Project-system course teaching grouping method and system, electronic equipment and product

Abstract

The invention belongs to the technical field of teaching management, and aims to provide a project course teaching grouping method and system, electronic equipment and a product. According to the invention, coding processing of project attribute information and student personal attribute information is realized in a trained auto-encoder, group leader students are selected according to the matching degree between each student and the to-be-taught project, and further grouping of the students is realized according to the matching degree between each group member student and each group leader student. According to the technical scheme, the matching degree between the students in the project groups is high, it can be ensured that each group member student in each project group and the corresponding group leader student can form an effective cooperation relation, the team cooperation efficiency in the project groups can be improved, meanwhile, automatic grouping can be achieved, and the grouping process of project-system courses conducted by teachers is simplified.

Description

Technical Field

[0001] The present invention belongs to the technical field of teaching management, and specifically relates to a project-based course teaching grouping method, system, electronic equipment and product. Background Art

[0002] With the continuous development of medical education, the traditional teaching model based on lectures can no longer meet the needs of modern talent training. As an emerging teaching method, project-based learning (PBL) has been widely used and studied in the field of education in recent years. Project-based learning emphasizes student-centeredness and promotes students' active learning and problem-solving skills by designing and implementing real project tasks. It can not only help students better master professional knowledge, but also cultivate their comprehensive abilities such as clinical thinking, teamwork and communication.

[0003] At present, in the process of grouping project-based course teaching, students usually need to be grouped according to the project situation. In the prior art, when grouping students, it is often based on the subjective judgment of teachers, or grouping in sequence, simple random grouping or referring to questionnaires.

[0004] However, in the process of using the prior art, the inventors found that the prior art has at least the following problems: The existing technology often groups students in a fixed or random way, and fails to fully consider students' individual needs such as skills, interests, and preferences for team roles (such as leaders or coordinators). For example, some students may be more suitable to work with classmates with specific skills, but the existing technology usually does not fully collect and analyze these personalized preference data, resulting in a low match between students in the group, affecting the subsequent team collaboration efficiency. Summary of the invention

[0005] The present invention aims to solve the above technical problems at least to a certain extent. The present invention provides a project-based course teaching grouping method, system, electronic equipment and product.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions: In a first aspect, the present invention provides a project-based course teaching grouping method, comprising: Acquire historical attribute information, and use the historical attribute information to train an initial autoencoder to obtain a trained autoencoder; Acquire project attribute information of the project to be taught, and encode the project attribute information based on the trained autoencoder to obtain project feature data of the project to be taught; Obtaining personal attribute information of each student among the students to be taught, and encoding the personal attribute information of each student based on the trained autoencoder to obtain personal characteristic data of each student; Calculate the matching degree between each student and the to-be-taught project based on the project characteristic data and each student's personal characteristic data; According to the matching degree between each student and the teaching project, the n students with the greatest matching degree with the teaching project are set as group leaders, and the students other than the group leaders among the teaching students are set as group members; wherein n is a natural number greater than 1; According to the personal characteristic data of each group member student and the personal characteristic data of each group leader student among the students to be taught, the matching degree between each group member student and each group leader student is calculated; According to the matching degree between each group member student and each group leader student, each group member student is grouped to obtain n project groups.

[0007] In a possible design, the initial autoencoder includes an initial encoder and an initial decoder; correspondingly, the initial autoencoder is trained using the historical attribute information to obtain a trained autoencoder, including: Inputting the historical attribute information into an initial encoder of the initial autoencoder, and obtaining low-dimensional feature data corresponding to the historical attribute information according to the initial encoder; Inputting the low-dimensional feature data into an initial decoder of the initial autoencoder, and obtaining reconstructed high-dimensional feature data corresponding to the historical attribute information according to the initial decoder; Based on a preset loss function, the mean square error between the historical attribute information and the reconstructed high-dimensional feature data is obtained, and the weight matrices in the initial encoder and the initial decoder are adjusted according to the mean square error until the preset autoencoder convergence condition is reached, thereby obtaining the trained autoencoder.

