CN114299772B - Geometric coaching system and method based on semantic web - Google Patents
Geometric coaching system and method based on semantic web Download PDFInfo
- Publication number
- CN114299772B CN114299772B CN202210018504.0A CN202210018504A CN114299772B CN 114299772 B CN114299772 B CN 114299772B CN 202210018504 A CN202210018504 A CN 202210018504A CN 114299772 B CN114299772 B CN 114299772B
- Authority
- CN
- China
- Prior art keywords
- geometric
- module
- semantic
- learning
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 68
- 230000008569 process Effects 0.000 claims abstract description 50
- 238000010586 diagram Methods 0.000 claims abstract description 25
- 238000000605 extraction Methods 0.000 claims description 7
- 239000000284 extract Substances 0.000 claims description 6
- 238000009223 counseling Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 10
- 230000000750 progressive effect Effects 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000010354 integration Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 230000009295 sperm incapacitation Effects 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
Landscapes
- Electrically Operated Instructional Devices (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a geometric coaching system and method based on semantic Web, which relates to the technical field of intelligent teaching, and comprises a geometric knowledge base module, a coaching module, a learning module, a drawing module, an analysis module, a scoring module and a prompting module; the geometric knowledge base module establishes a semantic net according to the knowledge points, the learning guiding module positions the knowledge points, and the learning module combines the answer scores to provide learning problems with different difficulties; the drawing module and the analyzing module synchronously generate a geometric diagram and a solving process, the geometric diagram visualizes the learning problem, manual mechanical input in advance is not needed, and labor and time cost are saved; the scoring module judges whether the answer of the user is correct according to the solving process, calculates the answer score and sends the answer score to the learning module; the prompt module displays knowledge points or solving processes of the learning problem to the user, and consolidates knowledge blind points in time. The invention has strong universality, low labor and time cost, meets the requirement of digital combination of geometric coaching and learning, and has good coaching effect.
Description
Technical Field
The invention relates to the technical field of intelligent teaching, in particular to a geometric coaching system and method based on a semantic web.
Background
With the continuous development of information technology, the novel education mode has generated great impact on traditional education modes. The traditional education mode cannot meet the demand of education given in the times more and more, and in order to ensure the progress of education, the integration of the continuously developed information technology and the stable education mode is urgently needed. In traditional classroom teaching, a teacher occupies a central position while students are in a passive position. In the new educational field, it is emphasized that students learn "self-learning" more than the teaching mode in which students "listen" to "teacher" teaching. When students learn autonomously, the ideal state is that all related learning is performed by the students, and teachers only play an auxiliary role. In addition, in the teaching process, the basic abilities of students are different, and how to achieve 'teaching from the stock' is also a problem of concern. Taking the mathematical field as an example, in the mathematical teaching process, students can complete basic exercises under the guidance of teachers when learning in class, but when the students independently go to solve the problems, the students cannot go from the bottom, and the knowledge points for the problems cannot be clarified. In order to take account and improve the learning improvement rate, the subject-sea tactics are generally adopted, but the result is often half-done, the result is not ideal, the enthusiasm is frustrated, and the learning is gradually lost. Geometry is one of courses based on comparison in mathematical disciplines, in the process of first-class mathematical geometry teaching, the combination of figures is a widely adopted method, geometric theories, properties, propositions and the like described by words are expressed by geometric figures, and some conclusions deduced according to the geometric axiom are proved by measuring and transforming geometric objects in the geometric figures. At present, geometric coaching software on the market records teacher lectures into videos and combines practice problems, and students watch the videos; the other is in the form of a question bank, and the purpose of grasping knowledge points is achieved by doing a large number of questions. The two forms are relatively weak in the culture of the learner in the capability of solving the problems, and the coaching form of video courses is an on-line form of off-line teacher classroom teaching, and the defects of off-line teaching still exist; in the form of question bank learning, when a learner encounters a question which cannot be met, software only mechanically gives out answers to the questions, and the learner's ability to solve the questions is not exercised; moreover, learning questions in the software are imported by mechanical manual work, proper questions cannot be provided for the learner to strengthen learning according to the capability change of the learner, so that the learner can repeatedly learn knowledge points which are mastered, and weak places are not strengthened; in addition, the thematic pattern can only be manually introduced in the early stage, which consumes labor and time.
The prior art discloses a geometric problem solving intelligent coaching method, which relates to the technical field of intelligent problem solving coaching and comprises the following steps: s1, establishing a question library and an association library; s2, acquiring a question from a question library; s3, judging whether the user needs to conduct or not according to the answer of the user, if so, performing step S4, and if not, performing step S6; s4, judging the coaching level according to the answer of the user or identifying the coaching level selected by the user, and acquiring an intermediate conclusion from the association library according to the coaching level; s5, comparing the user answering result with corresponding question answers in the question library, ending the tutoring if the user answering is successful, further judging the tutoring level if the user answering is wrong, returning to the step S4 if the current tutoring level is smaller than the maximum tutoring level, and ending the tutoring if the current tutoring level is equal to the maximum tutoring level; s6, comparing the user answering result with the corresponding question answers in the question library, ending the coaching if the answering is successful, and returning to the step S3 if the answering is failed. According to the method, when the question library is to be established, the questions, the question solving process and the final result are required to be manually input, and when the association library is to be established, the theorem, the concept or the axiom are required to be manually input, so that the labor and time cost is high; in the coaching process, a geometric schematic diagram for helping a user understand the questions cannot be generated, and the requirement of digital combination cannot be met; when the user solves the problem, the user can only mechanically give out the answer to the problem, the user's ability to solve the problem is not trained, and the coaching effect is poor.
