Teaching method and device based on subject knowledge graph, and storage medium

Abstract

The embodiment of the invention provides a teaching method and device based on a knowledge graph and a storage medium, and the method comprises the steps: building a subject knowledge graph based on AI4e according to a teaching material and a teaching outline; selecting knowledge elements in the subject knowledge graph; and mounting teaching auxiliary data under the knowledge elements, wherein the teaching auxiliary data is used for helping students understand the knowledge points recorded by the knowledge elements and supervising the teaching quality of teachers. According to the application, fusion and association among the subject knowledge maps can be realized, and personalized learning is realized for each student.

Description

Technical Field

[0001] This document relates to the field of artificial intelligence and natural language processing technology, and in particular to a teaching method, device and storage medium based on knowledge graph. Background Art

[0002] Subject knowledge graphs enable students to quickly grasp learning information, accurately and quickly help students find the key points of the subject, and construct a knowledge framework, thereby helping educators and students better understand and apply subject knowledge.

[0003] Existing technologies mainly use neural networks to construct subject knowledge graphs, connecting massive amounts of knowledge points, allowing educators and students to search based on their own needs.

[0004] However, the existing technology only realizes the breadth connection of knowledge, but does not mine individual knowledge elements. There are many knowledge points, and it is difficult to split each knowledge point and mount it on the corresponding knowledge graph. It is also impossible to track each student's mastery of each knowledge point and make personalized learning recommendations. Summary of the invention

[0005] In view of the above scheme, the present application aims to propose a teaching method and device based on knowledge graph to solve at least one of the above technical problems.

[0006] In a first aspect, one or more embodiments of this specification provide a teaching method based on a subject knowledge graph, including:

[0007] Based on AI4e, create subject knowledge graphs according to textbooks and syllabus;

[0008] Selecting knowledge elements in the subject knowledge graph; and

[0009] Teaching auxiliary data is mounted under the knowledge element, and the teaching auxiliary data is used to help students understand the knowledge points recorded in the knowledge element and supervise the teaching quality of teachers.

[0010] Furthermore, the teaching auxiliary data includes data slices, and

[0011] Mounting teaching auxiliary data under the knowledge element includes:

[0012] Collect electronic data of learning materials;

[0013] Based on optical character recognition technology, according to the knowledge elements in the subject knowledge graph, data slices are obtained from the electronic data of the learning materials; and

[0014] The knowledge element and the data slice are associated.

[0015] Further, obtaining the students' knowledge meta-test accuracy; and

[0016] When the test accuracy of the knowledge element is less than a threshold, the data slice corresponding to the knowledge element is pushed.

[0017] Furthermore, the knowledge element includes a resource list, and the method further includes:

[0018] Determine a slice title according to the content in the data slice; and

[0019] Place the slice title in the resource list under the knowledge element.

[0020] Further, the associating the knowledge element with the data slice includes:

[0021] According to the knowledge element, a knowledge element vector is obtained;

[0022] Obtaining a text vector according to the preset text data;

[0023] Calculating the similarity between the knowledge element vector and the text vector; and

[0024] According to the similarity, the knowledge element and the data slice are associated.

[0025] Furthermore, the teaching auxiliary data includes a graph subject, the graph subject includes a plurality of knowledge elements, and

[0026] The step of mounting teaching auxiliary data under the knowledge element includes:

[0027] Setting a list of associated courses for a knowledge element; and

[0028] Displays the course list.

[0029] Furthermore, the teaching auxiliary data includes application scenario data, and

[0030] The step of mounting teaching auxiliary data under the knowledge element includes:

[0031] Select target knowledge element;

[0032] Creating at least one application scenario list according to the target knowledge element; and

[0033] Fill in the application scenario data in each of the application scenario lists.

[0034] In a second aspect, the embodiment of the present application provides a teaching device based on a subject knowledge graph, including:

[0035] The graph module is used to create subject knowledge graphs based on AI4e and textbooks and syllabus;

[0036] A determination module, used for selecting knowledge elements in the subject knowledge graph; and

[0037] The auxiliary module is used to mount teaching auxiliary data under the knowledge element, and the teaching auxiliary data is used to help students understand the knowledge points recorded in the knowledge element and supervise the teaching quality of the teacher.

