Student practice management system and method

Abstract

The invention relates to the technical field of education management, in particular to a student practice management system and method, and the system comprises a post distribution optimization module which carries out the weighted calculation based on the student practice intention and skill matching degree information, obtains the student priority score, carries out the sorting of all students according to the student priority score, and carries out the calculation of the student practice intention and skill matching degree information; and distributing posts according to the sorting result, and generating an internship post distribution result. According to the invention, through multi-dimensional data analysis of intentions, skill levels and post demands of the students, the students are subjected to priority ranking, and the most suitable posts are matched, so that the rationality and scientificity of resource allocation are ensured, and phenomena of post resource waste and non-uniform student allocation are reduced. Meanwhile, a classification boundary structure is constructed through standardized processing of the task completion rate and the attendance rate, the performance expressions of different classes of students are accurately recognized, and quantitative management and targeted tracking guidance can be achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of education management, and particularly to a student internship management system and method. Background Art

[0002] The technical field of education management is a comprehensive field that improves the efficiency and quality of education management through information technology, data management, and intelligent tools. This field mainly covers aspects such as student management, curriculum management, examination assessment, teaching resource allocation, and education decision-making.

[0003] Among them, the student internship management system is a digital system specifically used to manage and track the student internship process. Its main purpose is to help schools, enterprises, and students realize functions such as recording, approving, monitoring, and evaluating internship information. Therefore, schools can conveniently release internship information, assign internship tasks, and track the progress of students' internships in real time. Enterprises can manage the demand for internship positions, and students can apply for internships and record their internship achievements.

[0004] In the prior art, it is difficult to achieve precise matching of job resources in internship management, mainly relying on a single data dimension or manual subjective decision-making, resulting in often unreasonable allocation results. For example, the skill level of students does not match the job requirements, easily leading to highly skilled students being assigned to ordinary positions while high-demand job resources are wasted. In addition, it is difficult to dynamically track the internship process in the prior art, unable to promptly capture task progress and attendance anomalies, which easily causes management delays. For example, if a student's attendance interruption is not discovered in time, it will affect the completion of internship tasks and the overall evaluation. For performance evaluation, the prior art often lacks a unified standard and is difficult to classify and analyze students' performances, resulting in inaccurate and objective evaluation results. The cooperation between schools and enterprises also lacks a deep analysis and optimization mechanism, unable to effectively predict potential cooperation opportunities, with low efficiency in matching the supply and demand of cooperation resources, resulting in underutilization of enterprise positions. These problems make the internship management inefficient, with serious resource waste, and unable to achieve the overall optimization and management of the student internship process. Summary of the Invention

[0005] To solve the technical problems existing in the prior art, an embodiment of the present invention provides a student internship management system and method. The technical solution is as follows:

[0006] A student internship management system, the system includes: The job allocation optimization module calculates a weighted score based on the internship intention and skill matching degree information of students, obtains the student priority score, sorts all students according to the student priority score, and allocates jobs according to the sorting result to generate an internship job allocation result;

[0007] Based on the internship position allocation result, the student performance classification module obtains the task completion rate and attendance rate information of students during the internship, performs standardized processing, and classifies the student performance to generate the student performance classification result;

[0008] The internship data update module converts the student performance classification result into time-series data, updates the task progress and attendance status of students, and generates the internship dynamic data update result;

[0009] Based on the internship dynamic data update result, the enterprise cooperation optimization module forms an internship cooperation network between schools and enterprises by extracting all cooperation data between schools and enterprises and the corresponding relationship between job requirements and student allocation, predicts potential relationships according to the internship cooperation network, and obtains the enterprise cooperation relationship prediction result;

[0010] The job resource feedback module analyzes the utilization rate of job resources and the satisfaction rate of student needs according to the enterprise cooperation relationship prediction result, verifies the balance of job allocation, and evaluates the stability of cooperation nodes to generate the internship resource allocation feedback result.

[0011] The improvements of the present invention are as follows: the internship position allocation result includes the student priority score, the position allocation list, the list of unallocated students, and the remaining job resource pool; the student performance classification result includes the classification of student task completion rate, attendance rate classification, enterprise feedback score classification, and the confidence level of each category classification; the internship dynamic data update result includes time-series task progress data, time-series attendance record data, abnormal task progress marks, and attendance interruption marks; the enterprise cooperation relationship prediction result includes the school-enterprise cooperation node list, the node matching degree sorting result, the potential cooperation node prediction list, and the node edge weight information; the internship resource allocation feedback result includes the analysis of job resource utilization rate, the analysis of student demand satisfaction rate, the verification result of job allocation balance, and the abnormal configuration data mark.

[0012] The improvements of the present invention are as follows: the job allocation optimization module includes:

[0013] The data collection and scoring sub-module collects the internship intention data, skill level data, and job requirement data of students, performs priority scoring based on the weights of the data, and generates the student priority score result;

[0014] The job matching and allocation sub-module sorts the students according to the student priority score result, selects the student with the highest score, obtains the remaining internship position data, sorts them according to the matching degree between student skills and job requirements, and selects the optimal position for allocation to generate the position allocation list;

[0015] Based on the job assignment list, the resource pool update sub-module removes the assigned jobs from the job resource pool, updates the unassigned student list and the remaining job resource data, and generates the internship job assignment result.

