A method, system, device, and medium for assisting in the arrangement of university course examinations.

By constructing a network diagram and a decision tree group fitting function to automatically schedule college exams, the problem of time-consuming manual assignment of sessions, exam rooms, and invigilation was solved, achieving efficient and high-quality exam scheduling.

CN117670602BActive Publication Date: 2026-11-10HUNAN QIANGZHI TECH DEV CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202311481975.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-11-08
Publication Date
2026-11-10
Estimated Expiration
2043-11-08

AI Technical Summary

Technical Problem

The automated methods for scheduling university exams can only complete part of the work; the remaining part still needs to be manually assigned by the academic secretary, resulting in a heavy workload and long processing time.

Method used

By constructing a network diagram of courses, classes, sessions, examination rooms, and invigilators, and combining preset exploration depth and weights, a vector set is calculated and an attribute matrix is ​​constructed. Attributes are randomly selected and the examination schedule is calculated using a decision tree swarm fitting function. Conflict checks are performed to automatically arrange sessions, examination rooms, and invigilators.

Benefits of technology

It improved the efficiency and quality of exam scheduling, reduced the time spent on manual adjustments, suited the work habits of teaching secretaries, saved scheduling time, and increased satisfaction with the scheduling process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117670602B_ABST
    Figure CN117670602B_ABST
Patent Text Reader

Abstract

This invention discloses a method, system, device, and medium for assisting in the scheduling of university course examinations. The method constructs a set of courses, classes, sessions, examination rooms, and invigilators based on historical datasets; it then constructs a network graph based on these sets; using the network graph, preset exploration depth, and preset exploration weights, it calculates vector sets for courses, classes, sessions, examination rooms, and invigilators; it constructs an attribute matrix using these vector sets; it randomly selects multiple attributes from the attribute matrix, and based on the combined attributes of the courses and classes to be scheduled, the multiple attributes, and a constructed decision tree group fitting function, it calculates multiple examination arrangements including sessions, examination rooms, and invigilators; and it performs conflict checks on these multiple examination arrangements to obtain the results. This invention can improve the efficiency of examination scheduling and save time.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of course examination arrangement technology, and in particular to a method, system, device and medium for assisting in the arrangement of course examinations in colleges and universities. Background Technology

[0002] Currently, the automatic scheduling method for university exams only completes part of the exam scheduling work. The remaining part of the exam scheduling needs to be manually assigned by the academic secretary. Manual assignment requires the academic secretary to select the session, exam room and invigilator, and at least three conflict checks must be carried out. The manual adjustment cycle generally takes about two weeks, which is a heavy workload and takes a long time. Summary of the Invention

[0003] This invention aims to at least solve one of the technical problems existing in the prior art. To this end, this invention proposes a method, system, device, and medium to assist in the arrangement of university course examinations, which can improve the efficiency of examination arrangement and save time.

[0004] In a first aspect, embodiments of the present invention provide a method for assisting in the arrangement of university course examinations, the method comprising:

[0005] Based on historical datasets, construct sets of courses, classes, sessions, exam rooms, and invigilators;

[0006] A network diagram is constructed based on the course set, class set, session set, examination room set, and invigilator set; wherein, a node in the network diagram is a data record from the course set, class set, session set, examination room set, and invigilator set;

[0007] Based on the network diagram, preset exploration depth, and preset exploration weight, calculate the vector sets of courses, classes, sessions, examination rooms, and invigilation rooms;

[0008] An attribute matrix is ​​constructed using the set of vectors for courses and classes, and the set of vectors for sessions, examination rooms, and invigilators.

[0009] Multiple attributes are randomly selected from the attribute matrix, and based on the course and class merging attributes of the exam to be scheduled, the multiple attributes, and the constructed decision tree group fitting function, multiple exam arrangements including sessions, exam rooms, and invigilators are calculated.

[0010] A conflict check is performed on the multiple exam schedules to obtain the check results, and the session, exam room, and invigilator for the exam to be scheduled are selected based on the check results.

