CN117575265A

CN117575265A - Intelligent course arrangement system, method and product based on multiple condition demands

Info

Publication number: CN117575265A
Application number: CN202311612958.1A
Authority: CN
Inventors: 李翔; 赵璧; 詹歆; 吴美玲
Original assignee: Xinlicheng Education Technology Co ltd
Current assignee: Xinlicheng Education Technology Co ltd
Priority date: 2023-11-29
Filing date: 2023-11-29
Publication date: 2024-02-20

Abstract

The invention provides an intelligent course arrangement system, method and product based on multiple condition demands, relating to the field of intelligent course arrangement, wherein the system comprises: the user interface is used for inputting multiple condition requirements of a user on course arrangement information; the screening module is used for screening out the class arrangement related information corresponding to the multiple condition demands; the course arrangement related information comprises course information dimension, lecturer information dimension, teacher information dimension and teaching, researching and course arrangement rules; the lecturer determining module is used for determining lecturers meeting the multiple condition requirements according to the screened lecture-ranking related information; the lecturer recommended value sequence generation module is used for calculating lecturer recommended values corresponding to lectures meeting the multiple condition requirements according to the lecturer information dimension and sequentially generating lecturer recommended value sequences; and the course arrangement plan generation module is used for generating a course arrangement plan according to the lecturer recommended value sequence based on an intelligent course arrangement algorithm. The invention can improve the rationality of the course arrangement plan.

Description

Intelligent course arrangement system, method and product based on multiple condition demands

Technical Field

The invention relates to the field of intelligent course arrangement, in particular to an intelligent course arrangement system, method and product based on multiple condition requirements.

Background

The existing mainstream course arrangement system is a course arrangement system developed based on a fixed school district fixed course arrangement mode (such as a course arrangement mode of a junior middle school of a primary school), can not provide course arrangement rules meeting overall requirements aiming at special complicated course arrangement limiting requirements and national multi-school district point sharing lecturer resource requirements, and can solve the problems that lecturer resource course arrangement rate is low, high-level lectures are arranged to a low-level school district for course arrangement, unreasonable course arrangement places lead to the fact that lectures cross school district commute time is too high, and lectures are continuously arranged to have too full of rest to influence teaching effects. Affecting corporate efficiency.

Disclosure of Invention

The invention aims to provide an intelligent course arrangement system, method and product based on multiple condition requirements, so as to solve the problem that the course arrangement plan of the existing intelligent course arrangement system is unreasonable.

In order to achieve the above object, the present invention provides the following solutions:

an intelligent course arrangement system based on multiple conditional demands, comprising:

the user interface is used for inputting multiple condition requirements of a user on course arrangement information;

the screening module is used for screening out the class arrangement related information corresponding to the multiple condition demands; the course arrangement related information comprises course information dimension, lecturer information dimension, teacher information dimension and teaching, researching and course arrangement rules;

The lecturer determining module is used for determining lecturers meeting the multiple condition requirements according to the screened lecture-ranking related information;

the lecturer recommended value sequence generation module is used for calculating lecturer recommended values corresponding to lectures meeting the multiple condition requirements according to the lecturer information dimension and sequentially generating lecturer recommended value sequences;

and the course arrangement plan generation module is used for generating a course arrangement plan according to the lecturer recommended value sequence based on an intelligent course arrangement algorithm.

Optionally, the method further comprises:

and the data processing module is used for cleaning and formatting the multiple condition requirements and converting the processed multiple condition requirements into standard formats required by the intelligent course arrangement system based on the multiple condition requirements.

Optionally, the method further comprises:

the system security module is used for sequentially carrying out format verification, data filtering and authority verification on the processed multiple condition demands to generate a security log record; the security log record is used for recording the operation log and the security event of the user.

Optionally, the lecturer recommended value sequence generating module specifically includes:

the lecturer information dimension score determining unit is used for determining a lecturer information dimension score according to the lecturer information dimension;

The lecturer recommended value calculation unit is used for calculating lecturer recommended values corresponding to lectures meeting the multiple condition requirements according to the sum of the dimension scores, the lecturer state recommended coefficient and the lecturer teaching proficiency recommended coefficient;

and the lecturer recommended value sequence generating unit is used for sequencing the lecturer recommended values in the order from big to small or from small to big to generate a lecturer recommended value sequence.

Optionally, the method further comprises:

the feedback module is used for collecting and analyzing feedback information of the user on the course arrangement plan; the feedback information comprises satisfaction evaluation, curriculum schedule advice and use experience;

and the optimizing module is used for adjusting the course arrangement plan according to the feedback information and generating an optimized course arrangement plan.

Optionally, the method further comprises:

and the visualization module is used for visualizing the course arrangement plan.

Optionally, the method further comprises:

the personalized recommendation module is used for personalized recommendation of course arrangement plan suggestions according to historical data and feedback information of the user; the historical data includes course participation records, school achievements and performances, attendance records, and learning preferences and interests.

An intelligent course arrangement method based on multiple condition demands, comprising:

Inputting multiple condition demands of a user on course arrangement information;

screening out relevant information of course arrangement corresponding to the multiple condition demands; the course arrangement related information comprises course information dimension, lecturer information dimension, teacher information dimension and teaching, researching and course arrangement rules;

determining lecturers meeting the multiple condition requirements according to the screened lesson-arranging related information;

according to the lecturer information dimension, calculating lecturer recommended values corresponding to lectures meeting the multiple condition requirements, and generating a lecturer recommended value sequence in sequence;

based on an intelligent course arrangement algorithm, a course arrangement plan is generated according to the lecturer recommended value sequence.

An electronic device comprising a memory for storing a computer program and a processor that runs the computer program to cause the electronic device to perform the intelligent lesson-arranging method based on multiple conditional demands described above.

A computer readable storage medium storing a computer program which when executed by a processor implements the intelligent lesson-arranging method based on multiple condition requirements described above.

