
s133, generating an initial class list in an individual optimization mode;
s134, copying the initial class list to generate an initial class list group.
4. The intelligent shift-walking course-arranging method based on the genetic algorithm of claim 1, wherein the method comprises the following steps: the fitness of the population described in step S2 is calculated using the fitness function:
（2）
in the method, in the process of the invention,to take into account the number of constraints; />For the index taking into account constraints, the range is from 1 to +.>；/>A weight for each fitness function; />An evaluation function which is an fitness function;
and has the following steps:
（3）
in the method, in the process of the invention,to violate the number of course arrangement constraints +.>Is a penalty factor;
the lesson-discharging constraint conditions comprise a teacher space constraint condition, a fixed lesson-discharging constraint condition, a lesson-discharging constraint condition forbidden, a priority lesson-discharging constraint condition, a continuous lesson-discharging constraint condition, a teacher collective lesson-preparing constraint condition, a weekly dispersion lesson-discharging constraint condition and a shift-moving path constraint condition;
converting the fitness function into:
（4）
in the method, in the process of the invention,evaluation function of fitness function representing teacher space constraint +.>Representing violation of teacher space constraintsQuantity of->Penalty factors representing teacher space constraints; />Evaluation function of fitness function representing fixed class-arrangement constraints +.>Indicating the number of violations of the fixed rank condition, +.>Penalty factors representing fixed course scheduling constraints; />Evaluation function of fitness function representing forbidden class constraint>Representing the number of violations of the forbidden course arrangement constraint, < +.>A penalty factor representing a forbidden course arrangement constraint; />Evaluation function of fitness function representing priority class-ranking constraints +.>Indicating the number of violations of the priority class constraint,/>A penalty factor representing violation of a priority class-ordering constraint; />Representing continuous course arrangement constraintsEvaluation function of the fitness function of the conditions, +.>Representing the number of violations of the continuous course arrangement constraint, < +.>A penalty factor representing violating a continuous course arrangement constraint; />Evaluation function of fitness function representing constraint conditions of teacher collective lesson preparation, < ->Representing the number of violations of the teacher collective lesson preparation constraint,/-)>A penalty factor indicating violation of the teacher collective lesson preparation constraint; />An evaluation function of the fitness function representing weekly dispersion class-arrangement constraints, +.>Indicating the number of violations of the weekly dispersion class arrangement constraint,/->A penalty factor indicating violation of a weekly dispersion class-arrangement constraint; />Evaluation function of fitness function representing travel path constraints +.>Indicating the number of violations of the shift path constraint, +.>And a penalty factor for violating the constraint condition of the shift path is represented.
5. The intelligent shift-walking course-arranging method based on the genetic algorithm of claim 1, wherein the method comprises the following steps: the step S3 is to select two classes of a class in a class list randomly for exchange in a small granularity;
the variation is as follows: two classes in the same class time period are randomly selected for exchange.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310723576.XA CN116468416A (en) | 2023-06-19 | 2023-06-19 | Intelligent shift-walking course-arranging method based on genetic algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310723576.XA CN116468416A (en) | 2023-06-19 | 2023-06-19 | Intelligent shift-walking course-arranging method based on genetic algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116468416A true CN116468416A (en) | 2023-07-21 |
Family
ID=87173950
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310723576.XA Pending CN116468416A (en) | 2023-06-19 | 2023-06-19 | Intelligent shift-walking course-arranging method based on genetic algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116468416A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112435147A (en) * | 2020-11-02 | 2021-03-02 | 佛山科学技术学院 | Intelligent class-dividing method, system, computer equipment and storage medium for new college entrance examination |