[0038] Further, the teaching auxiliary data includes data slices, and the auxiliary module is configured to:

[0039] Collect electronic data of learning materials;

[0040] Based on optical character recognition technology, according to the knowledge elements in the subject knowledge graph, data slices are obtained from the electronic data of the learning materials; and

[0041] The knowledge element and the data slice are associated.

[0042] In a third aspect, an embodiment of the present application provides a storage medium for storing computer-executable instructions, characterized in that when the computer-executable instructions are executed, the steps of the teaching method of the subject knowledge graph described in any one of the first aspects are implemented.

[0043] Compared with the prior art, this application can at least achieve the following technical effects:

[0044] This application can build knowledge graphs of various disciplines based on the AI4e big model, and then mine the knowledge elements under the knowledge graph, realize the integration of subject knowledge points from multiple perspectives, and deeply analyze the content of knowledge elements, so as to realize personalized learning for each student. In addition, it is also possible to compare knowledge elements and their mounted teaching auxiliary data to determine whether teachers are imparting knowledge strictly in accordance with the syllabus, so as to supervise the teaching quality of teachers. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate one or more embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0046] Figure 1 A flow chart of a teaching method based on knowledge graph provided for one or more embodiments of this specification;

[0047] Figure 2 A schematic diagram of a course video resource provided for one or more embodiments of this specification;

[0048] Figure 3 The corresponding subtitles and timestamps in the video provided for one or more embodiments of this specification;

[0049] Figure 4 Slice video title provided for one or more embodiments of this specification;

[0050] Figure 5 A learning trajectory provided for one or more embodiments of this specification;

[0051] Figure 6 A list of course maps provided for one or more embodiments of this specification;

[0052] Figure 7 An operation interface for editing application scenarios in knowledge elements provided in one or more embodiments of this specification;

[0053] Figure 8 A list of scenario applications in the knowledge element provided for one or more embodiments of this specification;

[0054] Fig. 9 A schematic diagram of the structure of a knowledge graph-based teaching device provided for one or more embodiments of this specification. DETAILED DESCRIPTION

[0055] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the following will be combined with the drawings in one or more embodiments of this specification to clearly and completely describe the technical solutions in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this document.

[0056] With the rapid development of AI technology, it is possible to map subject knowledge, which can realize the neural network of knowledge and the connection of massive knowledge points. However, this only realizes the breadth connection of knowledge first, and the deep mining of single knowledge element is far from enough. Especially for practical application teaching, whether students have mastered this knowledge point, whether there are deep learning resources, and whether they can apply what they have learned are all urgent problems to be solved. The ultimate goal of education is to be able to use the learned knowledge, to integrate the knowledge points, to be able to draw inferences from one example, and to truly apply what they have learned. To achieve this, we must first deeply mine the content of a single knowledge point, broaden the breadth of knowledge, and strengthen the depth construction of knowledge elements. This requires deep linking of learning resources with knowledge elements. However, the resources of the school are general, and teachers do not have so much energy to split the knowledge points one by one for resource mounting, which is not only time-consuming and labor-intensive, but also limited by the incomplete classroom teaching equipment. The second is the problem of subject barriers. Because in a real environment, a course is generally taught by one teacher, but the knowledge points are interdisciplinary, and it is impossible to require a teacher to teach all related subjects. Therefore, if you want to apply what you have learned, you must break down disciplinary barriers and achieve the integration of multidisciplinary knowledge. In addition, to determine how well students have mastered the knowledge points, it is necessary to track students' learning paths, implement personalized resource recommendations, and keep track of students' learning progress. At present, there is no better way to test students' learning effects except for exams. However, it is impossible to test a single knowledge point at any time during daily teaching. Schools and teachers do not have the time and energy to provide targeted and personalized teaching to individual students.

[0057] In response to the above technical problems, this application proposes a teaching method based on subject knowledge graph, such as Figure 1 As shown, the specific steps are as follows:

[0058] Step S1: Based on AI4e, create a subject knowledge graph according to the textbooks and syllabus.

