TWI447682B - Intelligent planning system and method for learning actives, and comupter program product and readable medium thereof - Google Patents

Description

Intelligent teaching plan planning system and method and its computer program product and record Recorded media

The invention relates to an intelligent teaching plan planning system and method, a computer program product thereof and a computer readable recording medium.

With the development of information technology, the computing speed of computer systems has been continuously improved, and the functions that they can perform have become more diverse. Computer systems have played an important role in human life and work. For example, in the case of teachers writing lesson plans, through the assistance of the Office software, teachers can design, write, and modify various teaching activities more easily, and complete a lesson plan based on teaching indicators.

Although the above office software can improve the efficiency of teachers writing lesson plans, such office software is only a platform for writing lesson plans on computer systems. All the contents of the lesson plans must be designed and planned by the teachers themselves. Therefore, even with the help of such office software, teachers still have to spend considerable time editing the lesson plans.

The invention provides an intelligent lesson planning system capable of automatically generating a lesson plan according to the needs of the teacher.

The invention provides an intelligent lesson planning method capable of automatically generating a lesson plan according to the needs of the teacher.

The present invention provides a computer program product that is loaded into a computer system After the system, the teaching plan can be automatically generated according to the needs of the teacher.

The invention provides a computer readable recording medium with a built-in program, wherein the stored program can automatically generate a lesson plan according to the needs of the teacher after being loaded into the computer system.

The exemplary embodiment of the present invention provides a smart teaching plan planning system, which includes a teaching ability index ontology knowledge database, a teaching activity ontology knowledge database, an input unit, and a smart teaching plan scheduling unit. The teaching ability index ontology knowledge database stores a plurality of teaching indicators. The teaching activity ontology knowledge database stores a plurality of teaching activity schemas, wherein each teaching activity base mold has a plurality of activity attributes and corresponds to at least one of the teaching indicators. The input unit is coupled to the teaching ability index ontology knowledge database, and is configured to input a plurality of planning parameters and select at least one of the teaching indicators from the teaching ability index ontology knowledge database. The intelligent lesson scheduling unit is coupled to the teaching activity ontology knowledge base and the input unit. The intelligent teaching plan scheduling unit selects from the teaching activity ontology knowledge database according to the input planning parameters, the selected teaching indicators, the activity attributes of each teaching activity model and the teaching indicators corresponding to each teaching activity model. At least one teaching activity model and a teaching plan based on the selected teaching activity model.

In an embodiment of the invention, the planning parameters include an expected teaching content keyword, an expected teaching hour, and an expected environmental parameter.

In an embodiment of the present invention, the activity attribute includes an activity indicator, an activity keyword, an activity time, a device, a teaching material, a group demand annotation, a special student annotation, and an activity content.

In an embodiment of the present invention, the intelligent teaching plan scheduling unit A multi-objective mathematical programming function is used to generate the above lesson plans.

In an embodiment of the invention, the intelligent lesson plan scheduling unit uses a Bin Packing algorithm to solve the multi-objective mathematical programming function.

In an embodiment of the present invention, the smart teaching plan planning system further includes a negotiating unit coupled to the smart lesson scheduling unit and configured to adjust the lesson generated by the intelligent lesson scheduling unit. The negotiation unit includes the expected teaching time fine-tuning interface, the expected teaching target fine-tuning interface, the expected environmental parameter fine-tuning interface, and the teaching activity exchange unit. The expected teaching hours fine-tuning interface is used to fine-tune the expected teaching hours. It is expected that the fine-tuning interface of the teaching objectives is to delete the selected teaching indicators or to select other teaching indicators from the ontology knowledge database of the teaching ability indicators. The environmental parameter fine-tuning interface is expected to be used to fine-tune the expected environmental parameters. The teaching activity conversion unit is configured to provide at least one teaching activity basic model, wherein the teaching activity basic model is provided for replacing the teaching activity basic model selected in the teaching plan.

In an embodiment of the present invention, the smart lesson planning system further includes a teacher preference database coupled to the smart lesson scheduling unit and configured to record the replaced teaching activity base model.

In an embodiment of the present invention, the intelligent lesson scheduling unit further generates the lesson according to the record of the teacher preference database.

In an embodiment of the present invention, the smart lesson planning system further includes a student database coupled to the smart lesson scheduling unit and configured to store a plurality of student basic materials.

In an embodiment of the present invention, the above intelligent teaching plan planning system The method further includes a grouping unit coupled to the smart lesson scheduling unit and configured to generate a student grouping result according to the student basic information.

In an embodiment of the invention, the grouping unit uses a genetic algorithm to generate the student grouping result.

An exemplary embodiment of the present invention provides a smart teaching plan planning method. The intelligent teaching plan planning method includes storing a plurality of teaching indicators in an ontology knowledge database of teaching ability indicators, and storing a plurality of teaching activity schemas in a teaching activity ontology knowledge database, wherein each teaching activity base The mold has multiple activity attributes and corresponds to at least one of the teaching indicators. The intelligent teaching plan planning method also includes inputting a plurality of planning parameters and selecting at least one of the teaching indicators from the teaching ability index ontology knowledge database. The intelligent teaching plan planning method further includes the teaching activity ontology knowledge database according to the input planning parameters, the selected teaching indicators, the activity attributes of each teaching activity model, and the teaching indicators corresponding to each teaching activity model. At least one teaching activity model is selected and a teaching plan is generated according to the selected teaching activity model.