Disclosure of Invention
The invention provides a geometrical coaching system and a geometrical coaching method based on a semantic net, which can generate a learning problem according to the learning ability of a user only by inputting geometrical knowledge points, synchronously generate a geometrical diagram and a solving process, have strong universality and save labor and time cost, and overcome the defects of poor universality, high labor and time cost and poor coaching effect of coaching software caused by incapacitation of proper questions according to the learning ability of the user due to the fact that the questions, answers and diagrams in the conventional geometrical coaching software are imported by means of manual machinery.
In order to solve the technical problems, the technical scheme of the invention is as follows:
the invention provides a geometric coaching system based on semantic Web, comprising:
the geometric knowledge base module is used for establishing a geometric concept semantic net, a geometric theorem semantic net and a geometric proof semantic net according to the knowledge points;
the learning guiding module is used for identifying the selection of a user and positioning a semantic net where a knowledge point is located in the geometric knowledge base module according to the selection;
the learning module displays different types of learning questions according to the knowledge points positioned by the learning guide module and the answer scores calculated by the scoring module for the user to answer; the learning problem is automatically generated according to a geometric concept semantic net and a geometric theorem semantic net or selected from a geometric proof semantic net;
the drawing module synchronously generates a geometric schematic according to the learning problems generated by the learning module and assists the user in answering;
the analysis module synchronously generates a solving process according to the learning problem generated by the learning module;
the scoring module judges whether the answer of the user is correct, calculates the answer score, and sends the answer score to the learning module;
and the prompt module is used for identifying a prompt request of the user and displaying knowledge points or solving processes of the learning problem to the user.
Preferably, the geometric knowledge base module establishes a geometric concept semantic net, a geometric theorem semantic net and a geometric proof semantic net according to knowledge points, and the specific method comprises the following steps:
inputting knowledge points and proof questions of the geometric disciplines into a geometric knowledge base module, wherein the geometric knowledge base module creates a catalog according to the grade to which the knowledge points belong for classification, the catalog comprises a plurality of chapters, the chapters comprise a plurality of sections, and the sections comprise specific knowledge points; the geometric knowledge base module establishes a geometric concept semantic net and a geometric theorem semantic net according to the knowledge point attributes based on the semantic net, and establishes a geometric proof semantic net according to the knowledge point proof questions.
Preferably, the system further comprises a history recording module for recording the learning history of the user for reading by the learning guiding module;
after the learning guiding module identifies the selection of the user, firstly reading the learning history of the user in the history recording module, and if the learning history of the chapter or section selected by the user does not exist in the history recording module, positioning the geometric concept semantic net where the knowledge point is located in the geometric knowledge base module by the learning guiding module; if the history record module has the learning record of the chapter or the section selected by the user, the semantic web where the last learning record is located is jumped.
When a user learns for the first time, the system provides a learning route of geometric concepts, geometric theorem and geometric evidence, the learning guiding module positions the geometric concept semantic net where the knowledge points are positioned, reads and traverses the analysis semantic net, analyzes the semantic link relation and provides the learning module with the generation of learning problems.
Preferably, the learning module generates a selection question, a blank filling question or a proof question according to the semantic web where the knowledge points positioned by the learning guiding module are located and the answer score calculated by the scoring module;
when the answer score is smaller than the score threshold, generating one or more of a geometric concept selection question, a geometric concept blank filling question, a geometric theorem selection question and a geometric theorem blank filling question corresponding to the knowledge point according to the knowledge point position geometric concept net or the geometric theorem semantic net;
when the answer score is not smaller than the score threshold, the learning module selects the geometric proof questions from the geometric proof semantic net.
When answering, the initial value of answer score of the user is 0, the selected questions and the blank filling questions are generated based on geometric concepts and geometric theorem, and belong to basic question types; when the answer score is smaller than the score threshold, the learning module firstly proposes basic question learning basic knowledge to the user; when the accumulated answer score is not smaller than the score threshold, the learning module presents the geometric proof questions of the comprehensive questions to the user, so that the progressive learning effect is achieved.
Preferably, in the geometric concept semantic net or the geometric theorem semantic net, the semantic link relation of the keywords of the geometric concepts or the geometric theorem is set as ASSOC, the learning module analyzes the keywords of which the link relation is ASSOC in the geometric concepts or the geometric theorem, any one keyword is hidden, and the geometric concept selection questions, the geometric concept gap filling questions, the geometric theorem selection questions and the geometric theorem gap filling questions are generated, wherein the hidden keywords are used as standard answers.
Preferably, the drawing module comprises a set geometric mode library and a drawing instruction library;
the geometric pattern library traverses a geometric concept semantic web, a geometric theorem semantic web or a geometric proof semantic web corresponding to the learning problem, matches and invokes corresponding drawing instructions in a drawing instruction library according to all semantic link relations in the semantic web, and synchronously generates a geometric schematic.
The drawing module generates a geometric schematic diagram while providing the learning problem, meets the requirement of combining the geometric figures in geometric learning, visualizes the learning problem, and is beneficial to the understanding and the answering of the user on the learning problem.