[0059] In an embodiment of the present application, natural language processing, machine learning and other technologies in AI technology are used to automatically analyze teaching materials and teaching outlines to extract knowledge points and relationships; then a graph database (such as Neo4j) is used to store and manage the extracted knowledge points and relationships to form a subject knowledge graph.

[0060] Specifically, AI is used to conduct text analysis on electronic textbooks or teaching outlines to achieve knowledge modeling, knowledge extraction, and knowledge fusion of the course knowledge system. Entity extraction, entity disambiguation, relationship extraction, knowledge linking, ontology construction, and entity alignment are used to represent the knowledge extracted from electronic textbooks or teaching outlines as triples, and a "concept-entity-attribute-relationship" data model is established. In addition, in order to facilitate front-line teachers to use the platform, manual creation of graphs is supported to achieve functions such as creating, editing, and deleting knowledge groups. When users use the platform for AI analysis, experts can verify and modify the knowledge graph to make it more in line with school teaching needs and practical applications.

[0061] Step S2, selecting knowledge elements in the subject knowledge graph.

[0062] In the embodiment of the present application, knowledge elements are determined in the following two ways. First, after opening the subject knowledge graph, students and teachers can enter keywords in the search box to determine the field, and then search for knowledge elements based on the field, or they can click to search for knowledge elements by sliding the knowledge graph. Second, the system automatically selects knowledge elements based on course information. For example, for a Chinese class, the system can select the "Chinese" identifier based on the course information, and search for the knowledge element "Chinese" in the knowledge graph based on this identifier.

[0063] Step S3, mounting teaching auxiliary data under the knowledge element.

[0064] In the embodiment of the present application, during the learning process, it is often difficult for students to quickly find the most suitable content from the massive learning resources, thereby affecting learning efficiency. In order to solve the above problem, teaching auxiliary data is mounted under the knowledge element to help students understand the knowledge points recorded in the knowledge element.

[0065] In order to make the teaching auxiliary data mounted under the knowledge element more targeted, in this application, the subjects mounting the teaching auxiliary data can be teachers and systems.

[0066] When the system is the main body for mounting teaching auxiliary data, there are two mounting methods.

[0067] The first method is that the system collects the electronic data (video or courseware) of the learning materials involved in the teacher's daily classes through the automated timetable based on the multimedia equipment in the classroom. After that, it automatically classifies them into the corresponding knowledge element according to the course information.

[0068] Furthermore, in order to provide personalized recommendations for different students, the system performs data slicing on the electronic data of learning materials to obtain teaching auxiliary data, so that students can more accurately grasp relevant knowledge points. The specific process is: based on optical character recognition technology, according to the knowledge elements in the subject knowledge graph, data slices are obtained from the electronic data of the learning materials; and the knowledge elements and the data slices are associated.

[0069] Specifically, the electronic data of learning materials include: teaching video data and teaching materials (courseware). For teaching video data, first, the speech content in the teaching video is converted into text through speech-to-text technology. Secondly, the relevance between the contents is determined by calculating the distance between the text feature vector of the knowledge element and the text feature vector in speech-to-text; the video is sliced ​​according to the relevance and divided into multiple small segments; finally, each small segment after slicing is matched one-to-one with the knowledge element.

[0070] For teaching material data, optical character recognition technology is used to identify the uploaded courseware or electronic teaching materials and extract the text content; then, through vector calculation, the courseware content is compared with the knowledge elements in the knowledge graph, and the related knowledge elements are associated.

[0071] In this application, the course-related resources are compared and calculated with the knowledge elements through speech-to-text and OCR text recognition technology, and the range is divided according to the vector distance, so that the normalized course resources and the knowledge elements are effectively compared and mounted one by one, making the analysis and content presentation of the knowledge elements richer and more in-depth.

[0072] The specific association process is as follows: obtaining a knowledge element vector based on the knowledge element; obtaining a text vector based on the preset text data; calculating the similarity between the knowledge element vector and the text vector; and associating the knowledge element with the data slice based on the similarity.