In an embodiment of the invention, the step of inputting the planning parameters includes: inputting an expected teaching content keyword, an expected teaching hours, and an expected environmental parameter.

In an embodiment of the present invention, the foregoing is based on the input planning parameter, the selected teaching index, the activity attribute of each teaching activity model, and the teaching index corresponding to each teaching activity model. The step of selecting at least one of the teaching activity bases in the knowledge database and generating the lesson plans based on the selected teaching activity model includes: using a multi-mesh The mathematical programming function is selected from the teaching activity ontology knowledge database according to the input planning parameters, the selected teaching indicators, the activity attributes of each teaching activity model, and the teaching indicators corresponding to each teaching activity model. One of the teaching activities is based on a model and generates a lesson plan based on the selected teaching activity model.

In an embodiment of the present invention, the foregoing is based on the input planning parameter, the selected teaching index, the activity attribute of each teaching activity model, and the teaching index corresponding to each teaching activity model. The step of selecting at least one of the teaching activity bases in the knowledge database and generating the lesson plans according to the selected teaching activity model further includes: using a Bin Packing algorithm to solve the above multiple objective mathematical programming function.

In an embodiment of the present invention, the intelligent teaching plan planning method further includes: fine-tuning the expected teaching hours; deleting the selected teaching indicators or selecting other teaching indicators from the teaching ability index ontology knowledge database; fine-tuning the expected Environmental parameters; providing at least one teaching activity model, wherein the teaching activity model is provided for replacing the basic model of the teaching activity selected in the above teaching plan; and according to the fine-tuned expected teaching hours, the deleted teaching Indicators, re-selected instructional indicators, or a model of teaching activities that are replaced to adjust the resulting lesson plans.

In an embodiment of the present invention, the intelligent teaching plan planning method further includes recording the replaced teaching activity basic model in a teacher preference database.

In an embodiment of the present invention, the foregoing is based on the input planning parameters, the selected teaching indicators, the activity attributes of each teaching activity model, and The teaching index corresponding to each teaching activity model selects at least one of the teaching activity basic models from the teaching activity ontology knowledge database and generates a lesson plan according to the selected teaching activity base model, and further includes: according to the input plan Selecting at least one of the parameters from the teaching activity ontology knowledge database, parameters, selected teaching indicators, activity attributes of each teaching activity model, teaching indicators corresponding to each teaching activity model, and records of the teacher preference database The activity model is based on the selected teaching activity model to generate the lesson plan.

In an embodiment of the present invention, the smart teaching plan planning method further includes storing a plurality of student basic materials in a student database.

In an embodiment of the present invention, the smart teaching plan planning method further includes generating a student grouping result according to the student basic information.

In an embodiment of the present invention, the step of generating the student grouping result according to the student basic data comprises: generating the student grouping result by using a gene algorithm and according to the student basic data.

An exemplary embodiment of the present invention provides a computer program product including at least one program instruction, and the program instruction method is executed when the program instruction is loaded into a computer system.

An exemplary embodiment of the present invention provides a computer readable recording medium with a built-in program, and the smart teaching plan planning method is executed when the program is loaded into a computer system.

Based on the above, the intelligent lesson planning system of the exemplary embodiment of the present invention can quickly generate a lesson plan according to the needs of the teacher.

In order to make the above features and advantages of the present invention more obvious, the following The embodiments are described in detail with reference to the accompanying drawings.

FIG. 1 is a smart teaching plan planning system according to an exemplary embodiment of the present invention.

Referring to FIG. 1 , the smart lesson planning system 100 includes a smart lesson scheduling unit 102, an ontology knowledge database 104, a teaching activity ontology knowledge database 106, an input unit 108, and a student database 120. The grouping unit 130, the negotiating unit 140 and the teacher preference database 150.

The intelligent lesson scheduling unit 102 is configured to select from the teaching activity ontology knowledge database 106 according to various planning parameters, teaching indicators, activity attributes of each teaching activity model, and teaching indicators corresponding to each teaching activity model. The teaching activity model is based on the selected teaching activity model to automatically generate a lesson plan that meets the teacher's needs. In the present exemplary embodiment, the smart lesson scheduling unit 102 uses a multiple objective mathematical programming function and a Bin Packing algorithm to generate the lesson plans. Specifically, the plan of the lesson plan is a Constraint Satisfaction Problem (CSP), and the smart lesson scheduling unit 102 generates a corresponding multi-objective mathematical programming function according to the planning parameters input by the teacher and the expected teaching indicators; The boxing algorithm is used to find the multi-objective mathematical programming function generated by this; and according to the solution result, a lesson planning scheme that satisfies various restrictions is generated. The detailed functions of the smart lesson scheduling unit 102 will be described in more detail below with other components. In addition, it must be understood that despite In the present exemplary embodiment, the smart lesson scheduling unit 102 uses a multiple target mathematical programming function and a boxing algorithm to generate a lesson plan. However, the present invention is not limited thereto, and the smart lesson scheduling unit 102 may use other suitable functions. And other suitable algorithms to generate lesson plans

The teaching ability index ontology knowledge database 104 is coupled to the smart lesson scheduling unit 102 and is used to store information about a plurality of teaching indicators. Here, the so-called teaching index refers to the teaching goal achieved after the teacher performs the teaching activity. For example, in an English course, the teacher wants to teach students “can recognize the emotions and attitudes expressed by different sentences and tones”, “can participate in the classroom-directed discussion in the simple English”, “can describe life in a simple English context. People, things, things, etc., among which "can recognize the emotions and attitudes expressed by different sentence tones", "can participate in the classroom-directed discussion in the simple English" and "can describe the life related people in simple English" "Things, things," is the teaching index. In the present exemplary embodiment, various teaching indicators prepared by experts are classified and stored in the teaching ability index ontology knowledge database 104. For example, the teaching indicators stored in the teaching ability index ontology knowledge database 104 include English teaching indicators, Chinese teaching indicators, natural teaching indicators, and social teaching indicators.