Preferably, the parsing module comprises an extracting unit, an inference rule base and a known fact base;
in the geometric proof semantic net, setting the semantic link relation of the known condition keywords of the geometric proof questions as ATT, and setting the semantic link relation of the proof result keywords as VAL; when the learning module selects the geometric proof questions, the extraction unit extracts keywords with semantic link relations of ATT as known conditions and stores the keywords into a known fact library, a geometric reasoning rule is selected from a reasoning rule library and applied to the known fact library to generate new facts, the new facts are stored into the known fact library, and reasoning is repeated until the new facts cannot be generated; the extraction unit extracts keywords with semantic link relation VAL as a proving result, and if facts identical to the proving result exist in the fact library, the process that the geometric reasoning rule generates facts identical to the proving result is used as a solving process; if the fact that is the same as the proving result does not exist in the known fact library, selecting a new geometric reasoning rule in the reasoning rule library until the fact that is the same as the proving result is obtained.
Preferably, the specific method for judging whether the answer of the user is correct by the scoring module is as follows:
the scoring module obtains user answers, and matches the user answers with standard answers for the selection questions and the blank filling questions, if the user answers are the same, the user answers are correct, and if the user answers are different, the user answers are wrong; and for the proof questions, matching the user answers with the solving process generated by the analyzing module step by step, judging that the user answers are correct if the steps are the same, and judging that the user answers are wrong if the steps are different.
Preferably, the prompt module comprises a prompt sign, a prompt library and a prompt score;
setting a prompt tag TIPS as a semantic link relation, linking learning problems with knowledge points in a geometric concept semantic network and a geometric theorem semantic network, and storing the knowledge points in a prompt library;
the initial value of the prompt integral is set to 0, and the prompt integral is increased by a when a user finishes learning a knowledge point, and is reduced by b when the user uses a prompt request once, wherein a is smaller than b; when the current prompt integral is smaller than b, knowledge points of learning problems are displayed to the user; and when the current integral is not less than b, displaying the solving process to a user.
When the user encounters thinking disorder and cannot answer continuously in the process of solving the questions, the prompting module provides help for the user; by setting the prompt integral, the user is effectively prevented from actively thinking and giving a prompt request without limit, and the learning effect is influenced; when the integral is insufficient, knowledge points of learning problems are displayed to the user, so that the user consolidates basic knowledge of weak knowledge points; when the prompt integration is enough, the solving process is shown to the user, so that the user is helped to construct correct solving thinking.
The invention also provides a geometric coaching method based on the semantic web, which utilizes the geometric coaching system based on the semantic web, and comprises the following steps:
s1: establishing a geometric concept semantic net, a geometric theorem semantic net and a geometric proof semantic net according to the knowledge points;
s2: identifying the selection of a user, and positioning a semantic net where a knowledge point is located in a geometric knowledge base module according to the selection;
s3: displaying different types of learning questions according to the positioned knowledge points and answer scores for the user to answer; the learning problem is automatically generated according to a geometric concept semantic net and a geometric theorem semantic net or selected from a geometric proof semantic net;
s4: synchronously generating a geometric schematic according to the learning problem, and assisting the user in answering;
s5: synchronously generating a solving process according to the learning problem;
s6: judging whether the answer of the user is correct, calculating answer score, and sending the answer score to step S3;
s7: and identifying a prompt request of the user, and displaying knowledge points or solving processes of the learning problem to the user.
Compared with the prior art, the technical scheme of the invention has the beneficial effects that:
the geometrical knowledge base module of the invention establishes a geometrical concept semantic net, a geometrical theorem semantic net and a geometrical proof semantic net according to knowledge points based on the semantic net; the learning module recognizes the semantic net where the knowledge points are located after the selection of the user, the learning module presents different types of learning problems to the user according to the positions of the knowledge points and the answer scores, the answer scores reflect the learning ability of the user, the learning module presents the learning problems with different difficulties to the user by combining the answer scores, the universality is strong, and the progressive coaching effect is achieved; the drawing module and the resolving module synchronously generate a geometric schematic diagram and a solving process according to the learning problem respectively, the geometric schematic diagram visualizes the learning problem, the user is assisted in understanding and answering, manual mechanical input is not needed, and labor and time cost are saved; the scoring module judges whether the answer of the user is correct or not according to the solving process, and the obtained answer score is sent to the learning module to be used as a difficulty basis for generating the next learning problem; the prompt module provides help for users when the users encounter thinking disorder, shows knowledge points or solving processes of learning problems for the users, and consolidates knowledge blind points in time. The invention has strong universality and low labor and time cost, meets the requirement of digital combination of geometric tutoring learning, and provides targeted tutoring for users with different learning capacities.
Drawings
Fig. 1 is a schematic structural diagram of a geometric guidance system based on semantic web according to embodiment 1.
Fig. 2 is a schematic structural diagram of a geometric guidance system based on semantic web according to embodiment 2.
Fig. 3 is a schematic diagram of the geometric theorem semantic web described in example 2.
Fig. 4 is a schematic diagram of the drawing module in embodiment 2.
Fig. 5 is a geometric schematic generated by the drawing module described in embodiment 2.
Fig. 6 is a schematic diagram of the geometric proof semantic web described in example 2.
Fig. 7 is a schematic structural diagram of the analysis module in embodiment 2.
Fig. 8 is a schematic diagram of a geometric proof semantic web of a link hint as described in embodiment 2.
Fig. 9 is a schematic diagram of the geometric theorem semantic web of the link geometric proof questions described in example 2.
