CN112149941A - Intelligent course arrangement system and method - Google Patents
Intelligent course arrangement system and method Download PDFInfo
- Publication number
- CN112149941A CN112149941A CN201910583971.6A CN201910583971A CN112149941A CN 112149941 A CN112149941 A CN 112149941A CN 201910583971 A CN201910583971 A CN 201910583971A CN 112149941 A CN112149941 A CN 112149941A
- Authority
- CN
- China
- Prior art keywords
- teacher
- students
- sales
- course
- teachers
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000012549 training Methods 0.000 claims abstract description 14
- 238000010801 machine learning Methods 0.000 claims abstract description 13
- 230000006399 behavior Effects 0.000 claims description 19
- 238000006243 chemical reaction Methods 0.000 claims description 14
- 238000004891 communication Methods 0.000 claims description 2
- 238000003066 decision tree Methods 0.000 abstract description 3
- 230000000694 effects Effects 0.000 description 5
- 238000005070 sampling Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 229920006395 saturated elastomer Polymers 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000003245 working effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Educational Technology (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of teaching management, relates to an intelligent course arrangement system and method, and particularly relates to an intelligent course arrangement system and method based on a machine learning algorithm. According to the invention, historical data of teachers, students, sales and the like are obtained, a machine learning training model is adopted to match the matching degree between students and teachers, then off-line training data is combined with prediction data for splicing according to the model to obtain a latest prediction model, the prediction model is an iterative decision tree model, and finally, course arrangement results obtained according to the prediction model are output. The invention can realize that proper teachers are arranged for students in an optimal mode, and solves the problems of low efficiency and course arrangement conflict of the existing course arrangement.
Description
Technical Field
The invention relates to the technical field of teaching management, in particular to an intelligent course arrangement system and method based on a machine learning algorithm.
Background
As is well known in the industry, a school timetable is a command scheduling table for daily teaching work and other activities of a school, which is not only a bridge for students and teachers to attend classes, but also has direct influence on the unified arrangement of other works, for example, when more courses need to be arranged, manual class arrangement often takes the mutual lost, and the workload of the whole process from a class arrangement plan to a timetable is huge. In the traditional course arrangement mode, the requirement on the experience of course arrangement personnel is high, too many uncertain factors exist, for example, the quantity of students is large, the courses are many, the change is frequent, the resources of an education system are limited, the complexity of course arrangement is determined, whether the course arrangement reasonably and directly influences the progress of teaching, and the essence of course arrangement work is to arrange reasonable time for student courses and any course teachers, so that the teaching resources can not conflict.
The existing manual course arrangement has some problems, such as low course arrangement efficiency and course arrangement conflict; the traditional intelligent course arrangement is based on rules to match students and teachers, particularly the teaching arrangement of a very-day system, for example, through some limiting rules, such as whether the students and teachers come from the same province, whether the students and teachers have the same gender, whether the students have proper time and the like, the mode can ensure that the students have the teachers to go to the course, but the unmatched condition of teacher resources is often caused, and the condition of optimal matching cannot be achieved; meanwhile, some students have personalized requirements, such as situations requiring active teachers, interactive teachers and the like, and in summary, the personalized requirements cannot be met by traditional intelligent lesson arrangement.
Aiming at the current situation and problems in the prior art, the inventor of the application intends to provide an intelligent course arrangement system and method, in particular to an intelligent course arrangement system and method based on a machine learning algorithm.
The intelligent course arrangement system and the intelligent course arrangement method not only improve the course arrangement efficiency of the teaching teacher and reduce the complex workload, but also form the best matching effect between the teacher and the students.
Disclosure of Invention
The invention aims to provide an intelligent course arrangement system and method aiming at the current situation and problems in the prior art, and particularly relates to an intelligent course arrangement system and method based on a machine learning algorithm.
The intelligent course arrangement system and method based on the machine learning algorithm can realize that proper teachers are arranged for students in an optimal mode, and solve the problems of low efficiency and course arrangement conflict of the existing course arrangement.
