Intelligent examination scheduling method and system for online examination

Abstract

The application relates to the field of internet teaching, and discloses an intelligent examination arrangement method and system for online examination. The method comprises the following steps: determining an initial arrangement scheme set according to obtained basic information and hard constraint conditions; constructing a target function of the initial arrangement scheme according to obtained soft constraint conditions, and obtaining a candidate arrangement scheme set from the initial arrangement scheme set according to the target function values of the respective initial arrangement schemes; obtaining a new arrangement scheme set by randomly combining the candidate arrangement schemes, and selecting an optimal arrangement scheme according to the target function values of the initial arrangement schemes and the target function values of the new arrangement schemes; obtaining examinee reservation information, and determining an arrangement result according to the examinee reservation information and the optimal arrangement scheme. The application can significantly improve the utilization rate of computer rooms, the response capability to emergencies, the rationality of examination arrangement, and the flexibility of examination arrangement.

Description

Technical Field

[0001] This application relates to the field of computers and the Internet, and in particular to Internet-based teaching technology. Background Technology

[0002] With the development of modern educational information technology, online examinations will gradually replace traditional examination models, such as those for subjects that require computer support, like English and C programming.

[0003] However, most schools currently have limited computer lab resources, a large student population, and numerous exam subjects, making them unable to support the large-scale computer lab requirements of online exams. Furthermore, existing intelligent exam scheduling methods primarily address the optimal allocation of invigilators in traditional exam models, without considering the high demands of online exams on computer labs or the need to handle various unforeseen circumstances.

[0004] Therefore, it is necessary to consider how to improve the utilization rate of the computer room, the ability to respond to emergencies, and the rationality of the examination arrangements. Summary of the Invention

[0005] The purpose of this application is to provide an intelligent scheduling method and system for online examinations, which can significantly improve the utilization rate of computer rooms, the ability to respond to emergencies, and the rationality of examination arrangements. It can also support the mixed scheduling of different types of examinations, thereby improving the flexibility of examination arrangements.

[0006] This application discloses an intelligent scheduling method for online examinations, including: determining an initial scheduling scheme set based on the obtained basic scheduling information and hard constraints;

[0007] The objective function of the initial scheduling scheme is constructed based on the obtained soft constraints. Based on the objective function value of each initial scheduling scheme, a set of candidate scheduling schemes is obtained from the initial scheme set. Furthermore, a new set of scheduling schemes is obtained by randomly combining the candidate scheduling schemes. Based on the objective function value of the initial scheduling scheme and the objective function value of the new scheduling scheme, the optimal scheduling scheme is selected.

[0008] Obtain candidate appointment information and determine the exam scheduling result based on the candidate appointment information and the optimal exam scheduling plan.

[0009] In a preferred embodiment, determining the initial set of scheduling schemes based on the basic scheduling information and hard constraints further includes:

[0010] Obtain basic information on exam scheduling, hard constraints, and soft constraints;

[0011] Based on the basic scheduling information and hard constraints, an initial scheme set is generated, which includes the following sub-steps: Based on the basic scheduling information and hard constraints, a scheduling information table containing the correspondence between computer rooms and time periods is constructed; Based on the scheduling information table, N initial scheduling schemes are generated using an allocation function, where N is a pre-set positive integer.

[0012] In a preferred embodiment, in the step of obtaining a set of candidate schemes for the examination from the initial scheme set based on the objective function value corresponding to each initial scheme, the candidate scheme set is selected from the initial scheme set based on the proportion of the objective function in the total objective function value, wherein the higher the objective function value, the greater the probability that the initial scheme corresponding to the objective function value is selected as a candidate scheme.

[0013] In a preferred embodiment, in the step of obtaining a new set of examination scheduling schemes by randomly combining the candidate scheduling schemes, the random combination operation is to exchange the session information in two candidate scheduling schemes to obtain a new scheme with better scheduling results. When the objective function value of the new scheduling scheme no longer changes or the change range is extremely small for several consecutive generations, the iteration stops and the new set of scheduling schemes is output.

[0014] In a preferred embodiment, in the step of selecting the optimal scheduling scheme based on the objective function value of the initial scheduling scheme and the objective function value of the new scheduling scheme, the new scheduling scheme with the highest objective function value is taken as the optimal scheduling scheme.