According to the specific embodiment provided by the invention, the invention discloses the following technical effects: the invention provides an intelligent course arrangement system, method and product based on multiple condition demands, which are used for determining corresponding course arrangement related information with multiple dimensions based on multiple condition demands of users on course arrangement information so as to screen lecturers meeting the multiple condition demands, calculating corresponding lecturer recommended values to generate a course arrangement plan and considering the course arrangement related information with the multiple dimensions, thereby improving the rationality of the course arrangement plan and improving teaching effects.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic diagram of an intelligent course arrangement system based on multiple condition requirements according to the present invention;

FIG. 2 is a diagram of a student's self-test pie chart according to the present invention;

FIG. 3 is a pie chart of the present invention after learning to speak by the public;

FIG. 4 is a pie chart of the high-quality communication product force model provided by the invention;

FIG. 5 is a pie chart of a force model of a business communication product provided by the invention;

FIG. 6 is a pie chart of a manager communication product force model provided by the invention;

FIG. 7 is a diagram of a radar chart of personal competence values of a learner provided by the present invention;

FIG. 8 is a radar chart of learned post-speech competence provided by the present invention;

FIG. 9 is a graph of an analysis of a student's ability to learn prior to talking in the public, in accordance with the present invention;

FIG. 10 is a diagram showing the ability analysis of a learner after learning to speak in the public;

FIG. 11 is a diagram of a model radar of mass speaking product force provided by the present invention;

FIG. 12 is a view of a pilot force spoken product force model radar provided by the present invention;

FIG. 13 is a diagram of a force model radar for an impact mentor Ban Chanpin provided by the present invention;

fig. 14 is a schematic diagram of a service module architecture of a course arrangement system according to the present invention;

fig. 15 is a schematic diagram of an execution flow of the course arrangement system provided by the present invention.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

The invention aims to provide an intelligent course arrangement system, method and product based on multiple condition requirements, which can improve the rationality of a course arrangement plan.

In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.

Example 1

As shown in fig. 1, the intelligent course arrangement system based on multiple condition requirements of the present invention includes:

the user interface 1 is used for inputting multiple condition demands of a user on course arrangement information.

The screening module 2 is used for screening out the class arrangement related information corresponding to the multiple condition demands; the course arrangement related information comprises a course information dimension, a lecturer information dimension, a teacher information dimension and teaching, researching and course arrangement rules.

In practical use, the lesson-related information is stored in a database management system (Data Base Management System, DBMS).

Course information dimensions include course number, course name, course start time, course end time, number of courses, type of lessons on (work-on, work-on-weekend), total time of course, status of course release, number of inventory (number of undelivered persons), and the like.

The lecturer information dimension includes lecturer name, lecturer phone, lecturer level, the longest number of days of continuous lecture by lectures, whether or not the lectures are in the same city, lecturer resident place, lecturer characteristics (title, lecture experience, number of service students, reputation, etc.), and physical status (normal, ill, false, etc.).

Classroom information dimensions include classroom names, classroom IDs, school zones, classroom locations, classroom numbers, school zone levels, lecture distances, and the like.

Some other dimensions are also included, such as: course arrangement rules for teaching (priority of service class and service salon will be higher than delivery class) and temporary tuning.

And the lecturer determining module 3 is used for determining lecturers meeting the multiple condition requirements according to the screened lecture-ranking related information.

And the lecturer recommended value sequence generation module 4 is used for calculating lecturer recommended values corresponding to lectures meeting the multiple condition requirements according to the lecturer information dimension and sequentially generating lecturer recommended value sequences.

In practical application, the lecturer recommended value sequence generating module 4 specifically includes: the lecturer information dimension score determining unit is used for determining a lecturer information dimension score according to the lecturer information dimension; the lecturer recommended value calculation unit is used for calculating lecturer recommended values corresponding to lectures meeting the multiple condition requirements according to the sum of the dimension scores, the lecturer state recommended coefficient and the lecturer teaching proficiency recommended coefficient; and the lecturer recommended value sequence generating unit is used for sequencing the lecturer recommended values in the order from big to small or from small to big to generate a lecturer recommended value sequence.

For example: and selecting the lecturer grade, the longest continuous lecture days, the adjacent school zone state, lecturer teaching experience, the number of lectures serving students and the lecturer school zone matching degree from the lecturer dimension information, wherein the lecturer recommendation value= (lecturer grade recommendation score+lecturer longest continuous lecture days recommendation score+adjacent school zone state recommendation score+lecture experience recommendation score+lecture serving student number recommendation score+lecture school zone matching degree recommendation score) ×lecturer state recommendation coefficient.

And the course arrangement plan generation module 5 is used for generating a course arrangement plan according to the lecturer recommended value sequence based on an intelligent course arrangement algorithm.

In practical application, the specific course of course arrangement is as follows:

1. the intelligent course arrangement algorithm (Intelligent class scheduling Algorithm, IA) obtains data containing information of school zones, classrooms, lecturers and the like from the DBMS.

And 2. The IA uses an intelligent algorithm to generate a course arrangement plan according to the input relevant information of course arrangement, such as the class of a lecturer, the class of a school zone, the teaching distance, the longest continuous teaching days of the lecturer, the resident location, whether the lecturer is in the same city or not and other multiple condition requirements.

The detailed process of generating a course layout plan typically involves a number of steps including data preparation, algorithm selection, course layout plan generation, optimization, and the like. The following steps are specific:

1. data preparation (DataPreparation)

Acquisition Data (Data Retrieval):

the object is: basic data required for the course is acquired from a database management system (DBMS).

The operation is as follows: data containing information of school zones, classrooms, lecturers and the like is acquired through database query or other modes.

Preparing lesson-related information (Prepare Scheduling Information):

the object is: the detailed information required for the course arrangement and preparation will be used in the intelligent course arrangement algorithm.

