CN111080498A - Class-walking and course-arranging method, system, device and medium based on artificial fish shoal - Google Patents

Class-walking and course-arranging method, system, device and medium based on artificial fish shoal Download PDF

Info

Publication number
CN111080498A
CN111080498A CN201911126592.0A CN201911126592A CN111080498A CN 111080498 A CN111080498 A CN 111080498A CN 201911126592 A CN201911126592 A CN 201911126592A CN 111080498 A CN111080498 A CN 111080498A
Authority
CN
China
Prior art keywords
class
course
scheduling
artificial fish
arranging
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.)
Withdrawn
Application number
CN201911126592.0A
Other languages
Chinese (zh)
Inventor
林明付
周发辉
李卫群
兰海翔
陈天勇
孙春杨
王艳芳
颜卫星
秦永海
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guizhou Caishu Network Technology Co Ltd
Original Assignee
Guizhou Caishu Network Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guizhou Caishu Network Technology Co Ltd filed Critical Guizhou Caishu Network Technology Co Ltd
Priority to CN201911126592.0A priority Critical patent/CN111080498A/en
Publication of CN111080498A publication Critical patent/CN111080498A/en
Withdrawn legal-status Critical Current

Links

Images

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
    • 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
    • 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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations

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)
  • Educational Administration (AREA)
  • Economics (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • General Health & Medical Sciences (AREA)
  • Educational Technology (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Software Systems (AREA)
  • Primary Health Care (AREA)
  • Artificial Intelligence (AREA)
  • Development Economics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to a class-walking and course-arranging method, a system, a device and a medium based on artificial fish shoals, wherein the method comprises the steps of obtaining basic class-arranging data, and establishing a class-walking and course-arranging model according to the basic class-arranging data; setting a target optimization function and constraint conditions of the class-walking and class-scheduling model according to the class-scheduling basic data and the class-walking and class-scheduling model; and solving the class-moving and class-arranging model by using the constraint conditions and the target optimization function based on an artificial fish school optimization method to obtain an optimized class-moving and class-arranging scheme. The invention is based on the artificial fish shoal method, can simultaneously consider the course arrangement success rate, the course arrangement scheme optimization degree rate and the course arrangement efficiency, solves the technical problems of difficult work, course arrangement and difficult management of the existing course arrangement system, and has strong robustness, high course arrangement success rate, high course arrangement scheme optimization degree, high course arrangement efficiency and high self-adaption degree.

