CN113609265A - Knowledge graph-based PEC course question-answering method and robot for autonomous learning - Google Patents
Knowledge graph-based PEC course question-answering method and robot for autonomous learning Download PDFInfo
- Publication number
- CN113609265A CN113609265A CN202110778263.5A CN202110778263A CN113609265A CN 113609265 A CN113609265 A CN 113609265A CN 202110778263 A CN202110778263 A CN 202110778263A CN 113609265 A CN113609265 A CN 113609265A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- data
- user
- question
- graph
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/338—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Abstract
The invention relates to a PEC course question-answering method facing autonomous learning based on a knowledge graph, which comprises the following steps of obtaining a knowledge data packet provided by a teacher end, wherein the knowledge data packet comprises knowledge point data and processing problem data; carrying out data cleaning on the knowledge data packet; calling the Neo4j database and the elastic search database to construct a knowledge graph by the Neo4j technology; acquiring a keyword input by a user in a search engine; analyzing the key words to obtain a current question, and extracting answers which are matched with the current question before a first threshold value from an elastic search database; and displaying the answers and the corresponding knowledge graph according to the sequence of the matching degree from high to low. The invention can automatically and intelligently discover and reason the implicit knowledge from multiple angles from the existing knowledge, thereby facilitating the students to check and fill in the missing and digest of the knowledge and greatly saving the time of teachers.
Description
Technical Field
The invention relates to the technical field of network intelligent education, in particular to a knowledge graph-based PEC course question-answering method and a robot for autonomous learning.
Background
In the application-type home education and teaching, students are inevitable to encounter various problems in the learning process due to the characteristics, the individual differences and the diversification of learning modes of the students. When seeking a way to solve the problems, students rely too much on any teacher, which requires more energy and time for the teacher to pay attention to the social software to answer the problems posed by the students.
Although the current mainstream social software (such as WeChat, QQ and the like) increases good interaction between teachers and students and approaches the distance between teachers and students, the number of students is large, the problems of the students are various, or the inquiry times of similar problems are large, the work intensity of the teachers is undoubtedly increased by a large amount of repeated work, and the improvement of the autonomous learning ability of the students is not greatly facilitated.
Disclosure of Invention
The invention aims to solve at least one of the defects of the prior art and provides a PEC course question-answering method and a robot facing autonomous learning based on knowledge graph.
In order to achieve the purpose, the invention adopts the following technical scheme:
specifically, a knowledge graph-based PEC course question-answering method facing autonomous learning is provided, and the method comprises the following steps:
acquiring a knowledge data packet provided by a teacher end, wherein the knowledge data packet comprises knowledge point data and problem processing data;
carrying out data cleaning on the knowledge data packet, extracting knowledge point data in the knowledge data packet as a first part of data, storing the first part of data into a neo4j database, extracting problem processing data in the knowledge data packet as a second part of data, and storing the second part of data into an elastic search database;
calling the Neo4j database and the elastic search database to construct a knowledge graph by the Neo4j technology;
acquiring a keyword input by a user in a search engine;
analyzing the key words to obtain a current question, and extracting answers which are matched with the current question before a first threshold value from an elastic search database;
and displaying the answers and the corresponding knowledge graph according to the sequence of the matching degree from high to low.
Further, the knowledge data packet is specifically an Excel file provided by a teacher end, the knowledge point data includes an explanation of a proper noun related to teaching, and the problem processing data includes a problem and a knowledge point corresponding to the problem.
Further, the method for acquiring the keywords input by the user and the search engine comprises the steps of directly acquiring a text input by the user, converting the text according to the voice information of the user and converting the text through the picture information provided by the user.
Further, the process of data cleansing specifically comprises the following two parts,
a first part: establishing a relation between knowledge point data one by one, wherein the relation between the knowledge points comprises the following steps: the method comprises the following steps of (1) providing disciplines- [ knowledge points ] -knowledge points which are equivalent to discipline chapters, (ii) providing knowledge points which are equivalent to discipline chapters- [ detailed knowledge points ] -detailed knowledge points which are equivalent to subsections in the discipline chapters, wherein the knowledge point relation of the part can be displayed when a student searches for problems later, so that the student can learn more deeply;
a second part: processing the problem processing data in the Excel file, wherein the part comprises topics, topic options, topic answers, subjects to which the topics belong and knowledge points included by the topics are respectively stored in an elastic search database.
Further, the method further comprises the steps that when a user controls a mouse pointer to move to a certain node of the knowledge graph, the content related to the certain node is displayed, and when the user clicks the certain node, a display interface is controlled to jump to a problem interface corresponding to the node.
Further, the method also comprises the steps that when the user inputs the keywords, the keywords are prompted according to the keywords input by the user, and in addition, when the keywords input by the user have misspelling, the user is guided and reminded.