The operation is as follows: including multiple demands such as the level of the lecturer, the level of the school district, the teaching distance, the longest continuous teaching days of the lecturer, the resident location, whether the lecturer is in the same city, etc. This may involve preprocessing and formatting the data.

2. Algorithm selection (Algorithm Selection)

Select intelligent course arrangement algorithm (Select Intelligent Scheduling Algorithm):

the object is: and selecting an applicable intelligent algorithm according to the system requirements and the complexity of course arrangement.

The operation is as follows: possible algorithms include genetic algorithms, simulated annealing algorithms, tabu searches, and the like. The algorithm selected should be able to generate a reasonable course arrangement plan in the event that multiple conditional demands are met.

3. Course arrangement plan generation (Scheduling Plan Generation)

Applying a smart algorithm (Apply Intelligent Algorithm):

the object is: a course scheduling plan is generated using the selected intelligent algorithm.

The operation is as follows: the IA generates an initial course arrangement scheme using an intelligent algorithm according to input course arrangement related information, such as a lecturer level, a school zone level, and the like. This scheme is based on an algorithm that takes into account multiple conditions.

4. Optimization (Optimization)

Consider other constraints (Consider Other Constraints):

the object is: ensuring that the generated course arrangement plan meets other constraints.

The operation is as follows: the lecture planning may not fully meet all conditions such as classroom availability, curriculum duration, lecture available time for lectures, etc. Optimization is performed, and the course scheduling plan is adjusted to ensure the rationality and feasibility of the course scheduling plan.

Combined with other information (Incorporate Additional Information):

the object is: other information is used to further optimize the course scheduling.

The operation is as follows: further fine tuning and optimization of the course arrangement plan may be required in conjunction with other information, such as calendar, special events, etc.

5. To the visualization module (Transmission to Visualization Module)

Transmitting the generated course arrangement plan to a visualization module (Transfer Generated Plan to Visualization Module):

the object is: and graphically displaying the generated course arrangement plan to a user.

The operation is as follows: and transmitting the lesson planning generated and optimized by the intelligent algorithm to a visualization module. This module presents the course scheduling plan to the user, enabling the user to view the course scheduling situation through an intuitive graphical interface.

Together, these five steps constitute the overall process of course planning generation, covering all key links from data preparation to final presentation.

The ia optimizes the generated course arrangement plan in combination with other constraints such as classroom availability, course duration, lecture available time of lecturer, etc. to ensure the rationality and feasibility of the course arrangement plan.

The class planning generated by the ia is transferred to a visualization module.

5. The visualization module graphically presents the course placement plan to the user, who can view and fine tune the course placement plan through the user interface 1.

The user may fine tune the scheduling, classroom allocation, etc. to meet specific needs or adjust the course placement plan.

6. The fine tuning feedback of the user is collected and passed to the feedback module.

7. The feedback module performs data analysis on the feedback of the user, extracts valuable information and modes, and feeds the information back to the intelligent course arrangement algorithm.

And 8, the IA optimizes and adjusts by using feedback information of the user, and provides a reference for generating a next course arrangement plan so as to improve the course arrangement quality and meet the user requirements.

9. The personalized recommendation module provides customized course arrangement suggestions for the user according to the historical data, feedback and personalized requirements of the user. For example, appropriate courses and lectures are recommended according to the learning score, learning preference, and personal development direction of the user.

Through the above process, data is acquired from the DBMS and a course arrangement plan is generated using multiple conditional requirements and intelligent algorithms.

The visualization module graphically displays the course arrangement plan to the user, and the user can conduct fine adjustment and feedback. The feedback module collects user feedback information and provides the user feedback information for the IA to optimize, and the personalized recommendation module provides customized course arrangement suggestions according to the personalized requirements of the user.

In practical applications, the invention further comprises: and the data processing module is used for cleaning and formatting the multiple condition requirements and converting the processed multiple condition requirements into standard formats required by the intelligent course arrangement system based on the multiple condition requirements.

The data cleaning and formatting process comprises the following specific steps:

data cleaning: and cleaning the input course arrangement information, removing unnecessary characters, blank spaces or special symbols, and ensuring the accuracy and consistency of data.

Data deduplication: and if the repeated data record exists, performing de-duplication processing to avoid the influence of the repeated data on the operation and the result of the course arrangement system.

Missing data processing: missing data, such as missing time, place, etc., which may be present, is detected and processed. Missing information can be supplemented by default filling or interacting with the user.

And (5) format verification: and verifying whether the format of the input data meets the expected requirements, such as a date format, a time format, a place format and the like. If the format is not satisfactory, corresponding correction is carried out or the user is prompted to input again.

Data conversion: and processing the data needing format conversion, and converting the data into a standard format required by a system so as to facilitate subsequent processing and storage.

Specific process of formatting:

the specific process of information formatting is as follows:

data type conversion: the input data is subjected to appropriate data type conversion according to the meaning and purpose thereof, for example, character string type conversion into numerical value type, date type conversion into standard date format, and the like.

Data normalization: and carrying out standardized processing on the data to ensure the consistency and normalization of the data. For example, the input of the places is formatted uniformly, so that consistency of place names is ensured, and subsequent course arrangement and inquiry are facilitated.

Data normalization: and carrying out normalization processing on data with different magnitudes and ranges so as to eliminate the difference between the data and ensure the comparability and the processibility of the data.

And (3) data coding: and according to the specification and the requirements of the system, the specific data is coded so as to improve the storage and processing efficiency of the data.

And (3) data verification: and verifying the formatted data to ensure the integrity and correctness of the data. For example, check whether the time is reasonable, whether the place is valid, etc.

Through the specific process of the supplementary information cleaning and formatting, the quality and the usability of the input data can be ensured, and an accurate and consistent data basis is provided for the subsequent course arrangement system work.

In practical applications, the invention further comprises: the system security module is used for sequentially carrying out format verification, data filtering and authority verification on the processed multiple condition demands to generate a security log record; the security log record is used for recording the operation log and the security event of the user.