Description

Class-walking and course-arranging method, system, device and medium based on artificial fish shoal
Technical Field
The invention relates to the technical field of teaching management, in particular to a class-walking and course-scheduling method, system, device and medium based on artificial fish shoals.
Background
With the gradual implementation of new entrance examination policies, the traditional 'big unity' teaching form cannot meet the needs of students for learning, and the class-walking system becomes the inevitable choice of the common high school teaching organization mode. The class walking system refers to a teaching method that a subject classroom is fixed with a teacher, students select classes of self development to go to class according to self ability level and interest desire, the classes of different levels have different requirements on teaching content and degree, and the difficulty of homework and examination is also different. In this teaching mode, the complexity of the factors and limitations involved in the scheduling of the lessons has increased dramatically. Meanwhile, the problems of shortage of classroom resources of schools and teacher resources also increase a lot of difficulty for course arrangement. Manual course arrangement is not suitable for the current shift system, and an intelligent and efficient automatic course arrangement mode is needed to obtain a reasonable course arrangement scheme.
The course arrangement problem actually means that courses, teachers and students in a school are distributed to proper places in class in proper classes, and the problem is influenced by a plurality of factors to solve the overall optimal solution, namely the scheduling problem. At present, the automatic course arrangement method for solving the complex solving problem mainly comprises a simulated annealing algorithm, a genetic algorithm backtracking algorithm and the like. However, the method has inevitable defects in different degrees, for example, the simulated annealing algorithm has poor global search capability and insufficient accuracy for solving the optimal solution, and although the accuracy for solving the optimal solution by the genetic algorithm can meet the requirement, the genetic algorithm needs encoding, has long running time and is not efficient.
Therefore, no class-scheduling method capable of simultaneously considering the class-scheduling success rate, the class-scheduling scheme optimization degree and the class-scheduling efficiency exists.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a class-walking and course-arranging method, system, device and medium based on artificial fish shoals, which can simultaneously give consideration to the class-arranging success rate, the class-arranging scheme optimization degree rate and the class-arranging efficiency and solve the technical problems of difficult class walking, difficult class arranging and difficult management of the existing course-arranging system.
The technical scheme for solving the technical problems is as follows:
a class-walking and course-arranging method based on artificial fish shoals comprises the following steps:
step 1: acquiring basic course arrangement data, and establishing a class-moving and course-arranging model according to the basic course arrangement data;
step 2: setting a target optimization function and constraint conditions of the class-walking and class-scheduling model according to the class-scheduling basic data and the class-walking and class-scheduling model;
and step 3: and solving the class-moving and class-arranging model by using the constraint conditions and the target optimization function based on an artificial fish school optimization method to obtain an optimized class-moving and class-arranging scheme.
The invention has the beneficial effects that: firstly, acquiring basic course arrangement data, conveniently establishing a class-moving and course-arranging model which accords with the actual situation, and then setting a target optimization function and constraint conditions of the class-moving and course-arranging model, so that the subsequent solution of the class-moving and course-arranging model is more consistent with the actual situation, and an optimized class-moving and course-arranging scheme which meets the requirements is obtained; because in one class-moving and class-arranging course, the class-moving and class-arranging schemes meeting the requirements are various, the invention adopts a new artificial intelligent method, namely an artificial fish school method to solve the class-moving and class-arranging model, on one hand, the class-moving and class-arranging schemes can be adaptively optimized to obtain the globally optimal class-moving and class-arranging scheme, the class-arranging success rate and the scheme optimization degree are high, on the other hand, extra coding and longer running time are not needed, the class-arranging efficiency is high, and meanwhile, the over-convergence condition which easily occurs in the traditional genetic algorithm is avoided, and the adjustment of the class-moving and class-arranging scheme aiming at the emergency is not facilitated;
the class-scheduling method based on the artificial fish shoal method can simultaneously give consideration to class scheduling success rate, class scheduling scheme optimization degree rate and class scheduling efficiency, solves the technical problems of difficult class scheduling, difficult class scheduling and difficult management of the existing class scheduling system, and has the advantages of strong robustness, high class scheduling success rate, high class scheduling scheme optimization degree, high class scheduling efficiency and high self-adaption degree.
On the basis of the technical scheme, the invention can be further improved as follows:
further: the class arrangement basic data comprises class basic data, teacher basic data, student basic data, classroom basic data and course basic data;
wherein the class basic data includes a class number;
the teacher basic data comprises the number of teachers, teacher teaching courses and teacher teaching times;
the student basic data comprises the number of students and course selection courses of the students;
classroom profile data includes classroom number and classroom capacity;
the course basic data comprises the number of courses, the number of days of the courses, the number of the courses per day, the total number of the class hours of the courses and the class hours of the course continuous arrangement.
Further: the objective optimization function is specifically:
Figure BDA0002277028780000031
where M is the objective optimization function, f1For a first optimization function for determining the goodness of all the classes in a class-moving and course-scheduling scheme, f2A second optimization function for measuring the class-hour uniformity of all classes in a class-moving and course-scheduling scheme, f3Third optimization function for measuring interval reasonableness of all courses in one class-moving and course-scheduling scheme, omega1Is a first weight, omega, corresponding to the first optimization function2Is a second weight, omega, corresponding to the second optimization function3And e is a third weight corresponding to the third optimization function, wherein e is the feasibility of the scheme and is 0 or 1.
Further: the first optimization function is specifically:
Figure BDA0002277028780000032