Fig. 10 is a flowchart of a geometric coaching method based on semantic web according to embodiment 3.
Detailed Description
The drawings are for illustrative purposes only and are not to be construed as limiting the present patent;
for the purpose of better illustrating the embodiments, certain elements of the drawings may be omitted, enlarged or reduced and do not represent the actual product dimensions;
it will be appreciated by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The technical scheme of the invention is further described below with reference to the accompanying drawings and examples.
Example 1
The embodiment provides a geometric coaching system based on semantic web, as shown in fig. 1, including:
the geometric knowledge base module is used for establishing a geometric concept semantic net, a geometric theorem semantic net and a geometric proof semantic net according to the knowledge points;
the learning guiding module is used for identifying the selection of a user and positioning a semantic net where a knowledge point is located in the geometric knowledge base module according to the selection;
the learning module displays different types of learning questions according to the knowledge points positioned by the learning guide module and the answer scores calculated by the scoring module for the user to answer; the learning problem is automatically generated according to a geometric concept semantic net and a geometric theorem semantic net or selected from a geometric proof semantic net;
the drawing module synchronously generates a geometric schematic according to the learning problems generated by the learning module and assists the user in answering;
the analysis module synchronously generates a solving process according to the learning problem generated by the learning module;
the scoring module judges whether the answer of the user is correct, calculates the answer score, and sends the answer score to the learning module;
and the prompt module is used for identifying a prompt request of the user and displaying knowledge points or solving processes of the learning problem to the user.
In the specific implementation process, the geometric knowledge base module establishes a geometric concept semantic net, a geometric theorem semantic net and a geometric proof semantic net according to knowledge points based on the semantic net; the learning module recognizes the semantic net where the knowledge points are located after the selection of the user, the learning module presents different types of learning problems to the user according to the positions of the knowledge points and the answer scores, the answer scores reflect the learning ability of the user, the learning module presents the learning problems with different difficulties to the user by combining the answer scores, the universality is strong, and the progressive coaching effect is achieved; the drawing module and the resolving module synchronously generate a geometric schematic diagram and a solving process according to the learning problem respectively, the geometric schematic diagram visualizes the learning problem, the user is assisted in understanding and answering, manual mechanical input is not needed, and labor and time cost are saved; the scoring module judges whether the answer of the user is correct or not according to the solving process, and the obtained answer score is sent to the learning module to be used as a difficulty basis for generating the next learning problem; the prompt module provides help for users when the users encounter thinking disorder, shows knowledge points or solving processes of learning problems for the users, and consolidates knowledge blind points in time. The invention has strong universality and low labor and time cost, meets the requirement of digital combination of geometric tutoring learning, and provides targeted tutoring for users with different learning capacities.
Example 2
The embodiment provides a geometric coaching system based on semantic web, as shown in fig. 2, including:
the geometric knowledge base module is used for establishing a geometric concept semantic net, a geometric theorem semantic net and a geometric proof semantic net according to the knowledge points;
inputting knowledge points and proof questions of the geometric disciplines into a geometric knowledge base module, wherein the geometric knowledge base module creates a catalog according to the grade to which the knowledge points belong for classification, the catalog comprises a plurality of chapters, the chapters comprise a plurality of sections, and the sections comprise specific knowledge points; the geometric knowledge base module establishes a geometric concept semantic net and a geometric theorem semantic net according to knowledge point attributes based on the semantic net, and establishes a geometric proof semantic net according to knowledge point proof questions;
the learning guiding module is used for identifying the selection of a user and positioning a semantic net where a knowledge point is located in the geometric knowledge base module according to the selection;
the history recording module is used for recording the learning history of the user and is read by the learning guiding module;
after the learning guiding module identifies the selection of the user, firstly, reading the learning history of the user in the history recording module, and if the learning history of the chapter or section selected by the user does not exist in the history recording module, positioning a geometric concept semantic net where a knowledge point is located in the geometric knowledge base module by the learning guiding module; if the history record module has the learning record of the chapter or section selected by the user, jumping to a semantic web where the last learning record is located;
the learning module displays different types of learning questions according to the knowledge points positioned by the learning guide module and the answer scores calculated by the scoring module for the user to answer; the learning problem is automatically generated according to a geometric concept semantic net and a geometric theorem semantic net or selected from a geometric proof semantic net;
the learning problem is a selection problem, a blank filling problem or a proof problem;
when the answer score is smaller than the score threshold, generating one or more of a geometric concept selection question, a geometric concept gap filling question, a geometric theorem selection question and a geometric theorem gap filling question corresponding to the knowledge points according to the knowledge points in the geometric concept semantic network or the geometric theorem semantic network;
when the answer score is not smaller than the score threshold, the learning module selects the geometric proof questions from the geometric proof semantic net.
In this embodiment, the score threshold is set to 60 scores.
When answering, the initial value of answer score of the user is 0, the selected questions and the blank filling questions are generated based on geometric concepts and geometric theorem, and belong to basic question types; when the answer score is smaller than the score threshold, the learning module firstly proposes basic question learning basic knowledge to the user; when the accumulated answer score is not smaller than the score threshold, the learning module presents the geometric proof questions of the comprehensive questions to the user, so that the progressive learning effect is achieved.