The teaching activity ontology knowledge database 106 is coupled to the smart lesson scheduling unit 102 and is used to store a plurality of teaching activity schemas. Here, the basic model of the teaching activity is a model of the teaching activity established in advance, and the model of the teaching activity is established in the form of a basic model (also called "outline"). Specifically, each teaching activity stored in the teaching activity ontology knowledge database 106 is abstracted and modeled, and each teaching activity is set with a corresponding activity attribute. Therefore, when the teaching activity model is materialized into teaching activities, a rich and varied teaching activity can be generated. For example, the activity attributes of each teaching activity model include activity indicator attributes, activity keyword attributes, activity time attributes, equipment equipment attributes, teaching material attributes, grouping requirement annotation attributes, special student annotation attributes, and active content attributes. The following table is an example of a basic model of English teaching activities:

The activity indicator attribute is the teaching indicator corresponding to the basic model of this teaching activity. Specifically, after completing the teaching activities provided by the corresponding teaching activity model, the ability of the students to be taught is recorded in the activity indicator attributes. Here, since a teaching activity can simultaneously achieve a plurality of teaching indicators, the number of teaching indicators corresponding to the basic model of the teaching activity in the activity indicator attribute may be plural.

The activity keyword attribute is the type that records the base model of this teaching activity. In particular, the smart lesson scheduling unit 102 searches and filters the teaching activity model based on the data recorded in the activity keyword attributes.

The activity time attribute is the time required to record the teaching activities provided by the completion of this teaching activity. In the present exemplary embodiment, the time required to complete the teaching activity provided by the base of the teaching activity in the activity time attribute is set to a single value. However, the present invention is not limited thereto, and the time required to complete the teaching activity provided by the basic model of the teaching activity may also be set to a value having a range of upper and lower limits.

The equipment and equipment attributes are the equipment needed to record the teaching activities provided by the basic model of this teaching activity. Here, the equipment refers to a hardware device that can be used for teaching activities, such as a projector, a blackboard, a whiteboard, a computer, and the like.

The textbook attribute is the material required to record the teaching activities provided by the basic model of this teaching activity. Here, the textbook refers to the teaching props that the teacher needs to prepare, such as paper sheets, audio tapes, wall charts, photos, and the like.

The grouping requirement annotation attribute is to record whether the students need to be grouped when teaching activities provided by the basic model of this teaching activity. In some teaching activities, the students must be grouped in order to successfully complete the teaching activities. Therefore, the smart lesson scheduling unit 102 determines whether or not the instructed students are grouped by the grouping unit 130 based on the values in the grouping requirement annotation attribute.

The special student annotation attribute is to record whether special students need to be considered when conducting the teaching activities provided by the basic model of this teaching activity. In some teaching activities, it is designed to consider the special conditions of students. Therefore, the smart lesson scheduling unit 102 determines whether to arrange such teaching activities based on the values in the special student annotation attributes.

The activity content attribute is the teaching provided by the basic model of this teaching activity. The actual operation of the activity. Specifically, the complete steps and content of the teaching activity are recorded in the activity content attribute.

It must be understood that the activity attributes included in the teaching activity model in the present invention are not limited to the activity indicator attribute, the activity keyword attribute, the activity time attribute, the equipment equipment attribute, the teaching material attribute, the grouping requirement annotation attribute, the special student annotation attribute and Active content attribute.

Since the basic model of the teaching activity is established in a basic mode, the teaching activities provided can be generated based on the available equipment and materials. For example, the following table is an example of the materialized teaching activities corresponding to the above-mentioned basic model of English teaching activities, assuming that the equipment and equipment that can be used are “blackboards” and the available teaching materials are “flip charts”.

Materialized teaching activities

1. Show the extracurricular activity wall chart . After one minute, ask the students to tell what extracurricular activities are on the wall chart . At the beginning, students can answer single words or phrases, and then guide students to describe the wall charts they see in a sentence.

2. Write the sentences spoken by the students on the blackboard and guide the students to understand the correct statement of extracurricular activities .

3. Let the students see the flip chart and ask the students to tell what extracurricular activities they like (familiar).

The input unit 108 is coupled to the teaching ability indicator ontology knowledge database 104 and is configured to provide a lesson basic information interface 108a for the teacher to input the planning parameters.

Specifically, the teacher can input the expected teaching content keyword, the expected teaching time and the pre-preparation through the teaching plan basic information interface 108a of the input unit 108. Period environmental parameters.

The expected teaching content keyword refers to the teaching content and type of the lesson plan that the teacher wants to establish. For example, in the example in which the teacher inputs the expected teaching content keywords for "English" and "Extracurricular Activities" in the lesson basic information interface 108a of the input unit 108, the smart lesson scheduling unit 102 will input the expected teaching content according to the input. The keyword search is in the teaching activity ontology knowledge database 106 whose activity keyword attribute has a teaching activity model of "English" and "extracurricular activities".