[0008] In one possible design, the mapping function of the trained encoder in the trained autoencoder is: ; In the formula, is the preset activation function; is the weight matrix of the encoder after the training; is the preset encoding bias vector; is the information to be encoded which is input into the trained encoder, , is the total number of sub-information in the information to be encoded, is the dimension of the sub-information in the information to be encoded; is the low-dimensional feature data of the information to be encoded, , is the preset latent space dimension; The mapping function of the trained decoder in the trained autoencoder is: ; In the formula, is the weight matrix of the decoder after training; is the preset decoding bias vector; is the reconstructed high-dimensional feature data of the information to be encoded, ; The loss function is: ; In the formula, is the mean square error between the information to be encoded and its reconstructed high-dimensional feature data; is the first Child information and the reconstructed high-dimensional feature data Sub-characteristic data The norm of the difference.

[0009] In a possible design, the matching degree between any student and the item to be taught is: Matching Score ( )= ; In the formula, The project characteristic data; Personal characteristic data of any of the students; Personal characteristics data for any student Data related to the project characteristics The norm of the difference.

[0010] In one possible design, the degree of match between any group member student and any group leader student is: Member Matching Score ( )= ; In the formula, For any of the group members Personal characteristics data; For any of the above group leaders Personal characteristics data; For any of the group members Personal characteristics data The norm of For any of the above group leaders Personal characteristics data The norm of .

[0011] In one possible design, the degree of match between any group member student and any group leader student is: Updated Score ( ) = +λ( - ); In the formula, For any of the group members Personal characteristics data; For any of the above group leaders Personal characteristics data; For any of the group members Personal characteristics data The norm of For any of the above group leaders Personal characteristics data The norm of For any of the above group leaders A collection of students who have been assigned to the project team; For any of the group members Hope to meet with group members Another member student The preference value of the team; λ is the preset adjustment factor for controlling the preference weight; For any of the group members Do not want to gather with group students Another member student The preference value of the team; Avoid preferred weighting factors for preset controls.

[0012] In a possible design, when grouping the group members according to the matching degree between each group member and each group leader, the n project groups obtained all meet the following constraints: ,and ; in, is the ability balance constraint value of each member student in the project team, , For any student in the project team skill score, is the total number of student members in the project team; is the interest similarity constraint value of each member student in the project team, , For any student in the project team The interest vector, Be the leader of the project team The interest vector.

[0013] In a second aspect, the present invention provides a project-based course teaching grouping system, which is used to implement a project-based course teaching grouping method as described in any one of the above; the project-based course teaching grouping system includes: An autoencoder training module is used to obtain historical attribute information and use the historical attribute information to train an initial autoencoder to obtain a trained autoencoder; A first encoding module, which is in communication connection with the autoencoder training module, is used to obtain project attribute information of the project to be taught, and encode the project attribute information based on the trained autoencoder to obtain project feature data of the project to be taught; A second encoding module is connected to the autoencoder training module for obtaining personal attribute information of each student to be taught, and encoding the personal attribute information of each student based on the trained autoencoder to obtain personal feature data of each student; A group leader selection module is connected to the first encoding module and the second encoding module for calculating the matching degree between each student and the project to be taught according to the project characteristic data and the personal characteristic data of each student; and is also used to set the identities of n students with the greatest matching degree with the project to be taught as group leaders according to the matching degree between each student and the project to be taught, and set the identities of students other than the group leaders among the students to be taught as group members; wherein n is a natural number greater than 1; The group member grouping module is communicatively connected with the group leader selection module, and is used to calculate the matching degree between each group member student and each group leader student according to the personal characteristic data of each group member student and the personal characteristic data of each group leader student among the students to be taught; and is also used to group each group member student according to the matching degree between each group member student and each group leader student to obtain n project groups.

[0014] In a third aspect, the present invention provides an electronic device, comprising: a memory for storing computer program instructions; and, A processor is used to execute the computer program instructions to complete the operation of a project-based course teaching grouping method as described in any one of the above.

[0015] In a fourth aspect, the present invention provides a computer program product, including a computer program or instructions, which, when executed by a computer, implements a project-based course teaching grouping method as described in any one of the above.