[0015] In a preferred embodiment, the corresponding expression for the objective function is as follows:

[0016] F i =ω1f1+ω2f2+ω3f3+ω4f4

[0017] Among them, F i Let f1 represent the objective function value of the i-th exam scheduling plan, f2 represent the rationality of the exam arrangement, f3 represent the test paper utilization rate, and f4 represent the ability to respond to emergencies. Furthermore, ω1, ω2, ω3, and ω4 are the weight values ​​representing the importance of the above factors in the exam scheduling task.

[0018] In a preferred example, the reasonableness of the exam arrangement, f2, is calculated as follows:

[0019]

[0020] Among them, T e T indicates the exam deadline. s Indicates the start time of the exam, t i P represents iThe start time of the exam session, where s represents the total number of sessions.

[0021] In a preferred embodiment, the emergency response capability f4 is calculated as follows:

[0022]

[0023] Among them, S i , j R represents i The computer room is in P j The number of exam slots allocated for each session is n, where n is the total number of candidates and gn is g times the total number of candidates, where g∈(0,0.5], and can be dynamically adjusted according to the actual situation.

[0024] In a preferred embodiment, the basic exam scheduling information includes one or any combination of the following: a set of examinees, a set of exam time slots, and a set of computer labs.

[0025] In a preferred embodiment, the hard constraint is a condition that must be followed during scheduling and cannot be satisfied under any circumstances.

[0026] In a preferred embodiment, the hard constraints include one or any combination of the following: the computer room for scheduling exams must be a computer room not occupied by courses; only computer rooms with an opening time of not less than the exam time during the exam period can be used as computer rooms for scheduling exams; the total number of exam sessions cannot exceed the number of sets of exam papers provided by the teachers; the number of exam slots allocated to each computer room cannot exceed the remaining exam slots in the computer room; the total number of exam slots allocated cannot be less than the total number of candidates; and the exam deadline cannot exceed the end of the semester.

[0027] In a preferred embodiment, the soft constraint refers to a condition that affects the quality of the scheduling plan, but is not a mandatory requirement.

[0028] In a preferred embodiment, the soft constraints include one or any combination of the following: computer room utilization rate, test paper utilization rate, reasonableness of examination arrangements, and ability to respond to emergencies.

[0029] This application also discloses an intelligent scheduling system for online examinations, including:

[0030] The module for determining the initial test scheduling scheme set is used to determine the initial test scheduling scheme set based on the obtained basic test scheduling information and hard constraints.

[0031] The optimal exam scheduling module is used to construct the objective function of the initial exam scheduling scheme based on the obtained soft constraints, and to obtain a set of candidate exam scheduling schemes from the initial scheme set based on the objective function values ​​of each initial exam scheduling scheme; furthermore, a new set of exam scheduling schemes is obtained by randomly combining the candidate exam scheduling schemes, and the optimal exam scheduling scheme is selected based on the objective function values ​​of the initial exam scheduling schemes and the objective function values ​​of the new exam scheduling schemes.

[0032] The exam scheduling result determination module is used to obtain the candidate appointment information and determine the exam scheduling result based on the candidate appointment information and the optimal exam scheduling plan.

[0033] This application also discloses an intelligent scheduling system for online examinations, including:

[0034] Memory, used to store computer-executable instructions; and,

[0035] A processor for implementing the steps of the method as described above when executing the computer-executable instructions.

[0036] This application also discloses a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the method described above.

[0037] The implementation method of this application first generates n initial exam scheduling schemes randomly based on hard constraints set according to the basic exam scheduling information. Second, it constructs an objective function based on multiple soft constraints such as computer room utilization, exam arrangement rationality, test paper utilization, and emergency response capability to comprehensively evaluate the merits of the schemes. Furthermore, it iteratively optimizes the initial scheme set to obtain the optimal exam scheduling scheme. Finally, candidates freely book their exams, and the system automatically assigns invigilators and distributes test papers to obtain the final exam scheduling result. This significantly improves computer room utilization, emergency response capability, and exam arrangement rationality, and also supports mixed scheduling of different types of exams, increasing the flexibility of exam scheduling.