In the geometric concept semantic net or the geometric theorem semantic net, the semantic link relation of the keywords of the geometric concepts or the geometric theorem is set as ASSOC, the learning module analyzes the keywords of which the link relation is ASSOC in the geometric concepts or the geometric theorem, any one keyword is hidden, and the hidden keywords are used as standard answers to generate geometric concept selection questions, geometric concept gap filling questions, geometric theorem selection questions and geometric theorem gap filling questions. Taking the knowledge point "median line" as an example, as shown in fig. 3, the geometric theorem is that "the median line of the triangle is parallel to the third side of the triangle and equal to half of the third side," the keywords are "triangle, parallel, half," the keyword semantic link relationship is set to ASSOC, if the keyword "half" is hidden, the learning module proposes that the median line of the triangle is parallel to the third side of the triangle, and then the length relationship between the median line and the third side is? ", the answer is" half ".
The drawing module synchronously generates a geometric schematic according to the learning problems generated by the learning module and assists the user in answering;
the drawing module comprises a set geometric mode library and a drawing instruction library;
the geometric pattern library traverses a geometric concept semantic web, a geometric theorem semantic web or a geometric proof semantic web corresponding to the learning problem, matches and invokes corresponding drawing instructions in a drawing instruction library according to all semantic link relations in the semantic web, and synchronously generates a geometric schematic.
The drawing module generates a geometric schematic diagram while providing the learning problem, meets the requirement of combining the geometric figures in geometric learning, visualizes the learning problem, and is beneficial to the understanding and the answering of the user on the learning problem.
As shown in fig. 4, to learn the problem that the median of the triangle is parallel to the third side of the triangle, then the length of the median to the third side is? "schematic diagram of drawing module for example. According to the keywords 'triangle and median line', determining triangle ABC, wherein semantic link relations 'side' and 'MidPoint' exist, sides are AB, AC and BC, geometrical feature side MidPoint D and side AC MidPoint E are extracted, a geometrical pattern library has mapping relations 'side MidPoint D-MidPoint { point D and line segment AB }', a drawing instruction inventory is in a drawing instruction 'MidPoint { point D and line segment AB } - > MidPoint D A B', and a drawing instruction is called, so that automatic synchronization is realized to generate a geometrical schematic diagram, as shown in figure 5.
The analysis module synchronously generates a solving process according to the learning problem generated by the learning module;
as shown in fig. 6, the parsing module includes an extracting unit, an inference rule base and a known fact base;
in the geometric proof semantic net, setting the semantic link relation of the known condition keywords of the geometric proof questions as ATT, and setting the semantic link relation of the proof result keywords as VAL; when the learning module selects the geometric proof questions, the extraction unit extracts keywords with semantic link relations of ATT as known conditions and stores the keywords into a known fact library, a geometric reasoning rule is selected from a reasoning rule library and applied to the known fact library to generate new facts, the new facts are stored into the known fact library, and reasoning is repeated until the new facts cannot be generated; the extraction unit extracts keywords with semantic link relation VAL as a proving result, and if facts identical to the proving result exist in the fact library, the process that the geometric reasoning rule generates facts identical to the proving result is used as a solving process; if the fact that is the same as the proving result does not exist in the known fact library, selecting a new geometric reasoning rule in the reasoning rule library until the fact that is the same as the proving result is obtained.
As shown in fig. 7, the learning problem is "in triangle ABC, ab=ac, ++cad= ++bad, ask for evidence: in the diagram, when AB=AC and < CAD= < BAD > are known conditions, the semantic link relation is set to ATT, and when DeltaABC is congruent, deltaACD is a proving result, the semantic link relation is set to VAL.
The scoring module judges whether the answer of the user is correct, calculates the answer score, and sends the answer score to the learning module;
the scoring module obtains user answers, and matches the user answers with standard answers for the selection questions and the blank filling questions, if the user answers are the same, the user answers are correct, and if the user answers are different, the user answers are wrong; and for the proof questions, matching the user answers with the solving process generated by the analyzing module step by step, judging that the user answers are correct if the steps are the same, and judging that the user answers are wrong if the steps are different.
And the prompt module is used for identifying a prompt request of the user and displaying knowledge points or solving processes of the learning problem to the user.
The prompt module comprises a prompt mark, a prompt library and a prompt score;
setting a prompt tag TIPS as a semantic link relation, linking learning problems with knowledge points in a geometric concept semantic network and a geometric theorem semantic network, and storing the knowledge points in a prompt library;
the initial value of the prompt integral is set to 0, and the prompt integral is increased by a when a user finishes learning a knowledge point, and is reduced by b when the user uses a prompt request once, wherein a is smaller than b; when the current prompt integral is smaller than b, knowledge points related to the learning problem are displayed to the user; and when the current integral is not less than b, displaying the solving process to a user.
As shown in fig. 8, a semantic net diagram of a geometric proof question containing a hint is shown to learn the problem "in triangle ABC, ab=ac, ++cad= ++bad, ask for evidence: delta ABC is equal to delta ACD as an example, a prompt mark is TIPS, knowledge points are triangle congruent theorem, and the knowledge points of the triangle congruent theorem are stored in a prompt library; in this embodiment, a=1, b=10, that is, for each time the user completes learning of one knowledge point, the cue score increases by 1 minute, and for each use of a cue request, the cue score decreases by 10 minutes; when the current integral is less than 10 hours, displaying knowledge points of 'triangle congruence theorem' in a prompt library to a user, obtaining a problem solving thought, continuously completing the response, and simultaneously prompting the integral to be increased by 1 minute; the current integral is not less than 10 time sharing, and the prompting module displays the solving process generated by the analyzing module to the user step by step.