[0016] The improvement of the present invention is that for the setting, a priority score is calculated using the formula:

[0017] P = ∑(S i ·W 1 +K i ·W 2 )

[0018] Obtain the student priority score P;

[0019] Wherein, S i is the internship intention score of the i-th student, K i is the skill level score of the i-th student, W 1 is the weight of the internship intention score, W 2 is the weight of the skill level score.

[0020] The improvement of the present invention is that the student performance classification module includes:

[0021] The data standardization processing sub-module obtains the task completion rate and attendance information during the students' internship based on the internship job assignment result, standardizes the data, and generates a standardized data set;

[0022] The classification boundary construction sub-module constructs a classification boundary using the task completion rate and attendance data based on the standardized data set, divides the data into multiple classification intervals, and generates a classification boundary structure;

[0023] The student classification and recognition sub-module inputs the standardized data set into the classification boundary based on the classification boundary structure, classifies the students' performance, and identifies the performance of each category of students according to the confidence level of each classification, generating a student performance classification result.

[0024] The improvement of the present invention is that the internship data update module includes:

[0025] The time series conversion sub-module converts the task completion rate and attendance information into time series data based on the student performance classification result, generating a time series data conversion result;

[0026] The sliding window capture sub-module sets the time range and step size of the sliding window based on the time series data conversion result, captures and integrates the time series data in segments, deletes the expired data and appends new data, generating a sliding window data update result;

[0027] Based on the updated results of the sliding window data, the abnormal attendance data identification sub-module checks the task progress and attendance record data item by item, identifies abnormal situations such as sudden changes in task progress and attendance interruptions, marks them, and generates the updated results of the internship dynamic data.

[0028] The improvements of the present invention include that the enterprise cooperation optimization module includes:

[0029] The cooperation data extraction sub-module extracts all cooperation data between schools and enterprises based on the updated results of the internship dynamic data, including the correspondence between job requirements and student allocation, and generates the cooperation data analysis results;

[0030] The cooperation network construction sub-module constructs the internship cooperation network between schools and enterprises based on the cooperation data analysis results and the cooperation data extraction results. The nodes in the network represent the enterprise internship job requirements and the number of school students, and the edge weights represent the cooperation frequency and duration, generating the internship cooperation network structure;

[0031] The potential node screening sub-module, based on the internship cooperation network structure, calculates the matching degree between schools and enterprises, screens the node pairs with the highest matching degree scores, outputs the prediction list of potential cooperation nodes, and generates the enterprise cooperation relationship prediction results.

[0032] The improvements of the present invention include that for calculating the matching degree between schools and enterprises, the formula is adopted:

[0033]

[0034] Obtain the matching degree score M ij ;

[0035] Among them, N ij represents the number of students provided by school i to enterprise j, T ij represents the average internship duration of students in enterprise j, F ij is the cooperation adjustment factor set according to school i and enterprise j, S i represents the total number of students in school i, D j represents the total job requirements provided by enterprise j, and R j represents the actual job utilization rate of enterprise j.

[0036] The improvements of the present invention include that the job resource feedback module includes:

[0037] The resource utilization analysis sub-module obtains the matching situation between job resource allocation and student needs based on the enterprise cooperation relationship prediction results, analyzes the utilization rate of job resources and the satisfaction rate of student needs, and generates the resource utilization analysis results;

[0038] The allocation balance parity check sub-module checks the balance of job resource allocation based on the resource utilization analysis result, identifies the situation of uneven job resource allocation according to the allocation ratio of job resources between the student group and the enterprise demand, and generates an allocation balance check result;

[0039] The abnormal resource configuration data capture sub-module captures the abnormal data and allocation imbalance situations that occur during the internship resource configuration process based on the allocation balance check result, including the problems of idle job resources and student allocation conflicts, and generates an internship resource configuration feedback result.

[0040] A student internship management method, which is executed based on the above-mentioned student internship management system, includes the following steps:

[0041] S1: Based on the internship intention, skill level and job demand data of students, calculate the weighted student priority score, allocate jobs according to the score ranking and update the resource pool, and generate an internship job allocation result;

[0042] S2: Based on the internship job allocation result, obtain the task completion rate and attendance rate data, perform standardization processing and then classify the student performance, and generate a student performance classification result;

[0043] S3: Based on the student performance classification result, convert the task completion rate and attendance rate into time series data, set a sliding window to capture and update the data, identify abnormal tasks or attendance situations, and generate an internship dynamic data update result;

[0044] S4: Based on the internship dynamic data update result, extract the school-enterprise cooperation data, construct an internship cooperation network, calculate the matching degree and screen potential cooperation nodes, evaluate the resource utilization and allocation situation, and generate an internship resource configuration feedback result.