[0016] The beneficial effects of the present invention are: The present invention discloses a project-based course teaching grouping method, system, electronic equipment and product, which can improve the matching degree between students in each project group, and at the same time can simplify the operation process of student grouping, which is conducive to improving team collaboration efficiency. The present invention obtains the project attribute information of the project to be taught and the personal attribute information of each student among the students to be taught, and respectively encodes the project attribute information and the personal attribute information of each student based on the trained autoencoder to obtain the project feature data of the project to be taught and the personal feature data of each student; then, according to the project feature data and the personal feature data of each student, the matching degree between each student and the project to be taught is calculated, and then according to the matching degree between each student and the project to be taught, the identities of n students with the greatest matching degree with the project to be taught are set as group leaders, and the identities of students other than the group leaders among the students to be taught are set as group members; then, according to the personal feature data of each group member student who is a group member among the students to be taught and the personal feature data of each group leader student who is a group leader, the matching degree between each group member student and each group leader student is calculated; finally, according to the matching degree between each group member student and each group leader student, each group member student is grouped to obtain n project groups. In this process, the present invention realizes encoding processing of project attribute information and student personal attribute information in the trained autoencoder, selects the group leader student according to the matching degree between each student and the project to be taught, and further realizes the grouping of students according to the matching degree between each group member student and each group leader student. The matching degree between students in the project group is high, which can ensure that each group member student in each project group can form an effective collaborative relationship with the corresponding group leader student, which is conducive to improving the team collaboration efficiency within the project group. At the same time, automatic grouping can be realized, which simplifies the grouping process of teachers in project-based courses and has the value of promotion and application.

[0017] Other beneficial effects of the present invention will be further described in the specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a flow chart of a project-based course teaching grouping method in the embodiment; Figure 2 This is a module block diagram of a project-based course teaching grouping system in the embodiment; Figure 3 It is a module block diagram of an electronic device in an embodiment. DETAILED DESCRIPTION

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in combination with the drawings and the description of the embodiments or the prior art. Obviously, the following description of the structure of the drawings is only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention.

[0020] Embodiment 1: This embodiment discloses a project-based course teaching grouping method, which can be executed by, but is not limited to, a computer device or a virtual machine with certain computing resources, such as a personal computer, a smart phone, a personal digital assistant, or a wearable device, or by a virtual machine.

[0021] like Figure 1 As shown, a project-based course teaching grouping method may include but is not limited to the following steps: S1. Obtain historical attribute information, and use the historical attribute information to train the initial auto-encoder (AE) to obtain a trained auto-encoder. It should be noted that the auto-encoder is based on the back-propagation algorithm and optimization method to guide the neural network to try to learn the mapping relationship. It consists of an encoder and a decoder. Its goal is to learn the low-dimensional representation of the input data by minimizing the difference (reconstruction error) between the input data and the decoded output data; the role of the encoder is to encode the high-dimensional input data into a low-dimensional latent variable, and the role of the decoder is to restore the latent variable after dimensionality reduction to the initial dimension.

[0022] Specifically, in this embodiment, the training method of the initial autoencoder adopts unsupervised training, and the initial autoencoder is trained by minimizing the error between input data and reconstructed data.

[0023] It should be noted that the initial autoencoder includes an initial encoder and an initial decoder; correspondingly, in step S1, the initial autoencoder is trained using the historical attribute information to obtain a trained autoencoder, including: S101. Inputting the historical attribute information into the initial encoder of the initial autoencoder, and obtaining low-dimensional feature data corresponding to the historical attribute information according to the initial encoder; S102. Inputting the low-dimensional feature data into the initial decoder of the initial autoencoder, and obtaining reconstructed high-dimensional feature data corresponding to the historical attribute information according to the initial decoder; S103. Based on a preset loss function, the mean square error between the historical attribute information and the reconstructed high-dimensional feature data is obtained, and the weight matrices in the initial encoder and the initial decoder are adjusted according to the mean square error until the preset autoencoder convergence condition is reached, thereby obtaining the trained autoencoder.

[0024] Specifically, in this embodiment, during the training of the initial autoencoder, after obtaining the mean square error, an error threshold can be set. If the mean square error obtained is greater than the error threshold, the weight matrix in the initial encoder and the initial decoder is adjusted to form an adjusted autoencoder, and then the historical attribute information is re-input into the adjusted autoencoder until the mean square error is less than or equal to the set error threshold; at this time, the adjusted autoencoder is the required trained autoencoder. In addition, the training stop condition can also be set to reach the maximum number of iterations. In this case, the adjusted autoencoder obtained at the last iteration is the required trained autoencoder.