The expected teaching hours refer to the number of teaching hours that the teacher wants to establish. For example, in the example where the teacher inputs the expected teaching hours for "45 minutes" in the lesson basic information interface 108a of the input unit 108, the smart lesson scheduling unit 102 will depend on the expected teaching hours and each teaching activity. The active time attribute of the base model is used to plan the lesson plans. That is to say, the intelligent lesson plan scheduling unit 102 plans the activity time of the teaching activity in the generated lesson plan to meet the expected teaching hours input by the teacher.

The expected environmental parameters refer to the equipment and materials needed for the lesson plan that the teacher wants to establish. For example, in the example where the teacher inputs the expected environmental parameters for "blackboard" and "flipchart" in the lesson basic information interface 108a of the input unit 108, the smart lesson scheduling unit 102 will depend on the expected environmental parameters and each The teaching equipment properties and teaching material properties of the teaching activity base model are used to plan the lesson plans. That is to say, the intelligent lesson plan scheduling unit 102 plans the activity time of the teaching activity in the generated lesson plan to meet the expected environmental parameters input by the teacher.

In addition, the input unit 108 provides a teaching indicator selection interface 108b. For the teacher to select the teaching index to be reached from the teaching ability index ontology knowledge database 104. Specifically, the teaching indicator selection interface 108b loads the stored teaching indicators from the teaching ability index ontology knowledge database 104 and provides them to the teacher for selection. In particular, the smart lesson scheduling unit 102 will plan a proposal based on the selected teaching metrics. That is to say, the intelligent lesson plan scheduling unit 102 plans the teaching activities in the generated lesson plans to achieve the expected teaching indicators input by the teacher.

Based on the above, when the teacher inputs the planning parameters and selects the expected teaching indicators in the lesson basic information interface 108a of the input unit 108 and the teaching index selection interface 108b, the smart teaching plan scheduling unit 102 selects according to the input planning parameters and the selected teaching parameters. The teaching indicators are expected to automatically select the teaching activity model that meets the teacher's expectations from the teaching activity ontology knowledge database 106 and generate the lesson plans according to the selected teaching activity model. For example, in the present exemplary embodiment, the generated lesson plans are output via output unit 110 (eg, display, printer, etc.).

The student database 120 is coupled to the smart lesson scheduling unit 102 and is used to store a plurality of student basic materials about the taught students. For example, the student's basic materials include the gender, personality (introversion or extroversion), and English proficiency (listening, speaking, reading, and writing) of the students.

The grouping unit 130 is coupled to the smart lesson scheduling unit 102 and the student database 120, and is used to group the students. In particular, in the example in which the grouping requirement annotation attribute of the teaching activity model selected by the smart lesson scheduling unit 102 is required to group the instructed students, the grouping unit 130 may use the gender based on the student basic data of the student database 120. The average or ability (eg, English ability) averages the group of students and outputs the student grouping results. In the present exemplary embodiment, the grouping unit 130 performs the above-described grouping using a genetic algorithm. However, it must be understood that the present invention is not limited thereto, and the grouping unit 130 may also use other suitable algorithms to group the students. In addition, the grouping unit 130 can also automatically select the group leader according to the needs of the teacher. For example, the grouping unit 130 weights the English ability (listening, speaking, reading, and writing) of each student, and selects the English ability as the leader.

It is worth mentioning that in another exemplary embodiment of the present invention, the student database 120 and the grouping unit 130 may be non-essential components. That is to say, the teacher can group the lecture students according to the lesson plan planned by the smart lesson scheduling unit 102, instead of using the student database 120 and the grouping unit 130.

The negotiation unit 140 is coupled to the smart lesson scheduling unit 102, and is configured to generate an adjustment suggestion of the expected teaching hours, the expected teaching index and the expected environmental parameter, and adjust the smart teaching plan scheduling unit 102 according to the teacher's input. Lesson plan. Specifically, when the smart lesson scheduling unit 102 fails to generate the lesson plan under the condition that the planning parameter input by the teacher and the selected expected teaching index are met, the teaching plan generated by the smart lesson scheduling unit 102 does not meet the teacher's expectation. The negotiation unit 140 generates a new lesson plan based on the fine-tuning information input by the teacher.

The negotiation unit 140 includes an expected teaching time fine adjustment interface 142, an expected teaching target fine adjustment interface 144, an expected environmental parameter fine adjustment interface 146, and a teaching activity exchange unit 148.

The expected teaching time fine-tuning interface 142 is used to fine-tune the expected teaching hours; the expected teaching target fine-tuning interface 144 is used to delete the selected teaching indicators or select other teaching indicators from the teaching ability index ontology knowledge database 104; The environmental parameter fine-tuning interface 146 is contemplated to fine tune the expected environmental parameters. Specifically, in the example in which the smart lesson scheduling unit 102 cannot generate a lesson plan under the condition that the teacher inputs the planned parameters and the selected expected teaching indicators, the teacher can fine-tune the expected teaching hours and the expected teaching indicators. And the expected environmental parameters to cause the smart lesson scheduling unit 102 to regenerate the lesson that satisfies all input conditions.