[0011] Compared with the prior art, the first aspect of the present invention has the following beneficial effects:

[0012] This method constructs sets of courses, classes, sessions, examination rooms, and invigilators based on historical datasets, taking into account past exam scheduling habits and improving exam scheduling satisfaction. A network graph is constructed based on these sets. Using the network graph, preset exploration depth, and preset exploration weights, vector sets for courses, classes, sessions, examination rooms, and invigilators are calculated. An attribute matrix is ​​then built using these sets. Multiple attributes are randomly selected from the attribute matrix, and the combined attributes of the courses and classes to be scheduled for exams, along with the constructed attribute matrix, are used to further refine the matrix. The decision tree group fitting function calculates multiple exam arrangements including sessions, exam rooms, and invigilators. By comprehensively considering courses, classes, sessions, exam rooms, and invigilators, and based on the course and class merging attributes of the exams to be scheduled, multiple attributes, and the constructed decision tree group fitting function, it automatically calculates multiple exam arrangements including sessions, exam rooms, and invigilators. It can arrange sessions, exam rooms, and invigilators all at once, improving the efficiency of exam scheduling and saving time. Conflict checks are performed on multiple exam arrangements to obtain the check results, and the sessions, exam rooms, and invigilators for the exams to be scheduled are selected based on the check results. Conflict checks can improve the quality of exam scheduling.

[0013] According to some embodiments of the present invention, the step of calculating the vector sets of courses, classes, sessions, examination rooms, and invigilators based on the network graph, a preset exploration depth, and a preset exploration weight includes:

[0014] Based on the network diagram, preset exploration depth, and preset exploration weight, a set solution function is constructed;

[0015] Based on the course set and the class set, the set solving function is trained using the gradient descent method to obtain the course and class vector sets.

[0016] Based on the set of sessions, the set of examination rooms, and the set of invigilators, the gradient descent method is used to train the set solution function to obtain the set of session, examination room, and invigilator vectors.

[0017] According to some embodiments of the present invention, the set solving function is constructed in the following manner:

[0018]

[0019] Where h and t represent a data record in the course set, class set, session set, examination room set, and invigilation set, r represents the relationship between h and t, D represents the network graph, L1 represents the preset exploration depth set, L2 represents the preset exploration weight set, X represents the total number of the course set, class set, session set, examination room set, and invigilation set, c represents any set in the course set, class set, session set, examination room set, and invigilation set, and L2i represents the preset exploration weight corresponding to the i-th preset exploration depth.

[0020] According to some embodiments of the present invention, the random selection of multiple attributes from the attribute matrix, and the calculation of multiple examination arrangements including sessions, examination rooms, and invigilators based on the combined attributes of courses and classes to be scheduled for examinations, the multiple attributes, and the constructed decision tree group fitting function, includes:

[0021] Construct a random selection function, and use the random selection function to randomly select multiple attributes from the attribute matrix;

[0022] A decision tree is constructed based on the aforementioned multiple attributes, and a decision tree swarm fitting function is constructed using the decision tree.

[0023] Based on the decision tree group fitting function and the attribute matrix, an exam arrangement selection function is constructed;

[0024] Based on the combined attributes of the courses and classes to be scheduled for the exams, select multiple exam arrangements of equal number from the attribute matrix, and use the exam arrangement selection function to calculate each exam arrangement to obtain multiple calculation results;

[0025] The maximum calculation result is selected from the multiple calculation results to obtain multiple examination arrangements corresponding to the maximum calculation result, including the session, examination room, and invigilator.

[0026] According to some embodiments of the present invention, the random selection function is constructed in the following manner:

[0027]

[0028] Where random represents random selection, S represents the number of selected attributes, M represents the attribute matrix, A(M) represents all attributes in the attribute matrix, K represents the number of attribute categories in the attribute matrix, and P k This represents the proportion of the k-th class in the total data records, and F1 represents the random selection function.

[0029] According to some embodiments of the present invention, the decision tree group fitting function is constructed in the following manner:

[0030]

[0031] Where T represents the number of decision trees, f t (x) represents the decision tree, x represents the course and class merging attribute of the course to be scheduled for the exam, and F(x) represents the decision tree group fitting function.