[0025] In step S1 of this embodiment, the mapping function of the trained encoder in the trained autoencoder is: ; In the formula, is the preset activation function; is the weight matrix of the encoder after the training; is the preset encoding bias vector; is the information to be encoded which is input into the trained encoder, , is the total number of sub-information in the information to be encoded, is the dimension of the sub-information in the information to be encoded; is the low-dimensional feature data of the information to be encoded, , is the preset latent space dimension; It should be noted that, during the implementation process, the input data such as the project attribute information and the personal attribute information of each student are encoded by the post-trained encoder in the post-trained autoencoder to convert the input data into the most representative low-dimensional latent vector feature representation. Based on this, the key information of the input data can be retained, the computational complexity can be reduced, and subsequent data processing and analysis can be better performed.

[0026] The mapping function of the trained decoder in the trained autoencoder is: ; In the formula, is the weight matrix of the decoder after training; is the preset decoding bias vector; is the reconstructed high-dimensional feature data of the information to be encoded, ; In this embodiment, the loss function uses the reconstruction error, that is, the mean square error between the original input and the decoded output. Specifically, the loss function is: ; In the formula, is the mean square error between the information to be encoded and its reconstructed high-dimensional feature data; is the first Child information and the reconstructed high-dimensional feature data Sub-characteristic data The norm of the difference.

[0027] S2. Obtaining the project attribute information of the project to be taught, and encoding the project attribute information based on the trained autoencoder to obtain the project feature data of the project to be taught. Specifically, in this embodiment, in order to ensure that different dimensions of the project attribute information input into the trained autoencoder have the same numerical range, after obtaining the project attribute information of the project to be taught, the project attribute information is normalized to obtain the normalized project attribute information, and then the normalized project attribute information is encoded based on the trained autoencoder to obtain the project feature data of the project to be taught.

[0028] For example, in this embodiment, the project attribute information includes project capability requirement information. , Subject background information 、Project implementation information and project duration The project attribute information is processed in the form of a high-dimensional matrix; the project capability requirement information Such as analysis, programming and writing skills, subject background information Such as including background information on biology, computer science, physics and mathematics, and information on how the project is implemented Such as including information on implementation methods such as experiments, development and papers, and project duration The duration required for the teaching project.

[0029] S3. Obtain the personal attribute information of each student among the students to be taught, and encode the personal attribute information of each student based on the trained autoencoder to obtain the personal characteristic data of each student. Specifically, in this embodiment, in order to ensure that different dimensions of the personal attribute information input into the trained autoencoder have the same numerical range, after obtaining the personal attribute information of each student, the personal attribute information is normalized to obtain the normalized personal attribute information, and then the normalized personal attribute information is encoded based on the trained autoencoder to obtain the personal characteristic data of each student.

[0030] During the implementation process, the personal attribute information of each student can be obtained by teacher input, extraction from the teaching system, and student input, etc., which is not limited here. In this embodiment, the personal attribute information of any student can be obtained by vector To represent, for example, any student's personal attribute information, such as skill information , Academic background information , interests and willingness information , Personality Trait Information , task priority information and social background information Personal attribute information, etc.; among them, skill information Such as programming skills, teamwork skills, literature research skills, etc.; academic background information Such information includes any student's professional background, learning experience, courses studied, course grades studied, and scientific research or competition projects participated in, which can be directly extracted from the academic affairs system based on the student's student ID and other identification; interest and willingness information Such as project execution intention and interest direction; personality characteristics information Such as team role preference (such as whether to be a leader or a follower); task priority information Such as including any of the students' priorities when performing tasks, such as focusing on technical implementation or innovative thinking; social background information The system can also extract information such as gender, place of origin and family background from the educational affairs system.

[0031] S4. Based on the project characteristic data and the personal characteristic data of each student, the matching degree between each student and the project to be taught is calculated.

[0032] Specifically, in step S4, the matching degree between the student and the item to be taught is calculated by Euclidean distance. Specifically, in this embodiment, the matching degree between any student and the item to be taught is: Matching Score ( )= ; In the formula, The project characteristic data; Personal characteristic data of any of the students; Personal characteristics data for any student Data related to the project characteristics The norm of the difference.

[0033] S5. According to the matching degree between each student and the item to be taught, the n students with the greatest matching degree with the item to be taught are set as group leaders, and the students other than the group leaders among the students to be taught are set as group members; wherein n is a natural number greater than 1, and n is the number of groups.

