A method and system for preventing conflicts in computer-based examination time periods

Abstract

The present application provides a method and system for preventing conflicts in time periods for computer-based examinations, comprising: obtaining real-time examination reservation requests of examinees and recording the time period of each examination reservation request; predicting the examinee flow and examination room resource requirements during the examination based on the real-time examination reservation requests and a hybrid prediction model to obtain prediction results; dynamically adjusting the examination time period based on the prediction results to generate time period allocation results; optimizing the time period allocation results using a multi-objective optimization algorithm to generate a preliminary examination time period allocation plan; detecting whether there is a time conflict in the preliminary examination time period allocation plan using a real-time monitoring mechanism, and adjusting the preliminary examination time period allocation plan based on the severity of the time conflict to obtain a conflict-free examination schedule, thereby improving the efficiency and fairness of the examination schedule.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of computer-based examinations, and more particularly to a method and system for preventing conflicts in time periods for computer-based examinations. Background Art

[0002] With the popularity of online education and remote examinations, computer-based examinations have become a common form of examination for many educational institutions and certification test centers. However, due to the large number of candidates and their different appointment requirements, how to reasonably arrange the examination time slots to avoid conflicts has become an urgent problem to be solved. Especially in large-scale examinations, the diversity of candidates' appointment time options and the limited examination resources make it difficult for traditional manual scheduling methods to meet the needs of efficient, accurate and fair examination scheduling. Therefore, an intelligent method for preventing conflicts in computer-based examination time slots is needed to ensure the effective use of examination resources while meeting the personalized needs of candidates.

[0003] Currently, the most common methods for scheduling computer-based exams rely on manual management and simple automated systems. These methods usually include:

[0004] Manual scheduling: The staff will manually allocate the examination time slot based on the appointment information submitted by the candidates.

[0005] Single-objective optimization: Use basic optimization algorithms and consider only a single objective, such as candidate satisfaction or exam room resource utilization.

[0006] Although the existing scheduling methods have solved the basic needs of arranging examination time periods to a certain extent, they still have the following shortcomings:

[0007] Inefficiency: Manual scheduling is time-consuming and labor-intensive, prone to omissions and errors, and unable to meet the needs of large-scale examinations.

[0008] Waste of resources: Single-objective optimization often ignores the balance between resource utilization and candidate satisfaction, resulting in waste of resources or candidate dissatisfaction.

[0009] Lack of flexibility: When faced with unexpected events or changes in candidates’ needs, existing methods lack the ability to respond and adjust quickly and are unable to adapt to changes in real time.

[0010] Fairness issues: Simple scheduling methods may result in some candidates being unable to take the exam at their preferred time period, affecting the fairness of the exam.

[0011] Frequent conflicts: The lack of an effective conflict detection and resolution mechanism can easily lead to time overlap and affect the order of the examination. Summary of the invention

[0012] The embodiments of the present application provide a method and system for preventing conflicts in computer-based examination time periods, so as to solve the problems existing in the above-mentioned background technology.

[0013] In a first aspect, an embodiment of the present application provides a method for preventing conflicts in time periods for computer-based examinations, comprising: obtaining real-time examination appointment requests from examinees, and recording the time period of each examination appointment request, wherein the time period includes a preferred time period and a secondary time period; based on the real-time examination appointment requests and a hybrid prediction model, predicting the examinee flow and examination room resource requirements during the examination to obtain prediction results; using the prediction results to dynamically adjust the examination time period to generate a time period allocation result; using a multi-objective optimization algorithm to optimize the time period allocation result to generate a preliminary examination time period allocation plan; using a real-time monitoring mechanism to detect whether there is a time conflict in the preliminary examination time period allocation plan, and based on the severity of the time conflict, adjusting the preliminary examination time period allocation plan to obtain a conflict-free examination schedule.

[0014] Furthermore, the steps of constructing the hybrid prediction model include: obtaining historical examination appointment data and real-time appointment information, the historical examination appointment data including: candidate appointment preferences and actual attendance, and the real-time appointment information including: current appointment progress, candidate new appointment or cancellation; using time series analysis technology to perform trend analysis on the historical examination appointment data to obtain trend analysis results of the historical examination appointment data; using a preset algorithm to perform trend analysis on the real-time appointment information to obtain trend analysis results of the real-time appointment information, wherein the preset algorithm includes: sliding window algorithm or exponentially weighted moving average algorithm; using the trend analysis results of the historical examination appointment data and the trend analysis results of the real-time appointment information to optimize the preset hybrid prediction model to obtain the hybrid prediction model.