wherein N is the number of hours per day, K is the number of courses, αknGoodness of the kth course ranking on the nth order, θkThe importance of the kth course;
the second optimization function is specifically:
Figure BDA0002277028780000041
wherein C is the number of classes, rhocThe class hour uniformity of the c class;
the third optimization function is specifically:
Figure BDA0002277028780000042
wherein, ηkThe interval of the kth lesson is reasonable.
Further: the class hour uniformity of the c class is specifically as follows:
Figure BDA0002277028780000043
wherein, βicThe number of hours on day i of the week for the c class,
Figure BDA0002277028780000044
the mean value of the class hours of the c class in one week;
the interval rationality of the kth course is specifically as follows:
Figure BDA0002277028780000045
wherein, mu1Is a fourth weight, mu2As a fifth weight value, the weight value,
Figure BDA0002277028780000046
the average time interval for the kth class,
Figure BDA0002277028780000047
is the ideal time interval of the kth class, taujkFor the jth class hour interval of the kth class, JkThe number of the class hour intervals of the kth class.
Further: the constraint conditions comprise basic constraint conditions and optimization constraint conditions;
wherein the basic constraint conditions comprise maximum number of teachers, maximum teaching time of the teachers, maximum number of classrooms, maximum capacity of the classrooms and maximum total number of lessons;
the optimization constraint conditions comprise maximum curriculum days, maximum curriculum hours per day and maximum curriculum continuous curriculum time.
Further: the specific steps of the step 3 comprise:
step 3.1: setting initialization parameters by utilizing the constraint conditions and the target optimization function, randomly generating an artificial fish school comprising a plurality of artificial fishes, and initializing the artificial fish school according to the initialization parameters;
the method comprises the following steps that initialization parameters comprise fish school scale, initial positions of artificial fishes, sensing ranges of the artificial fish schools, maximum iteration times, crowding degree factors and maximum trial times;
step 3.2: setting an iterative calculator m to be 0, acquiring an initialized optimal value and storing the initialized optimal value on a bulletin board;
step 3.3: setting an iterative calculator m to be 1, updating the state after each artificial fish executes foraging behavior, clustering behavior and rear-end collision behavior, and acquiring a primary iterative concentration value corresponding to each artificial fish one by one;
step 3.4: respectively carrying out individual evaluation on each artificial fish according to the initial iterative concentration value and the initialized artificial fish optimal value which are in one-to-one correspondence with each artificial fish to obtain the initial iterative optimal value of each artificial fish and updating the initial iterative optimal value on the bulletin board;
step 3.5: obtaining a one-to-one corresponding secondary iteration concentration value of each artificial fish according to the method in the step 3.3 by using an iteration calculator m-2; respectively carrying out individual evaluation on each artificial fish according to the secondary iteration concentration value and the primary iteration optimal value corresponding to each artificial fish to obtain the secondary iteration optimal value of each artificial fish and updating the secondary iteration optimal value on the bulletin board;
step 3.6: and (4) gradually adding 1 to the iterative calculator, performing state updating and individual evaluation on each artificial fish according to the method from the step 3.3 to the step 3.5 until the value of the iterative calculator reaches the maximum iteration times, and taking the global optimal value in the current iteration optimal values of all the artificial fishes as the optimal solution of the class-scheduling model to obtain the optimized class-scheduling scheme.
According to another aspect of the invention, a class-walking and course-scheduling system based on artificial fish shoal is provided, which comprises a model construction module, a model setting module and an optimization solving module;
the model building module is used for acquiring basic course arrangement data and building a class-moving and class-arranging model according to the basic course arrangement data;
the model setting module is used for setting a target optimization function and a constraint condition of the class-walking and class-scheduling model according to the class-scheduling basic data and the class-walking and class-scheduling model;
and the optimization solving module is used for solving the class-moving and scheduling model by utilizing the constraint conditions and the target optimization function based on an artificial fish school optimization method to obtain an optimized class-moving and scheduling scheme.
The invention has the beneficial effects that: the class-scheduling system based on the artificial fish shoal method can simultaneously give consideration to class scheduling success rate, class scheduling scheme optimization degree rate and class scheduling efficiency, solves the technical problems of difficulty in class scheduling, class scheduling and management of the existing class scheduling system, and is strong in robustness, high in class scheduling success rate, high in class scheduling scheme optimization degree, high in class scheduling efficiency and high in self-adaption degree.
According to another aspect of the present invention, another class-walking and course-scheduling device based on artificial fish schools is provided, which includes a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps of a class-walking and course-scheduling method based on artificial fish schools according to the present invention when running.
The invention has the beneficial effects that: through the computer program stored in the memory and running on the processor, the class-walking and course-arranging system is realized, based on the artificial fish school method, the class-arranging success rate, the class-arranging scheme optimization degree rate and the class-arranging efficiency can be simultaneously considered, the technical problems of difficulty in class walking, difficulty in course arranging and difficulty in management of the existing class-arranging system are solved, and the system is strong in robustness, high in class-arranging success rate, high in class-arranging scheme optimization degree, high in class-arranging efficiency and high in self-adaption degree.
In accordance with another aspect of the present invention, there is provided a computer storage medium comprising: at least one instruction which, when executed, implements the steps in an artificial fish school based shift scheduling method of the present invention.
The invention has the beneficial effects that: through executing a computer storage medium containing at least one instruction, the class-moving and course-arranging system is realized, based on an artificial fish shoal method, the class-moving and course-arranging success rate, the class-arranging scheme optimization degree rate and the class-arranging efficiency can be simultaneously considered, the technical problems of difficulty in moving, difficulty in arranging and difficulty in managing of the existing course-arranging system are solved, and the system is strong in robustness, high in class-arranging success rate, high in class-arranging scheme optimization degree, high in class-arranging efficiency and high in self-adaption degree.