The teaching activity exchange unit 148 is a list of other teaching activity models for providing teaching indicators selected by the teacher among the teaching activity basic models stored in the teaching activity ontology knowledge database 106. Specifically, in the example in which the smart lesson scheduling unit 102 plans a lesson plan under the condition that the teacher inputs the planning parameters and selects the expected teaching index, if the teacher is dissatisfied with the smart lesson scheduling unit 102, In the case of a lesson plan, the teaching activity exchange unit 148 provides a list of other teaching activity models that can achieve the teaching indicators selected by the teacher, and the teacher can select a preferred teaching activity base model from the provided list to exchange the planning in the office. The basic model of teaching activities in the resulting lesson plans. In particular, when the teacher replaces the basic model of the teaching activity, the teaching activity exchange unit 148 checks whether the new lesson plans meet the constraints of the planning parameters input by the teacher (for example, does the expected teaching hours are met?), and checks the drawn In exchange for the dependence and sequence of the basic model of teaching activities and the original model of teaching activities.

The teacher preference database 150 is coupled to the negotiation unit 140 and smart The teaching plan scheduling unit is used to record the teaching activity base model and the preferred teaching activity basic model that the teacher replaces through the teaching activity exchange unit 148. That is to say, the teacher preference database 150 records the teaching activity model that the teacher prefers or does not prefer. In particular, when the teacher uses the smart lesson planning system 100 to generate the lesson plans, the smart lesson scheduling unit 102 intelligently generates the lesson plans that meet the teacher's expectations based on the information of the teacher preference database 150.

It is worth mentioning that in another exemplary embodiment of the present invention, the negotiating unit 140 and the teacher preference database 150 may be non-essential elements. That is to say, in the example of the non-negotiating unit 140 and the teacher preference database 150, the smart lesson planning system merely provides the function of automatically generating the lesson plan without providing the function of further negotiating with the teacher to generate the personalized lesson plan.

2 is a smart teaching plan planning method according to an exemplary embodiment of the present invention.

Referring to FIG. 2, first, in step S201, the teacher inputs the planning parameters and selects the teaching index to be reached. For example, the teacher inputs the expected teaching content keyword, the expected teaching hours, and the expected environmental parameters in the lesson basic information interface 108a, and selects the expected teaching indicator in the teaching indicator selection interface 108b.

Next, in step S203, it is determined whether the smart lesson scheduling unit 102 successfully generates the lesson plan. Specifically, in step S203, the smart lesson scheduling unit 102 attempts to perform teaching according to the input planning parameters, the selected teaching index, the activity attribute of each teaching activity model, and the basic model of each teaching activity. Indicators come from the teaching activity ontology knowledge database 106 The teaching activity model is selected and the teaching plan is generated according to the selected teaching activity model. As described above, a plurality of teaching activity models are pre-stored in the teaching activity ontology knowledge database 106, and each teaching activity base mold has a specific activity attribute. In step S203, the smart lesson scheduling unit 102 attempts to generate a lesson plan from among the pre-stored teaching activity basic models by selecting the teaching activity model that conforms to the planning parameters input in step S201 and the selected teaching index.

FIG. 3 is a detailed step of step S203.

Referring to FIG. 3, in step S301, the smart lesson scheduling unit 102 selects the teaching activity base model from the teaching activity ontology knowledge database 106 according to the teaching index. Specifically, the smart lesson scheduling unit 102 searches for the teaching activity model of the teaching activity ontology knowledge database 106 that conforms to the selected teaching index, the entered expected teaching content keyword, and the expected environmental parameter. In particular, the smart lesson scheduling unit 102 will simultaneously select the teaching activity base model by referring to the information in the teacher preference database 150.

In step S303, the smart lesson scheduling unit 102 determines whether the active time of the selected teaching activity model has reached the expected teaching hours entered.

If the activity time of the teaching activity model selected in step S303 does not reach the entered expected teaching hours, then step S301 is performed; otherwise, in step S305, the smart lesson scheduling unit 102 determines the selected one. Whether the basic model of teaching activities has reached the expected teaching indicators selected by the teacher.

If the teaching activity model selected in step S305 has been taught The expected teaching index selected by the teacher, in step S307, the smart lesson scheduling unit 102 generates an initial lesson plan according to the selected teaching activity base model, and outputs the result that the initial lesson plan has been generated; otherwise, judges the wisdom in step S309. The lesson plan scheduling unit 102 outputs the result that the initial lesson cannot be generated.

If the smart lesson scheduling unit 102 fails to generate the initial lesson plan in step S203, the negotiating unit 140 generates a parameter adjustment suggestion and receives the adjustment of the teacher input in step S205. Specifically, in step S205, the negotiating unit 140 generates suggestions for adjusting the expected teaching hours, the expected environmental parameters, and the selected teaching indicators according to the operation of the smart lesson scheduling unit 102, and the teacher can fine tune through the expected teaching hours. The interface 142, the expected instructional target fine-tuning interface 144, and the expected environmental parameter fine-tuning interface 146 input the expected adjustments. Next, step S203 is executed again.

If the smart lesson scheduling unit 102 successfully generates the initial lesson plan in step S203, then the smart lesson scheduling unit 102 determines in step S207 whether the teacher agrees with the generated initial lesson plan.

If the teacher agrees with the generated initial lesson in step S207, then the smart lesson scheduling unit 102 determines whether or not grouping is required in step S209. Specifically, the smart lesson scheduling unit 102 determines whether or not to perform grouping according to the grouping requirement annotation attribute of the selected teaching activity model.

If the smart lesson scheduling unit 102 determines that grouping is required, the grouping unit 130 will input the teacher according to the example in step S211 (example) For example, classifying students by gender average or ability average.

Next, the output unit 110 outputs the lesson plan in step S213, and the flow of FIG. 2 is ended.

