A big data configuration method and system for a smart campus management service platform

Abstract

The present invention discloses a big data configuration method and system for a smart campus management service platform, relates to the field of smart campuses, and solves the problem of poor teaching resource configuration effect in existing smart campus management service platforms. The method comprises the following steps: step S1: respectively obtaining a first learning resource matching coefficient and a second learning resource matching coefficient to obtain student work and rest monitoring data; step S2: performing an online course concentration assessment on a target student to obtain a third learning resource matching coefficient; and step S3: obtaining a resource configuration evaluation coefficient by analyzing the first learning resource matching coefficient, the second learning resource matching coefficient, and the third learning resource matching coefficient, and performing teaching resource configuration on the target student according to the resource configuration evaluation coefficient. The present invention can improve the pertinence of teaching resource configuration.

Description

Technical Field

[0001] The present invention belongs to the field of smart campus and relates to big data technology, specifically a big data configuration method and system for a smart campus management service platform. Background Art

[0002] The existing smart campus management service platform has the following specific defects when configuring courses:

[0003] 1. The existing smart campus management service platform is unable to configure courses based on students' personal habits, resulting in a lack of targeted teaching management services;

[0004] 2. The existing smart campus management service platform is unable to adjust the teaching method according to the students' concentration level in online courses, resulting in low teaching efficiency and hindering the improvement of students' academic performance.

[0005] To this end, we propose a big data configuration method and system for a smart campus management service platform. Summary of the Invention

[0006] In view of the shortcomings of the existing technology, the purpose of the present invention is to provide a big data configuration method and system for a smart campus management service platform. The present invention aims to improve the configuration level of school educational resources and ensure the pertinence of teaching management services.

[0007] In order to achieve the above objectives, the present invention adopts the following technical solution: a big data configuration method for a smart campus management service platform, comprising the following specific steps:

[0008] Step S1: Monitor the target student's independent learning period and obtain a first learning resource matching coefficient based on the monitoring results. Monitor the target student's clock-in sleep period and obtain a second learning resource matching coefficient based on the monitoring results to obtain student work and rest monitoring data.

[0009] Step S2: Randomly select a number of teaching hours from the online course that the target student is receiving instruction in. Analyze the student barrage interaction ratio, the course cumulative screen switching time ratio, and the student online time ratio corresponding to each teaching hour to obtain multiple student focus assessment coefficients. These multiple student focus assessment coefficients are then comprehensively processed to obtain a third learning resource matching coefficient.

[0010] Step S3: Obtain a resource configuration evaluation coefficient by analyzing the first learning resource matching coefficient, the second learning resource matching coefficient, and the third learning resource matching coefficient, obtain a resource configuration evaluation coefficient threshold, and perform a numerical comparison with the resource configuration evaluation coefficient, and configure teaching resources for the target students based on the numerical comparison results.

[0011] Furthermore, the step S1 further includes the following specific steps:

[0012] Step S11: Acquire student users served by the smart campus management service platform to obtain multiple platform student users, and randomly select a student user from the multiple platform student users as a target student;

[0013] Step S12: monitoring the target student's autonomous learning period to obtain a first learning resource matching coefficient;

[0014] Step S13: monitoring the target student's clock-in sleep period to obtain a second learning resource matching coefficient;

[0015] Step S14: defining the first learning resource matching coefficient and the second learning resource matching coefficient as student work and rest monitoring data.

[0016] Furthermore, the step S12 further includes the following specific steps:

[0017] Step S121: Obtaining target student autonomous learning check-in data from the smart campus management service platform, randomly selecting a number of learning check-in records from the target student autonomous learning check-in data, and naming the obtained learning check-in records as the first learning record to the zth learning record, respectively;

[0018] Step S122: Analyze the first learning record by time period to obtain the repetition rate of the first learning period and the first check-in learning duration;

[0019] Step S123: Obtain the check-in study duration corresponding to the second learning record to the zth learning record, and obtain the second check-in study duration to the zth check-in study duration. Obtain the check-in study duration corresponding to the second learning record to the zth learning record, and obtain the repetition rate of the second learning period to the zth learning period.

[0020] Step S124: Calculate the first learning resource matching coefficient by combining the first check-in learning duration to the zth check-in learning duration and the first learning period repetition rate to the zth learning period repetition rate;

[0021] Calculate the first learning resource matching coefficient.

[0022] Furthermore, the step S122 further includes the following specific steps:

[0023] Step S1221: Obtaining the time value corresponding to the target student starting to study based on the first learning record to obtain a first time value, and obtaining the time value corresponding to the target student ending to study based on the first learning record to obtain a second time value;

[0024] Step S1222: Name the time period between the first time value and the second time value as the first check-in study period;

[0025] Step S1223: Calculate the time difference between the first time value and the second time value to obtain the check-in study duration corresponding to the first study record, and name it the first check-in study duration;

[0026] Step S1224: Obtain the school teaching timetable, and obtain multiple teaching periods corresponding to the school's teaching working days according to the school teaching timetable;

[0027] Step S1225: Create a learning monitoring plane histogram using an existing spreadsheet program, mark the specific time period of the day as the coordinate y-axis of the learning monitoring plane histogram, and create a first feature histogram, a second feature histogram, and a third feature histogram in the coordinate x-axis of the learning monitoring plane histogram;

[0028] Step S1226: In the learning monitoring plane histogram, the first characteristic histogram is filled with the first clock-in learning period to obtain a first sample filling area, the second characteristic histogram is filled with multiple teaching periods to obtain a second sample filling area, and the overlapping area of ​​the first sample filling area and the second sample filling area on the coordinate y-axis is filled in the third characteristic histogram to obtain a third sample filling area;

[0029] Step S1227: Obtain the length ratio of the third sample filling area in the third characteristic histogram to obtain the repetition rate of the first learning period.