| CN116862210A (en) * | 2023-09-05 | 2023-10-10 | 成都泰盟软件有限公司 | Intelligent course arrangement method, device, equipment and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107016632A (en) * | 2017-06-16 | 2017-08-04 | 长沙理工大学 | A kind of Web Course Selection-Arrangement method and system based on the class's of walking delamination Teaching |
| 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 |
| CN111178751A (en) * | 2019-12-27 | 2020-05-19 | 广东宜教通教育有限公司 | Intelligent class scheduling method, system, computer equipment and storage medium for new college entrance examination shift |
| CN111950890A (en) * | 2020-08-10 | 2020-11-17 | 武汉因特利金科技有限公司 | Class scheduling system for new high school entrance examination |
-
2023
- 2023-06-19 CN CN202310723576.XA patent/CN116468416A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107016632A (en) * | 2017-06-16 | 2017-08-04 | 长沙理工大学 | A kind of Web Course Selection-Arrangement method and system based on the class's of walking delamination Teaching |
| 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 |
| CN111178751A (en) * | 2019-12-27 | 2020-05-19 | 广东宜教通教育有限公司 | Intelligent class scheduling method, system, computer equipment and storage medium for new college entrance examination shift |
| CN111950890A (en) * | 2020-08-10 | 2020-11-17 | 武汉因特利金科技有限公司 | Class scheduling system for new high school entrance examination |
Non-Patent Citations (1)
| Title |
|---|
| 徐向阳;刘文伟;傅蝶;徐刚;金澈清;王祥丰;王江涛;: "改进遗传算法求解新高考背景下的排课问题", 华东师范大学学报(自然科学版), no. 04, pages 1 - 4 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112435147A (en) * | 2020-11-02 | 2021-03-02 | 佛山科学技术学院 | Intelligent class-dividing method, system, computer equipment and storage medium for new college entrance examination |
| CN112435147B (en) * | 2020-11-02 | 2024-04-19 | 佛山科学技术学院 | New college entrance examination intelligent shift sorting method, system, computer equipment and storage medium |
| CN116862210A (en) * | 2023-09-05 | 2023-10-10 | 成都泰盟软件有限公司 | Intelligent course arrangement method, device, equipment and medium |
| CN116862210B (en) * | 2023-09-05 | 2024-03-15 | 成都泰盟软件有限公司 | Intelligent course arrangement method, device, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Maghsudi et al. | Personalized education in the artificial intelligence era: what to expect next | |
| CN116468416A (en) | Intelligent shift-walking course-arranging method based on genetic algorithm | |
| Rodgers | Syllabus design, curriculum development and policy determination | |
| Dimopoulou et al. | Implementation of a university course and examination timetabling system | |
| Stark | Planning introductory college courses: Content, context and form | |
| CN111178751A (en) | Intelligent class scheduling method, system, computer equipment and storage medium for new college entrance examination shift | |
| CN110837976B (en) | Intelligent department-selecting and shift-dividing method and system under shift-walking system | |
| CN111539581A (en) | Intelligent class scheduling method and system for different shifts | |
| Matias et al. | A hybrid genetic algorithm for course scheduling and teaching workload management | |
| Eckroth et al. | Tarot: a course advising system for the future | |
| Garland et al. | Advanced Course Offerings and Completion in Science, Technology, Engineering, and Math in Texas Public High Schools. REL 2018-276. | |
| Castro-Faix et al. | Do alternative instructional approaches result in different learning progressions? | |
| Long | A genetic algorithm based method for timetabling problems using linguistics of hedge algebra in constraints | |
| Beaton et al. | Providing data for educational policy in an international context: The Third International Mathematics and Science Study (TIMSS) | |
| Paulson et al. | Parent Expectations of an Elementary School Counsellor: A Concept-Mapping Approach. | |
| Sebastian | East African Scholars Journal of Education, Humanities and Literature | |
| CN113435647A (en) | Class-moving, height-controlling and middle-class-arranging method based on evolutionary algorithm | |
| Willett et al. | Student flow analysis for a community college | |
| van der Haar et al. | The long-term distributional impacts of a full-year interleaving math program in Nigeria | |
| Xiao | The Course Scheduling Problem with Room Considerations | |
| Basikhasteh et al. | Hybridizing genetic algorithm with biased chance local search | |
| ADESAGBA | DEVELOPMENT OF AN EXAMINATION TIMETABLING SYSTEM USING GENETIC ALGORITHM | |
| Veldkamp et al. | Mathematical-programming approaches to test item pool design | |
| Beroš et al. | An integer programming model for assigning students to elective courses | |
| Aizam | Effective computational models for timetabling problem |
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 |