When the user encounters thinking disorder and cannot answer continuously in the process of solving the questions, the prompting module provides help for the user; by setting the prompt integral, the user is effectively prevented from actively thinking and giving a prompt request without limit, and the learning effect is influenced; when the integral is insufficient, knowledge points of learning problems are displayed to the user, so that the user consolidates basic knowledge of weak knowledge points; when the prompt integration is enough, the solving process is shown to the user, so that the user is helped to construct correct solving thinking.
When a user completes the geometric concept and the geometric theorem of a knowledge point, the geometric proof questions of the knowledge point are linked to the knowledge point, the semantic linking relation is set to QA, and the geometric proof questions are used as the timely review and comprehensive application of the knowledge point, so that the progressive learning effect is achieved. As shown in fig. 9, the geometric proof title "triangle ABC, D, E is the midpoint of AB and AC, respectively, and the connection DE, proof +.ade+.acb+.bac=180°" links to knowledge point "the median line of the triangle is parallel to the third side of the triangle and equal to half of the third side", and the semantic link relationship is set to QA.
Example 3
The present embodiment provides a semantic web based geometric guidance method, and the semantic web based geometric guidance system described in embodiment 1 or 2 is used, as shown in fig. 10, where the method includes:
s1: establishing a geometric concept semantic net, a geometric theorem semantic net and a geometric proof semantic net according to the knowledge points;
s2: identifying the selection of a user, and positioning a semantic net where a knowledge point is located in a geometric knowledge base module according to the selection;
s3: displaying different types of learning questions according to the positioned knowledge points and answer scores for the user to answer; the learning problem is automatically generated according to a geometric concept semantic net and a geometric theorem semantic net or selected from a geometric proof semantic net;
s4: synchronously generating a geometric schematic according to the learning problem, and assisting the user in answering;
s5: synchronously generating a solving process according to the learning problem;
s6: judging whether the answer of the user is correct, calculating answer score, and sending the answer score to step S3;
s7: and identifying a prompt request of the user, and displaying knowledge points or solving processes of the learning problem to the user.
The same or similar reference numerals correspond to the same or similar components;
the terms describing the positional relationship in the drawings are merely illustrative, and are not to be construed as limiting the present patent;
it is to be understood that the above examples of the present invention are provided by way of illustration only and not by way of limitation of the embodiments of the present invention. Other variations or modifications of the above teachings will be apparent to those of ordinary skill in the art. It is not necessary here nor is it exhaustive of all embodiments. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the invention are desired to be protected by the following claims.
Claims (7)
1. A semantic web-based geometric coaching system comprising:
the geometric knowledge base module is used for establishing a geometric concept semantic net, a geometric theorem semantic net and a geometric proof semantic net according to the knowledge points;
the learning guiding module is used for identifying the selection of a user and positioning a semantic net where a knowledge point is located in the geometric knowledge base module according to the selection;
the learning module displays different types of learning questions according to the knowledge points positioned by the learning guide module and the answer scores calculated by the scoring module for the user to answer; the learning problem is automatically generated according to a geometric concept semantic net and a geometric theorem semantic net or selected from a geometric proof semantic net;
in a geometric concept semantic net or a geometric theorem semantic net, setting semantic link relations of keywords of geometric concepts or geometric theorems as ASSOCs, analyzing the keywords of which the link relations are ASSOCs by a learning module in the geometric concepts or the geometric theorems, hiding any one keyword, and generating geometric concept selection questions, geometric concept gap filling questions, geometric theorem selection questions and geometric theorem gap filling questions, wherein the hidden keywords are used as standard answers;
the drawing module synchronously generates a geometric schematic according to the learning problems generated by the learning module and assists the user in answering; the drawing module comprises a set geometric mode library and a drawing instruction library;
traversing a geometric concept semantic network, a geometric theorem semantic network or a geometric proof semantic network corresponding to the learning problem by the geometric pattern library, matching and calling corresponding drawing instructions in a drawing instruction library according to all semantic link relations in the semantic network, and synchronously generating a geometric schematic diagram;
the analysis module synchronously generates a solving process according to the learning problem generated by the learning module; the analysis module comprises an extraction unit, an inference rule base and a known fact base;
in the geometric proof semantic net, setting the semantic link relation of the known condition keywords of the geometric proof questions as ATT, and setting the semantic link relation of the proof result keywords as VAL; when the learning module selects the geometric proof questions, the extraction unit extracts keywords with semantic link relations of ATT as known conditions and stores the keywords into a known fact library, a geometric reasoning rule is selected from a reasoning rule library and applied to the known fact library to generate new facts, the new facts are stored into the known fact library, and reasoning is repeated until the new facts cannot be generated; the extraction unit extracts keywords with semantic link relation VAL as a proving result, and if facts identical to the proving result exist in the fact library, the process that the geometric reasoning rule generates facts identical to the proving result is used as a solving process; if the fact that the fact is the same as the proving result does not exist in the known fact library, selecting a new geometric reasoning rule in the reasoning rule library until the fact that the fact is the same as the proving result is obtained;
the scoring module judges whether the answer of the user is correct according to the solving process, calculates the answer score and sends the answer score to the learning module;
and the prompt module is used for identifying a prompt request of the user and displaying knowledge points or solving processes of the learning problem to the user.