[0032] According to some embodiments of the present invention, the examination schedule selection function is constructed as follows:

[0033] F1(x) = Max(F(x), M, N)

[0034] Where F(x) represents the decision tree group fitting function, F1(x) represents the exam arrangement selection function, N represents the number of selected exam arrangements, M represents the attribute matrix, and Max represents the N exam arrangements containing session, exam room, and invigilator that maximize the fitting result of the decision tree group fitting function.

[0035] Secondly, embodiments of the present invention also provide a system for assisting in the arrangement of university course examinations, the system comprising:

[0036] The set building unit is used to build sets of courses, classes, sessions, exam rooms, and proctoring based on historical datasets;

[0037] The network diagram construction unit is used to construct a network diagram based on the course set, the class set, the session set, the examination room set, and the invigilation set; wherein, a node in the network diagram is a data record from the course set, the class set, the session set, the examination room set, and the invigilation set;

[0038] The first calculation unit is used to calculate the vector sets of courses, classes, sessions, examination rooms, and invigilators based on the network diagram, preset exploration depth, and preset exploration weight.

[0039] A matrix building unit is used to build an attribute matrix using the set of course and class vectors and the set of session, examination room, and invigilation vectors.

[0040] The second calculation unit is used to randomly select multiple attributes from the attribute matrix, and calculate multiple exam arrangements including sessions, exam rooms and invigilators based on the course and class merging attributes of the exam to be scheduled, the multiple attributes and the constructed decision tree group fitting function.

[0041] The examination scheduling unit is used to perform conflict checks on the multiple examination schedules, obtain the check results, and select the session, examination room, and invigilator for the course examination to be scheduled based on the check results.

[0042] Thirdly, embodiments of the present invention also provide an apparatus for assisting in the arrangement of college course examinations, including at least one control processor and a memory for communicatively connecting to the at least one control processor; the memory stores instructions executable by the at least one control processor, the instructions being executed by the at least one control processor to enable the at least one control processor to perform a method for assisting in the arrangement of college course examinations as described above.

[0043] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing computer-executable instructions for causing a computer to execute a method for assisting in arranging college course examinations as described above.

[0044] It is understood that the beneficial effects of the second to fourth aspects compared with the related technologies are the same as the beneficial effects of the first aspect compared with the related technologies. Please refer to the relevant description in the first aspect above, which will not be repeated here. Attached Figure Description

[0045] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which:

[0046] Figure 1 This is a flowchart illustrating a method for assisting in the arrangement of university course examinations according to an embodiment of the present invention;

[0047] Figure 2 This is a flowchart of another embodiment of the method for assisting in the arrangement of college course examinations according to the present invention;

[0048] Figure 3 This is a structural diagram of a system for assisting in the arrangement of college course examinations according to an embodiment of the present invention. Detailed Implementation

[0049] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0050] In the description of this invention, the use of terms such as "first," "second," etc., is for the purpose of distinguishing technical features only and should not be construed as indicating or implying relative importance, or implicitly indicating the number of technical features indicated, or implicitly indicating the order of the technical features indicated.

[0051] In the description of this invention, it should be understood that the orientation descriptions, such as up, down, etc., are based on the orientation or positional relationship shown in the drawings and are only for the convenience of describing this invention and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this invention.

[0052] In the description of this invention, it should be noted that, unless otherwise explicitly defined, terms such as "setting," "installation," and "connection" should be interpreted broadly, and those skilled in the art can reasonably determine the specific meaning of the above terms in this invention in conjunction with the specific content of the technical solution.

[0053] First, let's analyze some of the terms used in this application:

[0054] Decision Tree: A decision tree is a predictive model that represents a mapping between object attributes and object values. Each node in the tree represents an object, each branch represents a possible attribute value, and each leaf node corresponds to the value of the object represented by the path from the root node to that leaf node. Decision trees have only a single output; to have multiple outputs, separate decision trees can be built to handle different outputs. Decision trees are a frequently used technique in data mining, used for both data analysis and prediction.

[0055] Currently, the automatic scheduling method for university exams only completes part of the exam scheduling work. The remaining part of the exam scheduling needs to be manually assigned by the academic secretary. Manual assignment requires the academic secretary to select the session, exam room and invigilator, and at least three conflict checks must be carried out. The manual adjustment cycle generally takes about two weeks, which is a heavy workload and takes a long time.