[0045] The beneficial effects brought by the technical solution provided by the embodiment of the present invention at least include:

[0046] Through multi-dimensional data analysis of students' intentions, skill levels, and job requirements, students are prioritized and matched with the most suitable jobs, ensuring the rationality and scientific nature of resource allocation, and reducing the phenomena of job resource waste and uneven student distribution. At the same time, through the standardization of task completion rates and attendance rates, a classification boundary structure is constructed to accurately identify the performance of different categories of students, which helps to achieve quantitative management and targeted tracking and guidance. The time series data conversion and sliding window mechanism can dynamically capture changes in internship data, quickly identify problems such as abnormal attendance and sudden changes in task progress, ensuring management timeliness and the high efficiency of problem-solving. In addition, the construction of the cooperation network and the screening of potential nodes optimize the cooperation relationship between schools and enterprises. By calculating the matching degree to screen high-potential nodes, the job demand satisfaction rate and cooperation depth are further improved. The analysis mechanism of job resource utilization rate and allocation balance effectively solves the problems of uneven resource allocation and job idleness, making the overall resource allocation more efficient. Description of the Drawings

[0047] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0048] Figure 1 It is a system module diagram of the present invention;

[0049] Figure 2 It is a system framework diagram of the present invention;

[0050] Figure 3 It is a schematic diagram of the job allocation optimization module of the present invention;

[0051] Figure 4 It is a schematic diagram of the student performance classification module of the present invention;

[0052] Figure 5 It is a schematic diagram of the internship data update module of the present invention;

[0053] Figure 6 It is a schematic diagram of the enterprise cooperation optimization module of the present invention;

[0054] Figure 7 It is a schematic diagram of the job resource feedback module of the present invention;

[0055] Figure 8 It is a method flow chart of the present invention. Detailed Embodiments

[0056] The following will describe the technical solutions in the present invention in conjunction with the drawings.

[0057] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as an "example" in the present invention should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, the use of the word "example" is intended to present concepts in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two can be selected.

[0058] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, the meanings they express are the same. "(of)", "corresponding", and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, the meanings they express are the same.

[0059] In the embodiments of the present invention, sometimes subscripts such as W 1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meanings they express are the same.

[0060] To make the technical problems to be solved, technical solutions and advantages of the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments.

[0061] The embodiments of the present invention provide a student internship management system, which includes: a job assignment optimization module that calculates weights based on the internship intentions and skill matching degree information of students, obtains student priority scores, sorts all students according to the student priority scores, and assigns jobs according to the sorting results to generate internship job assignment results;

[0062] A student performance classification module obtains the task completion rate and attendance information of students during the internship based on the internship job assignment results, performs standardization processing, and classifies student performance to generate student performance classification results;

[0063] An internship data update module converts the student performance classification results into time series data, updates the task progress and attendance status of students, and generates internship dynamic data update results;

[0064] An enterprise cooperation optimization module forms an internship cooperation network between schools and enterprises based on the internship dynamic data update results by extracting all cooperation data between schools and enterprises and the corresponding relationship between job requirements and student assignments, predicts potential relationships according to the internship cooperation network, and obtains enterprise cooperation relationship prediction results;

[0065] The job resource feedback module analyzes the utilization rate of job resources and the satisfaction rate of student needs based on the prediction results of enterprise cooperation relationships, verifies the balance of job allocation, evaluates the stability of cooperation nodes, and generates the feedback results of internship resource allocation.

[0066] The internship job allocation results include the student priority scores, job allocation lists, unallocated student lists, and remaining job resource pools. The student performance classification results include the classification of student task completion rates, attendance rates, enterprise feedback score classifications, and the confidence levels of each category classification. The internship dynamic data update results include time series task progress data, time series attendance record data, abnormal task progress markers, and attendance interruption markers. The enterprise cooperation relationship prediction results include the school-enterprise cooperation node lists, node matching degree sorting results, potential cooperation node prediction lists, and node edge weight information. The internship resource allocation feedback results include the analysis of job resource utilization rates, the analysis of student need satisfaction rates, the verification results of job allocation balance, and abnormal configuration data markers.

[0067] Please refer to Figure 2 and Figure 3 , the job allocation optimization module includes:

[0068] The data collection and scoring sub-module collects the internship intention data, skill level data, and job requirement data of students, performs priority scoring based on the weight setting of the data, and generates the student priority scoring results;

[0069] For priority scoring, the formula is used:

[0070] P = ∑(S i ·W 1 +K i ·W 2 )

[0071] Obtain the student priority score P;

[0072] Among them, S i is the internship intention score of the i-th student, obtained through a questionnaire survey. The five-point scoring method is used: very willing = 5, willing = 4, moderate = 3, unwilling = 2, very unwilling = 1. K i is the skill level score of the i-th student, obtained through a skills test. The quantification range is 0-10 points. The test content can include programming ability, technical operation, theoretical understanding, etc. required for the job, and is converted to a score between 0-10 points according to the proportion of the score of the questions in the total score. W 1 is the weight of the internship intention score, determined by analyzing historical matching data based on the proportion of the impact of the internship intention on the allocation result. W 2 is the weight of the skill level score, determined by experimentally analyzing the impact of the matching degree between the skill level and job requirements on the allocation success rate. For W1 and W 2 , assuming that by statistically analyzing the past successfully matched data, it is found that the skill level contributes more to the allocation result. Therefore, set W 1 = 0.4, W 2 = 0.6.