[0034] S6. Calculate the matching degree between each group member student and each group leader student based on the personal characteristic data of each group member student and the personal characteristic data of each group leader student among the students to be taught.

[0035] Specifically, as an implementation method of the matching degree between the group member students and the group leader students, in step S6 of this implementation, the cosine similarity is used to calculate the matching degree between the group member students and the group leader students. Specifically, the matching degree between any group member student and any group leader student is: Member Matching Score ( )= ; In the formula, For any of the group members Personal characteristics data; For any of the above group leaders Personal characteristics data; For any of the group members Personal characteristics data The norm of For any of the above group leaders Personal characteristics data The norm of .

[0036] As another implementation method of the matching degree between the team member students and the team leader students, in step S6 of this implementation, on the basis of using cosine similarity to calculate the matching degree between the team member students and the team leader students, the team pair preference value of the team member students is further introduced to improve the satisfaction of the team member students with the team formation results. Specifically, in this embodiment, the matching degree between any team member student and any team leader student is: Updated Score ( )= +λ( - ); In the formula, For any of the group members Personal characteristics data; For any of the above group leaders Personal characteristics data; For any of the group members Personal characteristics data The norm of For any of the above group leaders Personal characteristics data The norm of For any of the above group leaders A collection of students who have been assigned to the project team; For any of the group members Hope to meet with group members Another member student The preference value of the team; λ is the preset adjustment factor for the control preference weight. Specifically, the larger the λ value, the better the preference of any team member student. Priority is given to students who are members of the same group. Team up; For any of the group members Do not want to gather with group students Another member student The preference value of the team; Avoid biased weighting factors for preset controls, specifically, The larger the value, the more likely it is that any group of students Avoid sharing the same space with other group members Form a team.

[0037] It should be noted that, in this embodiment, the number of groups n can be pre-set by the teacher according to the teaching situation. After pre-setting an initial number of groups, further simulation is performed to obtain the optimal number of groups. In this process, the overall group matching degree under different numbers of groups can be simulated, and the number with the best overall group matching degree can be selected as the final value of the number of groups n.

[0038] In this embodiment, the overall group matching degree when the number of groups is different can be calculated based on the matching degree between the students and the teaching project obtained in step S4 and the matching degree between the group member students and the group leader student obtained in step S6. For example, the overall group matching degree when the number of groups is n is: Overall Score ( ) = + ; = ; = ; in, The number of groups is n When , the relative matching degree between all group leader students and the items to be taught is the sum; for n The sum of the matching degrees between the group leader students and the items to be taught; is the minimum value of the sum of the matching degrees between the group leader students and the teaching items under different numbers of groups; is the maximum value of the sum of the matching degrees between the group leader students and the teaching items under different numbers of groups; The number of groups is n When , the relative matching degree between all group members and the corresponding group leader is the sum of the matching degrees; The number of groups is n When , the sum of the matching degrees between all group members and the corresponding group leader students; It is the minimum value of the sum of the matching degrees between all group member students and the corresponding group leader students under different group numbers; It is the maximum value of the sum of matching degrees between all group member students and the corresponding group leader students under different group numbers; in, = , is the sum of the matching degrees between all students to be taught and the items to be taught; is the minimum value of the matching degree between all students to be taught and the items to be taught; is the maximum value of the matching degree between all students to be taught and the items to be taught; , is the sum of the matching degrees between all group member students and the corresponding group leader students when the number of groups is n; It is the minimum value of the matching degree between all group members and the corresponding group leader students in the group; It is the maximum value of the matching degree between all group members and the corresponding group leader students; In the formula, is the matching weight between the preset group leader student and the teaching project, The matching weight between the group member students and the group leader students in each preset group, and The default values ​​of are all 50%, which can be adjusted according to the priority factors of the project. It should also be noted that the overall group matching calculation formula adopts the standardized scoring method. By setting the relative value of the matching between the group leader student and the project to be taught, and the relative value of the matching between the student and the corresponding group leader student, the problem of extreme value deviation can be avoided.

[0039] During implementation, if the number of groups is n The overall group matching degree when is greater than the overall group matching degree when the number of groups is other values, then the number of groups is determined to be n Based on this, the optimal number of groups can be achieved, thereby further optimizing the grouping results.