In practical application, the system security module checks user input to prevent malicious attacks.

The specific security inspection process includes the following aspects:

input verification: the security module can verify the lesson-arranging information input by the user, so that the input data format is ensured to be correct and meets the requirements of the system. For example, for date and time information, the security module will verify that its format is correct to prevent illegal entry.

And (3) data filtering: the security module may filter the lesson-removing information entered by the user to filter out inputs that may contain malicious codes or dangerous characters. This may be accomplished by using techniques such as security filters or regular expressions to prevent security vulnerabilities such as cross site scripting attacks (XSS) or SQL injection.

The process of filtering lesson-removal information entered by a user by a security module involves a number of aspects, the primary purpose being to prevent malicious attacks and to ensure the legitimacy of the entered data. The process is an important link for guaranteeing the security in the course arrangement system, and the system can effectively prevent various malicious attacks and illegal input through multi-level verification and filtration.

Illustrating:

it is assumed that when the user inputs lecture-placement information through the user interface 1, there is an input box for inputting a lecturer name. The user entered the following: "John'; DROP TABLE Courses; - - "is a typical SQL injection attack attempt, where the user attempts to destroy the system database by entering special characters.

The following is a detailed description of the process by which the security module filters user input:

1. user input:

the user inputs lecture-placement information through the user interface 1, which includes an input box for inputting a lecturer name.

The user inputs: "John'; DROPTABLE Courses; - - "

2, data filtering process:

the security module performs input verification and data filtering after receiving user input.

Input verification: the security module first verifies the data format entered by the user to ensure that it meets the requirements of the system, e.g., the name contains only legal characters.

And (3) data filtering: the security module filters out inputs that may contain malicious code or dangerous characters using techniques such as security filters or regular expressions. In this example, the security module detects that the input contains a quotation mark and an SQL keyword, and processes the same to prevent SQL injection attacks.

3. Function of safety filter:

the security filter recognizes that special characters in the input, such as single quotation marks, may be subject to an escape or deletion operation to prevent such characters from being misinterpreted as part of the database query.

In this example, the single quotation mark in the input may be either escape as a double single quotation mark or deleted directly, preventing it from affecting the database query statement.

4. Delivering to a course arrangement system:

after the security module finishes filtering, the processed user input is transmitted to other modules of the course arrangement system, so that only information which is legal and does not contain malicious codes is further processed.

By means of the example, the security module in the course arrangement system successfully prevents SQL injection attacks possibly initiated by users, and input security is ensured. The security mechanism is helpful for protecting the system from malicious attacks and illegal inputs, and ensuring the safe operation of the course arrangement system.

And (3) authority verification: the security module can verify the identity and authority of the user, so that only the authorized user can conduct course arrangement operation. This may be achieved through user authentication and authorization mechanisms such as user name and password verification, role authority verification, etc.

Security log record: the security module may record the user's log of operations and security events for tracking and analysis when security problems or anomalies occur. This may help system administrators discover and resolve security threats in a timely manner.

In summary, the system security module plays an important role when the user inputs the course arrangement information through the user interface 1, and protects the system from malicious attack and illegal input through verification, filtering, authority verification and other modes, thereby ensuring the safe operation of the course arrangement system.

In practical applications, the invention further comprises: the feedback module is used for collecting and analyzing feedback information of the user on the course arrangement plan; the feedback information comprises satisfaction evaluation, curriculum schedule advice and use experience; and the optimizing module is used for adjusting the course arrangement plan according to the feedback information and generating an optimized course arrangement plan.

In practical application, the feedback information refers to feedback of the user on the course arrangement plan.

When the user views and fine-tunes the course arrangement plan, a rating, opinion, or suggestion for the course arrangement plan may be provided.

Such feedback information may include the following:

1. satisfaction evaluation: the user may evaluate the overall satisfaction of the course arrangement program, for example, giving a five-star rating or providing a textual description.

2. Course arrangement opinion: the user may make comments or suggestions for a particular course arrangement, such as adjusting the time, place, or lecturer of a certain course.

3. The use experience is as follows: users can share their experience and feel during use of the course arrangement system, including feedback on ease of use, interface design, functionality, etc.

In the actual operation, it is assumed that the user views the generated course arrangement plan through the user interface 1, and finds that the course arrangement on the day is not reasonable, and hopes to adjust the time of a lesson on the day. The user provides feedback on the user interface 1 and indicates a desire to adjust the lesson from morning to afternoon.

Feedback information for these users is transmitted to the feedback module. The feedback module collects and analyzes feedback from the user and identifies the user's needs and preferences. In this example, the feedback module analysis finds that the user has a particular preference for the time of day for which the lesson was scheduled, i.e., hoped to adjust the lesson to afternoon.

And then, the feedback module feeds back feedback information and analysis results of the user to the intelligent course arrangement algorithm. Upon receipt of the feedback information, the IA will consider this feedback as a reference for the next course planning generation. According to the feedback of the user, the IA can adjust the optimization strategy or constraint condition in the course arrangement algorithm so as to better meet the requirement of the user.

When the next course scheduling plan is generated, the IA acquires the course scheduling related information from the DBMS by using the feedback information of the user and the adjusted course scheduling algorithm, and generates a new course scheduling plan. In this way, the IA takes feedback from the user into account, improving accuracy of course placement and user satisfaction.

The process is circularly carried out, and as the user continuously provides feedback and the system continuously optimizes the course scheduling algorithm, the course scheduling plan generated each time can better meet the requirements and preferences of the user.

In practical applications, the invention further comprises: and the visualization module is used for visualizing the course arrangement plan.

In practical applications, the invention further comprises: the personalized recommendation module is used for personalized recommendation of course arrangement plan suggestions according to historical data and feedback information of the user; the historical data includes course participation records, school achievements and performances, attendance records, and learning preferences and interests.

1. Course participation record: records of courses and training activities in which the user participated in the past, including course names, lecturer of lectures, duration of courses, and the like.