[0056] To address the aforementioned issues, this invention constructs a set of courses, classes, sessions, examination rooms, and invigilators based on historical datasets, taking into account past exam scheduling habits and thus improving exam scheduling satisfaction. A network graph is constructed based on these sets of courses, classes, sessions, examination rooms, and invigilators. Based on the network graph, preset exploration depth, and preset exploration weights, vector sets for courses, classes, sessions, examination rooms, and invigilators are calculated. An attribute matrix is ​​then constructed using these vector sets. Multiple attributes are randomly selected from the attribute matrix, and the combined attributes of the courses and classes for the exams to be scheduled are determined. The system uses a constructed decision tree group fitting function to calculate multiple exam arrangements, including sessions, exam rooms, and invigilators. By comprehensively considering courses, classes, sessions, exam rooms, and invigilators, and based on the course and class merging attributes of the exams to be scheduled, multiple attributes, and the constructed decision tree group fitting function, it automatically calculates multiple exam arrangements, including sessions, exam rooms, and invigilators. This allows for the arrangement of sessions, exam rooms, and invigilators all at once, improving the efficiency of exam scheduling and saving time. Conflict checks are performed on multiple exam arrangements to obtain the check results, and the sessions, exam rooms, and invigilators for the exams to be scheduled are selected based on the check results. Conflict checks improve the quality of exam scheduling.

[0057] Reference Figure 1 This invention provides a method for assisting in the arrangement of university course examinations. This method includes, but is not limited to, steps S100 to S600, wherein:

[0058] Step S100: Based on the historical dataset, construct the course set, class set, session set, exam room set, and invigilator set;

[0059] Step S200: Construct a network diagram based on the course set, class set, session set, exam room set, and invigilation set; wherein, a node in the network diagram is a data record from the course set, class set, session set, exam room set, and invigilation set;

[0060] Step S300: Based on the network diagram, preset exploration depth, and preset exploration weight, calculate the vector sets of courses, classes, sessions, examination rooms, and invigilators;

[0061] Step S400: Construct an attribute matrix using the vector sets of courses, classes, sessions, examination rooms, and invigilators;

[0062] Step S500: Randomly select multiple attributes from the attribute matrix, and calculate multiple exam arrangements including sessions, exam rooms and invigilators based on the combined attributes of courses and classes to be scheduled for exams, multiple attributes and the constructed decision tree group fitting function.

[0063] Step S600: Perform conflict checks on multiple exam schedules, obtain the check results, and select the session, exam room, and invigilator for the exam to be scheduled based on the check results.

[0064] In this embodiment, to improve the satisfaction of exam scheduling, a set of courses, classes, sessions, exam rooms, and invigilators is constructed based on historical datasets. To improve the efficiency of exam scheduling and save time, a network graph is constructed based on these sets. Each node in the network graph represents a data record from one of these sets. Based on the network graph, a preset exploration depth, and preset exploration weights, vector sets for courses, classes, sessions, exam rooms, and invigilators are calculated. An attribute matrix is ​​constructed using these vector sets. Multiple attributes are randomly selected from the attribute matrix, and multiple exam schedules including sessions, exam rooms, and invigilators are calculated based on the merged attributes of the courses and classes to be scheduled, the multiple attributes, and the constructed decision tree group fitting function. To improve the quality of exam scheduling, conflict checks are performed on the multiple exam schedules to obtain the check results, and the sessions, exam rooms, and invigilators for the courses to be scheduled are selected based on these results.

[0065] In some embodiments, based on a network graph, a preset exploration depth, and preset exploration weights, the vector sets for courses, classes, sessions, examination rooms, and invigilators are calculated, including:

[0066] Based on the network diagram, preset exploration depth, and preset exploration weights, a set solution function is constructed.

[0067] Based on the course set and class set, the gradient descent method is used to train the set solving function to obtain the course and class vector sets;

[0068] Based on the set of sessions, the set of examination rooms, and the set of invigilators, the gradient descent method is used to train the set-solving function to obtain the set of vectors for sessions, examination rooms, and invigilators.