[0015] Furthermore, a multi-objective optimization algorithm is used to optimize the time period allocation results to generate a preliminary examination time period allocation plan, including: defining multiple objective functions, wherein the multiple objective functions are used to characterize: candidate satisfaction, examination room resource utilization and allocation fairness; constructing a multi-objective optimization problem based on the multiple objective functions; using a Pareto frontier algorithm to solve the multi-objective optimization problem to obtain a solution set; and selecting one or more solutions from the solution set to generate the preliminary examination time period allocation plan.

[0016] Furthermore, the prediction results are used to dynamically adjust the examination time periods to generate time period allocation results, including: taking each examination time period as a node and taking the examinee as an edge to construct a preference network, wherein the weight of the edge represents the examinee's preference for the corresponding time period; constructing an optimization problem of the preference network; and solving the optimization problem through an iterative algorithm to obtain the time period allocation result.

[0017] Furthermore, a real-time monitoring mechanism is utilized to detect whether there is a time conflict in the preliminary examination time period allocation plan, including: setting a time conflict warning value; continuously tracking the number of examinees corresponding to all allocated time periods; if the number of examinees is greater than the time conflict warning value, then there is a time conflict in the preliminary examination time period allocation plan.

[0018] Furthermore, based on the severity of the time conflict, the preliminary examination time period allocation plan is adjusted to obtain a conflict-free examination schedule, including: defining the level of the time conflict, wherein the level of the time conflict is determined according to the degree of overlap of the conflicting time periods and the number of affected candidates; based on the level of the time conflict and a preset conflict decision expression, the preliminary examination time period allocation plan is adjusted to obtain the conflict-free examination schedule.

[0019] Furthermore, the preset conflict decision expression is:

[0020] ;

[0021] in, For the non-conflict examination schedule, Allocate time slots for the preliminary examinations, To adjust the The weight of each candidate's time period, For the the level of time conflicts for each candidate in the initial examination time slot allocation, is the penalty factor, For the The utilization rate of examination resources in each time period, To maximize the utilization of examination resources.

[0022] In the second aspect, an embodiment of the present application provides a system for preventing conflicts in time periods for computer-based examinations, comprising: an acquisition unit, used to acquire real-time examination appointment requests from examinees, and record the time period of each examination appointment request, wherein the time period includes a preferred time period and a secondary time period; a prediction unit, used to predict the examinee flow and examination room resource requirements during the examination based on the real-time examination appointment requests and a hybrid prediction model, and obtain a prediction result; a dynamic adjustment unit, used to dynamically adjust the examination time period using the prediction result, and generate a time period allocation result; an optimization unit, used to optimize the time period allocation result using a multi-objective optimization algorithm, and generate a preliminary examination time period allocation plan; a detection and adjustment unit, used to detect whether there is a time conflict in the preliminary examination time period allocation plan using a real-time monitoring mechanism, and adjust the preliminary examination time period allocation plan based on the severity of the time conflict to obtain a conflict-free examination schedule.

[0023] In a third aspect, an embodiment of the present application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the method described in the first aspect above.

[0024] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program, which, when executed by a computer, implements the method described in the first aspect above.

[0025] In an embodiment of the present invention, by obtaining the real-time examination appointment request of the examinee and recording the time period of each examination appointment request, wherein the time period includes a preferred time period and a secondary time period; based on the real-time examination appointment request and the hybrid prediction model, predicting the examinee flow and examination room resource demand during the examination, and obtaining a prediction result; using the prediction result to dynamically adjust the examination time period, and generating a time period allocation result; using a multi-objective optimization algorithm, optimizing the time period allocation result, and generating a preliminary examination time period allocation plan; using a real-time monitoring mechanism, detecting whether there is a time conflict in the preliminary examination time period allocation plan, and adjusting the preliminary examination time period allocation plan based on the severity of the time conflict, and obtaining a conflict-free examination schedule, a hybrid prediction model combining real-time data and historical data is achieved, and a new method for intelligent arrangement using a multi-objective optimization algorithm is achieved, so as to overcome the limitations of existing solutions and improve the efficiency, fairness and flexibility of computer-based examination time period arrangement.