2. Learning performance and manifestation: data such as learning score, test score, job completion status, etc. of the user in the past courses are used for evaluating learning ability and performance of the user.

3. Attendance records: the attendance records of the user when participating in courses in the past, including attendance rates, times of late morning receptions, etc., are used to evaluate the learning attitudes and participation of the user.

4. Learning preferences and interests: the learning preference and interest of the user are presumed according to the type, theme, lecturer and other information of the user participating in the course in the past.

If the user is satisfied with the course arrangement of a particular lecturer and proposes that the lecture can continue to be arranged in future lectures, the personalized recommendation module may preferably recommend the relevant lecture of the lecturer to the user based on the user's history data and this feedback.

Through collecting and analyzing the feedback of the user, the personalized recommendation module can better know the preference, opinion and requirement of the user, so that personalized course arrangement advice is provided for the user, and the learning experience and satisfaction of the user are improved.

In the actual operation process, it is assumed that the user takes part in course arrangement for a plurality of times in the past several months, and the course arrangement plan is evaluated and fed back by the feedback function provided by the system. The history data of the user includes the engaged courses, attendance records, learning achievements, class arrangement preferences, and the like.

The personalized recommendation module firstly analyzes and models according to historical data of the user. The method can analyze the preference, learning ability and course arrangement history of the user by using a machine learning algorithm or other recommendation technology to find out potential modes and associations. For example, the personalized recommendation module may find the user easier to learn during a particular time period, more interested in certain types of courses, or higher ratings for courses of a particular lecturer.

The personalized recommendation module is used for analyzing and modeling according to historical data of a user through the following steps:

1. and (3) data collection:

user history data: the personalized recommendation module first collects historical data of the user, including courses in which the user participates, attendance records, learning achievements, course arrangement histories and the like. These data are the basis for understanding user behavior and preferences.

2. Data preprocessing:

data cleaning and conversion: and cleaning the collected user history data, and processing the missing value and the abnormal value. Converting the data into a format suitable for processing by a machine learning algorithm may require normalization or normalization.

3. Characteristic engineering:

feature selection and extraction: the selection of appropriate features prior to modeling is critical to model performance. Feature engineering involves selecting features related to recommended goals, which may include course type, lecturer information, lecture time, etc. This helps to improve the accuracy and generalization ability of the model.

4. Model selection:

machine learning algorithms or recommendation techniques: an appropriate machine learning algorithm or recommendation is selected for modeling. Common algorithms include collaborative filtering, content filtering, deep learning, and the like. The algorithm selected should be able to learn the underlying patterns and associations from the user history data.

5. Model training:

training a model: the selected model is trained using the user history data. The model learns the user's preferences, learning ability, and course placement history to provide more accurate recommendations in future courses.

6. Model evaluation:

evaluating model performance: the model is evaluated using evaluation indicators (e.g., accuracy, recall, F1 score, etc.). This helps determine the validity and adaptability of the model, and whether further adjustments or optimizations are needed.

7. Personalized recommendation generation:

generating a recommendation: after model training is completed, the personalized recommendation module can generate personalized course arrangement suggestions according to the current state and the requirements of the user. For example, if the model finds that the user is more likely to learn during a particular time period, is more interested in certain types of courses, or has a higher rating for a particular lecturer's course, the recommendation module may provide a corresponding recommendation based on these findings.

Through the process, the personalized recommendation module can utilize the historical data of the user to build understanding of the user behavior, provide course arrangement suggestions for the user according with interests and learning requirements of the user based on the understanding, and improve learning experience and satisfaction of the user.

Let us assume that a student, we call it a Ming. The junior high school uses a course-scheduling system in the past school, which records his course-scheduling history, attendance records, school achievements, and his feedback on each course-scheduling plan. Now, the personalized recommendation module analyzes and models according to the small historical data to provide course arrangement suggestions more meeting the interests and learning requirements of the user.

1. And (3) data collection:

the history data of the minds includes courses in which he participates, schedules of each course arrangement, lecturer information, and evaluation and feedback of each course arrangement.

2. Data preprocessing:

the data is cleaned and converted, possible missing values or abnormal values are processed, and the quality and the integrity of the data are ensured.

3. Characteristic engineering:

features associated with the recommended goals are selected. This may include the type of course, characteristics of the lecturer (e.g., lecture style, professional area), time of lecture, etc.

4. Model selection:

a machine learning algorithm suitable for personalized recommendation, such as collaborative filtering or deep learning models, is selected. The algorithm should be able to learn his learning preferences and patterns from the small, bright, historical data.

5. Model training:

the selected recommendation model is trained using the historical data of the minds. The model will learn less well-defined preferences, learning capabilities and course placement history to provide more accurate recommendations in future course placement.

6. Model evaluation:

and evaluating the model by using an evaluation index to ensure the accuracy and the effectiveness of the model. This may include using cross-validation to simulate the behavior of the model on unseen data.

7. Personalized recommendation generation:

once the model training is completed and the assessment passes, the personalized recommendation module may generate personalized course placement suggestions using the current state and requirements of the minds. For example, if the model finds that a min prefers lessons in the afternoon, the lesson rating for a particular lecturer is high, and the recommendation module may provide relevant lessons for the min based on these findings.

Through the process, the system can understand the learning behavior of the user by utilizing the small and clear historical data, and provide the lesson arrangement advice which is more suitable for the personal interests and learning requirements of the user for the user through the personalized recommendation module.

Based on these analysis results, the personalized recommendation module may generate personalized course placement suggestions. According to the preference and learning ability of the user, the user history data is combined to recommend course arrangement meeting the interest and learning requirement of the user. For example, if the personalized recommendation module finds that the user shows a high interest and learning ability in a certain class of courses, it may recommend similar courses or courses related thereto.

These personalized course-ranking suggestions will be sent to the user interface 1, where the user can view and evaluate the suggestions. The user may also provide feedback such as satisfaction with the advice, interest level, or specific needs. These feedback will be collected and integrated into the user's historical data by the personalized recommendation module.

The next time the user uses the system again to conduct lesson scheduling, the personalized recommendation module will continue to generate more personalized lesson scheduling suggestions according to the historical data and feedback of the user. By continuously collecting and analyzing feedback of users, the personalized recommendation module can continuously optimize course arrangement suggestions and provide recommendation results which meet the requirements of the users.

Therefore, the personalized recommendation module generates personalized course-arranging suggestions by analyzing historical data and feedback of the user and utilizing a recommendation algorithm, and continuously optimizes the suggestion results along with the feedback of the user so as to provide better user experience and meet the requirements of the user.

The personalized recommendation module gathers and analyzes these historical data, extracts features, preferences and capabilities of the relevant user, and models them in conjunction with the user's feedback information. Therefore, the recommendation module can know the characteristics of the user in aspects of learning tendency, hobbies and interests, learning capacity and the like according to the historical data of the user, and provide more personalized class-arrangement suggestions meeting the requirements of the user.

If the personalized recommendation module finds that courses in which the user participated in the past are mainly focused on psychological-type training and shows better learning results and active learning attitudes in the courses, the module can recommend the user to continue to participate in courses related to psychological-type training. In addition, if the user's historical data shows a higher course rating for a particular lecturer, the personalized recommendation module may recommend other courses of that lecturer to the user preferentially.

Through analyzing historical data and feedback of the user, the personalized recommendation module can better understand preferences and demands of the user, so that more accurate and personalized course arrangement suggestions are provided for the user, and learning experience and effect of the user are improved.

The intelligent lesson arranging system based on multiple condition requirements provided by the invention is applied to talent expression, and table 1 is a product force model dimension schematic table related to talent expression courses, as shown in table 1.

TABLE 1

Fig. 2-6 show corresponding course cake-shaped diagrams after students finish the oral presentation of courses, and each course has corresponding course dimension improvement on the premise that attendance records are qualified and examination results are qualified.

The "after learning the speech of the public" is better than the "student's self-test" pie chart, which has a data dimension improvement, that is, represents the improvement of the ability value (the test will be performed again) after the student finishes learning, as shown in fig. 7-10, and table 2 is a comparison table of the student's self-test and each ability after the student's speech, as shown in table 2.

TABLE 2

Dimension(s)	Deductive presentation	Logic thinking	Same theory of mind	Emotion management	Self value	Tissue coordination
							Self-test by students	5	10	20	10	15	20
After the people speak	20	20	30	15	20	25
							Speaking to the public	15	10	10	5	5	5
Psychological diathesis	5	5	10	15	10	5
							Lecture art	15	10	5	5	10	5
Leading force to take part in	50	20	10	10	50	10
							Influence guide class	70	15	15	15	70	15
Blossom of life	10	15	40	70	50	15
							Creations of life	20	25	70	90	80	15
High quality communication	5	5	15	5	5	15
							Business communication	5	5	15	5	10	10
Manager communication	15	15	20	10	70	70

A plurality of product force model radar maps are shown in fig. 11-13.

Example two

An intelligent course arrangement system (hereinafter referred to as system) based on multiple condition requirements provided in the first embodiment, the process of cooperative work of the intelligent course arrangement algorithm is as follows:

1. and the basic information of the lecturer is manually input in advance, the basic information of the classroom is manually input, and the recommendation weight of each information is input in advance and enters the DBMS.

2. And the responsible person in the school zone submits a lesson scheduling application to the system according to the lesson name.

2. The system recommends the lecturer of the course to the school zone according to the intelligent algorithm.

3. The weight and the score of each screening item are different, and the intelligent algorithm can sort according to the overall recommendation score of each lecturer from high to low to conduct intelligent recommendation.

The intelligent course arrangement pre-conditions are as follows:

1. the lecturer basic information input system in advance comprises:

1.1, lecturer name. XXX (administrator inputs this information in advance, which would be present in the system).

1.2, lecturer phone. 13XXXXXXXXX (the administrator enters this information in advance, which would be present in the system).

1.3, lecturer level. Senior lecturer, advanced lecturer, intermediate lecturer, and primary lecturer. (the administrator inputs this information in advance, which would be pre-existing in the system).

1.4, the maximum continuous days of lectures. 1 day, 2 days, 3 days, 4 days, 5 days, 6 days, 7 days, and more. (the administrator inputs this information in advance, which would be pre-existing in the system).

1.5, lecturer resident location. First North China, second North China, first China, second China, third China, first south China, and second south China. (the administrator inputs this information in advance, which would be pre-existing in the system).

1.6, whether the city is the same. Same city/different city. The method refers to whether the current location of the lecturer is the same as the geographical location of the lecture application submitted by the school district. (the system can judge whether the lectures are in the same city or not according to the geographical position of the lecture place of the lecturer and the lecture application submitted by the school district).

1.7, lecturer teaching experience. 1-3 years; 3-5 years; 5-10 years; for 10 years or more. (the administrator inputs this information in advance, which would be pre-existing in the system).

1.8, the number of lecturer service students. 5 ten thousand+man times; 5-10 ten thousand+man times; 10-50 ten thousand times; 50-100 thousands of times; 100 tens of thousands of times and more (the administrator inputs this information in advance, and there is in advance in the system).

1.9, lecturer teaching style. Fun humor, good idea, passion overflow, gentle and durable, creative initiation, interactive guidance, practice guidance, encouragement appreciation, interdisciplinary connection, etc. (administrator inputs this information in advance, will exist in the system in advance).

1.10, lecturer status. Normal, sick, false, etc. (the administrator inputs this information in advance, which would be pre-existing in the system).

1.11, the proficiency of the lecturer to the course. Proficiency, general, and inadequacy. (the administrator inputs this information in advance, which would be pre-existing in the system).

2. Classroom basic information advanced input system:

2.1, classroom name. XXX (administrator inputs this information in advance, which would be present in the system).

2.2, classroom ID. The unique ID of this classroom (the administrator enters this information in advance, which would be present in the system).

2.3, correcting area. The name of the school zone in the classroom (the administrator inputs this information in advance, which will be present in the system).

2.4, classroom places. The actual location of the classroom (the administrator enters this information in advance, which may be present in the system).

2.5, school zone grades. A+, A, B, C (administrator inputs this information in advance, which may be pre-existing in the system).

2.6, the adjacent situation of the large area. The first North China region is adjacent to the second North China region; the second North China area is adjacent to the first North China area; the first Huazhong region is adjacent to the second Huazhong region and the third Huazhong region; the second Huazhong region is adjacent to the first Huazhong region and the third Huazhong region; the third Huazhong region is adjacent to the first Huazhong region and the second Huazhong region; the first south China area is adjacent to the second south China area; the second south China area is adjacent to the first south China area.

3. Course basic information input system in advance:

and 3.1, arranging lessons and numbering. The unique ID of the course arrangement information is automatically generated in sequence when the course arrangement information is issued.

3.2, course names. Such as "high-intelligence business communication", the "popular speech", the "lecture art", etc., the curriculum name is unique. (the administrator inputs this information in advance, which would be pre-existing in the system).

3.3, course starting time. Format year-month-day. (the administrator inputs this information in advance, which would be pre-existing in the system).

And 3.4, course ending time. Format year-month-day. (the administrator inputs this information in advance, which would be pre-existing in the system).

3.5, course period number. The system numbers according to the names of the courses published in the system. For example: high definition is communication phase 101. The public speaks for period 23.

And 3.6, class type. Night shift, zhou Moban. (the administrator would enter this information in advance based on the start time of the course, and would be present in the system in advance). For example: the administrator inputs the lesson of "high-efficiency communication" in advance on day 7 and 1, and the lesson type is Zhou Moban since day 7 and 1 are Saturday.

And 3.7, course total hours. The total teaching time of the course. (the administrator inputs this information in advance, which would be pre-existing in the system). For example: the system of the "high-efficiency business communication" defaults to 12 hours. The overall course of the course here shows the number 12.

And 3.8, curriculum release state. Published, unpublished.

3.9, number of inventory people (number of undelivered people). Refer to how many people remain for the course. The actual number of people in a class is also required. The data is calculated according to the course name, the data is increased according to the newly added number of the registered persons, and the data is reduced according to the number of students who have actually completed the course.

4. The recommendation score of each information is input in advance into the system:

4.1, lecturer level recommendation score (1.3). Recommendation score: 30 points (senior lecturer), recommendation score: 20 points (advanced lecturer), recommendation score: 10 points (middle lecturer), recommendation score: 5 minutes (primary lecturer).

4.2, the maximum continuous lesson days (1.4) of the lecturer. Recommendation score: 30 minutes (1 day), recommendation score: 25 points (2 days), recommendation score: 20 points (3 days), recommendation score: 15 points (4 days), recommendation score: 10 points (5 days), recommendation score: score 5 (6 days), recommendation score: 0 minutes (7 days and more).

And 4.3, correcting the adjacent states of the areas. Recommendation score for the same city: 30 points (according to 1.6 rules of the same city), adjacent recommendation scores: 20 points (according to the rule of 2.6 adjacency), non-adjacency recommendation score: 5 minutes (according to the rule of 2.6 adjacency).

4.4, lecturer teaching experience. Recommendation score: 20 minutes (10 years and more), 15 minutes (5-10 years), 10 minutes (3-5 years), 5 minutes (1-3 years).

4.5, the number of lecturer service students. Recommendation score: 5 minutes (0-5 ten thousand+man times); 10 minutes (5-10 ten thousand+twice); 15 minutes (10-50 ten thousand times); 20 minutes (50-100 tens of thousands times); 25 minutes (100 tens of thousands times and more).

4.6, lecturer state. Recommendation coefficient: 1 (normal), 0 (ill), 0 (false).

And 4.7, correcting the matching degree of the area. Recommendation score: 30 (class a+ matched senior lecturer) 20 (class a+ matched senior lecturer) 10 (class a+ matched senior lecturer) 5 (class a+ matched senior lecturer) 20 (class a matched senior lecturer) 30 (class a matched senior lecturer) 10 (class a matched senior lecturer) 5 (class a matched senior lecturer) 10 (class B matched senior lecturer) 30 (class B matched senior lecturer) 5 (class C matched senior lecturer) 10 (class C matched senior lecturer) 20 (class C matched senior lecturer) 30 (class C matched senior lecturer).

4.8, teaching proficiency of lecturer. Recommendation system: 1.4 (proficiency), 1.2 (proficiency), 1 (general), 0 (failure). (rules based on proficiency of the lecturer at the lesson of 1.11).

Recommendation score calculation rules:

total recommendation score= (4.1+4.2+4.3+4.4+4.5+4.7) ×4.6×4.8.

The following examples are given:

a+ school district provides the course arrangement requirement of course "high-efficiency business communication", and the system automatically matches with the teacher and the resource library:

lecturer 1: the teaching proficiency of the senior teacher in the class is proficiency, the number of days of continuous class is 4 days, the teacher is the adjacent large area of the school area, the teaching experience of the teacher is 8 years, the number of students of the teacher is 30 ten thousand, and the current state of the teacher is normal (no illness and false).

The recommended index of the prune teacher is: (30+15+20+15+30) ×1×1.3=175 minutes.

Lecturer 2: the teaching proficiency of the high-grade teacher, namely the teacher, on the course of the gate is general, the number of days of continuous teaching is 1 day, the teacher is the same district as the city of the school, the teaching experience of the teacher is 12 years, the number of staff is 80 ten thousand, and the current state of the teacher is normal (no illness or false).

The recommended index of the nasu teacher is: (20+30+30+20+20) ×1×1=140 minutes.