[0073] Specifically, the preset text data includes the speech-to-text data obtained from the course video and the courseware materials uploaded by the teacher. These data are associated with the knowledge element respectively. The association situations are divided into the following two situations: Situation 1: When the teacher is teaching in the classroom, the recording and broadcasting equipment in the classroom will automatically record the teacher's class according to the class schedule command to form course resources. Therefore, a lot of excellent course video resources can be seen on the course homepage, such as Figure 2 All course videos are converted into text using AI technology, and the corresponding time between the text and the video is recorded to form subtitles and timestamps, such as Figure 3As described. Then, by means of vector calculation, compare and analyze the overlap between the knowledge point and the teacher's teaching content, confirm the minute of the video when the teaching content related to the knowledge point starts, and record the timestamp of the knowledge point to form a virtual slice. Students can click on the knowledge point to jump to the location where the video explains the knowledge point and study the knowledge point directly. Case 2: After the teacher uploads the courseware materials, the system receives the courseware materials and uses OCR technology to identify the courseware materials to obtain the corresponding text data; vectorizes the text data and knowledge elements to determine the similarity between the vectorized text data and the knowledge elements; slices the courseware materials according to the similarity to obtain slice data; associates the slice data with the knowledge elements so that students can find the corresponding courseware materials more quickly when learning the corresponding knowledge points.

[0074] In the second method, the system makes personalized recommendations based on the student's learning situation and obtains the student's knowledge element test accuracy rate; when the knowledge element test accuracy rate is less than a threshold, the data slice corresponding to the knowledge element is pushed.

[0075] Furthermore, in order to accurately identify the learning needs of each student and effectively help them master the learning content, the system will continuously monitor the accuracy of students' knowledge meta-tests and push data slices according to students' needs. This can gradually build students' knowledge systems and help each student achieve their learning goals, thereby improving learning efficiency.

[0076] Specifically, after students have learned the knowledge points of the relevant chapters, they are tested on the relevant knowledge points through test questions, and the system automatically grades them to obtain the test scores. The system determines the knowledge elements that have not been mastered based on the test scores. Then, the sliced ​​data titles are pushed to the knowledge elements that have not been mastered. Clicking on the titles allows students to enter the relevant videos for learning, so that students can check for deficiencies and make up for them in time. When the system obtains the test scores, it sends the test scores to the corresponding teachers. The teachers will record targeted explanation videos based on the students' usual performance in class and the test scores. Later, the system can mount the targeted explanation videos on the corresponding knowledge elements.

[0077] For example, the students' mastery of knowledge elements can be judged by the test results for this knowledge element. After learning the relevant resources of the knowledge point, the students click the button to take the test and take the knowledge element test. After the test, submit it and the system will automatically mark it. Based on the completion rate and accuracy of the knowledge element test, the system can know which knowledge elements the students have not learned in place, so as to know the weak situation of the students' knowledge points. When the correct rate of the student's knowledge element test is lower than the custom setting percentage, the relevant resource column will be pushed to the recommendation list with this knowledge element as the anchor point, so as to facilitate the students to check for deficiencies and make up for the gaps. According to the algorithm, each student will see different recommended resources according to their test results to meet personalized recommendations. After obtaining the completion rate of the student's knowledge element test, if the completion rate is not equal to 100%, knowledge will be pushed for the questions that the students have done wrong and the questions that they have not done, so as to avoid the students who are ambiguous about a certain knowledge point and mistakenly think that the current knowledge point has been mastered after they get it right by chance by randomly choosing an answer, which creates the illusion that the current knowledge point has been mastered. For example: When students are taking a test, they do not need to answer questions they do not know how to answer, and the system will recommend resources for the unanswered questions.

[0078] Furthermore, in order to facilitate users to quickly find the mounted teaching auxiliary data, the system also includes a resource list in the knowledge element, determines the slice title according to the content in the data slice, and places the slice title in the resource list under the knowledge element.

[0079] Specifically, when AI performs video text analysis, it will also summarize the text content and summarize the virtual sliced ​​video clips into subheadings. The title list is displayed under the video resource corresponding to the knowledge element, which is convenient for students to watch on demand. Figure 4 As shown in the figure, a subheading "1. Principles and representative drugs of blood stasis-removing and hemostatic drugs" is summarized under the resource list according to the knowledge points mentioned in the teaching video. Alternatively, the courseware materials can be sliced ​​according to the knowledge elements, and the titles can be summarized for the courseware content to facilitate students to find the required knowledge.

[0080] When the teacher is the subject of mounting teaching auxiliary data, the teaching teacher mounts the courseware materials of the class to the corresponding knowledge element.

[0081] Specifically, teachers recommend learning resources for the parts of content that they think are weak, and attach video resources and courseware resources to the corresponding knowledge element to combine video resources with courseware resources to help students break through knowledge points one by one and achieve in-depth learning of knowledge elements. Students can click on a knowledge point to check which resources are associated with the current knowledge point, which helps students quickly and conveniently find resources accurately for targeted learning.

[0082] In the embodiment of the present application, in order to provide personalized services to students, an intelligent question-answering system is also set up and includes. If students have questions, they can also mount the questions under the corresponding knowledge element and mark the knowledge element. The teacher can enrich the knowledge points or conduct special explanations based on the student's mark. Or the system will provide students with scientific and rigorous learning suggestions as soon as possible to improve students' learning efficiency and interest. Specifically, during the learning process, if students have completed a certain knowledge point, they can automatically light up this knowledge element to form a learning trajectory diagram, such as Figure 5 As shown, dark colors represent knowledge elements that students have already learned, and light colors represent knowledge elements that students have not yet learned or have only learned part of. For knowledge elements that have been learned, apply for an offline exam for this course. Based on the exam results, learning trajectory, or knowledge element mastery, each student can actively request the teacher or system to push relevant resources.

[0083] After clarifying the responsibilities of teachers, students, and the system through the above process, the knowledge points of different disciplines can be integrated through the following subject integration and scenario application, so that multiple graphs on the same page can be associated and cross-disciplinary searches can be performed. Scenario applications can better integrate knowledge points into actual application scenarios, allowing students to learn knowledge through examples and understand the application and association of knowledge.

[0084] In an embodiment of the present application, the same knowledge elements in different graph disciplines are associated; when a certain knowledge element is clicked, a list of corresponding courses associated with the knowledge element will be displayed under the knowledge element.

[0085] Specifically, the same knowledge in multiple courses is associated so that when searching for a certain course or a knowledge element in a certain course, multiple course maps can be presented on the same page dimension. And as long as it is a course that has created a map, its map name can appear in the list. Click on the map in the list to call out the map on the current page to display the knowledge element. Different map knowledge groups will be distinguished by different colors. After calling different maps on the page of the same dimension, click search to retrieve the knowledge elements in all subject maps on the page, thus realizing the search and learning of cross-disciplinary knowledge points. There are two ways to call up maps. One is manual calling. Click on the knowledge map list to see a list of all course maps. Manually clicking on any map can directly call it to the page. This method can help teachers and students flexibly choose the course maps they want to present, such as Figure 6 The second method is for the teacher to click the Add button to create an associated graph, create an associated relationship between the graph associated with this course, and click the associated graph in the list to retrieve all graphs related to this course on the page at once. This function allows teachers to associate subject graphs and help students understand the correlation between courses, which is of guiding significance.

[0086] Through this application, you can call up a list of knowledge graphs for all courses, and click on the corresponding graph to display multiple course graphs on one canvas. Students can not only see the logical relationship between knowledge points in different courses, but also continue to search for corresponding knowledge points across courses and disciplines through knowledge retrieval. Especially when the knowledge points involve multiple disciplines, all the corresponding knowledge points in these courses can be found at the same time, which greatly facilitates students' learning and exploration, saves students' retrieval time, and improves learning efficiency. And by clicking on the target knowledge element, the knowledge element can be automatically enlarged and displayed in the center from the massive knowledge base, making it more convenient and efficient to use.

[0087] For example, different colors can be used to distinguish knowledge elements of different subjects. Hawthorn is a drug that belongs to the pharmacological knowledge of the digestive system in "Chinese Materia Medica Pharmacology" and also has health knowledge in "Inner Canon of Medicine". If the knowledge graphs of these two courses are retrieved on the page, and then by searching for the knowledge point of hawthorn, the knowledge points about hawthorn in the two courses can be found and highlighted, which is convenient for students to carry out systematic integrated learning.

[0088] In real life, since knowledge is stagnant in books, it can only be truly digested and absorbed when used by students in specific scenarios. Therefore, application scenarios are added to each knowledge element in the knowledge graph, and the scenarios are combined with specific application scenarios, so that students can learn knowledge in depth through implementation examples and improve learning efficiency. At the same time, when the scenarios are associated with the knowledge graph, the association between knowledge elements and application scenarios of the knowledge graphs of multiple courses is supported to ensure that students can view the related scenarios associated with them when learning any knowledge element, so that the integration between disciplines is higher and it is easier for students to learn and understand. Therefore, the teaching auxiliary data includes application scenario data, selecting a target knowledge element; creating at least one application scenario list based on the target knowledge element; and filling in the application scenario data in each of the application scenario lists.

[0089] In an embodiment of the present application, target knowledge elements are used to add application scenarios to the knowledge elements in the knowledge graph, thereby combining the knowledge elements with specific scenarios.

[0090] Specifically, Figure 7 As shown, select the knowledge element to which you need to add a specific application scenario, open the editing page, edit the scenario name and scenario description, select the associated graph and associated nodes, and then submit. This will enable the association of scenarios between knowledge elements in the knowledge graph of each course. Then, extract the content of the specific application scenario, obtain relevant information, and summarize and extract relevant knowledge for easy query. When the specific scenario is constructed, click the "Related Scenario Application" button of the knowledge graph to retrieve the scenario list, as shown in the figure below. Figure 8As shown, click on any scene to expand and view the scene details, and light up the knowledge element associated with the scene. Click on the knowledge element list under the scene to highlight the knowledge element in the center. Then click on the knowledge element full screen button. If the knowledge element has an associated scene, you can also click to view it.

[0091] For example: Taking the heat-clearing drugs in Unit 11 of "Pharmacology of Traditional Chinese Medicine" as an example, it is necessary to understand the main pharmacological effects of heat-clearing drugs: anti-pathogenic microorganisms, immunomodulation, anti-inflammatory, antipyretic and analgesic, and improvement of microcirculation. So in what diseases can this pharmacological effect be used? According to the research on the modern scientific connotation of the traditional anti-tumor method of clearing heat and detoxification, it can be understood that heat-clearing drugs are helpful for anti-tumor treatment. Therefore, a scenario of tumor treatment plan can be created, and the heat-clearing drug knowledge element can be included. When students query the tumor treatment scenario, they can expand their learning of the pharmacological knowledge of heat-clearing drugs in traditional Chinese medicine, and they can have a preliminary understanding of tumor treatment plans when learning heat-clearing pharmacology, which effectively expands students' learning ideas and strengthens students' practical application ability when learning knowledge elements.

[0092] In the embodiment of the present application, based on the above scheme, the scientific knowledge graph can not only assist students in learning, but also assist schools in supervising the teaching quality of teachers. Specifically, after a teacher finishes a class, the system can automatically split the video of the class into data slices according to the knowledge points, and then automatically mount these slices under the corresponding knowledge elements. At this time, by comparing the data slices and the knowledge elements, it can be known whether the teacher is teaching according to the content in the knowledge element, thereby supervising the teacher's teaching quality.

[0093] The present application embodiment provides a teaching device based on subject knowledge graph, such as Fig. 9 As shown, including:

[0094] Graph module 101, used to create a subject knowledge graph based on AI4e and textbooks and syllabus;

[0095] A determination module 102, configured to select knowledge elements in the subject knowledge graph; and

[0096] The auxiliary module 103 is used to mount teaching auxiliary data under the knowledge element, and the teaching auxiliary data is used to help students understand the knowledge points recorded in the knowledge element and supervise the teaching quality of the teacher.

[0097] Further, the teaching auxiliary data includes a slice video, and the auxiliary module is configured to:

[0098] Collect teaching video data;

[0099] Converting the voice data in the teaching video data into subtitle data;

[0100] Extracting a timestamp according to the voice data and the subtitle data;

[0101] Based on optical character recognition technology, a plurality of sliced ​​videos are obtained from the teaching video data according to the knowledge elements in the preset subject knowledge graph, the subtitle data and the timestamp; and

[0102] The knowledge element is associated with the sliced ​​video.

[0103] An embodiment of the present application provides a storage medium for storing computer-executable instructions, which, when executed, implement the steps of the subject knowledge graph teaching method described in any one of the above embodiments.

[0104] It should be noted that the embodiments of the storage medium in this specification and the embodiments of the blockchain-based service provision method in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the aforementioned corresponding implementation of the blockchain-based service provision method, and the repeated parts will not be repeated.

[0105] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0106] In the 1930s, improvements to a technology could be clearly distinguished as hardware improvements (for example, improvements to circuit structures such as diodes, transistors, switches, etc.) or software improvements (improvements to method flows). However, with the development of technology, many improvements to method flows today can be regarded as direct improvements to hardware circuit structures. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask a chip manufacturer to design and produce a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0107] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.

[0108] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0109] For the convenience of description, the above devices are described in terms of functions and are divided into various units. Of course, when implementing the embodiments of this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0110] It should be understood by those skilled in the art that one or more embodiments of this specification may be provided as a method, system or computer program product. Therefore, one or more embodiments of this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0111] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0112] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0113] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0114] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0115] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0116] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0117] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0118] One or more embodiments of the present specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. One or more embodiments of the present specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0119] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0120] The above description is only an embodiment of this document and is not intended to limit this document. For those skilled in the art, this document may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this document should be included in the scope of the claims of this document.

Claims

1. A teaching method based on subject knowledge graph, characterized by include: Based on AI4e, create subject knowledge graphs according to textbooks and syllabus; Select a knowledge element in the subject knowledge graph; as well as Teaching auxiliary data is mounted under the knowledge element, and the teaching auxiliary data is used to help students understand the knowledge points recorded in the knowledge element and supervise the teaching quality of teachers.

2. The method according to claim 1, characterized in that The teaching auxiliary data includes data slices, and Mounting teaching auxiliary data under the knowledge element includes: Collect electronic data of learning materials; Based on optical character recognition technology, according to the knowledge elements in the subject knowledge graph, data slices are obtained from the electronic data of the learning materials; and The knowledge element and the data slice are associated.

3. The method according to claim 2, characterized in that Also includes: Obtain students’ knowledge meta-test accuracy; as well as When the test accuracy of the knowledge element is less than a threshold, the data slice corresponding to the knowledge element is pushed.

4. The method according to claim 2, characterized in that The knowledge element includes a resource list, and the method further includes: Determine a slice title according to the content in the data slice; and Place the slice title in the resource list under the knowledge element.

5. The method according to claim 2, characterized in that: The associating the knowledge element with the data slice comprises: According to the knowledge element, a knowledge element vector is obtained; According to the preset text data, a text vector is obtained; Calculating the similarity between the knowledge element vector and the text vector; and According to the similarity, the knowledge element and the data slice are associated.

6. The method according to claim 1, characterized in that The teaching auxiliary data includes a graph subject, the graph subject includes a plurality of knowledge elements, and The step of mounting teaching auxiliary data under the knowledge element includes: Setting a list of associated courses for a knowledge element; and Displays the course list.

7. The method according to claim 1, characterized in that The teaching auxiliary data includes application scenario data, and The step of mounting teaching auxiliary data under the knowledge element includes: Select target knowledge element; Creating at least one application scenario list according to the target knowledge element; and Fill in the application scenario data in each of the application scenario lists.

8. A teaching device based on subject knowledge graph, characterized in that include: The graph module is used to create subject knowledge graphs based on AI4e and textbooks and syllabus; A determination module, used for selecting knowledge elements in the subject knowledge graph; as well as The auxiliary module is used to mount teaching auxiliary data under the knowledge element, and the teaching auxiliary data is used to help students understand the knowledge points recorded in the knowledge element and supervise the teaching quality of the teacher.

9. The device according to claim 8, characterized in that The teaching auxiliary data includes data slices, and the auxiliary module is configured to: Collect electronic data of learning materials; Based on optical character recognition technology, data slices are obtained from the electronic data of the learning materials according to the knowledge elements in the subject knowledge graph; as well as The knowledge element and the data slice are associated.

10. A storage medium for storing computer executable instructions, characterized in that: When executed, the computer executable instructions implement the steps of the subject knowledge graph teaching method described in any one of claims 1-7.

Images