Drawings
Fig. 1 is a schematic flow chart of a class-walking and course-scheduling method based on an artificial fish school according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of obtaining an optimized shift-taking and course-scheduling scheme in the first embodiment of the present invention;
fig. 3 is a schematic structural diagram of a class-walking and course-scheduling system based on an artificial fish school according to a second embodiment of the present invention.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
The present invention will be described with reference to the accompanying drawings.
In the first embodiment, as shown in fig. 1, a class-walking and course-scheduling method based on artificial fish school includes the following steps:
s1: acquiring basic course arrangement data, and establishing a class-moving and course-arranging model according to the basic course arrangement data;
s2: setting a target optimization function and constraint conditions of the class-walking and class-scheduling model according to the class-scheduling basic data and the class-walking and class-scheduling model;
s3: and solving the class-moving and class-arranging model by using the constraint conditions and the target optimization function based on an artificial fish school optimization method to obtain an optimized class-moving and class-arranging scheme.
The class-scheduling method based on the artificial fish shoal method can give consideration to class scheduling success rate, class scheduling scheme optimization degree rate and class scheduling efficiency, solves the technical problems of difficulty in scheduling, class scheduling and difficulty in management of the existing class scheduling system, and is strong in robustness, high in class scheduling success rate, high in class scheduling scheme optimization degree, high in class scheduling efficiency and high in self-adaption degree.
Preferably, the course arrangement basic data includes class basic data, teacher basic data, student basic data, classroom basic data, and course basic data;
wherein the class basic data includes a class number;
the teacher basic data comprises the number of teachers, teacher teaching courses and teacher teaching times;
the student basic data comprises the number of students and course selection courses of the students;
classroom profile data includes classroom number and classroom capacity;
the course basic data comprises the number of courses, the number of days of the courses, the number of the courses per day, the total number of the class hours of the courses and the class hours of the course continuous arrangement.
The class, the teacher, the students, the classroom and the course are combined in an all-around manner through the class basic data, the teacher basic data, the student basic data, the classroom basic data and the course basic data, all practical situations are comprehensively included, a class-moving and course-arranging model which is more suitable for the practical situations can be conveniently and subsequently established, the class-moving and course-arranging model can be optimized and solved, and a final class-moving and course-arranging optimization scheme with high optimization degree is obtained.
Specifically, in the embodiment, the students independently log in the educational administration system to select courses which the students want to learn, so that the students select the courses to collect; the teacher logs in the educational administration system and inputs a teacher teaching course, a teacher teaching course time and a course arrangement course time; then, counting the number of classes, the number of teachers, the number of students, the number of classrooms, the classroom capacity, the number of courses, the number of days of the courses, the number of times of the courses each day and the total number of the times of the courses by the teachers managing the educational administration; the acquisition of the course arrangement basic data of the embodiment is completed.
Preferably, the objective optimization function is specifically:
Figure BDA0002277028780000081
where M is the objective optimization function, f1For a first optimization function for determining the goodness of all the classes in a class-moving and course-scheduling scheme, f2A second optimization function for measuring the class-hour uniformity of all classes in a class-moving and course-scheduling scheme, f3Third optimization function for measuring interval reasonableness of all courses in one class-moving and course-scheduling scheme, omega1Is a first weight, omega, corresponding to the first optimization function2Is a second weight, omega, corresponding to the second optimization function3And e is a third weight corresponding to the third optimization function, wherein e is the feasibility of the scheme and is 0 or 1.
Since the first optimization function is to measure the goodness of all the classes in a class-moving and course-scheduling scheme, the class-moving and course-scheduling scheme is passedThe first optimization function can avoid the situation that the courses with higher importance degree are ranked in the lower-priority courses; the second optimization function is used for measuring the class time uniformity of all classes in a class-walking and class-scheduling scheme, so that the second optimization function can avoid over-concentration or over-dispersion of class times of certain classes; the third optimization function is used for measuring the interval reasonableness of all courses in a class-moving and scheduling scheme, so that the third optimization function can avoid the too short or too long class time intervals of some courses; based on the first optimization function, the second optimization function, the third optimization function and the target optimization function obtained by the scheme feasibility degree, the optimization degree of a class-scheduling scheme can be measured comprehensively, and the obtained final optimized class-scheduling scheme is guaranteed to be most reasonable and optimized; the higher the goodness of all the classes in one class-moving and class-arranging scheme is, the higher the class-time uniformity of all the classes is, and the higher the interval reasonableness of all the classes is, the higher the optimization degree of the class-moving and class-arranging scheme is; wherein, ω is1、ω2And ω3Are all taken as [0, 1]And ω is1+ω2+ω3＝1。
Specifically, in the present embodiment, ω1＝0.4，ω2＝ω3＝0.3。
Preferably, the first optimization function is specifically:
Figure BDA0002277028780000091
wherein N is the number of hours per day, K is the number of courses, αknGoodness of the kth course ranking on the nth order, θkThe importance of the kth course;
the second optimization function is specifically:
Figure BDA0002277028780000092
wherein C is the number of classes, rhocThe class hour uniformity of the c class;
the third optimization function is specifically:
Figure BDA0002277028780000093
wherein, ηkThe interval of the kth lesson is reasonable.