[0073] If the intention score S of student A i = 4, and the skill level score K i = 8.5, with weights W 1 = 0.4, W 2 = 0.6, then: P = (4·0.4) + (8.5·0.6) = 6.7. The result shows that the priority score of student A is 6.7.

[0074] The job matching and allocation sub-module sorts the students according to the student priority score results, selects the student with the highest score, obtains the remaining internship job data, sorts according to the matching degree between the student skills and job requirements, selects the optimal job for allocation, and generates a job allocation list;

[0075] All students are sorted from high to low according to their scores. The sorting process is implemented through programming tools such as the pandas library in Python. Read the priority score data table of all students and sort them in descending order of scores. Then select the information of the student with the current highest score and read the data from the job resource database. The job database contains parameters such as the skill level required for the job, the remaining job capacity, and the job time requirements. For the comparison of the skills required for the job, the absolute difference between the skill level score and the skill level required for the job is used to measure the matching degree. By traversing and comparing the matching degrees of all remaining jobs, select the job with the smallest matching degree as the optimal job for the current student, allocate the student to the job, update the remaining job capacity data at the same time, and record this allocation information in the job allocation list. The job resource data is updated in real time through database operation tools such as the UPDATE command in SQL. Subtract 1 from the current remaining job capacity and mark the current student status as allocated.

[0076] The resource pool update sub-module removes the allocated jobs from the job resource pool based on the job allocation list, updates the list of unallocated students and the remaining job resource data, and generates the internship job allocation result;

[0077] Read the numbers of the assigned positions and the allocation data of the associated students, and sequentially remove these positions from the position resource data table. During the operation, use database operation tools such as SQL to clear the assigned position records. Then update the list of unassigned students. By comparing the position allocation records with the student data table, filter out the students who still do not have assigned positions currently, and summarize their information back into the list of unassigned students. At the same time, read the remaining position resource data table, obtain the required skill levels, the number of positions, and the position duration data of the current positions, and use statistical tools such as Excel to classify and summarize the remaining position resource data, and re - count parameters such as the remaining number of each position and the corresponding skill requirement levels to ensure that the list of unassigned students and the remaining position resource data are kept in real - time correspondence, and finally generate the updated remaining position resource data and the list of unassigned students.

[0078] Please refer to Figure 2 and Figure 4 , the student performance classification module includes:

[0079] The data standardization processing sub - module, based on the internship position allocation results, obtains the task completion rate and attendance rate information of students during the internship, standardizes the data, and generates a standardized data set;

[0080] Obtain the task completion rate and attendance rate information of students during the internship. The task completion rate calculates the ratio of the number of completed tasks to the total number of tasks by counting the task completion status recorded in the daily task assignment system. The attendance rate calculates the ratio of the actual attendance days of each student to the number of days in the internship period through the internship attendance system. After the data acquisition is completed, export the original data of the task completion rate and attendance rate to a data table in Excel tools or Python for standardization processing. The processing process includes cleaning missing values, removing outliers, and normalization transformation. During the normalization process, the data of the task completion rate and attendance rate are uniformly scaled to the range of 0 - 1 to facilitate the unified standard for subsequent analysis. Finally, generate a standardized data set. For example, if a student's task completion rate is 80% and the attendance rate is 90%, the standardized data is 0.8 and 0.9, and the data set is stored in a data management file for further analysis.

[0081] The classification boundary construction sub - module, based on the standardized data set, uses the task completion rate and attendance rate data to construct a classification boundary, and divides the data into multiple classification intervals to generate a classification boundary structure;

[0082] First, sort the student data according to the distribution of task completion rate and attendance rate. Use the quantile method to divide the data into three categories of intervals. For example, a task completion rate greater than 85% and an attendance rate greater than 90% are defined as the high-performance interval. A task completion rate between 60% - 85% and an attendance rate between 70% - 90% are defined as the medium-performance interval. A task completion rate lower than 60% or an attendance rate lower than 70% is defined as the low-performance interval. Then, the system traverses the standardized data of students one by one, classifies the students' data according to the interval thresholds of the classification boundaries, and constructs a classification boundary structure. The classification boundary structure records the upper and lower limits of each category of intervals and the corresponding performance category labels. For example, if a student's standardized data is 0.88 and 0.92, which meets the conditions of the high-performance interval, the student is classified into the high-performance category, and a structure file containing the classification boundary and classification results is generated.

[0083] Based on the classification boundary structure, the student classification and recognition sub-module inputs the standardized data set into the classification boundary, classifies the students' performance, and identifies the performance of students in each category according to the confidence level of each classification, generating the student performance classification results.