The invention aims to solve the technical problem that proper teachers are arranged for students in an optimal mode so as to reduce the pressure of manual course arrangement and improve the efficiency of manual course arrangement.
In order to achieve the purpose, the invention provides an intelligent course arrangement system based on a machine learning algorithm, which comprises a teacher information management module, a student information management module, a sales information management module, a course information management module and a model selection module.
In the invention, the teacher information management module mainly comprises the teaching quality of a teacher, the teaching saturation of the teacher and the information matching degree of the teacher; the teaching quality of the teacher is based on the conversion condition of students brought by the teacher in a period of time, the condition of the teacher on formal lessons and the like; the teacher teaching saturation refers to the class hour number of the teacher in a period of time, the future idle time of the teacher and the like; the information matching degree of the teacher refers to whether the teacher and the student come from one place, whether the teacher and the student have common hobbies, and the like.
In the invention, the student information management module mainly refers to the class willingness degree of students, the personal basic information of students and the like;
in the invention, the sales information management module refers to sales capability value, sales order and drumbeat value and the like. The ability values include conversion rate, renewal rate and the like of students brought to sale. The due diligence value comprises working duration in a period of time, communication times of students and the like;
in the invention, the course information management module refers to the importance degree of the course, the attribute of the course and the like. The importance degree comprises the source of a student channel, whether the student is the referral, whether the student changes the teacher, the urban source of the student, the rate of selling escape orders, selling new endorsement assessment courses and the like.
In another aspect, the present invention provides an intelligent course arrangement method (as shown in fig. 1), which includes the following steps:
(1) acquiring historical data of teachers, students, sales and the like, wherein the historical data comprises personal basic information of the teachers, behavior information of the teachers, personal information of the students, behavior information of the sales and the like;
(2) according to the historical data, matching degree between the students and the teachers is fitted and matched, and the conversion rate of the courses is equivalent to the matching degree between the students and the teachers, so that the optimization goal of the invention is to improve the conversion rate of the courses, namely the machine learning training model is characterized by personal information, behavior information and the like of the teachers, the students and sales, and the training goal is the conversion rate of the courses; the personal basic information of the teacher comprises sex, age group, academic calendar, graduation institutions, provinces of colleges and universities, the number of 985 of graduation institutions of the teacher, the first subject of the teacher, the class of preference of the teacher and the like; the behavior information of the teacher comprises the duration of the total class, the number of active students, the number of new signs of the evaluation class and the like. The personal basic information of the students comprises gender, provinces of the students, cities of the students, grades of the cities of the students, whether the students are transferred to the introductions or not and the like; the behavior data of the students comprises the number of new courses for sale, the rate of the escape of the students and the like. The personal basic information for sale comprises the gender of sale, the province of sale, the city of sale, the grade of the city of sale, the time of employment, the number of new courses signed and the conversion rate of the new courses signed and the like;
(3) counting data of newly signed students, teachers, sales and the like in a certain time period; the statistical data comprises student basic personal information, behavior information, teacher basic dimension information, behavior information and the like.
(4) Training the model according to the target conversion rate, the student basic dimension information, the behavior information, the teacher basic dimension information, the behavior information and the like; the method specifically comprises the following steps: dividing the sampled data into positive and negative sample data, wherein the positive sample data is the data of students who newly sign an assessment course and converted into formal courses, and the negative sample data is the data of students who newly sign the assessment course and not converted into formal courses;
(5) according to model offline training data and combined with prediction data splicing, obtaining a latest prediction model, wherein the prediction model is eXtreme Gradient Boosting (XGboost);
the XGboost is one of Boosting algorithms, the Boosting algorithm is based on the idea that a plurality of weak classifiers are integrated to form a strong classifier, because the XGboost is a tree lifting model, a plurality of tree models are integrated to form a strong classifier, and the used tree model is a CART regression tree model;
the optimal objective function of the XGboost model is as follows:
where T represents the number of leaf nodes and w represents the score of a leaf node. Gamma can control the number of leaf nodes, and lambda can control the fraction of the leaf nodes not to be too large, so as to prevent overfitting;
(6) and outputting the course arrangement result obtained according to the prediction model.