Because the courses have different categories, such as more important professional courses and non-professional courses with lower importance, or mandatory courses and non-mandatory courses, the importance (i.e., importance) of each category of courses is different; in addition, each class has different goodness in the classes arranged every day, for example, generally, it is considered that the goodness of the course arranged in the first and second sections in the morning is highest, the goodness of the course arranged in the first and second sections in the afternoon is the same as the goodness of the course arranged in the third and fourth sections in the morning, the third and fourth sections in the afternoon and the goodness of the evening are lowest, and if the course with lower importance is arranged in the section with higher goodness or the course with higher importance is arranged in the section with lower goodness, the optimization degree is unreasonable, and the optimization degree is lower, which is not beneficial to improving the learning efficiency of students and the teaching efficiency of teachers; therefore, the obtained first optimization function is used for measuring the goodness of all the sections in the class-moving and class-arranging scheme more accurately based on the importance of each course and the goodness of each section in each course arrangement, and the optimization degree of the class-moving and class-arranging scheme measured by the target optimization function is further improved; the goodness of each section and the importance of each course can be set and adjusted according to actual conditions;
the requirement of completing a certain learning target can be met only when each class generally has a specified class time total number, the class time total number of each class can be distributed and completed by going and scheduling, and if the class time arrangement of some classes is too centralized or too scattered, the learning efficiency of students and the teaching efficiency of teachers are not facilitated; therefore, the obtained second optimization function is used for measuring the class time uniformity of all classes in the class-moving and class-arranging scheme more accurately based on the class time uniformity of each class, and the optimization degree of the class-moving and class-arranging scheme measured by the target optimization function is further improved;
because each student can learn a plurality of courses, each course usually has a specified total number of course class time, and can meet the requirement of completing a certain learning target, the total number of course class time of each course can be distributed and completed by going to work and arranging courses, and if the arrangement of course time of some courses is too concentrated or too dispersed, the learning efficiency of students and the teaching efficiency of teachers are not good; therefore, based on the interval reasonability of each course, the obtained third optimization function is used for measuring the interval reasonability of all courses in the class-moving and class-arranging scheme more accurately, and the optimization degree of the class-moving and class-arranging scheme measured by the target optimization function is further improved.
Specifically, in this embodiment, a priority table may be set for the priority of each section, where the rows of the priority table represent the sections, and the columns represent the priorities corresponding to each section; the importance of each course may also be set up as an importance table, where the rows of the importance table represent courses and the columns represent the corresponding importance of each course.
Preferably, the class hour uniformity of the c-th class is specifically as follows:
Figure BDA0002277028780000111
wherein, βicThe number of hours on day i of the week for the c class,
Figure BDA0002277028780000112
the mean value of the class hours of the c class in one week;
the interval rationality of the kth course is specifically as follows:
Figure BDA0002277028780000113
wherein, mu1Is a fourth weight, mu2As a fifth weight value, the weight value,
Figure BDA0002277028780000114
the average time interval for the kth class,
Figure BDA0002277028780000115
is the ideal time interval of the kth class, taujkFor the jth class hour interval of the kth class, JkThe number of the class hour intervals of the kth class.
For the time uniformity of any class in any week, if the class number of each day of the week of the class is close to the average value of the class number of the week, the class time uniformity of the class is higher, which indicates that the class time arranged on each day of the week of the class is more uniform; for the interval reasonableness of any course, if the average class time interval of the course is closer to the ideal class time interval and each class time interval of the course is closer to the average class time interval, the interval arrangement among the class times of the course is more uniform and is close to the ideal class time interval, and the interval reasonableness of the course is higher; wherein, mu1And mu2Are all taken as [0, 1]And μ1+μ2＝1；
Through the class time uniformity and the class interval reasonableness of the class, the values of the second optimization function and the third optimization function can be accurately obtained, so that an accurate target optimization function can be conveniently obtained, and the class-moving and scheduling scheme is optimized and solved.
Specifically, in this embodiment, the average number of class hours of the c-th class in a week is specifically:
Figure BDA0002277028780000116
the average class time interval of the kth course is specifically as follows:
Figure BDA0002277028780000121
the ideal class hour interval of the kth course is specifically as follows:
Figure BDA0002277028780000122
wherein, the total number of the kth lessons is.
Specifically, in the present embodiment, μ1＝0.4，μ2＝0.6。
Preferably, the constraints include basic constraints and optimization constraints;
wherein the basic constraint conditions comprise maximum number of teachers, maximum teaching time of the teachers, maximum number of classrooms, maximum capacity of the classrooms and maximum total number of lessons;
the optimization constraint conditions comprise maximum curriculum days, maximum curriculum hours per day and maximum curriculum continuous curriculum time.
Usually, the maximum number of teachers, the maximum number of classrooms and the maximum capacity of the classrooms are fixed and unchangeable, and the maximum teaching time and the maximum class time total number of the teachers are specified according to the education bureau, so that the class-moving and arranging scheme can be preliminarily constrained through the basic constraint conditions to obtain a reasonable class-moving and arranging scheme; the maximum number of days of the course, the maximum number of hours per day and the maximum continuous course arrangement can be changed and adjusted due to the actual course selection of students and the actual teaching situation of teachers, so that the class-moving and arranging scheme can be constrained again through the optimization constraint conditions, the self-adaptive adjustment of the class-moving and arranging scheme is facilitated, and the class-moving and arranging scheme with higher optimization degree is obtained.
Specifically, in this embodiment, the maximum number of teachers is 20, the maximum number of classrooms is 100, the maximum teaching time of the teachers is 200, the maximum total number of lessons is 60, the maximum number of days of lessons is 5, the maximum number of hours per day is 10, and the maximum class continuous-course time is 2.
Preferably, as shown in fig. 2, the specific step of S3 includes:
s3.1: setting initialization parameters by utilizing the constraint conditions and the target optimization function, randomly generating an artificial fish school comprising a plurality of artificial fishes, and initializing the artificial fish school according to the initialization parameters;
the method comprises the following steps that initialization parameters comprise fish school scale, initial positions of artificial fishes, sensing ranges of the artificial fish schools, maximum iteration times, crowding degree factors and maximum trial times;
s3.2: setting an iterative calculator m to be 0, acquiring an initialized optimal value and storing the initialized optimal value on a bulletin board;
s3.3: setting an iterative calculator m to be 1, updating the state after each artificial fish executes foraging behavior, clustering behavior and rear-end collision behavior, and acquiring a primary iterative concentration value corresponding to each artificial fish one by one;
s3.4: respectively carrying out individual evaluation on each artificial fish according to the initial iterative concentration value and the initialized artificial fish optimal value which are in one-to-one correspondence with each artificial fish to obtain the initial iterative optimal value of each artificial fish and updating the initial iterative optimal value on the bulletin board;
s3.5: obtaining a one-to-one corresponding secondary iteration concentration value of each artificial fish by the iteration calculator m-2 according to the method of S3.3; respectively carrying out individual evaluation on each artificial fish according to the secondary iteration concentration value and the primary iteration optimal value corresponding to each artificial fish to obtain the secondary iteration optimal value of each artificial fish and updating the secondary iteration optimal value on the bulletin board;
s3.6: and gradually adding 1 to the iterative calculator, performing state updating and individual evaluation on each artificial fish according to the method from S3.3 to S3.5 until the value of the iterative calculator reaches the maximum iteration times, and taking the global optimal value in the current iteration optimal values of all the artificial fishes as the optimal solution of the class-scheduling model to obtain the optimized class-scheduling scheme.
In each iteration, comparing the current iteration concentration value corresponding to each artificial fish one by one with the optimal value stored on the bulletin board at the previous time, so as to update the state and evaluate each artificial fish individually, and taking the global optimal value in the current iteration optimal values of all the artificial fish reaching the maximum iteration times as the optimal solution of the class-scheduling-for-shift model, namely, the final class-scheduling-for-shift optimization method; the self-adaptive strategy is applied to the artificial fish shoal method, the aim of improving convergence precision is achieved, extra coding and longer running time are not needed, the over-convergence condition easily occurring in the traditional genetic algorithm is avoided, and the course arrangement success rate, the course arrangement scheme optimization degree rate and the course arrangement efficiency are considered at the same time.
In the second embodiment, as shown in fig. 3, a class-walking and course-scheduling system based on artificial fish school includes a model building module, a model setting module and an optimization solving module;
the model building module is used for acquiring basic course arrangement data and building a class-moving and class-arranging model according to the basic course arrangement data;
the model setting module is used for setting a target optimization function and a constraint condition of the class-walking and class-scheduling model according to the class-scheduling basic data and the class-walking and class-scheduling model;
and the optimization solving module is used for solving the class-moving and scheduling model by utilizing the constraint conditions and the target optimization function based on an artificial fish school optimization method to obtain an optimized class-moving and scheduling scheme.
According to the class-moving and class-arranging system, the model building module is used for firstly obtaining basic class-moving and class-arranging data, so that a class-moving and class-arranging model meeting the actual condition can be conveniently built, the model setting module is used for setting a target optimization function and constraint conditions of the class-moving and class-arranging model, a subsequent optimization solving module is convenient for solving the class-moving and class-arranging model to be more consistent with the actual condition, and an optimized class-moving and class-arranging scheme meeting the requirements is obtained; based on the artificial shoal method, the course arrangement success rate, the course arrangement scheme optimization degree rate and the course arrangement efficiency can be simultaneously considered, the technical problems that an existing course arrangement system is difficult to walk, arrange courses and manage are solved, the robustness is strong, the course arrangement success rate is high, the course arrangement scheme optimization degree is high, the course arrangement efficiency is high, and the self-adaption degree is high.
Third embodiment, based on the first embodiment and the second embodiment, the present embodiment further discloses a class-walking and course-scheduling device based on an artificial fish school, which includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor, and when the computer program runs, the specific steps of S1 to S3 shown in fig. 1 are implemented.
Through the computer program stored on the memory and running on the processor, the class-walking and course-arranging system of the embodiment is realized, based on the artificial fish school method, the class-arranging success rate, the class-arranging scheme optimization degree rate and the class-arranging efficiency can be simultaneously considered, the technical problems of difficulty in class walking, difficulty in course arranging and difficulty in management of the existing class-arranging system are solved, and the system is strong in robustness, high in class-arranging success rate, high in class-arranging scheme optimization degree, high in class-arranging efficiency and high in self-adaption degree.
The present embodiment also provides a computer storage medium having at least one instruction stored thereon, where the instruction when executed implements the specific steps of S1-S3.
Through executing a computer storage medium containing at least one instruction, the class-scheduling and course-scheduling system of the embodiment is realized, based on an artificial fish school method, the class-scheduling success rate, the class-scheduling scheme optimization degree rate and the class-scheduling efficiency can be simultaneously considered, the technical problems that an existing class-scheduling system is difficult to schedule, schedule and manage are solved, the robustness is strong, the class-scheduling success rate is high, the class-scheduling scheme optimization degree is high, the class-scheduling efficiency is high, and the self-adaption degree is high.
Details of S1 to S3 in this embodiment are not described in detail in the first embodiment and fig. 1 to fig. 2, which are not repeated herein.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims (10)