[0069] In this embodiment, by using the gradient descent method to train the set solution function, the vector sets of courses, classes, sessions, examination rooms, and invigilators are obtained. This lays a good data foundation for arranging the sessions, examination rooms, and invigilators all at once in the later stage, thereby improving the efficiency of examination scheduling.

[0070] In some embodiments, the set solving function is constructed as follows:

[0071]

[0072] Where h and t represent a data record in the course set, class set, session set, exam room set, and invigilation set, r represents the relationship between h and t, D represents the network diagram, L1 represents the preset exploration depth set, L2 represents the preset exploration weight set, X represents the total number of course sets, class sets, session sets, exam room sets, and invigilation sets, c represents any set in the course set, class set, session set, exam room set, and invigilation set, and L2i represents the preset exploration weight corresponding to the i-th preset exploration depth.

[0073] In some embodiments, multiple attributes are randomly selected from the attribute matrix, and based on the combined attributes of the course and class for the exam to be scheduled, the multiple attributes, and the constructed decision tree group fitting function, multiple exam arrangements including sessions, exam rooms, and invigilation are calculated, including:

[0074] Construct a random selection function and use the random selection function to randomly select multiple attributes from the attribute matrix;

[0075] Decision trees are constructed based on multiple attributes, and decision tree swarm fitting functions are constructed using decision trees;

[0076] Based on the decision tree group fitting function and attribute matrix, a function for selecting exam schedules is constructed.

[0077] Based on the combined attributes of the courses and classes to be scheduled for the exams, select multiple exam arrangements with the same number from the attribute matrix, and use the exam arrangement selection function to calculate each exam arrangement, resulting in multiple calculation results;

[0078] The maximum calculation result is selected from multiple calculation results to obtain multiple exam arrangements corresponding to the maximum calculation result, including the session, exam room, and invigilator.

[0079] In this embodiment, a decision tree is constructed by selecting multiple attributes each time, and then the attribute matrix is ​​fitted using a decision tree swarm fitting function to automatically obtain the most suitable multiple exam arrangements, which can improve the efficiency and quality of exam arrangements.

[0080] In some embodiments, the random selection function is constructed as follows:

[0081]

[0082] Where random represents random selection, S represents the number of selected attributes, M represents the attribute matrix, A(M) represents all attributes in the attribute matrix, K represents the number of attribute categories in the attribute matrix, and P k This represents the proportion of the k-th class in the total data records, and F1 represents the random selection function.

[0083] In this embodiment, a random selection function is used to select multiple attributes from the attribute matrix. This can be done based on the attribute classification and the proportion of each category, ensuring the rationality of the data selection.

[0084] In some embodiments, the decision tree group fitting function is constructed as follows:

[0085]

[0086] Where T represents the number of decision trees, f t F(x) represents the decision tree, x represents the course and class merging attribute of the course to be scheduled for the exam, and F(x) represents the decision tree group fitting function.

[0087] In this embodiment, fitting the attribute matrix with the average value of the decision tree group can lay a theoretical foundation for selecting a more reasonable examination arrangement in the later stage.

[0088] In some embodiments, the exam scheduling selection function is constructed as follows:

[0089] F1(x) = Max(F(x), M, N)

[0090] Where F(x) represents the decision tree group fitting function, F1(x) represents the exam arrangement selection function, N represents the number of selected exam arrangements, M represents the attribute matrix, and Max represents the N exam arrangements containing session, exam room, and invigilator that maximize the fitting result of the decision tree group fitting function.

[0091] In this embodiment, by comparing the calculated values ​​of the attributes corresponding to each selected N number of exam arrangements in the decision tree group fitting function, the N number of exam arrangements corresponding to the largest calculated value can be selected, thereby improving the quality and efficiency of exam arrangements.

[0092] To facilitate understanding by those skilled in the art, a set of preferred embodiments is provided below:

[0093] This embodiment is based on the actual work needs of teaching secretaries and considers their exam scheduling habits. It provides auxiliary prompts, allowing teaching secretaries to select prompts and complete the arrangement of sessions, exam rooms, and invigilation in one go, greatly reducing their workload and quickly completing the exam course scheduling work. (Refer to...) Figure 2 This embodiment specifically includes the following steps:

[0094] 1. Parameter settings.