The intelligent course arrangement system and the intelligent course arrangement method not only improve the course arrangement efficiency of the teacher, reduce the complex workload, but also form the beneficial effect of optimal matching between the teacher and the students.
The invention provides an intelligent course arrangement system and method based on a machine learning algorithm, which are characterized in that a system comprising a teacher information management module, a student information management module, a sales information management module, a course information management module and a model selection module is adopted to obtain historical data of teachers, students, sales and the like, a machine learning training model is adopted to fit and match the matching degree between the students and teachers, then the model is spliced according to model off-line training data and combined with prediction data to obtain a prediction model, namely an iterative decision tree model, and finally, course arrangement results obtained according to the prediction model are output.
Practice shows that the invention can realize that proper teachers are arranged for students in an optimal mode, solves the problems of low efficiency and conflict of course arrangement in the prior art, improves the course arrangement efficiency of teaching teachers, reduces complex workload, and simultaneously forms an optimal matching effect between the teachers and the students.
Drawings
FIG. 1 is a schematic diagram of the intelligent course scheduling system and method according to the present invention.
An embodiment of the present invention will be described with reference to fig. 1. The present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a specific operation process are given, but the scope of the present invention is not limited to the following embodiments.
Detailed Description
Example 1 Intelligent course scheduling
According to the implementation principle schematic diagram of the intelligent course arrangement system and the method shown in fig. 1, the implementation steps are as follows:
one) sampling of samples:
the intelligent course arrangement model based on the machine learning algorithm is adopted to match students and teachers to carry out lessons in the optimal degree;
firstly, filtering out teachers meeting conditions based on business rules, for example, if the students have time, the teachers have time; whether the teacher is saturated with the amount of class in the last period of time, etc. Secondly, sampling data such as courses, teachers, students and sales, and the like, and specifically comprising the following steps:
(1) acquiring sampling data, wherein the sampling data comprises the basic dimension information of the teacher, the behavior information of the teacher, the basic dimension information of the students, the behavior information of the students and the sales behavior information; the method specifically comprises the following steps:
i dynamic property: class duration, number of active students, number of late arrival times, number of early exit times, number of students brought by a teacher, number of times of being changed, and class refusal;
ii static attributes: the number of days of the teacher in work, the working property of the teacher, the correction time of the teacher, the class of colleges and universities of the teacher, the channel of the teacher, the gender and the age;
iii output tag: distribution of conversion (new signatures, number of conversions);
(2) dividing a training set and a test set according to time periods; the training set comprises a positive sample and a negative sample, the current class time is taken as a reference, the positive sample is converted for the course in the next two weeks, and the negative sample is not converted for the course in the next two weeks. The test set is to collect course data of students and teachers who have the same class by taking the time of the latest month as a node so as to verify the prediction effect of the model.
II), establishing characteristic engineering:
whether the course is converted or not is not only related to the behaviors of students, but also closely related to the teaching level and education concept of teachers, the service level of sales and the service capability; after the business investigation and model practice, the invention extracts the personal basic information of students, the behavior data of students, the personal basic information of teachers, the behavior information of teachers and the personal basic information for sale; the personal basic information of the students comprises gender, provinces of the students, cities of the students, grades of the cities of the students, whether to transfer introduction and the like; the student behavior data comprises the number of new courses sold correspondingly, the rate of student escaping orders and the like. The teacher personal basic information comprises gender, age group, academic calendar, colleges and universities, provinces of colleges and universities, 985 of colleges and universities, first subjects of the teacher, class of preference of the teacher and the like. The teacher behavior information comprises the total class duration, the number of active students, the number of new signs and conversion of the evaluation class and the like; the basic information of the sales individuals comprises the sex of sales, the province of sales, the city of sales, the grade of the city of sales, the time of job entry, the number of new courses signed and converted, the conversion rate of the new courses signed and the like;
thirdly), setting each parameter of the objective function by adopting a model XGboost prediction result;
the optimal objective function of the XGboost model is as follows:
where T represents the number of leaf nodes and w represents the score of a leaf node. Gamma can control the number of leaf nodes, and lambda can control the fraction of the leaf nodes not to be too large, so as to prevent overfitting;
in the embodiment, a machine learning training model is adopted to fit and match the matching degree between students and teachers, then the prediction model, namely the iterative decision tree model, is obtained according to model off-line training data and combined with prediction data for splicing, and finally, the course arrangement result obtained according to the prediction model is output. The result shows that the invention can realize that a proper teacher is arranged for the students in an optimal mode, solves the problems of low efficiency and course arrangement conflict of the existing course arrangement and can form the effect of optimal matching between the teacher and the students.