Further, the method comprises the steps that when the current problem obtained by analyzing the key words input by the user cannot be matched in the elastic search database, the current problem is recorded and pushed to the teacher end, the reply content of the teacher end is obtained, the reply content is associated with the current problem and serves as a new knowledge point to be stored in the elastic search database, and the elastic search database is updated.
Further, the method further comprises the step of receiving an off-site search channel and displaying the off-site search result to the user when the current problem obtained by analyzing the keyword input by the user cannot be matched in the elastic search database.
Further, the platforms accessed by the off-site search include, but are not limited to, a known name, a hundred degree, V2ex, CSDN, a blog garden and a personal blog, and when the results of the off-site search are presented to the user, the number of the platforms obtained by the off-site search according to the current problem is calculated and presented in the form of a pie chart.
The invention also provides a knowledge graph-based PEC course question-answering robot for autonomous learning, which comprises the following components:
the knowledge acquisition module is used for acquiring a knowledge data packet provided by a teacher end, wherein the knowledge data packet comprises knowledge point data and problem processing data;
the data processing module is used for cleaning the knowledge data packet, extracting knowledge point data in the knowledge data packet as a first part of data and storing the first part of data into the neo4j database, and extracting processing problem data in the knowledge data packet as a second part of data and storing the second part of data into the elastic search database;
the knowledge graph building module is used for calling the Neo4j database and the elastic search database to build a knowledge graph through the Neo4j technology;
the keyword acquisition module is used for acquiring keywords input by a user in a search engine;
the answer matching module is used for analyzing the keywords to obtain a current question and extracting an answer which is matched with the current question before a first threshold value from an elastic search database;
and the display module is used for displaying the answers and the corresponding knowledge graph according to the sequence of the matching degree from high to low.
The invention has the beneficial effects that:
the knowledge graph of the course is established based on the subject background, the association of common questions, exercises, homework and test questions and the knowledge graph is realized, the knowledge recommendation and automatic response based on the knowledge graph are realized, and the robot can answer the questions provided by students in a standby mode within 24 hours; and for the problem which cannot be solved, the problem can be recorded in real time and pushed to a teacher, the teacher replies manually, and the teacher replies as new knowledge points to be updated into the database of the curriculum knowledge graph. The project can be used for facilitating students to check, fill and lose knowledge, digest and absorb the knowledge; and the time of teachers is also saved to a great extent.
Drawings
The foregoing and other features of the present disclosure will become more apparent from the detailed description of the embodiments shown in conjunction with the drawings in which like reference characters designate the same or similar elements throughout the several views, and it is apparent that the drawings in the following description are merely some examples of the present disclosure and that other drawings may be derived therefrom by those skilled in the art without the benefit of any inventive faculty, and in which:
FIG. 1 is a block flow diagram illustrating a knowledge-graph based PEC course question-answering method for autonomous learning oriented learning according to the present invention;
FIG. 2 is a schematic diagram illustrating the proper noun interpretation function of the knowledge-graph-based PEC course question-answering robot facing autonomous learning according to the present invention;
fig. 3 is a diagram showing the off-site search function of the PEC course question-and-answer method for autonomous learning based on knowledge graph.
Detailed Description
The conception, the specific structure and the technical effects of the present invention will be clearly and completely described in conjunction with the embodiments and the accompanying drawings to fully understand the objects, the schemes and the effects of the present invention. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The same reference numbers will be used throughout the drawings to refer to the same or like parts.
The embodiment 1 provides a PEC course question-answering method facing autonomous learning based on knowledge graph, which comprises the following steps:
acquiring a knowledge data packet provided by a teacher end, wherein the knowledge data packet comprises knowledge point data and problem processing data;
carrying out data cleaning on the knowledge data packet, extracting knowledge point data in the knowledge data packet as a first part of data, storing the first part of data into a neo4j database, extracting problem processing data in the knowledge data packet as a second part of data, and storing the second part of data into an elastic search database;
calling the Neo4j database and the elastic search database to construct a knowledge graph by the Neo4j technology;
acquiring a keyword input by a user in a search engine;
analyzing the key words to obtain a current question, and extracting answers which are matched with the current question before a first threshold value from an elastic search database;
specifically, for the answer retrieval, the answer retrieval is performed in the following manner, the questions are segmented, different words are segmented according to different questions, inverted index processing is performed, the segmented words are counted, indexes corresponding to the words are summarized, when a user inputs the words or the questions in an input box, the elastic search can quickly find corresponding document data according to the correspondence with the inverted indexes, and therefore the answer with the matching degree of the current questions being before the first threshold value is extracted.
And displaying the answers and the corresponding knowledge graph according to the sequence of the matching degree from high to low.
The knowledge graph of the course is established based on the subject background, the association of common questions, exercises, homework and test questions and the knowledge graph is realized, the knowledge recommendation and automatic response based on the knowledge graph are realized, and the robot can answer the questions provided by students in a standby mode within 24 hours; and for the problem which cannot be solved, the problem can be recorded in real time and pushed to a teacher, the teacher replies manually, and the teacher replies as new knowledge points to be updated into the database of the curriculum knowledge graph. The project can be used for facilitating students to check, fill and lose knowledge, digest and absorb the knowledge; and the time of teachers is also saved to a great extent.