[0095] Define the exploration depth L1, with a default value of 4; define the exploration weight L2, with a default value of [0.5, 0.4, 0.3, 0.2]; define the number of decision trees T, with a default value of 5; define the number of hints N, with a default value of 8.

[0096] 2. Network diagram calculation model.

[0097] Construct a course set C1, containing the fields [course code, course name, course category, course attribute]; construct a class set C2, containing the fields [class code, class name, major, department]; construct a session set C3, containing the fields [session name, start time, end time]; construct an examination room set C4, containing the fields [examination room number, examination room name, examination room type, building]; construct an invigilator set C5, containing the fields [invigilator number, name, title]. Based on the course set, class set, session set, examination room set, and invigilator set, construct a network diagram D, where each node of D is defined as d.<h,r,t> Where h and t represent a data record in course sets C1, C2, C3, C4, or C5, and r represents the relationship between h and t. The relationship r in D is updated using historical scheduling data. Combining the network diagram D, exploration depth L1, and exploration weight L2, the following set-solving function is used to obtain the set of merged course and class vectors (i.e., the set of course and class vectors) V1, and the set of merged session, exam room, and invigilation vectors V2:

[0098]

[0099] Where h and t represent a data record in the course set, class set, session set, exam room set, and invigilation set, r represents the relationship between h and t, D represents the network diagram, L1 represents the preset exploration depth set, L2 represents the preset exploration weight set, X represents the total number of course sets, class sets, session sets, exam room sets, and invigilation sets, when X takes the value 1 and 2 it refers to C1, C2, when X takes the value 3, 4, 5 it refers to C3, C4, C5, c represents any set in the course set, class set, session set, exam room set, and invigilation set, and L2i represents the preset exploration weight corresponding to the i-th preset exploration depth.

[0100] Using historical data, gradient descent is used to train a set to solve for the function and minimize it, thus obtaining V1 and V2. An attribute matrix M is constructed from V1 and V2, where the matrix values ​​are denoted as 1 if V1 and V2 have been arranged, and 0 otherwise. Let f... t (x) is one of the decision trees. Multiple attributes are randomly selected for each decision tree from the M-attribute matrix according to the following function:

[0101]

[0102] Where random represents random selection, S represents the number of attributes selected, A(M) represents all attributes in the attribute matrix, with a default value of 2, K represents the number of attribute categories in the attribute matrix, with a default value of 2, and P krepresents the proportion of the k-th class in the total data records, and F1 represents the random selection function. Based on each decision tree, a decision tree swarm fitting function M is constructed, as shown below:

[0103]

[0104] Where T represents the number of decision trees, x represents the course and class merging attribute of the courses to be scheduled for exams, and F(x) represents the decision tree group fitting function.

[0105] 3. Prompt the calculation model.

[0106] When selecting an exam record, this embodiment uses an exam record selection function to prompt the user with N exam record selections. The calculation formula for the exam record selection function is as follows:

[0107] F1(x) = Max(F(x), M, N)

[0108] Where F(x) represents the decision tree group fitting function, F1(x) represents the exam arrangement selection function, N represents the number of selected exam arrangements, M represents the attribute matrix, and Max represents the N exam arrangements containing session, exam room, and invigilator that maximize the fitting result of the decision tree group fitting function. After performing basic conflict judgments on the N exam arrangements regarding session, class, course, invigilator, and exam room, the user is prompted to select the non-conflicting session, invigilator, and exam room.

[0109] It should be noted that the default values ​​in this embodiment can be changed according to the actual situation, and this embodiment does not impose any specific limitations.

[0110] In this embodiment, firstly, the teaching secretary can quickly complete the manual exam scheduling work, greatly shortening the scheduling time and improving efficiency; secondly, it aligns with the teaching secretary's work habits, increasing their satisfaction, and also considers past arrangements for classes, courses, invigilation, and venues, making the exam scheduling more reasonable. Through the implementation of this method in several universities, trial applications have yielded generally positive feedback from teaching secretaries and invigilators.