2. The semantic-net-based geometric coaching system according to claim 1, wherein the geometric knowledge base module establishes the geometric concept semantic net, the geometric theorem semantic net and the geometric proof semantic net according to knowledge points by the following specific methods:
inputting knowledge points and proof questions of the geometric disciplines into a geometric knowledge base module, wherein the geometric knowledge base module creates a catalog according to the grade to which the knowledge points belong for classification, the catalog comprises a plurality of chapters, the chapters comprise a plurality of sections, and the sections comprise specific knowledge points; the geometric knowledge base module establishes a geometric concept semantic net and a geometric theorem semantic net according to the knowledge point attributes based on the semantic net, and establishes a geometric proof semantic net according to the knowledge point proof questions.
3. The semantic web-based geometric coaching system according to claim 1, further comprising a history recording module for recording a learning history of the user for reading by the coaching module;
after the learning guiding module identifies the selection of the user, firstly reading the learning history of the user in the history recording module, and if the learning history of the chapter or section selected by the user does not exist in the history recording module, positioning the geometric concept semantic net where the knowledge point is located in the geometric knowledge base module by the learning guiding module; if the history record module has the learning record of the chapter or the section selected by the user, the semantic web where the last learning record is located is jumped.
4. The geometrical counseling system based on semantic net according to claim 1, wherein the learning module displays the selection questions, the blank filling questions or the proof questions according to the semantic net where the knowledge points positioned by the guiding module are and the answer score calculated by the scoring module;
when the answer score is smaller than the score threshold, generating one or more of a geometric concept selection question, a geometric concept blank filling question, a geometric theorem selection question and a geometric theorem blank filling question corresponding to the knowledge point according to the knowledge point position geometric concept net or the geometric theorem semantic net;
when the answer score is not smaller than the score threshold, the learning module selects the geometric proof questions from the geometric proof semantic net.
5. The geometric guidance system based on semantic web according to claim 1, wherein the specific method for judging whether the answer of the user is correct by the scoring module is as follows:
the scoring module obtains user answers, and matches the user answers with standard answers for the selection questions and the blank filling questions, if the user answers are the same, the user answers are correct, and if the user answers are different, the user answers are wrong; and for the proof questions, matching the user answers with the solving process generated by the analyzing module step by step, judging that the user answers are correct if the steps are the same, and judging that the user answers are wrong if the steps are different.
6. The semantic web-based geometric coaching system according to claim 5, wherein the hint module includes hint marks, a hint library, and hint points;
setting a prompt tag TIPS as a semantic link relation, linking learning problems with knowledge points in a geometric concept semantic network and a geometric theorem semantic network, and storing the knowledge points in a prompt library;
the initial value of the prompt integral is set to 0, the prompt integral is increased by a when a user finishes learning a knowledge point, and the prompt integral is reduced by b when the user uses a prompt request every time, wherein a < b; when the current prompt integral is smaller than b, knowledge points of learning problems are displayed to the user; and when the current integral is not less than b, displaying the solving process to a user.
7. A semantic web-based geometric coaching method, characterized in that the semantic web-based geometric coaching system according to any one of claims 1-6 is utilized, the method comprising:
s1: establishing a geometric concept semantic net, a geometric theorem semantic net and a geometric proof semantic net according to the knowledge points;
s2: identifying the selection of a user, and positioning a semantic net where a knowledge point is located in a geometric knowledge base module according to the selection;
s3: displaying different types of learning questions according to the positioned knowledge points and answer scores for the user to answer; the learning problem is automatically generated according to a geometric concept semantic net and a geometric theorem semantic net or selected from a geometric proof semantic net; in a geometric concept semantic net or a geometric theorem semantic net, setting semantic link relations of keywords of geometric concepts or geometric theorems as ASSOCs, analyzing the keywords of which the link relations are ASSOCs by a learning module in the geometric concepts or the geometric theorems, hiding any one keyword, and generating geometric concept selection questions, geometric concept gap filling questions, geometric theorem selection questions and geometric theorem gap filling questions, wherein the hidden keywords are used as standard answers;
s4: synchronously generating a geometric schematic according to the learning problem, and assisting the user in answering;
traversing a geometric concept semantic network, a geometric theorem semantic network or a geometric proof semantic network corresponding to the learning problem, calling corresponding drawing instructions according to all semantic link relations in the semantic network, and synchronously generating a geometric schematic diagram;
s5: synchronously generating a solving process according to the learning problem;