Lecturer 3: the teaching proficiency of the primary teacher to the course is insufficient, the number of days of continuous teaching is 8 days, the teacher is a large area which is not adjacent to the school area, the teaching experience of the teacher is 1 year, the number of staff is 2 ten thousand, and the current state of the teacher is normal (no illness or false).

The recommended index of the natal teacher is: (5+0+5+5+5) ×1×0=0 minutes.

Example III

The invention also provides an intelligent course arrangement method based on multiple condition demands, which comprises the following steps:

multiple conditional demands of the user for the course arrangement information are input.

Screening out relevant information of course arrangement corresponding to the multiple condition demands; the course arrangement related information comprises a course information dimension, a lecturer information dimension, a teacher information dimension and teaching, researching and course arrangement rules.

And determining lecturers meeting the multiple condition requirements according to the screened lesson-arranging related information.

And calculating lecturer recommended values corresponding to lectures meeting the multiple condition requirements according to the lecturer information dimension, and generating a lecturer recommended value sequence in sequence.

Example IV

The intelligent course arrangement system based on the multiple condition requirements provided by the embodiment I of the invention has a constructed course arrangement system business module architecture interface as shown in figure 14, wherein the course arrangement system business module architecture comprises course arrangement rules, lectures, products, course arrangement lists, reports and course-about APP which are in butt joint through the system; the course arrangement rules display the adaptation time, the course arrangement time, the continuous course days, whether the courses are in the same city or not, and the lowest stock number and the grades are matched; the lecturer displays the lecturer grade, the adequacy course, the leave information, the BEST address and the teaching range; the product displays the lesson time and the minimum inventory number; the course arrangement list displays course matching, lecturer matching, course arrangement date judgment, course arrangement date multi-selection, course arrangement detail generation and grade matching; the report displays the lecturer's lecture calendar, the analysis of the lecture course and the analysis of the lecture date; the lesson appointment APP displays lesson information, lesson time, lesson place and lesson release.

The execution flow is shown in fig. 15, based on teaching and research formulation rules, whether the pushing rules are met or not is judged according to purchase conditions, if the pushing rules are met, the course arrangement information is pushed to carry out course arrangement, audit and judge whether the course arrangement information is adjusted or not, if the course arrangement information is adjusted, the course arrangement information is edited and modified and the course is distributed, if the course is not modified, the course is directly issued, and the course is uploaded to an applet or an APP for display through an API interface to finish course arrangement; if not, not pushing the message, judging whether the message is in accordance with the course arrangement for multiple times, if so, pushing the course arrangement message, and if not, not pushing the message.

The invention provides a system for flexibly configuring various changing conditions at the front end to carry out system calculation and provide an optimal course arrangement plan, so that various conflict problems are avoided, and the course arrangement efficiency and the lecture efficiency of a lecturer are greatly improved.

The front end flexibly configures various changing conditions including:

1. after the lectures are arranged, the lecturer suddenly asks for the help, the lecturer needs to adjust the lecture arranging time and arrange the lectures in time, and the lectures can be replaced and added for the lectures arranged in the school area.

2. The school district is temporarily given lessons, needs to temporarily arrange lecturers meeting the conditions to give lessons.

3. The demands of students on lessons rise suddenly, the lessons can be arranged temporarily, and the information of the lessons-arranging school zone and the lecturer can be quickly known.

Calculating and proposing an optimal course arrangement plan comprises the following steps:

1. the high-grade lecturer arranges to the high-grade school district, improves the teaching conversion.

2. The lecturer can take lessons in different cities within one month, and the intelligent calculation is listed in the optimal city sequence, so that the commute time and cost are reduced.

The various collision problems avoided include:

1. excessive days of continuous lessons of the same lecturer lead to tired lectures and low working efficiency.

2. When the same lecturer plays class across cities, the arranged time is too compact, so that the lecturer cannot arrive at a class place in time or a bad experience caused by special driving is formed.

3. Due to the fact that the course arrangement is unreasonable, the unbalanced problem that the course arrangement rate of part of lectures is high and the course arrangement rate of part of lectures is low occurs.

4. The lecturer asks for the conflict caused by the fact that the information is not considered but the lectures are arranged.

The efficiency of arranging lessons and lecture efficiency of lecturer include by a wide margin:

1. the course arrangement in each school district is reasonable, and the course arrangement requirement of each month is met.

2. Each lecturer arranges the course rationally, and the lecturer is good in experience of going on business, and the state of having lessons is good.

3. The management and control degree of lecture-arranger resources by the operation department is high, and the lecture-arranger resources can be flexibly adjusted and quickly decided.

Example five

The embodiment of the invention provides an electronic device which comprises a memory and a processor, wherein the memory is used for storing a computer program, and the processor runs the computer program to enable the electronic device to execute the intelligent lesson arranging method based on multiple condition requirements.

Claims

1. An intelligent course arrangement system based on multiple condition requirements, comprising:

2. The intelligent lesson-planning system based on multiple condition requirements of claim 1, further comprising:

3. The intelligent lesson-planning system based on multiple condition requirements of claim 2, further comprising:

4. The intelligent lecture scheduling system based on multiple condition requirements according to claim 1, wherein the lecturer recommended value sequence generating module specifically includes:

5. The intelligent lesson-planning system based on multiple condition requirements of claim 1, further comprising:

6. The intelligent lesson-planning system based on multiple condition requirements of claim 1, further comprising:

7. The intelligent lesson-planning system based on multiple condition requirements of claim 1, further comprising:

8. An intelligent course arrangement method based on multiple condition demands is characterized by comprising the following steps:

9. An electronic device comprising a memory for storing a computer program and a processor that runs the computer program to cause the electronic device to perform the multiple condition demand based intelligent lesson-arranging method of claim 8.

10. A computer readable storage medium, characterized in that it stores a computer program, which when executed by a processor implements the intelligent lesson-arranging method based on multiple condition requirements according to claim 8.