If the teacher does not agree with the generated initial lesson plan in step S207, the negotiating unit 140 provides the other teaching activity basic model that can achieve the teaching index selected by the teacher according to the operation of the smart lesson scheduling unit 102 in step S215. The list, and in step S217, the teacher selects the base of the teaching activity to be exchanged according to the list provided by the negotiation unit 140.

Thereafter, in step S219, the negotiating unit 140 determines whether the new lesson plan meets the limitation of the planning parameter input by the teacher, and whether the dependency and the order of the translated teaching activity base model and the original planned teaching activity model are correct. .

If it is determined in step S219 that the new lesson plan meets the limitation of the planning parameter input by the teacher, and the dependency and order of the replaced teaching activity base model and the original planned teaching activity model are correct, then in step S221 The middle negotiation unit 140 adjusts the lesson plan, and then step S207 is executed.

If it is determined in step S219 that the new lesson plan does not meet the limitation of the planning parameter input by the teacher, or the dependency and order of the translated teaching activity base model and the original planned teaching activity model are incorrect, then In step S223, the negotiating unit 140 maintains the currently generated lesson and generates an error message, and step S207 is executed. That is to say, the negotiation unit 140 does not agree with the teaching activity model that the teacher has exchanged, and requests the teacher to confirm again.

It is worth mentioning that the negotiation unit 140 in step S221 will be about The adjusted information (i.e., the teacher's preferred and unsuited teaching activity model) is updated into the teacher preference database 150.

The following table is an execution example of the exemplary embodiment. When the teacher inputs the expected teaching content keyword (ie, holiday), the expected teaching hours (ie, 45 minutes) and the expected environment in the lesson basic information interface 108a of the input unit 108. After the parameters (ie, blackboard, wall chart) and the desired teaching indicators are selected in the lesson index selection interface 108b of the input unit 108, the smart lesson planning system 100 interacts with the teacher (as shown in the process of FIG. 2), and outputs Teaching plan.

Enter:

●Expected teaching content Keywords: Festival

●Expected teaching hours: 45 minutes

● Expected environmental parameters: blackboard, wall chart

● Teaching indicators: [1-2-2 can recognize the emotions and attitudes expressed by different sentence intonation] [2-2-2 can participate in the teacher-led discussion in the classroom with simple English] [2-2-4 can be in simple English Describe the people, things, and things involved in daily life]

Output (teaching plan):

● Activity 1 (15 minutes):

-1. Show the wall chart of the festival. After one minute, ask the students to tell which festivals are on the wall chart. At the beginning, students can answer single words or phrases, and then they can guide students to describe the contents of the wall charts as a whole sentence.

-2. Write the sentences spoken by the students on the blackboard and guide the students Know the correct way of saying the holiday.

-3. Let the students see the flip chart and ask the students to tell what festivals they like (familiar).

● Activity 2 (15 minutes):

-1. Let students pick up textbooks, simply describe the festival by storytelling, and draw students to understand the level of understanding and status.

-2. Have students spread the textbooks for students to read and explain the story.

-3. Send paper to allow students to rewrite the story and encourage students to write creatively into more interesting versions.

-4. Return it to a little extra work.

● Activity three (15 minutes):

-1. Show the holiday wall chart, write the relevant words on the blackboard, and take the students to read the words.

-2. Group students and give three to five minutes to observe the relationship between the wall chart and the listed words.

-3. Ask each group to send a student to the stage and use the words on the blackboard to create sentences related to the wall chart.

The invention further provides a computer program product, wherein the computer program product is composed of a plurality of program instructions. In particular, after loading these program instructions into the computer system and executing them, the steps of the above-mentioned smart lesson planning method can be completed, and the computer system has the function of a smart lesson planning system.

In addition, the above computer program product can be stored in a computer readable recording medium The computer readable recording medium can be any data storage device, which can be read by a computer system. For example, the computer readable recording medium is a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and a carrier. (for example, data transmission over the Internet).

In summary, the intelligent lesson planning system of the exemplary embodiment of the present invention can automatically plan a lesson plan according to the needs of the teacher, and adjust the planned lesson plan through interaction with the teacher. In addition, through the teacher preference database to record the results of interaction with teachers, the intelligent lesson planning system can continuously learn the teacher's preferences and plan the lesson plans based on the teacher's preferences. In addition, the intelligent lesson planning system of the exemplary embodiment of the present invention can automatically group the students according to the characteristics of the teaching activities.

Although the present invention has been disclosed in the above embodiments, it is not intended to limit the invention, and any one of ordinary skill in the art can make some modifications and refinements without departing from the spirit and scope of the invention. The scope of the invention is defined by the scope of the appended claims.

100‧‧‧Smart lesson planning system

102‧‧‧Smart lesson scheduling unit

104‧‧‧ Teaching ability index ontology knowledge database

106‧‧‧ Teaching Activity Ontology Knowledge Database

108‧‧‧Input unit

108a‧‧‧Basic information interface for teaching

108b‧‧‧ Teaching Indicator Selection Interface

110‧‧‧Output unit

120‧‧‧ Student Database

130‧‧‧ grouping unit

140‧‧ Consultation unit

142‧‧‧Expected teaching hours fine-tuning interface

144‧‧‧ Expected teaching target fine-tuning interface

146‧‧‧ Expected environmental parameter fine-tuning interface

148‧‧‧ Teaching activity exchange unit

150‧‧‧Teacher preference database

Steps of S201, S203, S205, S207, S209, S211, S213, S215, S217, S219, S221‧‧‧Smart lesson planning method

S301, S303, S305, S307, S309‧‧‧ steps to create a lesson plan

FIG. 1 is a smart teaching plan planning system according to an exemplary embodiment of the present invention.