in the geometric proof semantic net, setting the semantic link relation of the known condition keywords of the geometric proof questions as ATT, and setting the semantic link relation of the proof result keywords as VAL; when the geometric proof questions are selected, extracting keywords with semantic link relations of ATT as known conditions for storage, selecting geometric reasoning rules for application to generate new facts, storing the new facts, and repeating reasoning until the new facts cannot be generated; extracting keywords with semantic link relation VAL as a proving result, and taking a process that the geometric reasoning rule generates facts identical to the proving result as a solving process if the facts identical to the proving result exist; if the fact which is the same as the proving result does not exist, selecting a new geometric reasoning rule from the reasoning rule base until the fact which is the same as the proving result is obtained;
s6: judging whether the answer of the user is correct, calculating answer score, and sending the answer score to step S3;
s7: and identifying a prompt request of the user, and displaying knowledge points or solving processes of the learning problem to the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210018504.0A CN114299772B (en) | 2022-01-07 | 2022-01-07 | Geometric coaching system and method based on semantic web |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210018504.0A CN114299772B (en) | 2022-01-07 | 2022-01-07 | Geometric coaching system and method based on semantic web |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114299772A CN114299772A (en) | 2022-04-08 |
| CN114299772B true CN114299772B (en) | 2024-03-19 |
Family
ID=80975631
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210018504.0A Active CN114299772B (en) | 2022-01-07 | 2022-01-07 | Geometric coaching system and method based on semantic web |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114299772B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117350274A (en) * | 2023-10-08 | 2024-01-05 | 华中师范大学 | Method and system for automatically synthesizing new geometric proof questions based on existing problems |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107423287A (en) * | 2017-07-05 | 2017-12-01 | 华中师范大学 | The automatic answer method and system of Proving Plane Geometry topic |
| CN107644572A (en) * | 2016-07-21 | 2018-01-30 | 上海莘越软件科技有限公司 | A kind of tutoring system based on thought process |
| CN111326040A (en) * | 2020-01-16 | 2020-06-23 | 深圳市芥菜种科技有限公司 | Intelligent test and intelligent tutoring system and method for Chinese reading understanding |
| CN112115275A (en) * | 2020-09-18 | 2020-12-22 | 湖南工学院 | Knowledge graph construction method and system for math tutoring question-answering system |
| CN112509404A (en) * | 2020-11-19 | 2021-03-16 | 江苏乐易学教育科技有限公司 | Teaching system and teaching method for space geometric thinking process |
| CN112966092A (en) * | 2020-11-25 | 2021-06-15 | 安徽教育网络出版有限公司 | Knowledge graph personalized semantic recommendation method based on basic education |
-
2022
- 2022-01-07 CN CN202210018504.0A patent/CN114299772B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107644572A (en) * | 2016-07-21 | 2018-01-30 | 上海莘越软件科技有限公司 | A kind of tutoring system based on thought process |
| CN107423287A (en) * | 2017-07-05 | 2017-12-01 | 华中师范大学 | The automatic answer method and system of Proving Plane Geometry topic |
| CN111326040A (en) * | 2020-01-16 | 2020-06-23 | 深圳市芥菜种科技有限公司 | Intelligent test and intelligent tutoring system and method for Chinese reading understanding |
| CN112115275A (en) * | 2020-09-18 | 2020-12-22 | 湖南工学院 | Knowledge graph construction method and system for math tutoring question-answering system |
| CN112509404A (en) * | 2020-11-19 | 2021-03-16 | 江苏乐易学教育科技有限公司 | Teaching system and teaching method for space geometric thinking process |
| CN112966092A (en) * | 2020-11-25 | 2021-06-15 | 安徽教育网络出版有限公司 | Knowledge graph personalized semantic recommendation method based on basic education |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114299772A (en) | 2022-04-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Leelawong et al. | Designing learning by teaching agents: The Betty's Brain system | |
| Puchner et al. | Teacher learning and mathematics manipulatives: A collective case study about teacher use of manipulatives in elementary and middle school mathematics lessons | |
| Foshay et al. | Principles for teaching problem solving | |
| Sargent et al. | Empirical evidence that formative assessments improve final exams | |
| CN107644572A (en) | A kind of tutoring system based on thought process | |
| Domun et al. | Design and Development of a Self-Assessment Tool and Investigating its Effectiveness for E-Learning. | |
| CN114299772B (en) | Geometric coaching system and method based on semantic web | |
| Wahyudi et al. | The Development of Realistic Mathematics Education (RME) for Primary Schools' Prospective Teachers | |
| Pupah et al. | Enhancing EFL students’ reading learning process in COVID-19 pandemic through Nearpod | |
| Tan et al. | The role of feedback in preparation for future learning: A case study in learning by teaching environments | |
| Paolucci et al. | Examining preservice teachers' understanding of slope through posing problems and embedding learning in real-world contexts | |
| Atmosukarto et al. | Enhancing adaptive online chemistry course with ai-chatbot | |
| Ebby et al. | Pathways for analyzing and responding to student work for formative assessment: The role of teachers’ goals for student learning | |
| Feng et al. | Teachers' Perspective on Implementing Computational Thinking in Elementary Classrooms | |
| Magajna | Formal and informal mathematical methods in work settings | |
| Haswani et al. | English Teaching Material Development Based on Tynker Program in Improving Fourth-Grade Students’ Vocabularies | |
| Hu | Research on Ubd Teaching Design of Junior High School English Based on Big Concept | |
| Gionfriddo et al. | A methodology for mentoring writing in law practice: using textual clues to provide effective and efficient feedback | |
| Albelihi | Lexical and cohesive links in EFL learners' writing: Exploring the use of task based language teaching | |
| Zhetpisbayeva et al. | APPLICATION OF “ZONE OF PROXIMAL DEVELOPMENT” THEORY IN TEACHING FOREIGN LANGUAGES WITHIN INCLUSIVE EDUCATION | |
| Bishop et al. | TEACHING GROUNDED READING SKILLS VIA AN INTERACTIVE ROBOT TUTOR | |
| Thurmond | EXPLORING THE IMPACT OF GROWTH MINDSET STRATEGIES ON MATHEMATICS PRE-SERVICE TEACHERS’BELIEFS | |
| Barkay | Teachers Use of Exemplification and Explanations in Mediating the Object of Learning | |
| Vodovozov et al. | Active Learning of Students with Diverse Goals and Backgrounds in the Light of Industry 4.0 Requirements | |
| Risko | Reading Teacher Education-Building an Evidence Base. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |