Teaching method and device based on artificial intelligence, equipment and medium

Abstract

The invention discloses a teaching method and device based on artificial intelligence, computer equipment and a storage medium. The method comprises the following steps: a data acquisition step: acquiring test questions and question solving elements of the test questions; a question solving step: the student inputs a question solving scheme of the test question into a first AI model according to the test question content; a completion step: the first AI model fills the relationship between the question solving elements according to the question solving scheme input by the student; and a judgment step: judging whether the relationship between the problem solving elements is complete and accurate, and if so, ending the teaching. According to the invention, the AI is converted into a learner like a student, the student is converted into a teacher, and the learning effect of the student is improved and the expression ability of the student is improved through a mode of'teaching instead of learning '.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a teaching method, device, equipment and medium based on artificial intelligence. Background Art

[0002] With the development of artificial intelligence (AI) technology, the development of the education field has also been promoted by artificial intelligence technology. The application of AI big models in the field of education has great potential and can help improve the quality of education, improve teaching efficiency, and increase the utilization rate of higher education resources.

[0003] At present, the online education field adopts the method of human-computer interaction in combining with artificial intelligence. Students ask questions to artificial intelligence and artificial intelligence answers them. This method is innovative and practical in the field of online education. The human-computer interaction model can break the limitations of time and space, allowing students to acquire knowledge and answer questions anytime and anywhere. By asking questions to artificial intelligence and getting answers, students' immediate needs can be quickly met, improving learning efficiency and autonomy.

[0004] Existing research shows that the Feynman learning method can achieve good teaching results in actual teaching, but it is difficult to implement in the current daily teaching process. The existing technology lacks a way to effectively implement the Feynman learning method. Summary of the invention

[0005] Based on this, in order to solve the above problems, this paper proposes a teaching method, device, equipment and medium based on artificial intelligence. The teaching method of the present invention transforms AI into a learner like a student, and the student becomes a teacher. Through the method of "teaching instead of learning", the learning effect of students is improved and the students' expression ability is improved.

[0006] According to a first aspect of the present invention, there is provided a teaching method based on artificial intelligence, comprising:

[0007] Data acquisition step, acquiring the test questions and the solution elements of the test questions;

[0008] A problem-solving step, in which the student inputs a solution to the test question into the first AI model according to the content of the test question;

[0009] In the completion step, the first AI model fills in the relationship between the problem-solving elements according to the problem-solving solution input by the student;

[0010] The judgment step is to judge whether the relationship between the problem-solving elements is complete and accurate. If so, the teaching ends.

[0011] In some embodiments, in the judging step, if the result of judging whether the relationship between the problem-solving elements is complete and accurate is no, the student is guided based on the erroneous part or the incomplete part.

[0012] In some embodiments, the guiding the students includes: asking questions to the students regarding the wrong parts or incomplete parts, and supplementing or modifying the relationship between the elements of the problem-solving according to the students' answers;

[0013] Or inform students of the knowledge points they have not mastered based on the wrong or incomplete parts;

[0014] Or based on the erroneous or incomplete parts, relevant knowledge point learning materials can be pushed to students.

[0015] In some embodiments, the problem-solving elements are entities and entity attribute values ​​in the relevant knowledge graph obtained based on the test question;

[0016] The relationship between the problem-solving elements is the entity relationship in the knowledge graph.

[0017] In some embodiments, the determination of whether the relationship between the problem-solving elements is complete and accurate is implemented through a second AI model.

[0018] In some embodiments, the method for determining whether the relationship between the problem-solving elements is complete and accurate includes:

[0019] The test question is input into the second AI model, and the second AI model solves the problem based on the problem-solving elements and the relationship between the problem-solving elements. If the relationship between the problem-solving elements is complete and accurate, the second AI model can obtain the correct answer. If the relationship between the problem-solving elements is incomplete or inaccurate, the second AI model cannot obtain the correct answer.

[0020] In some embodiments, obtaining the problem-solving elements of the test questions in the data acquisition step is achieved through a third AI model.

[0021] In some embodiments, the first AI model and the second AI model are the same AI model.

[0022] In some embodiments, the first AI model and the third AI model are the same AI model.

[0023] In some embodiments, the method for obtaining the problem-solving elements of the test question in the data acquisition step is:

[0024] A data set including problem-solving elements and relations between the problem-solving elements is obtained according to the test question, and the problem-solving elements of the test question are obtained by breaking the relations between the problem-solving elements in the data set.

[0025] In some embodiments, the knowledge graph is constructed by performing entity extraction, relationship extraction, and attribute extraction on the teaching material database.

[0026] In some embodiments, the second AI model is an LSTM model, the test question is input through an input gate, and the answer is obtained through an output gate;

[0027] The LSTM model can obtain the correct answer by inputting the test questions through the input gate only when the relationship between the problem-solving elements is complete and accurate.

[0028] In some embodiments, the method for obtaining the problem-solving elements of the test question in the data acquisition step is:

[0029] According to the test question, a data set including problem-solving elements and the relationship between the problem-solving elements is obtained, and the relationship between the problem-solving elements is interrupted by the LSTM model to obtain the problem-solving elements of the test question;

[0030] The method for interrupting the relationship between the problem-solving elements is: transforming the forget gate of the LSTM model into an incomplete gate that can interrupt the relationship between the problem-solving elements, thereby realizing the interruption of the relationship between the problem-solving elements.

[0031] According to a second aspect of the present invention, there is provided a teaching device based on artificial intelligence, comprising:

[0032] A data acquisition module is used to acquire test questions and solution elements of the test questions;

[0033] A problem-solving module, used for students to input the solution of the test question into the first AI model according to the content of the test question;

[0034] The completion module is used by the AI ​​model to fill in the relationship between the elements of the problem-solving solution according to the solution input by the student;

[0035] The judgment module is used to judge whether the relationship between the problem-solving elements is complete and accurate. If so, the teaching ends.

[0036] According to a third aspect of the present invention, there is provided a computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the above-mentioned method embodiments when executing the computer program.

[0037] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method of any of the above embodiments are implemented.

[0038] The technical solution of the present invention uses an AI model to fill in the relationship between the problem-solving elements according to the problem-solving solutions input by the students, so that the AI ​​model is transformed into the role of a "student", and by judging whether the relationship between the problem-solving elements is complete and accurate, the AI ​​model can provide feedback to the students on the knowledge points that have not been mastered, thereby realizing the teaching method of "teaching instead of learning". The teaching method of "teaching instead of learning" can not only improve the students' learning efficiency, but also exercise their expression ability. When using LSTM as an AI model, the forget gate is transformed into a specific entity information logical relationship incomplete gate, and the relationship between important knowledge points in the educational knowledge map is interrupted. After that, the interrupted relationship is completed by the students' narration of the content, thereby realizing the AI ​​learning companion function. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 are flow charts of some embodiments of the artificial intelligence-based teaching method of the present invention;

[0040] Figure 2 It is a schematic diagram of the horizontal projectile motion test question;

[0041] Figure 3 is a schematic diagram of a test question of Embodiment 2 of the present invention;

[0042] Figure 4 It is the eighth grade knowledge graph created by the teacher in the second embodiment of the present invention;

[0043] Figure 5 It is a schematic diagram of the structure of some embodiments of the teaching device based on artificial intelligence of the present invention;

[0044] Figure 6 It is a diagram of the internal structure of a computer device used to implement some embodiments of the present invention. DETAILED DESCRIPTION

[0045] Embodiments of the present invention will be described more fully below with reference to the accompanying drawings, in which embodiments of the present invention are shown. However, the present invention can be embodied in many different forms and should not be construed as limited to the embodiments set forth herein.

[0046] The terms used herein are used only for the purpose of describing specific embodiments and are not intended to limit the present disclosure. As used herein, the singular forms "a", "an", "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that when used herein, the term "comprising" specifies the presence of the claimed features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof.

[0047] Unless otherwise defined, the terms (including technical and scientific terms) used herein have the same meanings as commonly understood by those of ordinary skill in the art to which the present disclosure belongs. The terms used herein should be interpreted as having the meanings consistent with their meanings in the context of this specification and in the relevant field, and should not be interpreted in an idealized or overly formal sense, unless specifically defined as such herein.

[0048] AI: Artificial Intelligence.

[0049] Problem-solving elements: the knowledge points that need to be involved in the process of solving the test questions, including: specific names (corresponding numerical values).

[0050] The relationship between problem-solving elements: that is, the relationship between the knowledge points that need to be involved in the process of solving the test questions. Through the relationship between the knowledge points, the logical deduction, numerical calculation and other problem-solving steps between the knowledge points can be completed.

[0051] The AI ​​model can complete the correct answer to the test question when it knows the problem-solving elements and the relationship between the problem-solving elements (complete and accurate).

[0052] Figure 1 Flowcharts showing some embodiments of the artificial intelligence-based teaching method of the present invention.

[0053] like Figure 1 As shown, the method includes:

[0054] Data acquisition step S102, acquiring the test question and the solution elements of the test question.

[0055] In some embodiments, obtaining the problem-solving elements of the test question in the data acquisition step is implemented by a third AI model. Specifically, it includes: obtaining a data set containing problem-solving elements and the relationships between the problem-solving elements according to the test question, and obtaining the problem-solving elements of the test question by interrupting the relationships between the problem-solving elements in the data set. The third AI model can be an LSTM model, and the forget gate of the LSTM model is transformed into an incomplete gate that can interrupt the relationships between the problem-solving elements, so as to interrupt the relationships between the problem-solving elements.

[0056] In some embodiments, the problem-solving elements are entities and entity attribute values ​​in a related knowledge graph obtained according to the test question. The knowledge graph is constructed by performing entity extraction, relationship extraction, and attribute extraction on a teaching material database.

[0057] In the problem-solving step S104, the student inputs the solution to the test question into the first AI model according to the content of the test question.

[0058] In the completion step S106, the first AI model fills in the relationship between the problem-solving elements according to the problem-solving solution input by the student.

[0059] In some embodiments, the relationship between the problem-solving elements is an entity relationship in a knowledge graph.

[0060] In step S108, it is determined whether the relationship between the problem-solving elements is complete and accurate. If so, the teaching ends.

[0061] In some embodiments, if the result of judging whether the relationship between the problem-solving elements is complete and accurate is no, the student is guided according to the wrong part or the incomplete part. The guiding of the student includes: asking the student questions about the wrong part or the incomplete part, supplementing or modifying the relationship between the problem-solving elements according to the student's answer; or informing the student of the knowledge points that he has not mastered according to the wrong part or the incomplete part; or pushing relevant knowledge point learning materials to the student according to the wrong part or the incomplete part.

[0062] In some embodiments, the judgment of whether the relationship between the problem-solving elements is complete and accurate is implemented through a second AI model. Specifically, it includes: inputting the test question into the second AI model, and the second AI model solves the problem according to the problem-solving elements and the relationship between the problem-solving elements. If the relationship between the problem-solving elements is complete and accurate, the second AI model can obtain the correct answer. If the relationship between the problem-solving elements is incomplete or inaccurate, the second AI model cannot obtain the correct answer. The second AI model can be an LSTM model, which inputs the test question through the input gate and obtains the answer through the output gate.

[0063] In the present invention, the first AI model, the second AI model, and the third AI model may be the same AI model or different AI models.

[0064] Embodiment 1

[0065] 1. Get the test question of horizontal projectile motion, and obtain the knowledge map of horizontal projectile motion test question (with the relationship between entities marked). Test content: At a height of H = 45m above the ground, a small ball A moves with an initial velocity v 0 =10m / s 2 Throw it horizontally, A can be represented as a point mass, air resistance is ignored, and the acceleration due to gravity is g = 10m / s 2 . Find the time when ball A hits the ground and the horizontal distance it is thrown. Figure 2 This is a schematic diagram of a test question on horizontal projectile motion.

[0066] 2. Import the question into AI (when AI uses the LSTM model, import the question through the input gate) and obtain or create a knowledge graph related to the question (including knowledge graph entities and entity relationships).

[0067] The entities in the knowledge graph include: A's initial velocity v 0 (Attribute value: 10m / s 2 ), height from the ground H (attribute value: 45m), gravitational acceleration g (attribute value: 10m / s 2 ), landing time TA, horizontal distance SA.

[0068] The entity relationship of the knowledge point graph is as follows: SA = V 0 *TA;

[0069] 3. The AI ​​model interrupts the entity relationships in the knowledge graph (when AI uses the LSTM model, the interruption is completed through the incomplete gate).

[0070] 4. Students explain their problem-solving ideas to AI, which understands what the students are saying and fills in the interrupted entity relationships in the knowledge graph. For example, students say: Since the height is 45m, the acceleration due to gravity is 10m / s 2 According to the free fall formula, in free fall, the height is equal to the acceleration due to gravity multiplied by the square of time divided by two, so the time is equal to 2 multiplied by the height divided by the square root of the acceleration due to gravity, and the landing time is 3 seconds. Since air resistance is negligible, the horizontal distance is equal to time multiplied by the initial velocity, that is, 3 seconds multiplied by 10 meters per second equals 30 meters. At this time, AI can understand what the students are saying and fill in the knowledge graph relationship, that is: SA = V 0 *TA; At this point, AI determines that the entity relationships in the knowledge graph are complete and accurate (when AI uses the LSTM model, the output gate can fully output the answer), and ends the teaching. The entity relationship is missing, and AI will ask students based on the incomplete relationship: "How to calculate the time it takes for the ball to fall to the ground?" If the student answers correctly (for example: in free fall, the height is equal to the acceleration due to gravity multiplied by the square of the time divided by two, so the time is equal to 2 times the height divided by the square root of the acceleration due to gravity, ), then AI will continue to supplement the knowledge graph The teaching ends when the student answers incorrectly or does not answer. If the student does not have a good grasp of the free fall motion knowledge point, the AI ​​will inform the student that the free fall motion knowledge point is insufficient and push the corresponding learning materials. After the student has completed the relevant knowledge point learning, the AI ​​will continue to explain the solution to the problem.

[0071] Embodiment 2

[0072] 1. Get the test questions. Test content: Figure 3As shown, △ABC is an acute triangle. With AB and AC as sides, draw equilateral triangles △ABD and △ACE outwards. Connect BE and CD to intersect at point F. Connect AF. Prove that △ABE≌△ADC.

[0073] 2. Obtain the eighth-grade knowledge graph created by the teacher ( Figure 4 ), and then manually mark the knowledge points about eighth grade mathematics in the questions;

[0074] The problem-solving related entities in the knowledge graph include: acute triangles; equilateral triangles; congruent triangles; determination method of congruent triangles: SAS (other determination methods: SSS, AAS, ASA, HL); angle bisector (determination method: the points with equal distances to the two sides of the angle are on the angle bisector).

[0075] Among them: SSS: means that two triangles with three equal sides are congruent.

[0076] SAS: Indicates that two triangles with equal sides and included angles are congruent.

[0077] AAS: Indicates that two triangles are congruent if their two angles and the opposite side of one of the angles are equal.

[0078] ASA: Indicates that two triangles are congruent if their angles and included sides are equal.

[0079] HL: Two right triangles are congruent if one pair of right-angled sides and the corresponding hypotenuse are equal

[0080] 3. After the question is input into AI, AI automatically parses the question stem and breaks the relationship between the entities related to the problem in the knowledge graph.

[0081] 4. Student explanation: Equilateral triangles △ABD and △ACE have a common point A. So in the study, we will select two sides AB and AD and AC and AE from the two equilateral triangles around point A to form two congruent triangles △ABE and △ADC. Because there are two sides, combined with the determination method of congruent triangles, only SSS and SAS have two sides among the five methods, so the third congruent condition is selected. Analyze the question again, only one angle can be found. Because the equilateral sides with the same starting point have 60-degree equal angles, and the common angle BAC is sandwiched between the two equal angles, the third equal angle condition can be derived. The SAS determination method is satisfied, so the congruent triangles are proved.

[0082] 5. AI fills in the entity relationships in the knowledge graph through students’ explanations. Through students’ explanations, two equilateral triangles → two equal sides (satisfying the two equal sides in SAS), two equilateral triangles → two 60-degree angles + common angle BAC → two equal angles (satisfying the angles in SAS), thus filling in the relationship between congruent triangles and SAS in the knowledge graph. AI judges that the relevant entity relationships in the knowledge graph are complete and can obtain the correct answer. Students have mastered the congruent model SAS in congruent triangles.

[0083] In the present invention, the specific construction method of the knowledge graph may include:

[0084] 1. Construction of Knowledge Graph

[0085] 1. Knowledge Extraction

[0086] 1.1 Entity Extraction Identifying named entities from the learning material dataset

[0087] 1.2 Relationship Extraction After entity extraction, discrete knowledge point named entities are obtained from the textbook text corpus. The association relationship between entities is extracted from the relevant textbook corpus, and the textbook entities are connected through the relationship to form a network knowledge structure diagram.

[0088] 1.3 Attribute Extraction

[0089] 1.3.1 Treat the attributes of the textbook entity as a nominal relationship between the entity and the attribute value, and transform the textbook attribute extraction task into a textbook relationship extraction task.

[0090] 1.3.2 Extract textbook structured data based on rules and heuristic algorithms.

[0091] 1.3.3 Based on the semi-structured data of encyclopedia websites, textbook training corpus is generated through automatic extraction to train the textbook entity attribute labeling model, which is then applied to the entity attribute extraction of unstructured data.

[0092] 1.3.4 Use data mining methods to directly mine the relationship patterns between entity attributes and attribute values ​​from the textbook text, and locate the textbook attribute names and attribute values ​​in the textbook text.

[0093] 2. Knowledge Fusion

[0094] Through information extraction, entities, relationships and entity attribute information are obtained from the original unstructured and semi-structured data.

[0095] 2.1 Entity Linking

[0096] 2.1.1 Obtain entity references from text through entity extraction.

[0097] 2.1.2 Perform entity disambiguation and coreference resolution to determine whether the entities with the same name in the knowledge base represent different meanings and whether there are other named entities in the knowledge base that represent the same meaning.

[0098] 2.1.3 After confirming the correct entity object in the knowledge base, link the entity reference item to the corresponding entity in the knowledge base.

[0099] 2.2 Knowledge Fusion

[0100] After entity linking, the entity is linked to the corresponding correct entity object in the knowledge base, and the knowledge content is integrated with structured data such as external knowledge bases and relational databases.

[0101] 3. Knowledge Processing

[0102] 3.1 Ontology Extraction

[0103] Construct the ontology in a data-driven automated way. Use the automatic construction technology of the ontology library in the field of education to gradually expand the educational ontology data.

[0104] 3.2 Knowledge Reasoning

[0105] After the ontology is constructed, further knowledge discovery is completed using knowledge reasoning technology to make up for the incompleteness of the knowledge graph relationship.

[0106] 3.3 Quality Assessment

[0107] The credibility of knowledge is quantified, and the quality of the knowledge base is ensured by discarding knowledge with low confidence.

[0108] 2. Extract entity relationship variables by grade and subject according to the syllabus

[0109] 1. Rule-based Relation Extraction

[0110] The algorithm principle of rule-based relationship extraction is to identify the relationship between entities by defining a set of rules. The specific steps are as follows: define a set of rules based on domain knowledge; identify the relationship between entities based on these rules.

[0111] 2. Relationship Extraction Based on Machine Learning

[0112] The algorithm principle of relationship extraction based on machine learning is to identify the relationship between entities by training a machine learning model. The specific steps are as follows: preprocess text data, including removing stop words, marking parts of speech, word segmentation, etc.; mark text data as positive and negative examples to facilitate model training; train a machine learning model, such as support vector machine, random forest, deep learning, etc.; use the trained model to identify the relationship between entities.

[0113] When the present invention uses LSTM as an AI model, the core idea is to control the flow of information through three gates (input gate, defect gate, and output gate). These gates map the input to a value between 0 and 1 through the sigmoid function, thereby determining whether the information is retained or discarded. The basic process includes:

[0114] Data preprocessing,First, the input data needs to be preprocessed, including standardization,,normalization and other operations, so that the model can better learn the characteristics of the,data.

[0115] Create a model and use the Sequential class to create an educational knowledge graph entity relationship incomplete neural network. Then, add the necessary layers in the required order, such as the Dense layer (fully connected layer) for output predictions.

[0116] Define the network structure: In the incomplete neural network model of the entity relationship of the educational knowledge graph, the input of each time step will pass through three main "gate" structures: the incomplete gate, the input gate, and the output gate. These gate structures determine whether the information is retained or set to be incomplete through specific calculation formulas and control mechanisms. Among them, the incomplete gate: controls whether the hidden cell state of the previous layer is incomplete, and determines which information needs to be retained with a certain probability. Input gate: responsible for processing the input at the current sequence position and updating the cell state. It consists of two parts: one part uses the sigmoid activation function to calculate the value of the input gate, and the other part uses the tanh activation function to calculate the value of the candidate memory unit. Output gate: calculates and outputs the hidden state of the current time step based on the updated cell state.

[0117] Model training: The model is trained using preprocessed data. During the training process, the model learns how to adjust its parameters to minimize the prediction error. This is usually achieved through the back-propagation algorithm and the gradient descent optimizer. Model evaluation: After the training is completed, the model is evaluated using a validation set or a test set to check its performance. Evaluation metrics may include accuracy, loss function value, etc. Model application: Once the model has been trained and evaluated and meets the expected performance requirements, it can be applied to AI companion learning.

[0118] The present invention is different from the complete knowledge graph relationship linking method of the existing AI model, and can give AI a specific incomplete knowledge graph structure. AI completes the knowledge graph through the "teaching" of students. By changing the role of AI to a learner, the function of "teaching instead of learning" for students is realized.

[0119] Figure 5 The schematic diagrams of the structures of some embodiments of the teaching device based on artificial intelligence of the present invention are shown.

[0120] like Figure 5 As shown, including:

[0121] The data acquisition module 100 is used to acquire the test questions and the solution elements of the test questions;

[0122] The problem-solving module 200 is used for the student to input the solution of the test question into the first AI model according to the content of the test question;

[0123] A completion module 300 is used for the AI ​​model to fill in the relationship between the problem-solving elements according to the problem-solving solution input by the student;

[0124] The judgment module 400 is used to judge whether the relationship between the problem-solving elements is complete and accurate. If so, the teaching ends.

[0125] For the specific definition of a teaching device based on artificial intelligence, please refer to the definition of a teaching method based on artificial intelligence above, which will not be repeated here. Each module in the above-mentioned teaching device based on artificial intelligence can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0126] The present invention also provides a computer device, which may be a terminal, and its internal structure diagram may be as shown in Figure 6 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above-mentioned teaching method based on artificial intelligence is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc. Those skilled in the art can understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present invention, and does not constitute a limitation on the computer device to which the scheme of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0127] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned teaching method based on artificial intelligence is implemented.