[0040] S7. According to the matching degree between each group member student and each group leader student, each group member student is grouped to obtain n project groups. Specifically, in the implementation process of this embodiment, for any group leader student, each group member student is sorted from large to small according to the matching degree between the student and any group leader student, and according to the preset number of group students, multiple group members with the greatest matching degree are selected as members of any group leader student, and members of each group leader student are selected in a predetermined order, thereby completing the grouping of all group members.

[0041] In order to ensure the diversity and balance of personal characteristic data such as skills and interests of students within the project team, in step S7 of this embodiment, when grouping the team members according to the matching degree between each team member and each team leader, the obtained n project teams all meet the following constraints: ,and ; in, is the ability balance constraint value of each member student in the project team, , For any student in the project team skill score, is the total number of student members in the project team; is the interest similarity constraint value of each member student in the project team, , For any student in the project team The interest vector, Be the leader of the project team The interest vector.

[0042] It should be noted that the capacity balance constraint value It is used to ensure that the skills of the members of each project team are evenly distributed to avoid a project team with too strong or too weak skills. The default threshold is ±20%; interest similarity constraint value It is used to ensure that the interests of each project team member and the team leader match each other, so as to improve the teamwork efficiency in the project team. The default threshold is 70%.

[0043] This embodiment can improve the matching degree between students in each project team, and at the same time can simplify the operation process of student grouping, which is conducive to improving team collaboration efficiency; at the same time, this embodiment can realize comprehensive and automated project-based teaching management, which is conducive to teachers tracking project progress and student performance in real time, and can facilitate teachers to adjust teaching strategies in time. This embodiment obtains the project attribute information of the project to be taught and the personal attribute information of each student among the students to be taught, and encodes the project attribute information and the personal attribute information of each student based on the trained autoencoder to obtain the project feature data of the project to be taught and the personal feature data of each student; then, according to the project feature data and the personal feature data of each student, the matching degree between each student and the project to be taught is calculated, and then according to the matching degree between each student and the project to be taught, the identities of n students with the greatest matching degree with the project to be taught are set as group leaders, and the identities of students among the students to be taught except those with the identity of group leaders are set as group members; then, according to the personal feature data of each group member student who is a group member among the students to be taught and the personal feature data of each group leader student who is a group leader, the matching degree between each group member student and each group leader student is calculated; finally, according to the matching degree between each group member student and each group leader student, each group member student is grouped to obtain n project groups. In this process, this embodiment implements encoding processing of project attribute information and student personal attribute information in the trained autoencoder, selects the group leader student according to the matching degree between each student and the project to be taught, and further implements grouping of students according to the matching degree between each group member student and each group leader student. The matching degree between students in the project group is high, which can ensure that each group member student in each project group can form an effective collaborative relationship with the corresponding group leader student, thereby helping to improve the team collaboration efficiency within the project group. At the same time, automatic grouping can be realized, which simplifies the grouping process of teachers for project-based courses and has the value of promotion and application.

[0044] Embodiment 2: This embodiment discloses a project-based course teaching grouping system, which is used to implement the project-based course teaching grouping method in Example 1; Figure 2 As shown, the project-based course teaching grouping system includes: An autoencoder training module is used to obtain historical attribute information and use the historical attribute information to train an initial autoencoder to obtain a trained autoencoder; A first encoding module, which is in communication connection with the autoencoder training module, is used to obtain project attribute information of the project to be taught, and encode the project attribute information based on the trained autoencoder to obtain project feature data of the project to be taught; A second encoding module is connected to the autoencoder training module for obtaining personal attribute information of each student to be taught, and encoding the personal attribute information of each student based on the trained autoencoder to obtain personal feature data of each student; A group leader selection module is connected to the first encoding module and the second encoding module for calculating the matching degree between each student and the project to be taught according to the project characteristic data and the personal characteristic data of each student; and is also used to set the identities of n students with the greatest matching degree with the project to be taught as group leaders according to the matching degree between each student and the project to be taught, and set the identities of students other than the group leaders among the students to be taught as group members; wherein n is a natural number greater than 1; The group member grouping module is communicatively connected with the group leader selection module, and is used to calculate the matching degree between each group member student and each group leader student according to the personal characteristic data of each group member student and the personal characteristic data of each group leader student among the students to be taught; and is also used to group each group member student according to the matching degree between each group member student and each group leader student to obtain n project groups.