[0030] Furthermore, the step S13 further includes the following specific steps:

[0031] Step S131: Obtaining the target student's sleep check-in data from the smart campus management service platform, randomly selecting a number of sleep check-in records from the target student's autonomous sleep check-in data, and processing the obtained sleep check-in records to name them as the first sleep record to the sth sleep record respectively;

[0032] Step S132: Analyze the first sleep record by time period to obtain the repetition rate of the first sleep period and the first clock-in sleep duration;

[0033] Step S133: Obtain the clock-in sleep duration corresponding to the second sleep record to the sth sleep record to obtain the second clock-in sleep duration to the sth clock-in sleep duration; obtain the clock-in sleep duration corresponding to the second sleep record to the sth sleep record to obtain the second sleep period repetition rate to the sth sleep period repetition rate;

[0034] Step S134: Calculating the second learning resource matching coefficient by combining the first clock-in sleep duration to the sth clock-in sleep duration and the first sleep period repetition rate to the sth sleep period repetition rate;

[0035] Calculate the second learning resource matching coefficient.

[0036] Furthermore, the step S132 further includes the following specific steps:

[0037] Step S1321: obtaining a sleep time value corresponding to the start of study of the target student based on the first sleep record, obtaining a first sleep time value; obtaining a sleep time value corresponding to the end of study of the target student based on the first sleep record, obtaining a second sleep time value;

[0038] Step S1322: naming the time period between the first sleep time value and the second sleep time value as the first clock-in sleep period;

[0039] Step S1323: Calculate the time difference between the first sleep time value and the second sleep time value to obtain the clock-in sleep duration corresponding to the first sleep record, and name it the first clock-in sleep duration;

[0040] Step S1324: Obtain the school teaching timetable, and obtain multiple teaching periods corresponding to the school's teaching working days according to the school teaching timetable;

[0041] Step S1325: Create a sleep monitoring plane histogram using an existing spreadsheet program, mark the specific time period of the day as the coordinate y-axis of the sleep monitoring plane histogram, and create a first sample histogram, a second sample histogram, and a third sample histogram on the coordinate x-axis of the sleep monitoring plane histogram;

[0042] A big data configuration system for a smart campus management service platform, comprising:

[0043] Lifestyle module: used to monitor the target students' independent learning periods and obtain the first learning resource matching coefficient based on the monitoring results; monitor the target students' clock-in sleep periods and obtain the second learning resource matching coefficient based on the monitoring results to obtain student lifestyle monitoring data;

[0044] Learning Monitoring Module: This module randomly selects several teaching hours from the target student's online course and analyzes the student barrage interaction ratio, the course cumulative screen switching time ratio, and the student online time ratio corresponding to each teaching hour to obtain multiple student focus assessment coefficients. The module then performs a comprehensive processing of these multiple student focus assessment coefficients to obtain the third learning resource matching coefficient.

[0045] Resource allocation module: used to obtain the resource allocation evaluation coefficient by analyzing the first learning resource matching coefficient, the second learning resource matching coefficient and the third learning resource matching coefficient, obtain the resource configuration evaluation coefficient threshold and perform numerical comparison with the resource configuration evaluation coefficient, and allocate teaching resources to the target students according to the numerical comparison results.

[0046] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0047] 1. The present invention monitors the target students' independent learning periods and obtains a first learning resource matching coefficient based on the monitoring results. It also monitors the target students' clock-in sleep periods and obtains a second learning resource matching coefficient based on the monitoring results. Teaching resources are then configured based on the first and second learning resource matching coefficients, effectively improving the targeted configuration of teaching resources and the efficiency of teaching resource utilization.

[0048] 2. The present invention obtains multiple student concentration assessment coefficients by analyzing the student barrage interaction ratio, the course cumulative screen switching time ratio and the student online time ratio corresponding to each teaching class, and comprehensively processes the multiple student concentration assessment coefficients to obtain a third learning resource matching coefficient. The teaching resources are configured according to the third learning resource matching coefficient, which can effectively stimulate students' learning enthusiasm and learning efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] To facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0050] Figure 1 It is a diagram of the implementation steps of the present invention;

[0051] Figure 2 is a block diagram of the overall system of the present invention;

[0052] Figure 3 This is the histogram of the learning monitoring plane of the present invention. DETAILED DESCRIPTION

[0053] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0054] Example 1

[0055] See also Figure 1 The present invention provides a technical solution: a big data configuration method for a smart campus management service platform, comprising the following specific steps:

[0056] Step S1: Monitor the target student's independent learning period and obtain a first learning resource matching coefficient based on the monitoring results. Monitor the target student's clock-in sleep period and obtain a second learning resource matching coefficient based on the monitoring results to obtain student work and rest monitoring data.

[0057] The step S1 further includes the following specific steps:

[0058] Step S11: Acquire student users served by the smart campus management service platform to obtain multiple platform student users, and randomly select a student user from the multiple platform student users as a target student;

[0059] Step S12: monitoring the target student's autonomous learning period to obtain a first learning resource matching coefficient;

[0060] The step S12 further includes the following specific steps:

[0061] Step S121: Obtaining target student autonomous learning check-in data from the smart campus management service platform, randomly selecting a number of learning check-in records from the target student autonomous learning check-in data, and naming the obtained learning check-in records as the first learning record to the zth learning record, respectively;

[0062] Step S122: Analyze the first learning record by time period to obtain the repetition rate of the first learning period and the first check-in learning duration;

[0063] The step S122 further includes the following specific steps:

[0064] Step S1221: Obtaining the time value corresponding to the target student starting to study based on the first learning record to obtain a first time value, and obtaining the time value corresponding to the target student ending to study based on the first learning record to obtain a second time value;

[0065] Step S1222: Name the time period between the first time value and the second time value as the first check-in study period;

[0066] Step S1223: Calculate the time difference between the first time value and the second time value to obtain the check-in study duration corresponding to the first study record, and name it the first check-in study duration;

[0067] Step S1224: Obtain the school teaching timetable, and obtain multiple teaching periods corresponding to the school's teaching working days according to the school teaching timetable;

[0068] Step S1225: Create a learning monitoring plane histogram using an existing spreadsheet program, mark the specific time period of the day as the coordinate y-axis of the learning monitoring plane histogram, and create a first feature histogram, a second feature histogram, and a third feature histogram in the coordinate x-axis of the learning monitoring plane histogram;

[0069] Step S1226: In the learning monitoring plane histogram, use the first check-in learning period to fill the first characteristic histogram to obtain the first sample filling area, use multiple teaching periods to fill the second characteristic histogram to obtain the second sample filling area, and fill the overlapping area of ​​the first sample filling area and the second sample filling area on the coordinate y-axis in the third characteristic histogram to obtain the third sample filling area.

[0070] Step S1227: Obtain the length ratio of the third sample filling area in the third characteristic histogram to obtain the repetition rate of the first learning period;

[0071] Step S123: Obtain the check-in study duration corresponding to the second learning record to the zth learning record, and obtain the second check-in study duration to the zth check-in study duration. Obtain the check-in study duration corresponding to the second learning record to the zth learning record, and obtain the repetition rate of the second learning period to the zth learning period.

[0072] Step S124: Calculate the first learning resource matching coefficient by combining the first check-in learning duration to the zth check-in learning duration and the first learning period repetition rate to the zth learning period repetition rate;

[0073] Calculate the first learning resource matching coefficient. The specific formula is as follows:

[0074]

[0075] Among them, Zyx1 is the first learning resource matching coefficient, Dsc i is the learning duration of the i-th check-in, Cf li is the repetition rate of the i-th learning period, and z is the number of learning check-in records.

[0076] Step S13: Monitor the target student's clock-in sleep period to obtain a second learning resource matching coefficient.

[0077] The step S13 further includes the following specific steps:

[0078] Step S131: Obtaining the target student's sleep check-in data from the smart campus management service platform, randomly selecting a number of sleep check-in records from the target student's autonomous sleep check-in data, and processing the obtained sleep check-in records to name them as the first sleep record to the sth sleep record respectively;

[0079] Step S132: Analyze the first sleep record by time period to obtain the repetition rate of the first sleep period and the first clock-in sleep duration;

[0080] The step S132 further includes the following specific steps:

[0081] Step S1321: obtaining a sleep time value corresponding to the start of study of the target student based on the first sleep record, obtaining a first sleep time value; obtaining a sleep time value corresponding to the end of study of the target student based on the first sleep record, obtaining a second sleep time value;

[0082] Step S1322: naming the time period between the first sleep time value and the second sleep time value as the first clock-in sleep period;

[0083] Step S1323: Calculate the time difference between the first sleep time value and the second sleep time value to obtain the clock-in sleep duration corresponding to the first sleep record, and name it the first clock-in sleep duration;

[0084] Step S1324: Obtain the school teaching timetable, and obtain multiple teaching periods corresponding to the school's teaching working days according to the school teaching timetable;

[0085] Step S1325: Create a sleep monitoring plane histogram using an existing spreadsheet program, mark the specific time period of the day as the coordinate y-axis of the sleep monitoring plane histogram, and create a first sample histogram, a second sample histogram, and a third sample histogram on the coordinate x-axis of the sleep monitoring plane histogram;

[0086] Step S1326: In the sleep monitoring plane histogram, the first sample histogram is filled with the first clock-in sleep period to obtain a first sample filling area, the second sample histogram is filled with multiple teaching periods to obtain a second sample filling area, and the overlapping area of ​​the first sample filling area and the second sample filling area on the y-axis is filled in the third sample histogram to obtain a third sample filling area;

[0087] Step S1327: Obtain the length ratio of the third sample filling area in the third sample histogram to obtain the repetition rate of the first sleep period;

[0088] Step S133: Obtain the clock-in sleep duration corresponding to the second sleep record to the sth sleep record to obtain the second clock-in sleep duration to the sth clock-in sleep duration; obtain the clock-in sleep duration corresponding to the second sleep record to the sth sleep record to obtain the second sleep period repetition rate to the sth sleep period repetition rate;

[0089] Step S134: Calculating the second learning resource matching coefficient by combining the first clock-in sleep duration to the sth clock-in sleep duration and the first sleep period repetition rate to the sth sleep period repetition rate;

[0090] The matching coefficient of the second learning resource is calculated as follows:

[0091]

[0092] Where syx2 is the second learning resource matching coefficient, Msci is the sleep duration of the i-th clock-in, Mfli is the repetition rate of the i-th sleep period, and s is the number of sleep clock-in records.