Claims (6)
1. The intelligent course arrangement system is characterized by comprising a teacher information management module, a student information management module, a sales information management module, a course information management module and a model selection module.
2. The intelligent course scheduling system of claim 1, wherein: the teacher information management module comprises the teaching quality of a teacher, the teaching saturation of the teacher and the information matching degree of the teacher;
the teaching quality of the teacher comprises the conversion condition of students carried by the teacher in a period of time and the condition of the teacher on formal lessons;
the teacher teaching saturation is the class hour number of the teacher in a period of time and the future free time of the teacher;
the information matching degree of the teacher is whether the teacher and the students come from one place and have common hobbies.
3. The intelligent course scheduling system of claim 1, wherein: the student information management module comprises the willingness degree of the student in class and the personal basic information of the student.
4. The intelligent course scheduling system of claim 1, wherein: the sales information management module comprises a sales capability value and a sales attendance value; the sales capability value comprises the conversion rate and the renewal rate of students brought to sales; the sales work diligence value comprises working time length in a period of time and communication times of students.
5. The intelligent course scheduling system of claim 1, wherein: the course information management module comprises course importance and course attributes; the importance degrees comprise the source of a student channel, whether students are referrals, whether students change teachers, the source of a student city, the rate of selling escape orders and selling new endorsement assessment courses.
6. An intelligent course arrangement method based on a machine learning algorithm is characterized by comprising the following steps:
(1) obtaining historical data of teachers, students, sales and the like;
(2) according to the obtained historical data, matching degree between the students and the teachers is matched in a fitting mode;
(3) counting data of newly signed students, teachers, sales and the like in a certain time period;
(4) training the model according to the target conversion rate, the student basic dimension information, the behavior information, the teacher basic dimension information, the behavior information and the like;
(5) splicing according to model off-line training data and combined with prediction data to obtain a prediction model;
(6) and outputting the course arrangement result obtained according to the prediction model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910583971.6A CN112149941A (en) | 2019-06-28 | 2019-06-28 | Intelligent course arrangement system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910583971.6A CN112149941A (en) | 2019-06-28 | 2019-06-28 | Intelligent course arrangement system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112149941A true CN112149941A (en) | 2020-12-29 |
Family
ID=73891750
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910583971.6A Pending CN112149941A (en) | 2019-06-28 | 2019-06-28 | Intelligent course arrangement system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112149941A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112949925A (en) * | 2021-03-09 | 2021-06-11 | 北京昱新科技有限公司 | Online live course sales product optimization system and method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107767280A (en) * | 2017-10-16 | 2018-03-06 | 湖北文理学院 | A kind of high-quality node detecting method based on element of time |
| CN107832936A (en) * | 2017-10-31 | 2018-03-23 | 北京新学道教育科技有限公司 | A kind of E-learning evaluation method and system based on cloud data |
| CN109427218A (en) * | 2017-08-25 | 2019-03-05 | 北京三好互动教育科技有限公司 | A kind of on-line education system and method |
| US20190138614A1 (en) * | 2017-11-07 | 2019-05-09 | Beijing Dami Technology Co., Ltd. | Method for recommending a teacher in a network teaching system |