[0045] It should be noted that the working process, working details and technical effects of the project-based course teaching grouping system provided in this embodiment 2 can be found in embodiment 1 and will not be described in detail here.

[0046] Embodiment 3: Based on Embodiment 1 or 2, this embodiment discloses an electronic device, which may be a smart phone, a tablet computer, a laptop computer, or a desktop computer. The electronic device may be referred to as a user terminal, a portable terminal, a desktop terminal, etc. Figure 3 As shown, the electronic equipment includes: a memory for storing computer program instructions; and, A processor is used to execute the computer program instructions to complete the operation of a project-based course teaching grouping method as described in any one of Example 1.

[0047] Specifically, the processor 301 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 301 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 301 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 301 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen.

[0048] The memory 302 may include one or more computer-readable storage media, which may be non-transitory. The memory 302 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 302 is used to store at least one instruction, which is used to be executed by the processor 301 to implement the project-based course teaching grouping method provided in Example 1 of the present application.

[0049] In some embodiments, the terminal may further optionally include: a communication interface 303 and at least one peripheral device. The processor 301, the memory 302 and the communication interface 303 may be connected via a bus or a signal line. Each peripheral device may be connected to the communication interface 303 via a bus, a signal line or a circuit board. Specifically, the peripheral device includes: at least one of a radio frequency circuit 304, a display screen 305 and a power supply 306.

[0050] The communication interface 303 may be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 301 and the memory 302. In some embodiments, the processor 301, the memory 302, and the communication interface 303 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 301, the memory 302, and the communication interface 303 may be implemented on a separate chip or circuit board, which is not limited in this embodiment.

[0051] The radio frequency circuit 304 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 304 communicates with a communication network and other communication devices through electromagnetic signals.

[0052] The display screen 305 is used to display a UI (User Interface). The UI may include any combination of graphics, text, icons, and videos.

[0053] The power supply 306 is used to supply power to various components in the electronic device.

[0054] Embodiment 4: Based on any one of Embodiments 1 to 3, this embodiment discloses a computer program product, including a computer program or an instruction, which, when executed by a computer, implements a project-based course teaching grouping method as described in any one of Embodiments 1. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0055] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0056] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the above embodiments, a person skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features can be replaced by equivalents. 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 invention.

Claims

1. A project-based course teaching grouping method, characterized in that: include: Acquire historical attribute information, and use the historical attribute information to train an initial autoencoder to obtain a trained autoencoder; Acquire project attribute information of the project to be taught, and encode the project attribute information based on the trained autoencoder to obtain project feature data of the project to be taught; Obtaining personal attribute information of each student among the students to be taught, and encoding the personal attribute information of each student based on the trained autoencoder to obtain personal characteristic data of each student; Calculate the matching degree between each student and the to-be-taught project based on the project characteristic data and each student's personal characteristic data; According to the matching degree between each student and the teaching project, the n students with the greatest matching degree with the teaching project are set as group leaders, and the students other than the group leaders among the teaching students are set as group members; wherein n is a natural number greater than 1; According to the personal characteristic data of each group member student and the personal characteristic data of each group leader student among the students to be taught, the matching degree between each group member student and each group leader student is calculated; According to the matching degree between each group member student and each group leader student, each group member student is grouped to obtain n project groups.

2. A project-based course teaching grouping method according to claim 1, characterized in that: The initial autoencoder includes an initial encoder and an initial decoder; correspondingly, the initial autoencoder is trained using the historical attribute information to obtain a trained autoencoder, including: Inputting the historical attribute information into an initial encoder of the initial autoencoder, and obtaining low-dimensional feature data corresponding to the historical attribute information according to the initial encoder; Inputting the low-dimensional feature data into an initial decoder of the initial autoencoder, and obtaining reconstructed high-dimensional feature data corresponding to the historical attribute information according to the initial decoder; Based on a preset loss function, the mean square error between the historical attribute information and the reconstructed high-dimensional feature data is obtained, and the weight matrices in the initial encoder and the initial decoder are adjusted according to the mean square error until the preset autoencoder convergence condition is reached, thereby obtaining the trained autoencoder.