[0128] Those skilled in the art can understand that all or part of the processes in the above method embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus), direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0129] So far, the embodiments of the present invention have been described in detail. In order to avoid obscuring the concept of the present invention, some details known in the art are not described. Based on the above description, those skilled in the art can fully understand how to implement the technical solutions disclosed herein.

[0130] Although some specific embodiments of the present invention have been described in detail by way of examples, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present invention. It should be understood by those skilled in the art that the above embodiments may be modified or some technical features may be replaced by equivalents without departing from the scope and spirit of the present invention. The scope of the present invention is defined by the appended claims.

Claims

1. A teaching method based on artificial intelligence, characterized in that: The following steps are involved: Data acquisition step, acquiring the test questions and the solution elements of the test questions; A problem-solving step, in which the student inputs a solution to the test question into the first AI model according to the content of the test question; In the completion step, the first AI model fills in the relationship between the problem-solving elements according to the problem-solving solution input by the student; The judgment step is to judge whether the relationship between the problem-solving elements is complete and accurate. If so, the teaching ends.

2. The teaching method of artificial intelligence according to claim 1, characterized in that: In the judging step, if the result of judging whether the relationship between the problem-solving elements is complete and accurate is no, the student is guided according to the wrong part or the incomplete part.

3. The teaching method of artificial intelligence according to claim 2, characterized in that: The guiding of students includes: asking students questions about incorrect or incomplete parts, and supplementing or modifying the relationship between elements of the problem according to the students' answers; Or inform students of the knowledge points they have not mastered based on the wrong or incomplete parts; Or based on the erroneous or incomplete parts, relevant knowledge point learning materials can be pushed to students.

4. The teaching method of artificial intelligence according to claim 1, characterized in that: The problem-solving elements are entities and entity attribute values ​​in the relevant knowledge graph obtained according to the test question; The relationship between the problem-solving elements is the entity relationship in the knowledge graph.

5. The artificial intelligence teaching method according to claim 1, characterized in that: The judgment of whether the relationship between the problem-solving elements is complete and accurate is achieved through the second AI model.

6. The teaching method of artificial intelligence according to claim 5, characterized in that: The method for judging whether the relationship between the problem-solving elements is complete and accurate includes: The test question is input into the second AI model, and the second AI model solves the problem based on the problem-solving elements and the relationship between the problem-solving elements. If the relationship between the problem-solving elements is complete and accurate, the second AI model can obtain the correct answer. If the relationship between the problem-solving elements is incomplete or inaccurate, the second AI model cannot obtain the correct answer.

7. The artificial intelligence teaching method according to claim 1, characterized in that: The data acquisition step obtains the problem-solving elements of the test questions through a third AI model.

8. The teaching method of artificial intelligence according to claim 5, characterized in that: The first AI model and the second AI model are the same AI model.

9. The artificial intelligence teaching method according to claim 7, characterized in that: The first AI model and the third AI model are the same AI model.

10. The artificial intelligence teaching method according to claim 1, characterized in that: The method for obtaining the problem-solving elements of the test questions in the data acquisition step is: A data set including problem-solving elements and relations between the problem-solving elements is obtained according to the test question, and the problem-solving elements of the test question are obtained by breaking the relations between the problem-solving elements in the data set.

11. The artificial intelligence teaching method according to claim 4, characterized in that: The knowledge graph is constructed by performing entity extraction, relationship extraction, and attribute extraction on the teaching material database.

12. A teaching device based on artificial intelligence, characterized in that: include: A data acquisition module is used to acquire test questions and solution elements of the test questions; A problem-solving module, used for students to input the solution of the test question into the first AI model according to the content of the test question; A completion module, used for the first AI model to fill in the relationship between the problem-solving elements according to the problem-solving solution input by the student; The judgment module is used to judge whether the relationship between the problem-solving elements is complete and accurate. If so, the teaching ends.

13. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 11 are implemented.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 11 are implemented.

Images