| CN110162554A (en) * | 2019-05-24 | 2019-08-23 | 北京谦仁科技有限公司 | Data processing method, device, storage medium and electronic equipment |
-
2019
- 2019-06-28 CN CN201910583971.6A patent/CN112149941A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109427218A (en) * | 2017-08-25 | 2019-03-05 | 北京三好互动教育科技有限公司 | A kind of on-line education system and method |
| CN107767280A (en) * | 2017-10-16 | 2018-03-06 | 湖北文理学院 | A kind of high-quality node detecting method based on element of time |
| CN107832936A (en) * | 2017-10-31 | 2018-03-23 | 北京新学道教育科技有限公司 | A kind of E-learning evaluation method and system based on cloud data |
| US20190138614A1 (en) * | 2017-11-07 | 2019-05-09 | Beijing Dami Technology Co., Ltd. | Method for recommending a teacher in a network teaching system |
| CN110162554A (en) * | 2019-05-24 | 2019-08-23 | 北京谦仁科技有限公司 | Data processing method, device, storage medium and electronic equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112949925A (en) * | 2021-03-09 | 2021-06-11 | 北京昱新科技有限公司 | Online live course sales product optimization system and method |
| CN112949925B (en) * | 2021-03-09 | 2024-02-09 | 北京昱新科技有限公司 | Sales product optimization system and method for online live course |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Dexter | School technology leadership: Artifacts in systems of practice | |
| CN108805405A (en) | A kind of teaching assessment system and its construction method | |
| Madheswari et al. | Changing paradigms of engineering education-An Indian perspective | |
| CN108510418A (en) | A kind of talent cultivation index system educational administration management system | |
| Skourdoumbis | Assessing the productivity of schools through two “what works” inputs, teacher quality and teacher effectiveness | |
| Crammond | Progressing enterprising education within universities | |
| CN112149941A (en) | Intelligent course arrangement system and method | |
| Warlizasusi et al. | The Role of Collegial Supervision of School Supervisors and Head of Developing Teacher's Pedagogic Competence in Rejang Lebong Regency | |
| Emil et al. | Prospects for the use of foreign experience of Distance Learning | |
| Doctor | A predictive model using machine learning algorithm in identifying students probability on passing semestral course | |
| Liu et al. | Using learning analytics technologies to find learning structures from online examination system | |
| Usman et al. | An analysis of production units implementation in vocational schools in Aceh Besar, Indonesia | |
| TWM606688U (en) | Cloud intelligent item bank system for scoring knowledge point | |
| Sharipbay et al. | Software for automation of activity of the personnel in the smart-university | |
| Adamu et al. | Technical and vocational education teachers computer competencies using artificial intelligence | |
| CN111462558A (en) | Wisdom education platform based on artificial intelligence | |
| Zakeri et al. | Identifying Challenges in the Field of Performance and Providing Strategies for Strengthening Local Learning Centers of the Literacy Movement: A Case Study of Hormozgan Province | |
| Kusumawati | Implementation of Total Quality Management (TQM) TKQ Education Bogor District | |
| Rugh et al. | Comparing STEM Schools on Algebra Performance | |
| Zhang et al. | Construction of CDIO Integrated Teaching Management System of Software Course Based on Internet of Things | |
| Ode-sri et al. | A Case Study of How Centers of Excellence on TVET Are Operated in Asia and Europe to Enhance an Understanding of Definitions and Classification | |
| Orszaghova et al. | Perspectives and innovations in tertiary education in Slovakia | |
| Levkovich | Gender–related equal opportunities to develop the economy in stem subjects in international contexts (Israel and other countries) | |
| Lee et al. | Does the Knowledge Economy Advance the Green Economy? An Evaluation of Green Jobs in the 100 Largest Metropolitan Regions in the US | |
| Fungtammasan | Industry-oriented graduate programs in Thailand: A review |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20201229 |
|
| WD01 | Invention patent application deemed withdrawn after publication |