[0093] Step S14: defining the first learning resource matching coefficient and the second learning resource matching coefficient as student work and rest monitoring data.

[0094] Step S2: Randomly select a number of teaching hours from the online course that the target student is receiving instruction in. Analyze the student barrage interaction ratio, the course cumulative screen switching time ratio, and the student online time ratio corresponding to each teaching hour to obtain multiple student focus assessment coefficients. These multiple student focus assessment coefficients are then comprehensively processed to obtain a third learning resource matching coefficient.

[0095] The step S2 further includes the following specific steps:

[0096] Step S21: randomly selecting a number of teaching hours from the online course that the target student is receiving instruction, and selecting a sample teaching hour from the selected number of teaching hours;

[0097] Step S22: monitoring the sample teaching hours to obtain the student concentration evaluation coefficient corresponding to the sample teaching hours;

[0098] The step S22 further includes the following specific steps:

[0099] Step S221: Obtain the cumulative number of interactive bullet screens sent by the target student during the sample teaching class to obtain the first bullet screen number, obtain the cumulative number of teaching interactive bullet screens corresponding to the sample teaching class to obtain the second bullet screen number, calculate the ratio of the first bullet screen number to the second bullet screen number to obtain the student bullet screen interaction ratio;

[0100] Step S222: Obtain the course duration corresponding to the sample teaching class to obtain the first course duration;

[0101] Step S223: Capture multiple screen switching events of the target student during the sample teaching period, obtain the screen switching duration for each screen switching event, obtain multiple screen switching durations, and sum the multiple screen switching durations to obtain the cumulative screen switching duration for the course;

[0102] Step S224: Calculate the ratio of the cumulative screen switching time of the course to the course duration to obtain the student screen switching time ratio;

[0103] Step S225: Obtain the cumulative online time of the target student during the sample teaching period to obtain the student's cumulative online time, and calculate the ratio of the student's cumulative online time to the first course duration to obtain the student's online time ratio;

[0104] Step S226: Calculate the student focus evaluation coefficient corresponding to the sample teaching period by calculating the student bullet screen interaction ratio, the course cumulative screen switching time ratio, and the student online time ratio;

[0105] The student concentration evaluation coefficient corresponding to the sample teaching hours is calculated. The specific formula is as follows:

[0106]

[0107] Among them, Zzp is the student concentration evaluation coefficient corresponding to the sample teaching hours, Dmb is the student barrage interaction ratio, Qpb is the cumulative screen switching time ratio of the course, and Zxb is the student online time ratio.

[0108] Step S23: Obtain the student concentration evaluation coefficient corresponding to each teaching hour respectively to obtain multiple student concentration evaluation coefficients, and average the obtained multiple student concentration evaluation coefficients to obtain a third learning resource matching coefficient.

[0109] Step S3: Obtaining a resource allocation evaluation coefficient by analyzing the first learning resource matching coefficient, the second learning resource matching coefficient, and the third learning resource matching coefficient; obtaining a resource allocation evaluation coefficient threshold and performing a numerical comparison with the resource allocation evaluation coefficient; and allocating teaching resources to the target student based on the numerical comparison result;

[0110] The step S3 further includes the following specific steps:

[0111] Step S31: Obtaining student work and rest monitoring data, and obtaining a first learning resource matching coefficient and a second learning resource matching coefficient based on the student work and rest monitoring data;

[0112] Step S32: Obtaining a third learning resource matching coefficient;

[0113] Step S33: Calculating the first learning resource matching coefficient, the second learning resource matching coefficient, and the third learning resource matching coefficient to obtain a resource configuration evaluation coefficient;

[0114] The resource allocation evaluation coefficient is calculated as follows:

[0115]

[0116] Among them, Pzp is the resource configuration evaluation coefficient, Zyx1 is the first learning resource matching coefficient, Zyx2 is the second learning resource matching coefficient, and Zyx3 is the third learning resource matching coefficient;

[0117] Step S34: Obtain a resource configuration evaluation coefficient threshold, perform a numerical comparison between the resource configuration evaluation coefficient threshold and the resource configuration evaluation coefficient, and configure teaching resources for the target students based on the numerical comparison result.

[0118] The step S34 further includes the following specific steps:

[0119] Step S341: respectively obtaining a first learning resource matching coefficient threshold, a second learning resource matching coefficient threshold, and a third learning resource matching coefficient threshold;

[0120] Step S342: Calculating the first learning resource matching coefficient threshold, the second learning resource matching coefficient threshold, and the third learning resource matching coefficient threshold to obtain a resource configuration evaluation coefficient threshold;

[0121] The resource allocation evaluation coefficient threshold is calculated using the following formula:

[0122]

[0123] Wherein, Pzp is the resource configuration evaluation coefficient threshold, Zyx1 is the first learning resource matching coefficient threshold, Zyx2 is the second learning resource matching coefficient threshold, and Zyx3 is the third learning resource matching coefficient threshold;

[0124] Step S343: When the resource allocation evaluation coefficient is greater than or equal to the resource allocation evaluation coefficient threshold, online teaching resources are preferentially allocated to the target students;

[0125] Step S344: When the resource configuration evaluation coefficient is less than the resource configuration evaluation coefficient threshold, offline teaching resources are preferentially configured for the target students.

[0126] In this application, if a corresponding calculation formula appears, the above calculation formula is dimensionless and its numerical calculation is performed. The weight coefficient, proportional coefficient and other coefficients in the formula are set to a result value obtained by quantifying each parameter. Regarding the size of the weight coefficient and the proportional coefficient, as long as it does not affect the proportional relationship between the parameter and the result value, it is acceptable.

[0127] Example 2

[0128] See also Figure 2Based on another concept of the same invention, a big data configuration system for a smart campus management service platform is proposed, comprising a daily routine module, a learning monitoring module, a resource configuration module, and a server. The daily routine module, the learning monitoring module, and the resource configuration module are respectively connected to the server, and the server controls the daily routine module, the learning monitoring module, and the resource configuration module respectively.

[0129] The daily routine module monitors the target students' independent learning periods and obtains the first learning resource matching coefficient based on the monitoring results. It also monitors the target students' clock-in sleep periods and obtains the second learning resource matching coefficient based on the monitoring results to obtain the students' daily routine monitoring data.

[0130] Acquire student users served by the smart campus management service platform, obtain multiple platform student users, and randomly select a student user from the multiple platform student users as the target student;

[0131] It should be noted here that:

[0132] In this application, the target student involved here is a sample in the smart campus management service platform. In this application, the process of providing management services to the target students can be extended and applied to every student user served by the smart campus management service platform.

[0133] Monitor the target students' independent learning period to obtain the first learning resource matching coefficient;

[0134] The details are as follows:

[0135] Obtain target students' autonomous learning check-in data from the smart campus management service platform, randomly select several learning check-in records from the target students' autonomous learning check-in data, and name the obtained learning check-in records as the first learning record to the zth learning record respectively;

[0136] It should be noted here that:

[0137] Here, z is the number of learning check-in records, and z is an integer greater than 0;

[0138] The target students' independent learning check-in data involved here specifically refers to the target students' learning check-in data during non-teaching periods. The non-teaching periods involved here specifically refer to the learning periods outside the school teaching timetable. The non-teaching periods involved here do not include morning and evening self-study.

[0139] Perform time period analysis on the first learning record to obtain the repetition rate of the first learning period and the first check-in learning duration;

[0140] The details are as follows:

[0141] Obtaining a time value corresponding to when the target student starts studying according to the first learning record to obtain a first time value, and obtaining a time value corresponding to when the target student ends studying according to the first learning record to obtain a second time value;

[0142] The time period between the first time value and the second time value is named the first check-in study period;

[0143] Calculate the time difference between the first time value and the second time value to obtain the check-in study duration corresponding to the first study record, and name it the first check-in study duration.

[0144] Get the school teaching timetable, and obtain multiple teaching periods corresponding to the school's teaching working days based on the school teaching timetable;

[0145] See also Figure 3 , create a learning monitoring plane histogram through an existing spreadsheet program, mark the specific time period of the day as the coordinate y-axis of the learning monitoring plane histogram, and create a first feature histogram, a second feature histogram, and a third feature histogram in the coordinate x-axis of the learning monitoring plane histogram;

[0146] It should be noted here that:

[0147] The specific time period of a day involved here is 0-24 hours.

[0148] In the learning monitoring plane histogram, the first characteristic histogram is filled with the first punch-in learning period to obtain the first sample filling area, the second characteristic histogram is filled with multiple teaching periods to obtain the second sample filling area, and the overlapping area of ​​the first sample filling area and the second sample filling area on the coordinate y-axis is filled in the third characteristic histogram to obtain the third sample filling area;

[0149] Obtaining the length ratio of the third sample filling area in the third characteristic histogram to obtain the repetition rate of the first learning period;

[0150] Repeat the process of time period analysis for the first learning record, obtain the check-in learning time corresponding to the second learning record to the zth learning record, and obtain the check-in learning time corresponding to the second learning record to the zth learning record, and obtain the repetition rate of the second learning period to the repetition rate of the zth learning period.

[0151] The first learning resource matching coefficient is obtained by calculating the first check-in learning time to the zth check-in learning time and the first learning period repetition rate to the zth learning period repetition rate;

[0152] Calculate the first learning resource matching coefficient. The specific formula is as follows:

[0153]

[0154] Where Zyx1 is the first learning resource matching coefficient, Dsc i is the learning duration of the i-th check-in, Cf li is the repetition rate of the i-th learning period, and z is the number of learning check-in records.

[0155] It should be noted here that:

[0156] In this application, the i-th check-in learning duration involved here can be any check-in learning duration from the first check-in learning duration to the z-th check-in learning duration, and the i-th learning period repetition rate involved here can be any learning period repetition rate from the first learning period repetition rate to the z-th learning period repetition rate.