2 is a smart teaching plan planning method according to an exemplary embodiment of the present invention.

FIG. 3 is a detailed step of step S203.

100‧‧‧Smart lesson planning system

102‧‧‧Smart lesson scheduling unit

104‧‧‧ Teaching ability index ontology knowledge database

106‧‧‧ Teaching Activity Ontology Knowledge Database

108‧‧‧Input unit

108a‧‧‧Basic information interface for teaching

108b‧‧‧ Teaching Indicator Selection Interface

110‧‧‧Output unit

120‧‧‧ Student Database

130‧‧‧ grouping unit

140‧‧ Consultation unit

142‧‧‧Expected teaching hours fine-tuning interface

144‧‧‧ Expected teaching target fine-tuning interface

146‧‧‧ Expected environmental parameter fine-tuning interface

148‧‧‧ Teaching activity exchange unit

150‧‧‧Teacher preference database

Claims (28)

A smart lesson planning system includes: a teaching ability index ontology knowledge database, storing a plurality of teaching indicators; a teaching activity ontology knowledge database, storing a plurality of teaching activity models (Schema), each of which teaching activities The base mold has a plurality of activity attributes and corresponds to at least one of the teaching indicators; an input unit is coupled to the teaching ability index ontology knowledge database for inputting a plurality of planning parameters and the ontology knowledge from the teaching ability index Selecting at least one of the teaching indicators in the database, wherein the planning parameter includes an expected teaching content keyword, an expected teaching time and an expected environmental parameter; and a smart teaching plan scheduling unit coupled to the The teaching activity ontology knowledge database and the input unit are configured to use a multi-objective mathematical programming function and according to the planning parameters input by the user, the selected teaching indicators, the activity attributes of each of the teaching activity models, and each a teaching indicator corresponding to the basic model of the teaching activity to select the teaching activity from the teaching activity ontology knowledge base Learning at least one active group based on teaching mode and the fundamental mode selected to produce a lesson plan. For example, the smart lesson planning system described in claim 1 wherein the activity attributes include an activity indicator, an activity keyword, an activity time, an equipment, a teaching material, a group demand note, and a special student. Annotate with an activity content. Such as the intelligent teaching plan planning system mentioned in item 1 of the patent application scope The smart lesson scheduling unit uses a Bin Packing algorithm to solve the multiple objective mathematical programming function. For example, the smart lesson planning system described in claim 1 further includes a negotiating unit coupled to the smart lesson scheduling unit for adjusting the lesson generated by the intelligent lesson scheduling unit, wherein The negotiation unit includes: an expected teaching time fine-tuning interface for fine-tuning the expected teaching hours; an expected teaching target fine-tuning interface for deleting the selected teaching indicators or selecting the teaching knowledge from the teaching ability index ontology database Other teaching indicators among the teaching indicators; an expected environmental parameter fine-tuning interface for fine-tuning the expected environmental parameters; and a teaching activity exchange unit for providing at least one teaching activity base of the teaching activity basic models The model, which provides the basic model of the teaching activity, is used to replace the basic model of the teaching activity selected in the lesson generated by the intelligent lesson scheduling unit. For example, the smart lesson planning system described in claim 4 of the patent application further includes: a teacher preference database coupled to the smart lesson scheduling unit and used to record the replaced teaching activity model. For example, the smart lesson planning system described in claim 5, wherein the smart lesson scheduling unit generates the lesson according to the record of the teacher preference database. Such as the intelligent teaching plan planning system mentioned in item 1 of the patent application scope The system further includes: a student database coupled to the smart lesson scheduling unit and configured to store a plurality of student basic materials. The smart lesson planning system as described in claim 7 further includes: a grouping unit coupled to the smart lesson scheduling unit and configured to generate a student grouping result according to the student basic materials. The smart lesson planning system as described in claim 8 wherein the grouping unit uses a genetic algorithm to generate the student grouping result. A smart teaching plan planning method includes: storing a plurality of teaching indicators in an ontology knowledge database of a teaching ability index; storing a plurality of teaching activity schemas in a teaching activity ontology knowledge database, wherein each of the teachings The teaching activity base mold has a plurality of activity attributes and corresponds to at least one of the teaching indicators; inputting a plurality of planning parameters; selecting at least one of the teaching indicators from the teaching ability index ontology knowledge database; and using a multi-objective mathematical programming function is based on the planning parameters input by the user, the selected teaching indicators, the activity attributes of each of the teaching activity models, and the teaching indicators corresponding to each of the teaching activity models The teaching activity ontology knowledge database automatically selects at least one of the teaching activity fundamental models and generates a teaching plan according to the selected teaching activity base model; wherein the steps of inputting the planning parameters include: Enter an expected instructional content keyword, an expected teaching hour, and an expected environmental parameter. For example, the smart lesson planning method described in claim 10, wherein the activity attributes include an activity indicator, an activity keyword, an activity time, a equipment, a teaching material, a group demand note, and a special student. Annotate with an activity content. For example, the smart lesson planning method described in claim 10, wherein the multiple objective mathematical programming function is used and based on the planning parameters input by the user, the selected teaching indicators, and the basic model of each of the teaching activities. The activity attribute and the teaching indicator corresponding to each of the teaching activity models select at least one of the teaching activity model bases from the teaching activity ontology knowledge database and generate the according to the selected teaching activity model The teaching steps further include: using a Bin Packing algorithm to solve the multi-objective mathematical programming function. For example, the smart lesson planning method described in claim 10 of the patent application includes: fine-tuning the expected teaching hours; deleting the selected teaching indicators or selecting the teaching indicators from the teaching ability index ontology knowledge database. Other teaching indicators; fine-tuning the expected environmental parameters; providing at least one teaching activity model in the basic