[0084] Input the task completion rate and attendance rate in the standardized data set into the classification boundary one by one for classification and recognition. The system compares the students' data with the thresholds of the classification boundary item by item to determine the students' performance categories. After classification, count the number of students and distribution density in each category. For example, among a group of intern students, 15 are classified into the high-performance category, 25 into the medium-performance category, and 10 into the low-performance category. Through the analysis of the performance classification results, identify the performance of students in different categories. For students in the high-performance category, the management can give priority to recommending positions or opportunities for internship conversion. For students in the low-performance category, the internship progress can be strengthened by task decomposition and tracking. Finally, generate a student performance classification file containing the classification results and performance, which is convenient for differential management of students in different categories during the internship management process.

[0085] Please refer to Figure 2 and Figure 5 , the internship data update module includes:

[0086] Based on the student performance classification results, the time series conversion sub-module converts the task completion rate and attendance rate information into time-series data, generating the time series data conversion results.

[0087] First, sort the task completion rate and attendance rate data according to the daily record time. The time stamp records the data from the start date of the internship to the current date. Fill in the data for the unrecorded days through linear interpolation to ensure data continuity, and integrate the daily task completion rate and attendance rate into time series data. For example, from the 1st day to the 5th day of a student's internship, the task completion rates are 60%, 70%, 80%, missing, 90% respectively. Through linear interpolation, the task completion rate on the 4th day is supplemented to 85%, and the corresponding attendance rate data are 100%, 100%, 90%, 100%, 90%. Finally, generate time series data arranged in chronological order for subsequent window analysis.

[0088] Based on the time series data conversion result, the sliding window capture sub-module sets the time range and step size of the sliding window, captures and integrates the time series data in segments, deletes the expired data and appends new data to generate the sliding window data update result;

[0089] Set the time range and step size of the sliding window, capture and integrate the time series data in segments. The time range is set to 7 consecutive days, and the step size is 1 day. Each time the window slides, it moves forward 1 day. The data within the sliding window range is intercepted and integrated. The invalid records and expired records in the data are deleted, and at the same time, new data is appended to the time series data. For example, a student's task completion rates from the 1st to the 7th day are 70%, 75%, 80%, 85%, 90%, 95%, 100%, and the attendance rates are 100%, 100%, 90%, 90%, 80%, 100%, 100%. When the window slides forward to the 2nd - 8th day, the data on the 1st day is deleted, and the task completion rate and attendance rate data on the 8th day are appended to achieve real-time update and management of the data, generating the sliding window data update result.

[0090] Based on the sliding window data update result, the abnormal attendance data identification sub-module checks the task progress and attendance record data item by item, identifies the abnormal situations of sudden changes in task progress and attendance interruptions and marks them to generate the internship dynamic data update result;

[0091] Check the task progress and attendance record data item by item to identify abnormal situations of sudden changes in task progress and attendance interruptions. The sudden change in task progress is identified by comparing the change range of the task completion rate for adjacent days within a sliding window. If the change exceeds the set threshold (for example, the daily change in the task completion rate exceeds 30%), it is marked as an abnormal task progress. Attendance interruption is identified by counting the number of consecutive absent days. If the attendance rate is lower than 50% for 2 consecutive days or more, it is marked as abnormal attendance. For example, a student's task completion rate on the 3rd day is 80%, and it drops suddenly to 40% on the 4th day, with a change range of 50%, which is marked as an abnormal task progress. In the attendance rate record, the attendance rates on the 6th and 7th days are both lower than 50% (40% and 30%), and the student is marked as having an abnormal attendance interruption. The abnormal records are stored in a data file for the internship management party to view and process in a timely manner, providing specific basis for the management of students with low performance.

[0092] Please refer to Figure 2 and Figure 6 , the enterprise cooperation optimization module includes:

[0093] The cooperation data extraction sub-module extracts all cooperation data between the school and the enterprise based on the updated results of the internship dynamic data, including the corresponding relationship between job requirements and student allocation, and generates the cooperation data analysis results;

[0094] Extract the cooperation data between the school and the enterprise. Read the data file through data analysis tools such as the Pandas library in Python, extract the job requirement data and student allocation situation. The job requirement data includes the job names, job quantities, job durations, etc. provided by the enterprise. The student allocation situation includes the number of students allocated by the school to each enterprise, the internship duration, and the task completion ratio. Correlate and match the two types of data, summarize and organize them according to the corresponding relationship between the enterprise and the school, and use grouping and aggregation functions to count the data for each enterprise and school. For example, calculate the total number of allocated students and the cooperation duration for each enterprise, export and store these data in a cooperation data table, ensure data deduplication and format standardization processing, and generate the cooperation data analysis results.

[0095] The cooperation network construction sub-module constructs the internship cooperation network between the school and the enterprise based on the cooperation data analysis results. The nodes in the network represent the enterprise internship job requirements and the number of school students, and the edge weights represent the cooperation frequency and duration, generating the internship cooperation network structure;

[0096] Extract the information on the internship position requirements of enterprises and the number of students in schools, and use the graph data structure to construct an internship cooperation network between schools and enterprises. The network nodes are created by counting the total demand for positions in each enterprise and the total number of allocated students in schools. The weights of the edges are assigned based on the cooperation frequency and the internship duration. The cooperation frequency is obtained by counting the number of past collaborations between enterprises and schools, and the internship duration is accumulated by the total number of internship days for each position. For example, if an enterprise has collaborated with a school 10 times in the past 3 years and the total internship days for the positions are 900 days, the weight of the edge is obtained by combining the cooperation frequency and the internship duration. Then, the information of these nodes and edges is input into a graph data analysis tool such as NetworkX to generate the network structure, and the relationship between each node and edge in the graph structure is recorded in a data file to display the internship cooperation network relationship between schools and enterprises.

[0097] Based on the internship cooperation network structure, the potential node screening sub-module calculates the matching degree between schools and enterprises, screens the pair of nodes with the highest matching degree score, outputs a prediction list of potential cooperation nodes, and generates a prediction result of enterprise cooperation relationships.

[0098] For calculating the matching degree between schools and enterprises, the formula is adopted:

[0099]

[0100] Obtain the matching degree score M ij , which is used to compare the cooperation potential of different schools and enterprises. The higher the matching degree score, the better the cooperation performance.

[0101] Among them, N ij represents the number of students provided by school i to enterprise j, which is obtained from the school internship management data. For example, by counting from the student position allocation records, if school A has allocated 50 students to enterprise X, then N ij = 50, T ij represents the average internship duration of students in enterprise j, in days, which is calculated by counting the difference between the start time and end time of students' internships. The time records can be extracted from the enterprise internship attendance system. For example, if the average duration is 90 days, then T ij = 90, F ij is a cooperation adjustment factor set according to school i and enterprise j, which represents the comprehensive performance of the task completion rate and attendance rate of students during their internships in enterprise j, and is obtained by taking the average of the task completion rate and attendance rate during the internship period. For example, if a student's task completion rate is 80% and the attendance rate is 90%, then: S i represents the total number of students in school i, which is obtained from the school annual statistical data. For example, if school A has a total of 1000 students, then S i = 1000, D jDenotes the total number of job requirements provided by enterprise j, obtained from the enterprise recruitment demand record. For example, if enterprise X provides 200 job positions, then D j = 200, R j Denotes the actual job utilization rate of enterprise j, reflecting the saturation degree of job requirements, obtained by the ratio of the number of students actually arranged by the enterprise to the number of job requirements. For example, if enterprise X actually arranges 180 students and the total number of job requirements is 200, then:

[0102] Taking school A and enterprise X as an example, substituting specific parameters: N ij = 50, T ij = 90, F ij = 0.85, S i = 1000, D j = 200, R j = 0.9, calculate the matching degree score:

[0103]

[0104] The results show that the matching degree score between school A and enterprise X is 0.02125. Assuming that among the matching degree calculation results of school A, B, C and enterprise X, Y, Z, the node pairs with the highest matching degree include the matching degree score between school A and enterprise X being 0.028, the matching degree score between school B and enterprise Y being 0.025, and the matching degree score between school C and enterprise Z being 0.021. Record these node pairs in the prediction list and output the prediction results of potential cooperation nodes. The result list is as follows: School A - Enterprise X, matching degree score: 0.02125, School B - Enterprise Y, matching degree score: 0.0198, School C - Enterprise Z, matching degree score: 0.0189. The node pairs in the prediction list represent the potential cooperation relationships between schools and enterprises. The node pairs with higher matching degree scores have better cooperation potential. The matching degree score between school A and enterprise X is the highest, indicating that the number of student allocations, task completion rates and attendance rates of this school are highly matched with the enterprise job requirements and job saturation rates in actual cooperation. It is recommended to prioritize the allocation and expansion of cooperation resources.

[0105] Please refer to Figure 2 and Figure 7 , the job resource feedback module includes:

[0106] The resource utilization analysis sub-module, based on the prediction results of enterprise cooperation relationships, obtains the matching situation between job resource allocation and student requirements, analyzes the utilization rate of job resources and the satisfaction rate of student requirements, and generates resource utilization analysis results;

[0107] First, extract the total amount of job resources for each enterprise and the total demand for students in schools from the partnership data. The total amount of job resources is counted by the number of jobs provided by the enterprise, and the total demand for students is obtained by summarizing the internship allocation requirements of the school. The matching process compares the actual situation of job resource allocation to students with the demand ratio, calculates the job resource utilization rate and the student demand satisfaction rate, classifies and summarizes the data, and stores it in the analysis result table. By comparing the student allocation requirements with the actual job utilization situation, identify the situations of over-allocation or under-allocation of job resources, and generate the resource utilization analysis result. The data includes the specific values of the job resource utilization rate for each enterprise and the student demand satisfaction rate for the school.

[0108] Based on the resource utilization analysis result, the allocation balance verification sub-module verifies the balance of job resource allocation, identifies the situations of uneven job resource allocation according to the allocation ratio of job resources between the student group and the enterprise demand, and generates the allocation balance verification result.

[0109] First, classify and count the ratio of the actual number of allocated jobs to the total number of demanded jobs for job resources by enterprise, and compare the data with the number of students allocated to each school. Screen the balance of job resource allocation through the difference in the allocation ratio, and identify the situations of excessive or insufficient allocated resources. For the enterprises or schools with uneven allocation, mark their data separately and output it to the verification result table. For example, for enterprise A, the actual number of allocated jobs accounts for 90% of the demand ratio, but the proportion of students allocated to this enterprise by school B is only 60%, resulting in an imbalance between the job resource utilization rate and the student allocation ratio, and generate the allocation balance verification result.

[0110] Based on the allocation balance verification result, the abnormal resource configuration data capture sub-module captures the abnormal data and allocation imbalance situations that occur during the internship resource configuration process, including the problems of idle job resources and student allocation conflicts, and generates the internship resource configuration feedback result.

[0111] First, screen the data with a job resource utilization rate lower than 70% to identify the corresponding information of the enterprises and schools with idle job resources. Then, check the student allocation conflict situation. By comparing the allocation data of each school with the job demand of the enterprise, screen the conflict data of students being allocated to multiple jobs or not being allocated jobs. Classify and mark the abnormal data, and output the resource configuration abnormal result table. The data includes the job idle rate and the abnormal points of student allocation. For example, enterprise B provides 100 jobs but only allocates 70 people, and the job idle rate reaches 30%. At the same time, it is found that student X is allocated to the jobs of two different enterprises, and generate the internship resource configuration feedback result for further adjusting the job resources and student allocation situation.

[0112] Please refer to Figure 8, a student internship management method, which is executed based on the above-mentioned student internship management system, and includes the following steps:

[0113] S1: Based on the internship intention, skill level and job requirement data of students, calculate the weighted student priority score, allocate jobs according to the score ranking and update the resource pool, and generate the internship job allocation result;

[0114] S2: Based on the internship job allocation result, obtain the task completion rate and attendance rate data, perform standardized processing and then classify the student performance, and generate the student performance classification result;

[0115] S3: Based on the student performance classification result, convert the task completion rate and attendance rate into time series data, set a sliding window to capture and update the data, identify abnormal tasks or attendance situations, and generate the internship dynamic data update result;

[0116] S4: Based on the internship dynamic data update result, extract the school-enterprise cooperation data, construct an internship cooperation network, calculate the matching degree and screen potential cooperation nodes, evaluate the resource utilization and allocation situation, and generate the internship resource configuration feedback result.

[0117] It should be understood that the term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. These three situations, where A and B can be singular or plural. In addition, the character " / " in this article generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood by referring to the context.

[0118] In the present invention, "at least one" means one or more, and "a plurality" means two or more. "At least one (item)" or similar expressions thereof refer to any combination of these items, including any combination of single item (item) or plural items (items). For example, at least one (item) of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0119] It should be understood that in various embodiments of the present invention, the magnitudes of the sequence numbers of the above processes do not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0120] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0121] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described devices, apparatuses, and units can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0122] In several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the devices or units can be in an electrical, mechanical, or other form.

[0123] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0124] In addition, the functional units in each embodiment of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0125] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0126] As described above, the above are only specific implementation manners of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A student internship management system, characterized in that: The system comprises: The job allocation optimization module performs weighted calculation based on students' internship intention and skill matching information, obtains student priority scores, sorts all students according to their priority scores, and allocates jobs based on the sorting results to generate internship job allocation results; The student performance classification module obtains the task completion rate and attendance rate information of the students during the internship based on the internship position allocation result, performs standardization processing, classifies the student performance, and generates the student performance classification result; The internship data update module converts the student performance classification results into time series data, updates the student's task progress and attendance status, and generates internship dynamic data update results; The enterprise cooperation optimization module is based on the update result of the internship dynamic data, and forms an internship cooperation network between the school and the enterprise by extracting all the cooperation data between the school and the enterprise and the corresponding relationship between the job requirements and the student allocation situation, and predicts the potential relationship based on the internship cooperation network to obtain the enterprise cooperation relationship prediction result; The job resource feedback module analyzes the utilization rate of job resources and the satisfaction rate of student needs according to the enterprise cooperation relationship prediction results, verifies the balance of job allocation and evaluates the stability of cooperation nodes, and generates internship resource configuration feedback results.

2. The student internship management system according to claim 1, characterized in that: The internship position allocation results include student priority scores, position allocation lists, unassigned student lists and remaining position resource pools; the student performance classification results include student task completion rate classification, attendance rate classification, enterprise feedback score classification and confidence in each category classification; the internship dynamic data update results include time series task progress data, time series attendance record data, abnormal task progress marks and attendance interruption marks; the enterprise partnership prediction results include a list of school and enterprise cooperation nodes, node matching ranking results, a potential cooperation node prediction list and node edge weight information; the internship resource configuration feedback results include position resource utilization analysis, student demand satisfaction rate analysis, position allocation balance verification results and abnormal configuration data markings.

3. The student internship management system according to claim 1, characterized in that: The job allocation optimization module includes: The data collection and scoring submodule collects students' internship intention data, skill level data, and job requirement data, and performs priority scoring based on the weight setting of the data to generate student priority scoring results; The job matching and allocation submodule sorts the students according to the priority scores based on the student priority scoring results, selects the students with the highest scores, obtains the remaining internship job data, sorts them according to the matching degree between the students' skills and the job requirements, selects the best job for allocation, and generates a job allocation list; Based on the job allocation list, the resource pool update submodule removes the assigned jobs from the job resource pool, updates the unassigned student list and the remaining job resource data, and generates internship job allocation results.

4. The student internship management system according to claim 3, characterized in that: For setting priority scoring, the formula is used: P=∑(S i ·W1+K i ·W2) Get the student priority score P; Among them, S i is the internship intention score of the i-th student, K i is the skill level score of the ith student, W1 is the weight of the internship intention score, and W2 is the weight of the skill level score.

5. The student internship management system according to claim 1, characterized in that: The student performance classification module includes: The data standardization processing submodule obtains the task completion rate and attendance rate information of the students during the internship based on the internship position allocation results, standardizes the data, and generates a standardized data set; The classification boundary construction submodule constructs the classification boundary based on the standardized data set and uses the task completion rate and attendance rate data, and divides the data into multiple classification intervals to generate a classification boundary structure; The student classification identification submodule inputs the standardized data set into the classification boundary based on the classification boundary structure, classifies the student performance, and identifies the performance of each category of students according to the confidence of each classification to generate the student performance classification results.

6. The student internship management system according to claim 1, characterized in that: The internship data updating module comprises: The time series conversion submodule converts the task completion rate and attendance rate information into time series data based on the student performance classification result, and generates a time series data conversion result; The sliding window capture submodule sets the time range and step size of the sliding window based on the time series data conversion result, captures and integrates the time series data in segments, deletes expired data and appends new data, and generates a sliding window data update result; Based on the sliding window data update results, the abnormal attendance data identification submodule checks the task progress and attendance record data item by item, identifies and marks abnormal changes in task progress and attendance interruptions, and generates internship dynamic data update results.

7. The student internship management system according to claim 1, characterized in that: The enterprise cooperation optimization module includes: The cooperation data extraction submodule extracts all cooperation data between the school and the enterprise based on the internship dynamic data update result, including the correspondence between job requirements and student allocation, and generates cooperation data analysis results; The cooperation network construction submodule constructs an internship cooperation network between schools and enterprises based on the cooperation data analysis results and the cooperation data extraction results. The nodes in the network represent the internship job requirements of enterprises and the number of students in schools, and the edge weights represent the frequency and duration of cooperation, thereby generating an internship cooperation network structure. The potential node screening submodule is based on the internship cooperation network structure, calculates the matching degree between schools and enterprises, screens the node pairs with the highest matching scores, outputs a predicted list of potential cooperation nodes, and generates enterprise cooperation relationship prediction results.

8. The student internship management system according to claim 7, characterized in that: To calculate the matching degree between schools and enterprises, the formula is used: Get the matching score M ij ; Among them, N ij represents the number of students provided by school i to enterprise j, T ij represents the average duration of internship of students in enterprise j, F ij is the cooperation adjustment factor set according to school i and enterprise j, S i represents the total number of students in school i, D j represents the total number of job requirements provided by enterprise j, R j Represents the actual job utilization rate of enterprise j.

9. The student internship management system according to claim 1, characterized in that: The post resource feedback module includes: The resource utilization analysis submodule obtains the matching of job resource allocation and student demand based on the enterprise cooperation relationship prediction results, analyzes the utilization rate of job resources and the satisfaction rate of student demand, and generates resource utilization analysis results; The distribution balance verification submodule verifies the balance of job resource allocation based on the resource utilization analysis result, identifies the uneven distribution of job resources according to the distribution ratio of job resources between the student group and the enterprise demand, and generates a distribution balance verification result; The abnormal resource configuration data capture submodule captures abnormal data and allocation imbalances that occur during the internship resource configuration process based on the allocation balance verification results, including idle job resources and student allocation conflicts, and generates internship resource configuration feedback results.

10. A student internship management method, characterized in that: The student internship management system according to any one of claims 1 to 9 comprises the following steps: Based on students' internship intentions, skill levels, and job requirements, weighted student priority scores are calculated, and jobs are assigned according to the score rankings and the resource pool is updated to generate internship job assignment results. Based on the internship position allocation results, the task completion rate and attendance rate data are obtained, and student performance classification is performed after standardization to generate student performance classification results; Based on the student performance classification results, convert the task completion rate and attendance rate into time series data, set a sliding window to capture and update the data, identify abnormal tasks or attendance, and generate internship dynamic data update results; Based on the internship dynamic data update results, the school and enterprise cooperation data are extracted, the internship cooperation network is constructed, the matching degree is calculated and potential cooperation nodes are screened, the resource utilization and allocation are evaluated, and the internship resource configuration feedback results are generated.

Images