1. A class-walking and course-arranging method based on artificial fish shoals is characterized by comprising the following steps:
step 1: acquiring basic course arrangement data, and establishing a class-moving and course-arranging model according to the basic course arrangement data;
step 2: setting a target optimization function and constraint conditions of the class-walking and class-scheduling model according to the class-scheduling basic data and the class-walking and class-scheduling model;
and step 3: and solving the class-moving and class-arranging model by using the constraint conditions and the target optimization function based on an artificial fish school optimization method to obtain an optimized class-moving and class-arranging scheme.
2. The artificial fish school-based class scheduling method according to claim 1, wherein the class scheduling basic data includes class basic data, teacher basic data, student basic data, classroom basic data, and course basic data;
wherein the class basic data includes a class number;
the teacher basic data comprises the number of teachers, teacher teaching courses and teacher teaching times;
the student basic data comprises the number of students and course selection courses of the students;
classroom profile data includes classroom number and classroom capacity;
the course basic data comprises the number of courses, the number of days of the courses, the number of the courses per day, the total number of the class hours of the courses and the class hours of the course continuous arrangement.
3. The manual fish school-based class-scheduling method according to claim 2, wherein the objective optimization function is specifically:
Figure FDA0002277028770000011
where M is the objective optimization function, f1For a first optimization function for determining the goodness of all the classes in a class-moving and course-scheduling scheme, f2A second optimization function for measuring the class-hour uniformity of all classes in a class-moving and course-scheduling scheme, f3Third optimization function for measuring interval reasonableness of all courses in one class-moving and course-scheduling scheme, omega1Is a first weight, omega, corresponding to the first optimization function2Is a second weight, omega, corresponding to the second optimization function3And e is a third weight corresponding to the third optimization function, wherein e is the feasibility of the scheme and is 0 or 1.
4. The method for scheduling courses according to claim 3, wherein the first optimization function is specifically:
Figure FDA0002277028770000021
whereinN is the number of courses per day, K is the number of courses, αknGoodness of the kth course ranking on the nth order, θkThe importance of the kth course;
the second optimization function is specifically:
Figure FDA0002277028770000022
wherein C is the number of classes, rhocThe class hour uniformity of the c class;
the third optimization function is specifically:
Figure FDA0002277028770000023
wherein, ηkThe interval of the kth lesson is reasonable.
5. The manual fish school-based class-walking and scheduling method according to claim 4, wherein the class-hour uniformity of the c-th class is specifically as follows:
Figure FDA0002277028770000024
wherein, βicThe number of hours on day i of the week for the c class,
Figure FDA0002277028770000025
the mean value of the class hours of the c class in one week;
the interval rationality of the kth course is specifically as follows:
Figure FDA0002277028770000026
wherein, mu1Is a fourth weight, mu2As a fifth weight value, the weight value,
Figure FDA0002277028770000027
the average time interval for the kth class,
Figure FDA0002277028770000031
is the ideal time interval of the kth class, taujkFor the jth class hour interval of the kth class, JkThe number of the class hour intervals of the kth class.
6. The manual fish school-based class scheduling method according to claim 1, wherein the constraints include basic constraints and optimization constraints;
wherein the basic constraint conditions comprise maximum number of teachers, maximum teaching time of the teachers, maximum number of classrooms, maximum capacity of the classrooms and maximum total number of lessons;
the optimization constraint conditions comprise maximum curriculum days, maximum curriculum hours per day and maximum curriculum continuous curriculum time.
7. The manual fish school based class scheduling method according to any one of claims 1 to 6, wherein the specific steps of step 3 include:
step 3.1: setting initialization parameters by utilizing the constraint conditions and the target optimization function, randomly generating an artificial fish school comprising a plurality of artificial fishes, and initializing the artificial fish school according to the initialization parameters;
the method comprises the following steps that initialization parameters comprise fish school scale, initial positions of artificial fishes, sensing ranges of the artificial fish schools, maximum iteration times, crowding degree factors and maximum trial times;
step 3.2: setting an iterative calculator m to be 0, acquiring an initialized optimal value and storing the initialized optimal value on a bulletin board;
step 3.3: setting an iterative calculator m to be 1, updating the state after each artificial fish executes foraging behavior, clustering behavior and rear-end collision behavior, and acquiring a primary iterative concentration value corresponding to each artificial fish one by one;
step 3.4: respectively carrying out individual evaluation on each artificial fish according to the initial iterative concentration value and the initialized artificial fish optimal value which are in one-to-one correspondence with each artificial fish to obtain the initial iterative optimal value of each artificial fish and updating the initial iterative optimal value on the bulletin board;
step 3.5: obtaining a one-to-one corresponding secondary iteration concentration value of each artificial fish according to the method in the step 3.3 by using an iteration calculator m-2; respectively carrying out individual evaluation on each artificial fish according to the secondary iteration concentration value and the primary iteration optimal value corresponding to each artificial fish to obtain the secondary iteration optimal value of each artificial fish and updating the secondary iteration optimal value on the bulletin board;
step 3.6: and (4) gradually adding 1 to the iterative calculator, performing state updating and individual evaluation on each artificial fish according to the method from the step 3.3 to the step 3.5 until the value of the iterative calculator reaches the maximum iteration times, and taking the global optimal value in the current iteration optimal values of all the artificial fishes as the optimal solution of the class-scheduling model to obtain the optimized class-scheduling scheme.
8. A class-walking and course-scheduling system based on artificial fish shoal is characterized by comprising a model construction module, a model setting module and an optimization solving module;
the model building module is used for acquiring basic course arrangement data and building a class-moving and class-arranging model according to the basic course arrangement data;
the model setting module is used for setting a target optimization function and a constraint condition of the class-walking and class-scheduling model according to the class-scheduling basic data and the class-walking and class-scheduling model;
and the optimization solving module is used for solving the class-moving and scheduling model by utilizing the constraint conditions and the target optimization function based on an artificial fish school optimization method to obtain an optimized class-moving and scheduling scheme.
9. An artificial fish school based class scheduling device comprising a processor, a memory and a computer program stored in the memory and executable on the processor, wherein the computer program when executed implements the method steps according to any one of claims 1 to 7.
10. A computer storage medium, the computer storage medium comprising: at least one instruction which, when executed, implements the method steps of any one of claims 1 to 7.
CN201911126592.0A 2019-11-18 2019-11-18 Class-walking and course-arranging method, system, device and medium based on artificial fish shoal Withdrawn CN111080498A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911126592.0A CN111080498A (en) 2019-11-18 2019-11-18 Class-walking and course-arranging method, system, device and medium based on artificial fish shoal