[0026] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0028] Figure 1 A flowchart of a method for preventing conflicts in computer test time periods provided in an embodiment of the present application;

[0029] Figure 2 A schematic diagram of a system for preventing conflicts in machine test time periods provided in an embodiment of the present application;

[0030] Figure 3 A schematic diagram of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] Embodiment 1:

[0033] According to an embodiment of the present invention, an embodiment of a method for preventing conflicts in machine test time periods is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0034] Figure 1 FIG. 4 is a flow chart of a method for preventing conflicts in computer test time periods according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0035] Step S102, obtaining the real-time test appointment request of the examinee, and recording the time period of each test appointment request, wherein the time period includes a preferred time period and a secondary time period;

[0036] Step S104, predicting the candidate flow and examination room resource requirements during the examination period based on the real-time examination reservation request and the hybrid prediction model, and obtaining a prediction result;

[0037] Step S106, dynamically adjusting the test time period using the prediction result to generate a time period allocation result;

[0038] Step S108, using a multi-objective optimization algorithm to optimize the time period allocation result and generate a preliminary examination time period allocation plan;

[0039] Step S110, using a real-time monitoring mechanism to detect whether the preliminary examination time period allocation plan has a time conflict, and based on the severity of the time conflict, adjusting the preliminary examination time period allocation plan to obtain a conflict-free examination schedule.

[0040] In an embodiment of the present invention, it is necessary to receive a real-time test reservation request from a candidate. Each reservation request includes a time period when the candidate wishes to take the test, usually including a preferred time period and a secondary time period. The preferred time period refers to the time period when the candidate most wishes to take the test, while the secondary time period is a candidate time period in case the preferred time period cannot be met.

[0041] For example, if we receive a reservation request from candidate A, who wants to take the exam between 9:00-11:00 am (preferred time slot) and 14:00-16:00 pm (secondary time slot), we will record candidate A's reservation information and add it to the reservation database.

[0042] A hybrid prediction model combining historical data and real-time data is used to predict the number of candidates and the demand for exam room resources during the exam period. Historical data includes past appointments and actual attendance, while real-time data includes current appointment progress, new appointments, or cancellations. The prediction results are used to guide subsequent dynamic adjustments.

[0043] First, we collected the appointment data of the past few months and found that the number of appointments on Tuesday and Thursday mornings was relatively large. Combined with the current appointment progress, we found that 50 people have made appointments for next Tuesday morning, and 20 more are expected. We predict that the number of candidates for next Tuesday morning will be 70, and based on this, we predict the demand for examination room resources.

[0044] The test time slots are dynamically adjusted based on the prediction results to ensure that the number of candidates in each time slot does not exceed the capacity of the test center. The time slot allocation results are used to generate the time slot allocation results.

[0045] For example, according to the prediction results, the number of candidates on Tuesday morning next week is 70, while the examination room capacity is 60. Therefore, the system decides to divide the examination on Tuesday morning next week into two batches, the first batch from 9:00-11:00 and the second batch from 11:30-13:30. The initial time slot allocation result is: 40 candidates in the first batch and 30 candidates in the second batch.

[0046] Next, a multi-objective optimization algorithm is used to comprehensively consider multiple objectives such as candidates' preferred time period preference, examination room resource utilization efficiency and allocation fairness to generate a preliminary examination time period allocation plan.

[0047] Finally, a real-time monitoring mechanism is used to detect whether there are time conflicts in the preliminary examination time period allocation plan, and the preliminary examination time period allocation plan is adjusted according to the severity of the time conflict to ensure that a conflict-free examination schedule is finally generated.

[0048] A minor conflict is detected in the preliminary exam time slot allocation plan, that is, the number of candidates in some time slots is slightly higher than the capacity of the exam room. The system initiates the conflict resolution process based on the severity of the conflict. Assuming that the number of candidates in a certain time slot is 65 and the capacity of the exam room is 60, the system needs to adjust the exam time slots of at least 5 candidates.

[0049] For example, a heuristic algorithm (such as a genetic algorithm or a simulated annealing algorithm) is used to find an optimal or approximately optimal solution. The genetic algorithm is used to continuously adjust the test time period of candidate B, and ultimately find an optimal solution that satisfies candidate B's preference and avoids time conflicts. For example, the system may schedule candidate B in his second-choice time period of 11:30-13:30 to ensure that the number of candidates in this time period does not exceed the capacity of the examination room.

[0050] Through the above steps, the system will eventually generate a conflict-free examination schedule and promptly notify the candidates of their exact examination time period.

[0051] In an embodiment of the present invention, the step of constructing the hybrid prediction model includes:

[0052] Obtain historical exam reservation data and real-time reservation information. The historical exam reservation data includes: candidate reservation preferences and actual attendance. The real-time reservation information includes: current reservation progress, candidates adding or canceling reservations;

[0053] Using time series analysis technology, trend analysis is performed on the historical test reservation data to obtain trend analysis results of the historical test reservation data;

[0054] Performing trend analysis on the real-time reservation information using a preset algorithm to obtain a trend analysis result of the real-time reservation information, wherein the preset algorithm includes: a sliding window algorithm or an exponentially weighted moving average algorithm;

[0055] The preset hybrid prediction model is optimized by using the trend analysis results of the historical test reservation data and the trend analysis results of the real-time reservation information to obtain the hybrid prediction model.