model of the teaching activities, wherein the teaching activity model provided is used to replace the teaching selected in the teaching plan Active fundamental model; The resulting lesson plans are adjusted based on the fine-tuned expected teaching hours, the deleted teaching indicators, the re-selected teaching indicators, or the model of the teaching activity being exchanged. For example, the smart lesson planning method described in claim 13 of the patent application includes: recording the replaced teaching activity basic model in a teacher preference database. For example, the smart lesson planning method described in claim 14 wherein the multi-objective mathematical programming function is used and based on the planning parameters input by the user, the selected teaching indicators, and the basic model of each of the teaching activities. The activity attribute and the teaching indicator corresponding to each of the teaching activity models select at least one of the teaching activity model bases from the teaching activity ontology knowledge database and generate the according to the selected teaching activity model The teaching steps include: using the multiple objective mathematical programming function and according to the planning parameters input by the user, the selected teaching indicators, the activity attributes of each of the teaching activity models, and the basic model of each of the teaching activities Corresponding teaching indicators and records of the teacher preference database are used to select at least one of the teaching activity model bases from the teaching activity ontology knowledge database and generate the teaching plan according to the selected teaching activity model. For example, the smart lesson planning method described in claim 10 of the patent application includes: storing a plurality of basic student materials in a student database. For example, the smart lesson planning method described in claim 16 of the patent application further includes: generating a student grouping result based on the basic information of the students. The smart lesson planning method according to claim 17, wherein the step of generating the student grouping result according to the student basic materials comprises: using a gene algorithm and generating the student group according to the student basic materials. result. A computer program product comprising at least one program instruction for being loaded into a computer system to perform a plurality of steps, the steps comprising: storing a plurality of teaching indicators in a teaching ability index ontology knowledge database Storing a plurality of teaching activity schemas in a teaching activity ontology knowledge database, wherein each of the teaching activity base molds has a plurality of activity attributes and corresponds to at least one of the teaching indicators; Entering a plurality of planning parameters; selecting at least one of the teaching indicators from the teaching ability indicator ontology knowledge database; and using a multiple objective mathematical programming function and selecting the planning parameters according to the user input The teaching index, the activity attribute of each of the teaching activity basic models, and the teaching index corresponding to each of the teaching activity basic models select at least one of the teaching activity basic models from the teaching activity ontology knowledge database And generating a lesson according to the selected teaching activity model, wherein the steps of inputting the planning parameters include: inputting Expected teaching content keywords, a number expected when a pre-teaching and Period environmental parameters. The computer program product of claim 19, wherein the activity attributes include an activity indicator, an activity keyword, an activity time, an equipment, a teaching material, a group demand note, a special student note and An activity content. The computer program product according to claim 19, wherein the multi-objective mathematical programming function is used, and according to the planning parameters input by the user, the selected teaching index, and the activity attribute of each of the teaching activity models And each of the teaching activity corresponding to the teaching model to select at least one of the teaching activity model bases from the teaching activity ontology knowledge database and generate the teaching plan according to the selected teaching activity model The step further includes: using a Bin Packing algorithm to solve the multi-objective mathematical programming function. For example, in the computer program product described in claim 19, the steps further include: fine-tuning the expected teaching hours; deleting the selected teaching indicators or selecting the teaching indicators from the teaching ability index ontology knowledge database. Other teaching indicators; fine-tuning the expected environmental parameters; providing at least one teaching activity model in the basic model of the teaching activities, wherein the provided teaching activity model is used to replace the selected ones in the teaching plan The basic model of teaching activities; and based on the fine-tuned expected teaching hours, the deleted teaching indicators, the selected teaching indicators or the changed teaching activity model Lesson plan. For example, the computer program product described in claim 22, wherein the steps further comprise: recording the replaced teaching activity model in a teacher preference database. The computer program product according to claim 23, wherein the multi-objective mathematical programming function is used, and according to the planning parameters input by the user, the selected teaching index, and the activity attribute of each of the teaching activity models And each of the teaching activity corresponding to the teaching model to select at least one of the teaching activity model bases from the teaching activity ontology knowledge database and generate the teaching plan according to the selected teaching activity model The step includes: using the multi-objective mathematical programming function and according to the planning parameters input by the user, the selected teaching indicators, the activity attributes of each of the teaching activity fundamental models, and the corresponding corresponding to each of the teaching activity models The teaching indicator and the record of the teacher preference database are used to select at least one of the teaching activity model bases from the teaching activity ontology knowledge database and generate the teaching plan according to the selected teaching activity model. For example, the computer program product described in claim 19, wherein the steps further include: storing a plurality of basic student materials in a student database. The computer program product of claim 25, wherein the steps further comprise: generating a student grouping result based on the student basic information. The computer program product according to claim 26, wherein the step of generating the student grouping result according to the student basic materials Including: using a gene algorithm and generating the student grouping results based on the student basic data. A computer readable recording medium in which a program is executed, and when the program is loaded into a computer system and executed, the program executes the method as set forth in claim 10 of the patent application.