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911126592.0A CN111080498A (en) 2019-11-18 2019-11-18 Class-walking and course-arranging method, system, device and medium based on artificial fish shoal

Publications (1)

Publication Number Publication Date
CN111080498A true CN111080498A (en) 2020-04-28

Family

ID=70311236

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911126592.0A Withdrawn CN111080498A (en) 2019-11-18 2019-11-18 Class-walking and course-arranging method, system, device and medium based on artificial fish shoal

Country Status (1)

Country Link
CN (1) CN111080498A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116797423A (en) * 2023-08-23 2023-09-22 湖南强智科技发展有限公司 Automatic and rapid course arrangement method and system for universities based on global optimization
CN116843525A (en) * 2023-08-28 2023-10-03 湖南强智科技发展有限公司 Intelligent automatic course arrangement method, system, equipment and storage medium

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116797423A (en) * 2023-08-23 2023-09-22 湖南强智科技发展有限公司 Automatic and rapid course arrangement method and system for universities based on global optimization
CN116797423B (en) * 2023-08-23 2023-11-14 湖南强智科技发展有限公司 Automatic and rapid course arrangement method and system for universities based on global optimization
CN116843525A (en) * 2023-08-28 2023-10-03 湖南强智科技发展有限公司 Intelligent automatic course arrangement method, system, equipment and storage medium
CN116843525B (en) * 2023-08-28 2023-12-15 湖南强智科技发展有限公司 Intelligent automatic course arrangement method, system, equipment and storage medium

Similar Documents

Publication Publication Date Title
Law et al. Educational innovations beyond technology: Nurturing leadership and establishing learning organizations
Veenman et al. The relation between intellectual and metacognitive skills from a developmental perspective
Glynn et al. Contextual teaching and learning of science in elementary schools
CN110020831A (en) New college entrance examination timetabling algorithm based on particle swarm algorithm
CN111080498A (en) Class-walking and course-arranging method, system, device and medium based on artificial fish shoal
Batzli et al. Beyond Punnett squares: student word association and explanations of phenotypic variation through an integrative quantitative genetics unit investigating anthocyanin inheritance and expression in Brassica rapa Fast Plants
Ebrahim The effects of traditional learning and a learning cycle inquiry learning strategy on students' science achievement and attitudes toward elementary science
Kuchkarova et al. Quality management of engineering graphics teaching
Yamamoto Creativity and higher education: A review
Reilly Dynamic feedback as automated scaffolding to support learners and teachers in guided authentic scientific inquiry settings
CN111898988A (en) Seven-line course arrangement method based on NP complete problem extension
Roth Learning in praxis, learning for praxis
Hammons Five potholes in the road to community college excellence
POLIBINA INTELLIGENT TRAINING PROCESS MANAGEMENT
Govorov et al. Building Individual Educational Routes for Learning SQL Queries
Handzic Managing Knowledge through Experimentation and Socialisation.
CN118279100A (en) Intelligent course selection method and system for education in research
Wang et al. Design and Research of Course Arranging System Based on Niche Improved Genetic Algorithm
Ige et al. Instructional Practices of Science Teachers in Rural Learning Ecologies.
Heiss The Utilization of the College and University Teacher.
Andrzejewski et al. Facilitating student empowerment and agency through the “scaffolded autonomy” approach to curriculum design
Kuksinski et al. Methods of Automatic Generation of the University Timetable
Doty et al. Views: Undergraduate Science Education: An Overview: What is the experience of science majors and what are their career prospects? Some possible improvements in their education might serve long-range goals
Greene The Impact of Integrating Traditional Ecological Knowledge in Summer Camps on Middle School Students' Understanding of the Nature of Science
Yang et al. A Novel Grey Fuzzy Clustering Model and its Application on Students’ Performance Evaluation

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
WW01 Invention patent application withdrawn after publication

Application publication date: 20200428

WW01 Invention patent application withdrawn after publication