[0111] Reference Figure 3 This invention also provides a system for assisting in the scheduling of university course examinations. This system includes a set construction unit 100, a network graph construction unit 200, a first calculation unit 300, a matrix construction unit 400, a second calculation unit 500, and an examination scheduling unit 600, wherein:

[0112] Set construction unit 100 is used to construct sets of courses, classes, sessions, examination rooms, and invigilators based on historical datasets;

[0113] The network diagram construction unit 200 is used to construct a network diagram based on the course set, class set, session set, examination room set, and invigilation set; wherein, the node in the network diagram is a data record from the course set, class set, session set, examination room set, and invigilation set;

[0114] The first calculation unit 300 is used to calculate the vector sets of courses, classes, sessions, examination rooms, and invigilation rooms based on the network diagram, preset exploration depth, and preset exploration weights.

[0115] Matrix building unit 400 is used to build an attribute matrix using vector sets of courses, classes, sessions, examination rooms, and invigilation rooms.

[0116] The second calculation unit 500 is used to randomly select multiple attributes from the attribute matrix and calculate multiple exam arrangements including sessions, exam rooms and invigilators based on the combined attributes of courses and classes to be scheduled for exams, multiple attributes and the constructed decision tree group fitting function.

[0117] The exam scheduling unit 600 is used to perform conflict checks on multiple exam schedules, obtain the check results, and select the session, exam room, and invigilator for the courses to be scheduled based on the check results.

[0118] It should be noted that since the system for assisting in the arrangement of college course examinations in this embodiment is based on the same inventive concept as the method for assisting in the arrangement of college course examinations described above, the corresponding content in the method embodiment is also applicable to this system embodiment, and will not be described in detail here.

[0119] This invention also provides a device for assisting in the arrangement of college course examinations, comprising: at least one control processor and a memory for communicatively connecting to at least one control processor.

[0120] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0121] The non-transient software program and instructions required to implement the method for assisting in the arrangement of university course examinations described in the above embodiments are stored in memory. When executed by a processor, the method for assisting in the arrangement of university course examinations described in the above embodiments is executed, for example, the method described above is executed. Figure 1The method steps S100 to S600.

[0122] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0123] This invention also provides a computer-readable storage medium storing computer-executable instructions. These instructions are executed by one or more control processors, causing the processors to perform a method for assisting in arranging university course examinations as described in the above-described method embodiments. For example, they may execute the methods described above. Figure 1 The functions of steps S100 to S600 in the method.

[0124] It will be understood by those skilled in the art that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0125] The above is a detailed description of the preferred embodiments of this application. However, the embodiments of this application are not limited to the above-described implementation methods. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the embodiments of this application. All such equivalent modifications or substitutions are included within the scope defined by the claims of the embodiments of this application.

Claims

1. A method for assisting in the arrangement of university course examinations, characterized in that, The methods for assisting in the arrangement of university course examinations include: Based on historical datasets, construct sets of courses, classes, sessions, exam rooms, and invigilators; A network diagram is constructed based on the course set, class set, session set, examination room set, and invigilator set; wherein, a node in the network diagram is a data record from the course set, class set, session set, examination room set, and invigilator set; Based on the aforementioned network diagram, preset exploration depth, and preset exploration weights, calculate the vector sets for courses, classes, sessions, examination rooms, and invigilators, including: Based on the network diagram, preset exploration depth, and preset exploration weights, a set solving function is constructed, including: in, and This represents a data record within the set of courses, the set of classes, the set of sessions, the set of examination rooms, and the set of invigilators. express and The relationship between them This represents the network diagram. Indicates the preset exploration depth set. This represents the preset set of exploration weights. This represents the total number of the course set, the class set, the session set, the examination room set, and the invigilator set. This represents any one of the following sets: the course set, the class set, the session set, the examination room set, and the invigilator set. Indicates the first Preset exploration weights corresponding to preset exploration depth; Based on the course set and the class set, the set solving function is trained using the gradient descent method to obtain the course and class vector sets. Based on the set of sessions, the set of examination rooms, and the set of invigilators, the gradient descent method is used to train the set solution function to obtain the set of session, examination room, and invigilator vectors. An attribute matrix is ​​constructed using the set of vectors for courses and classes, and the set of vectors for sessions, examination rooms, and invigilators. Multiple attributes are randomly selected from the attribute matrix, and based on the course and class merging attributes of the exam to be scheduled, the multiple attributes, and the constructed decision tree group fitting function, multiple exam arrangements including sessions, exam rooms, and invigilators are calculated. A conflict check is performed on the multiple exam schedules to obtain the check results, and the session, exam room, and invigilator for the exam to be scheduled are selected based on the check results.