[0157] Monitor the target students' clock-in sleep periods to obtain the second learning resource matching coefficient;

[0158] The details are as follows:

[0159] Obtain the target student's sleep check-in data from the smart campus management service platform, randomly select several sleep check-in records from the target student's autonomous sleep check-in data, and process the obtained sleep check-in records and name them as the first sleep record to the sth sleep record respectively;

[0160] It should be noted here that:

[0161] Here, s refers to the number of sleep clock-in records, and s is an integer greater than 0;

[0162] The target students' autonomous sleep check-in data involved here specifically refers to the target students' sleep check-in data during non-teaching periods.

[0163] Performing a period analysis on the first sleep record to obtain the repetition rate of the first sleep period and the first clock-in sleep duration;

[0164] The details are as follows:

[0165] Obtaining a sleep time value corresponding to the start of study of the target student based on the first sleep record to obtain a first sleep time value; obtaining a sleep time value corresponding to the end of study of the target student based on the first sleep record to obtain a second sleep time value;

[0166] The time period between the first sleep time value and the second sleep time value is named the first clock-in sleep period;

[0167] Calculate the time difference between the first sleep time value and the second sleep time value to obtain the clock-in sleep duration corresponding to the first sleep record, and name it the first clock-in sleep duration;

[0168] Get the school teaching timetable, and obtain multiple teaching periods corresponding to the school's teaching working days based on the school teaching timetable;

[0169] Create a sleep monitoring plane histogram using an existing spreadsheet program, mark the specific time periods of the day as the coordinate y-axis of the sleep monitoring plane histogram, and create a first sample histogram, a second sample histogram, and a third sample histogram on the coordinate x-axis of the sleep monitoring plane histogram;

[0170] It should be noted here that:

[0171] The specific time period of a day involved here is 0-24 hours;

[0172] In the sleep monitoring plane histogram, the first sample histogram is filled with the first clock-in sleep period to obtain the first sample filling area, the second sample histogram is filled with multiple teaching periods to obtain the second sample filling area, and the overlapping area of ​​the first sample filling area and the second sample filling area on the coordinate y-axis is filled in the third sample histogram to obtain the third sample filling area;

[0173] Obtaining a ratio of the length of the third sample filling area in the third sample histogram to obtain a repetition rate of the first sleep period;

[0174] Repeat the process of period analysis for the first sleep record, obtain the clock-in sleep duration corresponding to the second sleep record to the sth sleep record, and obtain the clock-in sleep duration corresponding to the second sleep record to the sth sleep record to obtain the repetition rate of the second sleep period to the sth sleep period;

[0175] The second learning resource matching coefficient is obtained by calculating the sleep time from the first clock-in to the sth clock-in and the repetition rate of the first sleep period to the sth sleep period;

[0176] The matching coefficient of the second learning resource is calculated as follows:

[0177]

[0178] Where syx2 is the second learning resource matching coefficient, Msci is the sleep duration of the i-th clock-in, Mfli is the repetition rate of the i-th sleep period, and s is the number of sleep clock-in records.

[0179] It should be noted here that:

[0180] In the present application, the i-th clock-in sleep duration involved herein may be any clock-in sleep duration from the first clock-in sleep duration to the s-th clock-in sleep duration, and the i-th sleep period repetition rate involved herein may be any sleep period repetition rate from the first sleep period repetition rate to the s-th sleep period repetition rate;

[0181] The first learning resource matching coefficient and the second learning resource matching coefficient are defined as student work and rest monitoring data;

[0182] The daily routine module obtains the students' daily routine monitoring data and transmits it to the resource allocation module;

[0183] The learning monitoring module randomly selects several teaching hours from the online courses where the target students are receiving instruction, and obtains multiple student concentration assessment coefficients by analyzing the student barrage interaction ratio, the course cumulative screen switching time ratio, and the student online time ratio corresponding to each teaching hour. The multiple student concentration assessment coefficients are then comprehensively processed to obtain the third learning resource matching coefficient.

[0184] The details are as follows:

[0185] Randomly select a number of teaching hours in the online course where the target students receive teaching, and select a sample teaching hour from the selected number of teaching hours;

[0186] Monitor the sample teaching hours and obtain the student concentration evaluation coefficient corresponding to the sample teaching hours;

[0187] The details are as follows:

[0188] Obtain the cumulative number of interactive barrages sent by the target students during the sample teaching period to obtain the first barrage number, obtain the cumulative number of teaching interactive barrages corresponding to the sample teaching period to obtain the second barrage number, calculate the ratio of the first barrage number to the second barrage number to obtain the student barrage interaction ratio;

[0189] Get the course duration corresponding to the sample teaching hours and get the first course duration;

[0190] Capture multiple screen switching events of the target student during the sample teaching period, obtain the screen switching duration for each screen switching event, obtain multiple screen switching times, and sum up the multiple screen switching times to obtain the cumulative screen switching time for the course;

[0191] Calculate the ratio of the cumulative screen-switching time of the course to the course duration to obtain the student screen-switching time ratio;

[0192] Obtain the target student's cumulative online time during the sample teaching period to obtain the student's cumulative online time, and calculate the ratio of the student's cumulative online time to the first course duration to obtain the student's online time ratio;

[0193] The student concentration evaluation coefficient corresponding to the sample teaching hours is obtained by calculating the student barrage interaction ratio, the course cumulative screen switching time ratio, and the student online time ratio;

[0194] The student concentration evaluation coefficient corresponding to the sample teaching hours is calculated. The specific formula is as follows:

[0195]

[0196] Among them, Zzp is the student concentration evaluation coefficient corresponding to the sample teaching class, Dmb is the student barrage interaction ratio, Qpb is the cumulative screen switching time ratio of the course, and Zxb is the student online time ratio;

[0197] Repeat the process of obtaining the student concentration evaluation coefficient corresponding to the sample teaching hours, obtain the student concentration evaluation coefficient corresponding to each teaching hour respectively, obtain multiple student concentration evaluation coefficients, and calculate the average of the multiple student concentration evaluation coefficients obtained to obtain the third learning resource matching coefficient.

[0198] The learning monitoring module obtains the third learning resource matching coefficient and transmits it to the resource allocation module;

[0199] The resource allocation module obtains a resource allocation evaluation coefficient by analyzing the first learning resource matching coefficient, the second learning resource matching coefficient, and the third learning resource matching coefficient, obtains a resource configuration evaluation coefficient threshold, and compares it numerically with the resource configuration evaluation coefficient, and allocates teaching resources to the target students based on the numerical comparison results.

[0200] The details are as follows:

[0201] Obtain student work and rest monitoring data, and obtain a first learning resource matching coefficient and a second learning resource matching coefficient based on the student work and rest monitoring data;

[0202] Obtain the third learning resource matching coefficient;

[0203] The first learning resource matching coefficient, the second learning resource matching coefficient, and the third learning resource matching coefficient are calculated to obtain a resource configuration evaluation coefficient;

[0204] The resource allocation evaluation coefficient is calculated as follows:

[0205]

[0206] Among them, Pzp is the resource configuration evaluation coefficient, Zyx1 is the first learning resource matching coefficient, Zyx2 is the second learning resource matching coefficient, and Zyx3 is the third learning resource matching coefficient;

[0207] Obtaining a resource allocation evaluation coefficient threshold, performing a numerical comparison between the resource allocation evaluation coefficient threshold and the resource allocation evaluation coefficient, and allocating teaching resources to target students based on the numerical comparison result;

[0208] The details are as follows:

[0209] Obtaining a first learning resource matching coefficient threshold, a second learning resource matching coefficient threshold, and a third learning resource matching coefficient threshold respectively;

[0210] It should be noted here that:

[0211] In this application, the first learning resource matching coefficient threshold, the second learning resource matching coefficient threshold, and the third learning resource matching coefficient threshold involved herein are obtained by comprehensive analysis of student users in the smart campus management service platform through big data;

[0212] The first learning resource matching coefficient threshold, the second learning resource matching coefficient threshold, and the third learning resource matching coefficient threshold are calculated to obtain a resource configuration evaluation coefficient threshold;

[0213] The resource allocation evaluation coefficient threshold is calculated using the following formula:

[0214]

[0215] Wherein, Pzp is the resource configuration evaluation coefficient threshold, Zyx1 is the first learning resource matching coefficient threshold, Zyx2 is the second learning resource matching coefficient threshold, and Zyx3 is the third learning resource matching coefficient threshold;

[0216] When the resource allocation evaluation coefficient is greater than or equal to the resource allocation evaluation coefficient threshold, online teaching resources are allocated to the target students first;

[0217] When the resource allocation evaluation coefficient is less than the resource allocation evaluation coefficient threshold, offline teaching resources are preferentially allocated to the target students.

[0218] It should be noted here that:

[0219] In this application, the online teaching resources involved here include but are not limited to teaching videos, live courses and online tests, and the offline teaching resources involved here include but are not limited to extracurricular one-on-one tutoring, extracurricular practice and traditional classroom teaching.

[0220] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to specific embodiments. Obviously, many modifications and variations are possible based on the contents of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A big data configuration method for a smart campus management service platform, characterized in that: include: Step S1: Monitor the target student's independent learning period and obtain a first learning resource matching coefficient based on the monitoring results. Monitor the target student's clock-in sleep period and obtain a second learning resource matching coefficient based on the monitoring results to obtain student work and rest monitoring data. Monitor the target students' independent learning periods as follows: Obtain target student self-study check-in data, randomly select several learning check-in records from the target student self-study check-in data, and name the obtained several learning check-in records as the first learning record to the zth learning record respectively; Perform time period analysis on the first learning record to obtain the repetition rate of the first learning period and the first check-in learning duration; Obtain the check-in study duration corresponding to the second learning record to the zth learning record, and obtain the second check-in study duration to the zth check-in study duration. Obtain the check-in study duration corresponding to the second learning record to the zth learning record, and obtain the second learning period repetition rate to the zth learning period repetition rate; The first learning resource matching coefficient is obtained by calculating the first check-in learning time to the zth check-in learning time and the first learning period repetition rate to the zth learning period repetition rate; Calculating the first learning resource matching coefficient; Monitor the target students' clock-in sleep periods as follows: Obtain the target student's sleep check-in data from the smart campus management service platform, randomly select several sleep check-in records from the target student's autonomous sleep check-in data, and process the obtained sleep check-in records and name them as the first sleep record to the sth sleep record respectively; Performing a period analysis on the first sleep record to obtain the repetition rate of the first sleep period and the first clock-in sleep duration; Obtain the clock-in sleep duration corresponding to the second sleep record to the sth sleep record to obtain the second clock-in sleep duration to the sth clock-in sleep duration; obtain the clock-in sleep duration corresponding to the second sleep record to the sth sleep record to obtain the second sleep period repetition rate to the sth sleep period repetition rate; The second learning resource matching coefficient is obtained by calculating the sleep time from the first clock-in to the sth clock-in and the repetition rate of the first sleep period to the sth sleep period; Calculating the matching coefficient of the second learning resource; Step S2: Randomly select a number of teaching hours from the online course that the target student is receiving instruction in. Analyze the student barrage interaction ratio, the course cumulative screen switching time ratio, and the student online time ratio corresponding to each teaching hour to obtain multiple student focus assessment coefficients. These multiple student focus assessment coefficients are then comprehensively processed to obtain a third learning resource matching coefficient. Step S3: Obtain a resource configuration evaluation coefficient by analyzing the first learning resource matching coefficient, the second learning resource matching coefficient, and the third learning resource matching coefficient, obtain a resource configuration evaluation coefficient threshold, and perform a numerical comparison with the resource configuration evaluation coefficient, and configure teaching resources for the target students based on the numerical comparison results.