[0038] The specification of this application contains numerous technical features distributed across various technical solutions. Listing all possible combinations of these technical features (i.e., technical solutions) would make the specification excessively lengthy. To avoid this problem, the various technical features disclosed in the above-described invention, the various technical features disclosed in the following embodiments and examples, and the various technical features disclosed in the accompanying drawings can be freely combined to form various new technical solutions (all of which are considered to have been described in this specification), unless such a combination of technical features is technically infeasible. For example, one example discloses feature A+B+C, and another example discloses feature A+B+D+E. Features C and D are equivalent technical means that serve the same function, and technically only one needs to be used; they cannot be used simultaneously. Feature E can technically be combined with feature C. Therefore, the solution A+B+C+D should not be considered as described because it is technically infeasible, while the solution A+B+C+E should be considered as described. Attached Figure Description

[0039] Figure 1 This is a flowchart illustrating the intelligent scheduling method for online examinations according to the first embodiment of this application;

[0040] Figure 2 This is a schematic diagram illustrating the principle of the intelligent scheduling method for online examinations according to the first embodiment of this application;

[0041] Figure 3 This is a schematic diagram illustrating the specific steps of the intelligent scheduling method for online examinations according to the first embodiment of this application;

[0042] Figure 4 This is a schematic diagram of the structure of an intelligent scheduling system for online examinations according to the second embodiment of this application. Detailed Implementation

[0043] In the following description, many technical details are presented to help the reader better understand this application. However, those skilled in the art will understand that the technical solutions claimed in this application can be implemented even without these technical details and various variations and modifications based on the following embodiments.

[0044] The following is a brief summary of some of the innovative aspects of this application:

[0045] This solution proposes an intelligent scheduling method and system for online examinations. First, based on hard constraints set by the basic scheduling information, n initial scheduling schemes are randomly generated. Second, an objective function is constructed based on multiple soft constraints, such as computer room utilization, exam scheduling rationality, test paper utilization, and the ability to handle emergencies, to comprehensively evaluate the merits of each scheme. The optimal scheduling scheme is obtained through iterative optimization of the initial scheme set. Finally, candidates freely schedule exams, and the system automatically assigns invigilators and distributes test papers, obtaining the final scheduling result. This significantly improves computer room utilization, the ability to handle emergencies, and the rationality of exam scheduling. It also supports mixed scheduling of different types of exams, increasing the flexibility of exam scheduling.

[0046] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0047] The first embodiment of this application relates to an intelligent scheduling method for online examinations, the process of which is as follows: Figure 1 and Figure 2 As shown, the method includes the following steps:

[0048] Steps 110-120: Design an intelligent exam scheduling algorithm to obtain the optimal exam scheduling plan.

[0049] Specifically, in steps 110-120, an intelligent exam scheduling algorithm is designed based on specific exam scheduling requirements. This algorithm first generates n initial exam scheduling schemes; secondly, it constructs an objective function and evaluates the merits of each scheme, obtaining the optimal scheduling scheme through iterative optimization of the initial exam scheduling scheme set.

[0050] Furthermore, the specific implementation process of steps 110-120 above is as follows:

[0051] Step 110: Determine the initial set of scheduling schemes based on the basic information and hard constraints of the scheduling.

[0052] Optionally, step 110 may further include the following sub-steps;

[0053] Step 1102: Obtain basic scheduling information, hard constraints, and soft constraints. Details are as follows:

[0054] (1) Obtain basic information on exam scheduling

[0055] (1.1) Set of candidates S: S = {S1, ..., S2} i ,…,S n}, S i Let i represent the i-th candidate, and n be the total number of candidates.

[0056] (1.2) The set of exam time periods T: T = {T1, ..., T}i ,…,T m}, T i Let m represent the i-th exam time period, and m be the total number of time periods.

[0057] (1.3) Set of computer rooms R: R = {R1, ..., R2} i ,…,R r}, R i Let r represent the i-th computer room, and r be the total number of computer rooms.

[0058] (2) Obtain hard constraints.

[0059] It should be noted that hard constraints refer to conditions that must be followed and cannot be satisfied during the scheduling process.

[0060] (2.1) The computer lab for scheduling exams must be one that is not currently occupied by any course. The corresponding expression is as follows:

[0061]

[0062] In the above formula, R i,j R represents the idle state of computer room i during time period j. i,j If R = 0, no arrangement will be made. i,j =1 indicates that the computer room can be used as a waiting examination room.