2. The method for assisting in the arrangement of university course examinations according to claim 1, characterized in that, The random selection of multiple attributes from the attribute matrix, and based on the combined attributes of courses and classes to be scheduled for the exam, the multiple attributes, and the constructed decision tree group fitting function, calculates multiple exam arrangements including sessions, exam rooms, and invigilators, including: Construct a random selection function, and use the random selection function to randomly select multiple attributes from the attribute matrix; A decision tree is constructed based on the aforementioned multiple attributes, and a decision tree swarm fitting function is constructed using the decision tree. Based on the decision tree group fitting function and the attribute matrix, an exam arrangement selection function is constructed; Based on the combined attributes of the courses and classes to be scheduled for the exams, select multiple exam arrangements of equal number from the attribute matrix, and use the exam arrangement selection function to calculate each exam arrangement to obtain multiple calculation results; The maximum calculation result is selected from the multiple calculation results to obtain multiple examination arrangements corresponding to the maximum calculation result, including the session, examination room, and invigilator.

3. The method for assisting in the arrangement of university course examinations according to claim 2, characterized in that, The random selection function is constructed as follows: in, Indicates random selection. Indicates the number of attributes selected. This represents the attribute matrix. This represents all attributes in the attribute matrix. This indicates the number of attribute categories in the attribute matrix. Indicates the first The proportion of each category to the total data records. This represents the random selection function.

4. The method for assisting in the arrangement of university course examinations according to claim 2, characterized in that, The decision tree group fitting function is constructed as follows: in, Indicates the number of decision trees. Representing a decision tree, This indicates that the courses and classes for which exams are to be scheduled are combined. Let represent the fitting function of the decision tree group.

5. The method for assisting in the arrangement of university course examinations according to claim 2, characterized in that, The exam schedule selection function is constructed as follows: in, Denotes the fitting function of the decision tree group. This indicates the function used to select the exam schedule. This indicates the number of exam schedules selected. This represents the attribute matrix. This represents the result of maximizing the fitting function of the decision tree group. An examination arrangement that includes sessions, examination rooms, and invigilators.

6. A system for assisting in the arrangement of university course examinations, characterized in that, The method for assisting in arranging college course examinations according to any one of claims 1 to 5, wherein the system for assisting in arranging college course examinations comprises: The set building unit is used to build sets of courses, classes, sessions, exam rooms, and proctoring based on historical datasets; The network diagram construction unit is used to construct a network diagram based on the course set, the class set, the session set, the examination room set, and the invigilation set; wherein, a node in the network diagram is a data record from the course set, the class set, the session set, the examination room set, and the invigilation set; The first calculation unit is used to calculate the vector sets of courses, classes, sessions, examination rooms, and invigilators based on the network diagram, preset exploration depth, and preset exploration weight. A matrix building unit is used to build an attribute matrix using the set of course and class vectors and the set of session, examination room, and invigilation vectors. The second calculation unit is used to randomly select multiple attributes from the attribute matrix, and calculate multiple exam arrangements including sessions, exam rooms and invigilators based on the course and class merging attributes of the exam to be scheduled, the multiple attributes and the constructed decision tree group fitting function. The examination scheduling unit is used to perform conflict checks on the multiple examination schedules, obtain the check results, and select the session, examination room, and invigilator for the course examination to be scheduled based on the check results.

7. A device for assisting in the arrangement of university course examinations, characterized in that, It includes at least one control processor and a memory for communicatively connecting to the at least one control processor; the memory stores instructions executable by the at least one control processor to enable the at least one control processor to perform the method for assisting in arranging college course examinations as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions for causing a computer to perform the method for assisting in arranging college course examinations as described in any one of claims 1 to 5.

Citation Information

Patent Citations

  • Intelligent course scheduling system and method

    CN112149941A

  • Systems and methods for prioritizing job candidates using a decision-tree forest algorithm

    US8818910B1