3. A project-based course teaching grouping method according to claim 2, characterized in that: The mapping function of the trained encoder in the trained autoencoder is: ； In the formula, is the preset activation function; is the weight matrix of the encoder after the training; is the preset encoding bias vector; is the information to be encoded which is input into the trained encoder, , is the total number of sub-information in the information to be encoded, is the dimension of the sub-information in the information to be encoded; is the low-dimensional feature data of the information to be encoded, , is the preset latent space dimension; The mapping function of the trained decoder in the trained autoencoder is: ； In the formula, is the weight matrix of the decoder after training; is the preset decoding bias vector; is the reconstructed high-dimensional feature data of the information to be encoded, ; The loss function is: ； In the formula, is the mean square error between the information to be encoded and its reconstructed high-dimensional feature data; is the first Child information and the reconstructed high-dimensional feature data Sub-characteristic data The norm of the difference.

4. A project-based course teaching grouping method according to claim 1, characterized in that: The matching degree between any student and the item to be taught is: Matching Score ( )= ； In the formula, The project characteristic data; Personal characteristic data of any of the students; Personal characteristics data for any student Data related to the project characteristics The norm of the difference.

5. A project-based course teaching grouping method according to claim 1, characterized in that: The matching degree between any group member student and any group leader student is: Member Matching Score ( )= ； In the formula, For any of the group members Personal characteristics data; For any of the above group leaders Personal characteristics data; For any of the group members Personal characteristics data The norm of ; For any of the above group leaders Personal characteristics data The norm of .

6. A project-based course teaching grouping method according to claim 1, characterized in that: The matching degree between any group member student and any group leader student is: Updated Score ( ) = +λ( - ); In the formula, For any of the group members Personal characteristics data; For any of the above group leaders Personal characteristics data; For any of the group members Personal characteristics data The norm of ; For any of the above group leaders Personal characteristics data The norm of ; For any of the above group leaders A collection of students who have been assigned to the project team; For any of the group members Hope to meet with group members Another member student The preference value of the team; λ is the adjustment factor of the preset control preference weight; For any of the group members Do not want to gather with group students Another member student The preference value of the team; Avoid preferred weighting factors for preset controls.

7. A project-based course teaching grouping method according to claim 1, characterized in that: According to the matching degree between each team member and each team leader, when grouping each team member, the n project teams obtained all meet the following constraints: ,and ; in, is the ability balance constraint value of each member student in the project team, , For any student in the project team skill score, is the total number of student members in the project team; is the interest similarity constraint value of each member student in the project team, , For any student in the project team The interest vector, Be the leader of the project team The interest vector.

8. A project-based course teaching grouping system, characterized in that: Used to implement a project-based course teaching grouping method as described in any one of claims 1 to 7; The project-based course teaching grouping system includes: An autoencoder training module is used to obtain historical attribute information and use the historical attribute information to train an initial autoencoder to obtain a trained autoencoder; A first encoding module, which is in communication connection with the autoencoder training module, is used to obtain project attribute information of the project to be taught, and encode the project attribute information based on the trained autoencoder to obtain project feature data of the project to be taught; A second encoding module is connected to the autoencoder training module for obtaining personal attribute information of each student to be taught, and encoding the personal attribute information of each student based on the trained autoencoder to obtain personal feature data of each student; A group leader selection module is connected to the first encoding module and the second encoding module for calculating the matching degree between each student and the project to be taught according to the project characteristic data and the personal characteristic data of each student; and is also used to set the identities of n students with the greatest matching degree with the project to be taught as group leaders according to the matching degree between each student and the project to be taught, and set the identities of students other than the group leaders among the students to be taught as group members; wherein n is a natural number greater than 1; The group member grouping module is communicatively connected with the group leader selection module, and is used to calculate the matching degree between each group member student and each group leader student according to the personal characteristic data of each group member student and the personal characteristic data of each group leader student among the students to be taught; and is also used to group each group member student according to the matching degree between each group member student and each group leader student to obtain n project groups.

9. An electronic device, characterized in that: include: a memory for storing computer program instructions; as well as, A processor is used to execute the computer program instructions to complete the operation of a project-based course teaching grouping method as described in any one of claims 1 to 7.

10. A computer program product comprising a computer program or instructions, characterized in that When the computer program or the instruction is executed by a computer, the computer program or the instruction implements a project-based course teaching grouping method as described in any one of claims 1 to 7.

Images