[0056] In an embodiment of the present invention, reservation records for each examination in the past year are obtained from a database, including the examinee's preferred time period, second-preferred time period, and actual attendance, and the current examination reservation status is monitored in real time, including the current reservation progress, and the examinee's addition or cancellation of reservations.

[0057] For example, the historical exam reservation data obtained is as follows:

[0058] Candidate A: The preferred time period is 9:00-11:00, the second preferred time period is 14:00-16:00, and the actual arrival time is 9:00-11:00.

[0059] Candidate B: The preferred time period is 14:00-16:00, the second preferred time period is 9:00-11:00, and the actual arrival time is 14:00-16:00.

[0060] Real-time reservation information is as follows:

[0061] Current reservation progress: 50 people have made reservations.

[0062] New appointments: 10 new appointments were made in the past hour.

[0063] Cancelled appointments: 2 appointments were cancelled in the past hour.

[0064] Perform time series analysis on historical data to identify cyclical and non-cyclical patterns.

[0065] For example, it was found that the number of appointments on Mondays and Fridays increased significantly, which indicates that candidates tend to choose the examination time period around the weekend.

[0066] Use sliding window algorithm or exponentially weighted moving average algorithm to perform trend analysis on real-time appointment information.

[0067] Sliding window algorithm: Assume that the sliding window size is 2 hours, and calculate the average value of new appointments in the past 2 hours.

[0068] Exponentially weighted moving average algorithm: The decay factor is 0.9, and the weighted average of new bookings in the past few hours is calculated.

[0069] For example, using a sliding window algorithm:

[0070] The average number of new appointments in the past 2 hours is: (10 + 15) / 2 = 12.5.

[0071] Using the exponentially weighted moving average algorithm:

[0072] The initial value is 0, the decay factor is 0.9, and the weighted average of new appointments in the past few hours is calculated.

[0073] Hour 1: EWMA1 = 0.9 × 0 + 0.1 × 10 = 1;

[0074] Hour 2: EWMA2 = 0.9 × 1 + 0.1 × 15 = 2.4;

[0075] The forecasting model was modified by combining the historical trend analysis results (e.g., an increase in the number of reservations on Mondays and Fridays) with the real-time trend analysis results (e.g., an average of 12.5 new reservations in the past 2 hours).

[0076] The prediction model is a linear regression model, and the model parameters are adjusted according to historical and real-time data.

[0077] For example, the prediction model is:

[0078] ,in, represents the predicted value of the candidate flow in the tth time period, Indicates the results of historical trend analysis (e.g., the number of reservations increases on Mondays and Fridays), Indicates the results of real-time trend analysis (such as the average value of new reservations in the past 2 hours). , , are model parameters.

[0079] Through the above steps, the system can effectively combine historical data and real-time data to generate more accurate prediction results, thereby providing a reliable basis for the subsequent allocation of examination time periods.

[0080] In the embodiment of the present invention, a multi-objective optimization algorithm is used to optimize the time period allocation result to generate a preliminary examination time period allocation plan, including:

[0081] Define multiple objective functions, wherein the multiple objective functions are used to characterize: examinee satisfaction, examination room resource utilization, and allocation fairness;

[0082] Constructing a multi-objective optimization problem based on the multiple objective functions;

[0083] Using the Pareto frontier algorithm, the multi-objective optimization problem is solved to obtain a solution set;

[0084] One or more solutions are selected from the solution set to generate the preliminary examination time slot allocation plan.

[0085] In the embodiment of the present invention, first, multiple objective functions are defined:

[0086] Candidate Satisfaction: Measures candidates' satisfaction with their exam time slot arrangements.

[0087] If the candidate is arranged in the preferred time period, the satisfaction is 1; if arranged in the second preferred time period, the satisfaction is 0.5; if arranged in the non-preferred time period, the satisfaction is 0.

[0088] Examination room resource utilization rate: measures whether the examination room resources are fully utilized.

[0089] Calculate the ratio of the number of candidates to the examination room capacity in each time period.

[0090] Fairness of allocation: measures whether the allocation of exam time periods is fair.

[0091] Calculate the variance or standard deviation of the number of test takers in each time period.

[0092] For example, there are 100 candidates, the examination room capacity is 50 people, and there are 4 time periods to choose from.

[0093] The multiple objective functions are as follows:

[0094] Candidate satisfaction S: ,in, For the The weight of each candidate (which can be adjusted based on the importance of the candidate or other factors), For the The candidates' preference for their exam time period (1 represents the first choice, 0.5 represents the second choice, and 0 represents the non-preferred time period). is the total number of candidates.

[0095] Resource utilization U: ,in, It is The number of candidates in a time period, is the examination room capacity, is the number of time periods.

[0096] Distribution fairness F: .

[0097] Through the Pareto frontier algorithm, a set of non-inferior solutions P is obtained.

[0098] Select one or more solutions from the Pareto solution set that achieve a good balance between multiple objectives.

[0099] For example, suppose the Pareto solution set P includes the following solutions:

[0100] Option A: Candidate Satisfaction , resource utilization , distribution fairness .

[0101] Option B: Candidate Satisfaction , resource utilization , distribution fairness .

[0102] Option C: Candidate Satisfaction , resource utilization , distribution fairness .

[0103] Plan B was selected as the preliminary examination time slot allocation plan because it achieved a good balance between candidate satisfaction, resource utilization and allocation fairness.

[0104] Through the above steps, the system can comprehensively consider the satisfaction of candidates, resource utilization and allocation fairness, and generate a preliminary examination time period allocation plan to ensure the rationality and fairness of the examination arrangement.

[0105] In the embodiment of the present invention, the prediction result dynamically adjusts the examination time period to generate the time period allocation result, including:

[0106] Take each exam time period as a node and the examinee as an edge to construct a preference network, where the weight of the edge represents the examinee's preference for the corresponding time period;

[0107] constructing an optimization problem of the preference network;

[0108] The optimization problem is solved by an iterative algorithm to obtain the time period allocation result.

[0109] In the embodiment of the present invention, for example, there are four time periods: 9:00-11:00, 11:30-13:30, 14:00-16:00, 16:30-18:30, and there are three examinees: examinee A, examinee B, and examinee C. Each examinee has a preferred time period and a second preferred time period, with weights of 1 and 0.5 respectively.

[0110] For example:

[0111] Candidate A: The preferred time period is 9:00-11:00, and the second preferred time period is 14:00-16:00.

[0112] Candidate B: The preferred time period is 11:30-13:30, and the second preferred time period is 16:30-18:30.

[0113] Candidate C: The preferred time period is 14:00-16:00, and the second preferred time period is 9:00-11:00.

[0114] The preference network is constructed as follows:

[0115] Nodes: 9:00-11:00, 11:30-13:30, 14:00-16:00, 16:30-18:30.

[0116] Edges and their weights:

[0117] The weight of the edge between 9:00-11:00 and candidate A is 1.

[0118] The weight of the edge between 14:00-16:00 and candidate A is 0.5.

[0119] The weight of the edge between 11:30-13:30 and candidate B is 1.

[0120] The weight of the edge between 16:30-18:30 and candidate B is 0.5.

[0121] The weight of the edge between 14:00-16:00 and candidate C is 1.

[0122] The weight of the edge between 9:00-11:00 and candidate C is 0.5.

[0123] The goal is to minimize the sum of the weights of the edges in the entire network, that is, to minimize the total degree of dissatisfaction.

[0124] Design an optimization problem so that the number of candidates in each time period does not exceed the capacity of the examination room and the candidates' preferred time periods are met as much as possible.

[0125] The optimization problem can be expressed as: , For the The weight of each candidate (the first choice time period is 1, the second choice time period is 0.5), It is The preference of each candidate for their exam time period (1 represents the first choice, 0.5 represents the second choice), is the total number of candidates.

[0126] Solve the above optimization problem using an iterative algorithm such as greedy algorithm, genetic algorithm, or simulated annealing algorithm.

[0127] Through multiple iterations, the test time slots of candidates are gradually adjusted to minimize dissatisfaction.

[0128] For example, using a greedy algorithm to solve:

[0129] Initialization: The number of candidates in each time period is 0.

[0130] According to the priority of the candidates' preferred time periods, we will try to assign the candidates to their preferred time periods in turn.

[0131] If the preferred time slot is full, an attempt is made to allocate to the secondary time slot.

[0132] If the second-choice time slot is also full, continue trying the next time slot until a suitable allocation solution is found.

[0133] For example, assuming the examination room capacity is 50 people, and each time period can accommodate a maximum of 50 people:

[0134] Candidate A's first choice time period is 9:00-11:00, and the second choice time period is 14:00-16:00.

[0135] Candidate B's first choice time period is 11:30-13:30, and the second choice time period is 16:30-18:30.

[0136] Candidate C's first choice time period is 14:00-16:00, and the second choice time period is 9:00-11:00.

[0137] Initial Allocation:

[0138] 9:00-11:00: Candidate A (weight is 1).

[0139] 11:30-13:30: Candidate B (weight 1).

[0140] 14:00-16:00: Candidate C (weight 1).

[0141] Final distribution results:

[0142] 9:00-11:00: Candidate A (weight is 1).

[0143] 11:30-13:30: Candidate B (weight 1).

[0144] 14:00-16:00: Candidate C (weight 1).

[0145] Through the above steps, the system can build a preference network and solve the optimization problem through an iterative algorithm, and finally generate the time slot allocation result. This can ensure that the number of candidates in each time slot does not exceed the capacity of the examination room and try to meet the candidates' preferred time slots, thereby improving the candidates' satisfaction.

[0146] In an embodiment of the present invention, a real-time monitoring mechanism is used to detect whether the preliminary examination time period allocation scheme has a time conflict, including:

[0147] Set time conflict warning value;

[0148] Keep track of the number of candidates for all allocated time slots;

[0149] If the number of examinees is greater than the time conflict warning value, then there is a time conflict in the preliminary examination time period allocation plan.

[0150] In the embodiment of the present invention, the examination room capacity is 50 people, and the time conflict warning value is set to 45 people.

[0151] Establish a real-time monitoring system to continuously track the number of candidates in each allocated time period.

[0152] For example, the system has allocated four time periods: 9:00-11:00, 11:30-13:30, 14:00-16:00, 16:30-18:30.

[0153] The real-time monitoring system displays as follows:

[0154] 9:00-11:00: 48 people

[0155] 11:30-13:30: 40 people

[0156] 14:00-16:00: 42 people

[0157] 16:30-18:30: 35 people

[0158] If the number of candidates is greater than the time conflict warning value, then the preliminary examination time period allocation plan has a time conflict:

[0159] If the number of candidates in a certain period of time exceeds 45, the conflict resolution procedure will be initiated to make adjustments.

[0160] Since the number of candidates in the time period of 9:00-11:00 is 48, which exceeds the time conflict warning value of 45, there is a time conflict.

[0161] The system detects that there are too many candidates in the time period of 9:00-11:00, and the examination time period of some candidates needs to be adjusted.

[0162] The system will adjust some candidates to other time periods based on the candidates' second-choice time period preferences, for example, adjusting some candidates from 9:00-11:00 to 14:00-16:00 or 16:30-18:30.

[0163] After adjustment, the final distribution results are as follows:

[0164] 9:00-11:00: 43 people

[0165] 11:30-13:30: 40 people

[0166] 14:00-16:00: 45 people

[0167] 16:30-18:30: 38 people

[0168] Through the above steps, the system can monitor the number of candidates in each time period in real time, and promptly detect and resolve time conflicts, ensuring that the number of candidates in each time period does not exceed the capacity of the examination room, thereby avoiding waste of resources and conflicts.

[0169] In an embodiment of the present invention, based on the severity of the time conflict, the preliminary examination time period allocation scheme is adjusted to obtain a conflict-free examination schedule, including:

[0170] Defining the level of the time conflict, wherein the level of the time conflict is determined according to the overlap degree of the conflicting time periods and the number of affected candidates;

[0171] Based on the level of the time conflict and a preset conflict decision expression, the preliminary examination time period allocation plan is adjusted to obtain the conflict-free examination schedule.

[0172] In the embodiment of the present invention, first, the conflict level is defined:

[0173] Minor conflict: The overlap is less than 10% and the number of affected candidates is less than 5.

[0174] Moderate conflict: The overlap is between 10% and 30%, and the number of candidates affected is between 5 and 10.

[0175] Serious conflict: The overlap is greater than 30% and the number of affected candidates exceeds 10.

[0176] The default conflict decision expression is:

[0177] ;

[0178] in, For the non-conflict examination schedule, Allocate time slots for the preliminary examinations, To adjust the The weight of each candidate's time period, For the the level of time conflicts for each candidate in the initial examination time slot allocation, is the penalty factor, For the The utilization rate of examination resources in each time period, To maximize the utilization of examination resources.

[0179] Minor conflicts: No adjustment required.

[0180] Moderate conflict: Minor adjustments to the exam time periods for some candidates.

[0181] Major conflicts: Reschedule the exam time slot for affected candidates.

[0182] For example, suppose the initial allocation is as follows:

[0183] 9:00-11:00: 48 people

[0184] 11:30-13:30: 40 people

[0185] 14:00-16:00: 42 people

[0186] 16:30-18:30: 35 people

[0187] Assume that the examination room capacity is 50 people and the time conflict warning value is 45 people.

[0188] The number of candidates in the time period of 9:00-11:00 is 48, which exceeds the time conflict warning value of 45 people, which is a serious conflict.

[0189] The number of candidates in the time period of 11:30-13:30 was 40, which did not exceed the time conflict warning value and there was no conflict.

[0190] The number of candidates in the time period of 14:00-16:00 was 42, which did not exceed the time conflict warning value and there was no conflict.

[0191] The number of candidates in the time period of 16:30-18:30 was 35, which did not exceed the time conflict warning value and there was no conflict.

[0192] Since the 9:00-11:00 time period is a serious conflict, the examination time period for the affected candidates needs to be rescheduled.

[0193] Reschedule the examination time slots for the affected candidates based on the preset conflict decision expression.

[0194] For example, if you need to reschedule 5 candidates from 9:00-11:00 to other time slots:

[0195] Adjust candidate A's time from 9:00-11:00 to 11:30-13:30.

[0196] Adjust the time for Candidate B from 9:00-11:00 to 14:00-16:00.

[0197] Adjust the time for candidate C from 9:00-11:00 to 16:30-18:30.

[0198] Adjust the time for candidate D from 9:00-11:00 to 14:00-16:00.

[0199] Adjust the time for candidate E from 9:00-11:00 to 16:30-18:30.

[0200] After adjustment, the final distribution results are as follows:

[0201] 9:00-11:00: 43 people

[0202] 11:30-13:30: 41 people

[0203] 14:00-16:00: 44 people

[0204] 16:30-18:30: 40 people

[0205] Through the above steps, the system can take corresponding adjustment strategies according to the severity of time conflicts to ensure that the final generated examination schedule has no time conflicts, thereby ensuring the rationality and fairness of the examination arrangement.

[0206] Embodiment 2:

[0207] An embodiment of the present invention also provides a system for preventing conflicts in computer-based examination time periods. The system for preventing conflicts in computer-based examination time periods is used to execute the method for preventing conflicts in computer-based examination time periods provided in the above content of the embodiment of the present invention. The following is a specific introduction to the system for preventing conflicts in computer-based examination time periods provided in an embodiment of the present invention.

[0208] like Figure 2 As shown, Figure 2 The schematic diagram of the system for preventing conflicts in the time periods of the above-mentioned computer-based examinations is as follows, wherein the system comprises:

[0209] The acquisition unit 10 is used to acquire the real-time test appointment request of the examinee and record the time period of each test appointment request, wherein the time period includes a preferred time period and a secondary time period;

[0210] A prediction unit 20, configured to predict the candidate flow and examination room resource requirements during the examination period based on the real-time examination reservation request and the hybrid prediction model, and obtain a prediction result;

[0211] A dynamic adjustment unit 30, configured to dynamically adjust the test time period using the prediction result to generate a time period allocation result;

[0212] The optimization unit 40 is used to optimize the time period allocation result by using a multi-objective optimization algorithm to generate a preliminary examination time period allocation plan;

[0213] The detection and adjustment unit 50 is used to use a real-time monitoring mechanism to detect whether there is a time conflict in the preliminary examination time period allocation plan, and adjust the preliminary examination time period allocation plan based on the severity of the time conflict to obtain a conflict-free examination schedule.

[0214] Embodiment three:

[0215] The embodiment of the present invention further provides a computing device for executing a program of the method described in the first embodiment, such as Figure 3 As shown, the computing device may include a storage component 41 and a processing component 42;

[0216] The storage component 41 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 42 .

[0217] The processing component 42 may include one or more processors to execute computer instructions to complete all or part of the steps in the method of embodiment 1. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0218] The storage component 41 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0219] The display component 43 may be an electroluminescent (EL) element, a liquid crystal display or a micro display having a similar structure, or a retinal direct display or a similar laser scanning display.

[0220] Of course, a computing device may also include other components, such as input / output interfaces, communication components, etc.

[0221] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0222] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0223] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0224] Embodiment 4:

[0225] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The method of the illustrated embodiment.

[0226] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0227] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0228] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0229] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for preventing conflicts in time periods for computer-based examinations, characterized in that: include: Acquire the real-time examination reservation request of the examinee, and record the time period of each examination reservation request, wherein the time period includes a preferred time period and a secondary time period; Based on the real-time test reservation request and the hybrid prediction model, predict the candidate flow and test room resource requirements during the test period to obtain a prediction result; Dynamically adjust the test time period using the prediction results to generate a time period allocation result; Utilizing a multi-objective optimization algorithm, the time period allocation result is optimized to generate a preliminary examination time period allocation plan; Using a real-time monitoring mechanism, detecting whether the preliminary examination time period allocation plan has a time conflict, and adjusting the preliminary examination time period allocation plan based on the severity of the time conflict to obtain a conflict-free examination schedule; The method of dynamically adjusting the test time period using the prediction result to generate the time period allocation result includes: Take each exam time period as a node and the examinee as an edge to construct a preference network, where the weight of the edge represents the examinee's preference for the corresponding time period; constructing an optimization problem of the preference network; The optimization problem is solved by an iterative algorithm to obtain the time period allocation result.

2. The method according to claim 1, characterized in that The steps of constructing the hybrid prediction model include: Obtain historical exam reservation data and real-time reservation information. The historical exam reservation data includes: candidate reservation preferences and actual attendance. The real-time reservation information includes: current reservation progress, candidates adding or canceling reservations; Using time series analysis technology, trend analysis is performed on the historical test reservation data to obtain trend analysis results of the historical test reservation data; Performing trend analysis on the real-time reservation information using a preset algorithm to obtain a trend analysis result of the real-time reservation information, wherein the preset algorithm includes: a sliding window algorithm or an exponentially weighted moving average algorithm; The preset hybrid prediction model is optimized by using the trend analysis results of the historical test reservation data and the trend analysis results of the real-time reservation information to obtain the hybrid prediction model.

3. The method according to claim 1, characterized in that The time period allocation result is optimized by using a multi-objective optimization algorithm to generate a preliminary examination time period allocation plan, including: Define multiple objective functions, wherein the multiple objective functions are used to characterize: examinee satisfaction, examination room resource utilization, and allocation fairness; Constructing a multi-objective optimization problem based on the multiple objective functions; Using the Pareto frontier algorithm, the multi-objective optimization problem is solved to obtain a solution set; One or more solutions are selected from the solution set to generate the preliminary examination time slot allocation plan.

4. The method according to claim 1, characterized in that: Using a real-time monitoring mechanism, detect whether the preliminary examination time period allocation plan has time conflicts, including: Set time conflict warning value; Keep track of the number of candidates for all allocated time slots; If the number of examinees is greater than the time conflict warning value, then there is a time conflict in the preliminary examination time period allocation plan.

5. The method according to claim 1, characterized in that Based on the severity of the time conflict, the preliminary examination time period allocation plan is adjusted to obtain a conflict-free examination schedule, including: Defining the level of the time conflict, wherein the level of the time conflict is determined according to the overlap degree of the conflicting time periods and the number of affected candidates; Based on the level of the time conflict and the preset conflict decision expression, the preliminary examination time period allocation plan is adjusted to obtain the conflict-free examination schedule.

6. The method according to claim 5, characterized in that The preset conflict decision expression is: ； in, For the conflict-free exam schedule, Allocate time slots for the preliminary examinations, To adjust the The weight of each candidate's time period, For the the level of time conflicts for each candidate in the initial examination time slot allocation, is the penalty factor, For the The utilization rate of examination resources in each time period, To maximize the utilization of examination resources.

7. A system for preventing conflicts in computer-based examination time periods, characterized in that: include: An acquisition unit, used to acquire a real-time examination reservation request of a candidate and record a time period of each examination reservation request, wherein the time period includes a preferred time period and a secondary time period; A prediction unit, configured to predict the candidate flow and examination room resource requirements during the examination period based on the real-time examination reservation request and the hybrid prediction model, and obtain a prediction result; A dynamic adjustment unit, used to dynamically adjust the test time period using the prediction result to generate a time period allocation result; An optimization unit, used to optimize the time period allocation result by using a multi-objective optimization algorithm to generate a preliminary examination time period allocation plan; A detection and adjustment unit, configured to detect whether the preliminary examination time period allocation scheme has a time conflict by using a real-time monitoring mechanism, and adjust the preliminary examination time period allocation scheme based on the severity of the time conflict to obtain a conflict-free examination schedule; Wherein, the optimization unit is used for: Take each exam time period as a node and the examinee as an edge to construct a preference network, where the weight of the edge represents the examinee's preference for the corresponding time period; constructing an optimization problem of the preference network; The optimization problem is solved by an iterative algorithm to obtain the time period allocation result.

8. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the method according to any one of claims 1 to 6.

9. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, the method according to any one of claims 1 to 6 is implemented.

Images