[0063] (2.2) Only computer rooms that are open for at least the duration of the exam during the exam period can be used as waiting rooms for exams. The corresponding expression is as follows:

[0064] T s ≤T i,j

[0065] In the above formula, T s Indicates exam duration, T i,j This indicates the duration of time that computer room i is open during time period j.

[0066] (2.3) The total number of examination sessions shall not exceed the number of test papers provided by the teacher. The corresponding expression is as follows:

[0067] s≤u

[0068] In the above formula, s represents the total number of exam sessions, and u represents the number of sets of exam papers provided by the teacher.

[0069] (2.4) The number of exam slots allocated to each computer room shall not exceed the remaining number of exam slots in the computer room, as shown in the following expression:

[0070] S i，j ≤RC i，j

[0071] In the above formula, S i,j This represents the number of exam slots allocated to computer room i during time period j. RCi,j This represents the remaining exam slots for the i-th computer room during the j-th time period.

[0072] (2.5) The total number of examination slots allocated shall not be less than the total number of candidates, as shown in the following expression:

[0073]

[0074] In the above formula, r represents the total number of computer rooms, s represents the total number of sessions, and S i,j This represents the number of exam slots allocated to computer room i in session j, where n is the total number of examinees.

[0075] (2.5) The exam deadline cannot exceed the end of the semester, as shown in the following expression:

[0076] T e ≤T t

[0077] In the above formula, T e T indicates the deadline for the last session. t This indicates the end time of the semester.

[0078] (3) Obtain soft constraint conditions.

[0079] It should be noted that soft constraints refer to conditions that affect the quality of the scheduling plan, but are not mandatory.

[0080] (3.1) Computer room utilization rate f1: Under the condition of meeting all hard constraints, the number of examination slots arranged in the same computer room should be as large as possible;

[0081] (3.2) Test paper utilization rate f2: The same test paper is used by as many people as possible;

[0082] (3.3) Reasonableness of examination arrangement f3: The number of examination sessions should be distributed as evenly as possible, and the examination cycle should be as short as possible.

[0083] (3.4) Emergency response capability f4: The allocation of examination slots should ensure a certain margin to cope with emergencies.

[0084] Step 1104: Generate an initial set of solutions based on the basic information and hard constraints of the scheduling.

[0085] (1) Based on the basic information of the scheduling and the hard constraints, generate a scheduling information table that includes the correspondence between computer rooms and time periods.

[0086] In this step, based on the basic scheduling information and hard constraints, a scheduling information table is constructed, with computer labs as columns and time periods as rows. The table lists the scheduling status of each computer lab in different time periods before the end of the semester. The specific generated data table is shown below:

[0087]

[0088] Note: R represents the computer room, T represents the time period, and RC represents the remaining exam slots in the computer room. r,m R represents r The computer room is in T m The remaining exam slots for the specified time period. Where, for any R... i The computer room is in any T j There are two scenarios within a given time period: exams can be scheduled or they cannot be scheduled (either there are scheduled classes or the open time within the exam period is less than the exam duration).

[0089] (2) Based on the available exam information table, generate N initial exam scheduling schemes using the allocation function, where N is a pre-set positive integer.

[0090] The generation of the initial plan is a randomized process. First, s time periods are randomly selected from the available exam slots information table. Then, the exam slots are allocated to the available computer labs using an allocation function, generating one exam scheduling plan. This process is repeated until the number of initial plans reaches N, forming an initial plan set. The specific process is as follows:

[0091] A. Randomly select s time periods (s≤u) from the available exam information table as exam sessions, and use the allocation function f=h*RC i,j (h = random[0.8,1), the range can be dynamically adjusted according to the actual situation), and the exam slots are allocated to the computer rooms that can be scheduled for exams in these s time periods;

[0092] B. If This will be used as an initial solution; otherwise, repeat step A. A specific initial solution generated is shown below:

[0093]

[0094] Note: R represents the computer room, P represents the session, and S represents the allocated number of exam slots. R represents i The computer room is in P j Sessions cannot be scheduled, R r S r,k P s R represents r The computer room is in P s S sessions were allocated r,s The number of exam slots.

[0095] C. Repeat steps A and B until N scheduling schemes are generated, forming the initial scheduling scheme set.

[0096] Step 120: Determine the optimal scheduling scheme from the initial scheduling scheme set based on the soft constraints.

[0097] Specifically, see Figure 3 In this step, an objective function for the initial scheduling scheme is constructed based on the obtained soft constraints. A candidate scheduling scheme set is obtained from the initial scheme set based on the objective function values ​​of each initial scheme. Furthermore, a new scheduling scheme set is obtained by randomly combining the candidate schemes. The optimal scheduling scheme is selected based on the objective function values ​​of the initial schemes and the new schemes. Preferably, in the step of obtaining the candidate scheme set, the higher the objective function value, the greater the probability of selection. Preferably, the scheduling scheme with the highest objective function value is selected as the optimal scheduling scheme.

[0098] Optionally, step 120 further includes the following sub-steps:

[0099] Step 1202: Construct the objective function based on the soft constraints.

[0100] Specifically, based on the aforementioned soft constraints, an objective function is constructed. A linear weighted method is then used to transform the multi-objective optimization problem into a single-objective optimization problem. A higher objective function value indicates a better optimization result. Optionally, the corresponding expression for the objective function is as follows:

[0101] F i =ω1f1+ω2f2+ω3f3+ω4f4

[0102] Among them, F i Let f1 represent the objective function value of the i-th exam scheduling plan, f2 represent the rationality of the exam arrangement, f3 represent the exam paper utilization rate, and f4 represent the ability to respond to emergencies. Based on the importance of each factor in the exam scheduling task, weight values ​​ω1, ω2, ω3, and ω4 are set respectively.

[0103] Furthermore, the specific calculation methods for each parameter are as follows:

[0104]

[0105]

[0106] Step 1204: Select a set of candidate solutions from the initial set of solutions based on the proportion of the objective function in the total objective function value.

[0107] Based on the aforementioned objective function, the objective function value corresponding to each initial scheduling scheme in the initial scheduling scheme set is calculated. Schemes are selected based on the proportion of each initial scheduling scheme's objective function value to the total objective function value; the higher the objective function value, the greater the probability of selection. The selected initial scheduling schemes constitute a candidate scheme set, which will then undergo a further random combination process. The specific operations of the above steps are as follows:

[0108] (1) Calculate the objective function value F of each scheme in the initial scheme set using the objective function. i (i = 1, 2, ..., N), where N is the total number of schemes in the initial scheme set;

[0109] (2) Calculate the probability of each option being selected:

[0110]

[0111] (3) Sort the options in descending order according to the objective function value and calculate the cumulative selection probability of each option;

[0112] (4) Generate a random number between 0 and 1. If this number is within the cumulative interval corresponding to a certain scheme, then the scheme is selected.

[0113] (5) Repeat step (4) until all selections are completed.

[0114] Step 1206: By randomly combining the candidate schemes for the examination, a new scheme with better examination results is obtained.

[0115] The candidate solution set obtained above is randomly combined according to a certain probability. This random combination operation involves exchanging the session information of two solutions to obtain a new solution with a better ranking result. The iteration stops when the objective function value of the new solution no longer changes or the change is extremely small after several consecutive generations, and a new solution set is output. The specific operation is as follows:

[0116] (1) Perform random combination prediction on all schemes to generate a random value rdc; where rdc (randomconstant) is a term that represents a random number generated in the range of 0 to 1.

[0117] (2) Calculate the probability of random combination of schemes. If rdc is less than the combination probability, then perform a random combination operation. The random combination probability is calculated as follows:

[0118]

[0119] Among them, P c f represents the probability of random combinations of individual options. maxf represents the objective function value of the optimal solution in the candidate solution set. avg f represents the average objective function value of the candidate solution set. c Let c represent the objective function value of an individual scheme in a random combination operation, where c is a random number between 0 and 1.

[0120] Specifically, this part is similar to the crossover operation in genetic algorithms. When the objective function value of an individual solution is greater than or equal to the average objective function value, the probability of random combination will decrease accordingly; when the objective function value of an individual solution is less than the average fitness value, the probability of random combination will increase accordingly in order to obtain a better solution.

[0121] Step 1208: Take the optimal scheduling plan from the initial scheduling plan set and the new plan set as the final scheduling plan and output it.

[0122] In other words, based on the initial set of scheduling schemes and the new set of schemes, the optimal scheduling scheme is selected as the final scheduling scheme and output.

[0123] Preferably, the new scheduling scheme with the highest objective function value is taken as the optimal scheduling scheme, that is, the final scheduling scheme.

[0124] Step 130: Obtain the candidate appointment information and determine the exam scheduling result based on the candidate appointment information and the final exam scheduling plan, i.e., the optimal exam scheduling plan.

[0125] Preferably, the exam scheduling results include: invigilators, exam paper assignments, etc.

[0126] Preferably, this step follows the principle of candidates making their own appointments on a first-come, first-served basis.

[0127] Furthermore, in the embodiments of this application, the computer uniformly publishes the final exam scheduling plan, and candidates voluntarily choose the exam venue and session. The system allocates quotas according to the time when the candidate submits the application, and supports candidates to temporarily cancel their reservations within a preset time before the exam in case of emergencies. They can then make reservations for exam sessions that have not yet started.

[0128] Furthermore, in the embodiments of this application, if the computer room changes during the examination period, corresponding arrangements need to be made based on the examination schedule and candidate reservations. The specific operations are as follows:

[0129] (1) Obtain information about the affected candidates, including: name, student ID, exam name, exam session, exam duration, etc.

[0130] (2) Determine whether the number of affected candidates exceeds the remaining computer room capacity. If it does not exceed the capacity, arrange them directly to the corresponding computer room and notify them of the new arrangement information. If it exceeds the capacity, the administrator should be notified to cancel the candidates' reservations and notify the candidates simultaneously. After the session is re-arranged and the exam scheduling plan is released, the candidates will be notified to make reservations.

[0131] Step 140: Output the scheduling results.

[0132] In this step, the computer automatically assigns teachers to invigilate and distributes exam papers based on the exam session information; finally, it outputs the exam subject, exam session (including the exam room, exam time period, and number of examinees) and the corresponding examinee and invigilator information, confirming the completion of the exam scheduling.

[0133] The preferred exam scheduling results include: exam subjects, exam sessions, corresponding candidates, invigilator information, etc.

[0134] Preferably, the examination session includes: examination room, examination time period, number of examinees, etc.

[0135] It should be noted that in this embodiment, the initial test set contains all test sets that satisfy the hard constraints. The candidate test set is composed of test sets with higher objective function values ​​selected from the initial set, which are then randomly combined to obtain test sets with even higher objective function values. The new test set is composed of new test sets obtained through random combination. Finally, the test set with the highest objective function value is selected from the initial set and the new test set as the optimal test set to obtain a test set with an even higher objective function, which is a test set that better satisfies the soft constraints.

[0136] Technical effects:

[0137] The above embodiment first generates n initial scheduling schemes randomly based on hard constraints set according to the basic scheduling information. Second, it constructs an objective function based on multiple soft constraints such as computer room utilization, exam arrangement rationality, test paper utilization, and emergency response capability to comprehensively evaluate the merits of the schemes. Furthermore, it iterative optimization of the initial scheme set yields the optimal scheduling scheme. Finally, candidates freely book their exams, and the system automatically assigns invigilators and distributes test papers to obtain the final scheduling result. This significantly improves computer room utilization, emergency response capability, and exam arrangement rationality. It also supports mixed scheduling of different types of exams, increasing the flexibility of exam arrangements.

[0138] The second embodiment of this application relates to an intelligent scheduling system for online examinations, the structure of which is as follows: Figure 4 As shown, the intelligent scheduling system for this online exam includes:

[0139] The module for determining the initial test scheduling scheme set is used to determine the initial test scheduling scheme set based on the obtained basic test scheduling information and hard constraints.

[0140] The optimal exam scheduling module is used to construct the objective function of the initial exam scheduling scheme based on the obtained soft constraints, and to obtain a set of candidate exam scheduling schemes from the initial scheme set based on the objective function values ​​of each initial exam scheduling scheme; furthermore, a new set of exam scheduling schemes is obtained by randomly combining the candidate exam scheduling schemes, and the optimal exam scheduling scheme is selected based on the objective function values ​​of the initial exam scheduling schemes and the objective function values ​​of the new exam scheduling schemes.

[0141] The exam scheduling result determination module is used to obtain the candidate appointment information and determine the exam scheduling result based on the candidate appointment information and the optimal exam scheduling plan.

[0142] The first embodiment is a method embodiment corresponding to this embodiment. The technical details in the first embodiment can be applied to this embodiment, and the technical details in this embodiment can also be applied to the first embodiment.

[0143] It should be noted that those skilled in the art should understand that the implementation functions of each module shown in the above-described intelligent online examination scheduling system can be understood with reference to the relevant description of the above-described intelligent online examination scheduling method. The functions of each module shown in the above-described intelligent online examination scheduling system can be implemented by a program (executable instructions) running on a processor, or by specific logic circuits. If the above-described intelligent online examination scheduling system is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application embodiment, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, mobile hard drives, read-only memory (ROM), magnetic disks, or optical disks. Thus, this application embodiment is not limited to any specific hardware and software combination.

[0144] Accordingly, this application also provides a computer storage medium storing computer-executable instructions, which, when executed by a processor, implement the various method implementations of this application.

[0145] Furthermore, this application also provides an intelligent online examination scheduling system, including a memory for storing computer-executable instructions and a processor; the processor is used to implement the steps in the above-described method embodiments when executing the computer-executable instructions in the memory. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The aforementioned memory may be read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or solid-state drive, etc. The steps of the methods disclosed in the various embodiments of this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor.

[0146] It should be noted that in this patent application, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one" does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element. In this patent application, if it refers to performing an action according to an element, it means performing the action at least according to that element, including two cases: performing the action only according to that element, and performing the action according to that element and other elements. Expressions such as "multiple," "repeatedly," and "various" include two, two times, two kinds, and more than two, more than two times, and more than two kinds.

[0147] All documents mentioned in this application are considered to be incorporated in their entirety into the disclosure of this application so that they can serve as a basis for modifications if necessary. Furthermore, it should be understood that after reading the foregoing disclosure of this application, those skilled in the art can make various alterations or modifications to this application, and these equivalent forms also fall within the scope of protection claimed in this application.

Claims

1. An intelligent scheduling method for online examinations, characterized in that, include: Based on the obtained basic information on exam scheduling and hard constraints, an initial set of exam scheduling schemes is determined; wherein, the basic information on exam scheduling includes one or any combination of the following: a set of candidates, a set of exam time periods, and a set of computer labs; the hard constraints refer to conditions that must be followed in the exam scheduling process and cannot be satisfied under any conditions. Based on the obtained soft constraints, an objective function is constructed for the initial scheduling scheme. Based on the objective function values ​​of each initial scheduling scheme, a set of candidate scheduling schemes is obtained from the initial scheme set. The candidate scheme set is selected based on the proportion of the objective function in the total objective function value; the higher the objective function value, the greater the probability that the initial scheme corresponding to that objective function value will be selected as a candidate scheme. Furthermore, a new scheduling scheme set is obtained by randomly combining the candidate scheduling schemes. This random combination operation involves exchanging the session information in two candidate scheduling schemes to obtain a new scheme with better scheduling results. When the objective function value of the new scheduling scheme no longer changes or the change is extremely small for several consecutive generations, the iteration stops, the new scheduling scheme set is output, and the optimal scheduling scheme is selected based on the objective function values ​​of the initial scheduling schemes and the new scheduling schemes. The corresponding expression for the objective function is as follows: F i =ω1f1+ω2f2+ω3f3+ω4f4 Among them, f i Let f1 represent the objective function value of the i-th exam scheduling plan, f2 represent the rationality of exam arrangement, f3 represent the exam paper utilization rate, and f4 represent the ability to handle emergencies. Furthermore, ω1, ω2, ω3, and ω4 represent the weight values ​​indicating the importance of each factor in the exam scheduling task. The rationality of exam arrangement f2 is calculated as follows: Among them, T e T indicates the exam deadline. s Indicates the start time of the exam, t i P represents i The exam start time for each session, where s represents the total number of sessions; and the calculation method for the emergency response capability f4 is as follows: Among them, S i,j R represents i The computer room is in P j The number of exam slots allocated for each session is n, where n is the total number of candidates and gn is g times the total number of candidates, where g∈(0,0.5], and can be dynamically adjusted according to the actual situation. Obtain candidate appointment information and determine the exam scheduling result based on the candidate appointment information and the optimal exam scheduling plan.

2. The method as described in claim 1, characterized in that, The step of determining the initial set of scheduling schemes based on the obtained basic information and hard constraints further includes: Obtain basic information on exam scheduling, hard constraints, and soft constraints; Based on the basic scheduling information and hard constraints, an initial scheme set is generated, which includes the following sub-steps: Based on the basic scheduling information and hard constraints, a scheduling information table containing the correspondence between computer rooms and time periods is constructed; Based on the scheduling information table, N initial scheduling schemes are generated using an allocation function, where N is a pre-set positive integer.

3. The method as described in claim 1, characterized in that, In the step of selecting the optimal examination scheduling scheme based on the objective function value of the initial examination scheduling scheme and the objective function value of the new examination scheduling scheme, the new examination scheduling scheme with the highest objective function value is taken as the optimal examination scheduling scheme.

4. The method as described in claim 1, characterized in that, The hard constraints include one or any combination of the following: the computer room for scheduling exams must be a computer room that is not occupied by courses; only computer rooms that are open for no less than the exam duration during the exam period can be used as computer rooms for scheduling exams; the total number of exam sessions cannot exceed the number of sets of exam papers provided by the teachers; the number of exam slots allocated to each computer room cannot exceed the remaining exam slots in the computer room; the total number of exam slots allocated cannot be less than the total number of candidates; and the exam deadline cannot exceed the end of the semester.

5. The method as described in claim 1, characterized in that, The soft constraints refer to conditions that affect the quality of the test scheduling plan, but are not mandatory.

6. The method as described in claim 5, characterized in that, The soft constraints include one or any combination of the following: computer room utilization rate, test paper utilization rate, reasonableness of examination arrangements, and ability to respond to emergencies.

7. An intelligent scheduling system for online examinations, characterized in that, include: The module for determining the initial exam scheduling scheme set is used to determine the initial exam scheduling scheme set based on the obtained basic exam scheduling information and hard constraints. The basic exam scheduling information includes one or any combination of the following: a set of candidates, a set of exam time periods, and a set of computer labs. The hard constraints refer to conditions that must be followed in the exam scheduling process and cannot be satisfied under any conditions. The optimal scheduling module is used to construct the objective function of the initial scheduling scheme based on the obtained soft constraints, and to obtain a set of candidate scheduling schemes from the initial scheme set based on the objective function values ​​of each initial scheduling scheme. The selection of candidate schemes is based on the proportion of the objective function in the total objective function value; the higher the objective function value, the greater the probability that the initial scheme corresponding to that objective function value will be selected as a candidate scheme. Furthermore, a new scheduling scheme set is obtained by randomly combining the candidate scheduling schemes. This random combination operation involves exchanging the session information of two candidate scheduling schemes to obtain a new scheme with better scheduling results. When the objective function value of the new scheduling scheme no longer changes or the change is extremely small for several consecutive generations, the iteration stops, the new scheduling scheme set is output, and the optimal scheduling scheme is selected based on the objective function values ​​of the initial scheduling schemes and the new scheduling schemes. The corresponding expression of the objective function is as follows: F i =ω1f1+ω2f2+ω3f3+ω4f4 Among them, F i Let f1 represent the objective function value of the i-th exam scheduling plan, f2 represent the rationality of the exam arrangement, f3 represent the test paper utilization rate, f4 represent the ability to respond to emergencies, and ω1, ω2, ω3, and ω4 represent the weight values ​​of the importance of each factor in the exam scheduling task. The calculation method for the reasonableness of the exam arrangement, f2, is as follows: Among them, T e T indicates the exam deadline. s Indicates the start time of the exam, t i P represents i The exam start time for each session, where s represents the total number of sessions; and the calculation method for the emergency response capability f4 is as follows: Among them, S i,j R represents i The computer room is in P j The number of exam slots allocated for each session is n, where n is the total number of candidates and gn is g times the total number of candidates, where g∈(0,0.5], and can be dynamically adjusted according to the actual situation. The exam scheduling result determination module is used to obtain the candidate appointment information and determine the exam scheduling result based on the candidate appointment information and the optimal exam scheduling plan.

8. An intelligent scheduling system for online examinations, characterized in that, include: Memory is used to store executable instructions for a computer; as well as, A processor configured to implement the steps of the method as described in any one of claims 1 to 6 when executing the computer-executable instructions.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions that, when executed by a processor, implement the steps of the method as described in any one of claims 1 to 6.

Images