2. A big data configuration method for a smart campus management service platform according to claim 1, characterized in that: The step S1 further includes the following specific steps: Step S11: Acquire student users served by the smart campus management service platform to obtain multiple platform student users, and randomly select a student user from the multiple platform student users as a target student; Step S12: monitoring the target student's autonomous learning period to obtain a first learning resource matching coefficient; Step S13: monitoring the target student's clock-in sleep period to obtain a second learning resource matching coefficient; Step S14: defining the first learning resource matching coefficient and the second learning resource matching coefficient as student work and rest monitoring data.

3. A big data configuration method for a smart campus management service platform according to claim 1, characterized in that: Conduct period analysis of the first learning record, including: Obtaining a time value corresponding to when the target student starts studying according to the first learning record to obtain a first time value, and obtaining a time value corresponding to when the target student ends studying according to the first learning record to obtain a second time value; The time period between the first time value and the second time value is named the first check-in study period; Calculate the time difference between the first time value and the second time value to obtain the check-in study duration corresponding to the first study record, and name it the first check-in study duration.

4. A big data configuration method for a smart campus management service platform according to claim 3, characterized in that: The period analysis of the first learning record also includes: Get the school teaching timetable and obtain multiple teaching periods based on the school teaching timetable; Create a learning monitoring plane histogram using an existing spreadsheet program, mark the specific time periods of the day as the coordinate y-axis of the learning monitoring plane histogram, and create a first feature histogram, a second feature histogram, and a third feature histogram in the coordinate x-axis of the learning monitoring plane histogram; In the learning monitoring plane histogram, the first characteristic histogram is filled with the first punch-in learning period to obtain the first sample filling area, the second characteristic histogram is filled with multiple teaching periods to obtain the second sample filling area, and the overlapping area of ​​the first sample filling area and the second sample filling area on the coordinate y-axis is filled in the third characteristic histogram to obtain the third sample filling area; The length ratio of the third sample filling area in the third characteristic histogram is obtained to obtain the repetition rate of the first learning period.

5. The big data configuration method for a smart campus management service platform according to claim 1, characterized in that: Perform period analysis on the first sleep record, including: Obtaining a sleep time value corresponding to the start of study of the target student based on the first sleep record to obtain a first sleep time value; obtaining a sleep time value corresponding to the end of study of the target student based on the first sleep record to obtain a second sleep time value; The time period between the first sleep time value and the second sleep time value is named the first clock-in sleep period.

6. A big data configuration method for a smart campus management service platform according to claim 5, characterized in that: The first sleep record is analyzed during a period, further comprising: Calculate the time difference between the first sleep time value and the second sleep time value to obtain the clock-in sleep duration corresponding to the first sleep record, and name it the first clock-in sleep duration; Get the school teaching timetable, and obtain multiple teaching periods corresponding to the school's teaching working days based on the school teaching timetable; A sleep monitoring plane histogram is created through an existing spreadsheet program, specific time periods of the day are marked as the coordinate y-axis of the sleep monitoring plane histogram, and a first sample histogram, a second sample histogram, and a third sample histogram are created in the coordinate x-axis of the sleep monitoring plane histogram.

7. A big data configuration system for a smart campus management service platform, applicable to a big data configuration method for a smart campus management service platform according to any one of claims 1 to 6, characterized in that: The big data configuration system includes: Lifestyle module: used to monitor the target students' independent learning periods and obtain the first learning resource matching coefficient based on the monitoring results; monitor the target students' clock-in sleep periods and obtain the second learning resource matching coefficient based on the monitoring results to obtain student lifestyle monitoring data; Learning Monitoring Module: This module randomly selects several teaching hours from the target student's online course and analyzes the student barrage interaction ratio, the course cumulative screen switching time ratio, and the student online time ratio corresponding to each teaching hour to obtain multiple student focus assessment coefficients. The module then performs a comprehensive processing of these multiple student focus assessment coefficients to obtain the third learning resource matching coefficient. Resource allocation module: used to obtain the resource allocation evaluation coefficient by analyzing the first learning resource matching coefficient, the second learning resource matching coefficient and the third learning resource matching coefficient, obtain the resource configuration evaluation coefficient threshold and perform numerical comparison with the resource configuration evaluation coefficient, and allocate teaching resources to the target students according to the numerical comparison results.

Images