As a preferred embodiment of the present invention, the knowledge data packet is specifically an Excel file provided by a teacher, the knowledge point data includes an explanation of a proper noun related to teaching, and the problem processing data includes a problem and a knowledge point corresponding to the problem.
As a preferred embodiment of the present invention, the method for acquiring the keywords input by the user and the search engine includes directly acquiring a text input by the user, a text formed by converting the voice information of the user, and a text formed by converting the picture information provided by the user.
As a preferred embodiment of the present invention, the process of data cleansing specifically includes the following two parts,
a first part: establishing a relation between knowledge point data one by one, wherein the relation between the knowledge points comprises the following steps: the method comprises the following steps of (1) providing disciplines- [ knowledge points ] -knowledge points which are equivalent to discipline chapters, (ii) providing knowledge points which are equivalent to discipline chapters- [ detailed knowledge points ] -detailed knowledge points which are equivalent to subsections in the discipline chapters, wherein the knowledge point relation of the part can be displayed when a student searches for problems later, so that the student can learn more deeply;
a second part: processing the problem processing data in the Excel file, wherein the part comprises topics, topic options, topic answers, subjects to which the topics belong and knowledge points included by the topics are respectively stored in an elastic search database.
As a preferred embodiment of the present invention, the method further includes displaying the content related to a certain node when the user controls the mouse pointer to move to the certain node of the knowledge graph, and controlling the display interface to jump to the problem interface corresponding to the node when the user clicks the certain node.
As a preferred embodiment of the present invention, the method further includes, when the user inputs a keyword, performing keyword prompt according to the keyword input by the user, and when the keyword input by the user has a misspelling, performing guidance prompt to the user.
As a preferred embodiment of the present invention, the method further includes, when the current question obtained by parsing the keyword input by the user cannot be matched in the elastic search database, recording and pushing the current question to the teacher's end, acquiring a reply content of the teacher's end, associating the reply content with the current question as a new knowledge point, and storing the new knowledge point in the elastic search database to update the elastic search database.
As a preferred embodiment of the present invention, the method further includes, when the current question obtained by parsing the keyword input by the user cannot be matched in the elastic search database, accessing the outbound search channel and presenting the result of the outbound search to the user.
As a preferred embodiment of the present invention, the platforms accessed by the off-site search include, but are not limited to, a known name, a hundred degree, V2ex, CSDN, a blog garden, and a personal blog, and when the results of the off-site search are presented to the user, the number ratio of the above platforms to the amount of data obtained by off-site search according to the current problem is also calculated and presented in the form of a pie chart.
Based on the above, the specific operation process comprises the following steps,
and step S1, acquiring knowledge point data (including interpretations of certain proper nouns) in the Excel file uploaded by the teacher and data for processing the question, wherein the question data includes the knowledge point of the question.
Step S2, storing the data of the knowledge points into a neo4j map database, and storing the data of the processing problems into an elastic search database;
step S3, calling two recorded databases, and constructing a knowledge graph by using Neo4j technology;
step S4, inputting keywords (the APP terminal can be in a voice or photographing mode) into a search engine, analyzing the keywords input by a user by the system, and then extracting answers with high matching degree with the current questions from an elastic search database;
and step S5, finally displaying the searched result and the corresponding knowledge graph on the user interface.
In addition, based on the related design of the present invention, the following functional points can be provided:
f1, displaying the knowledge graph corresponding to the question. The user can input the target problem in the search box according to the requirement of the user, and the system can display the knowledge graph corresponding to the problem. When a mouse is placed at a certain node of the knowledge graph, the related contents of the node are as follows: the name, the explanation and the subject belonging to the discipline are displayed, so that the user can visually observe the relation between two or more knowledge points, the user can learn more deeply, the learning direction is provided, and the learning efficiency is improved.
F2, proper noun knowledge graph interpretation. Referring to fig. 2, a user searches for proper nouns according to the needs of the user, the platform not only performs corresponding explanation on the explanation of the corresponding nouns, but also returns knowledge points related to the noun knowledge points, and forms a knowledge graph to be displayed, the user can click on corresponding node tags, and the system automatically jumps to a problem interface to display the topics containing the knowledge points to perform autonomous learning.
F3, automatic response. The robot can answer questions proposed by a user in a standby mode within 24 hours, the user inputs the questions into a search engine, a system automatically analyzes the questions input by the user, and then answers with high matching degree with the current questions are extracted from an elastic search database and displayed.
F4, expanding the knowledge graph. For the problems which cannot be solved by the question-answering system, the system can record and push the problems to a teacher in real time, the teacher replies manually, and the replies of the teacher are used as new knowledge points to be updated into a database of a curriculum knowledge graph, so that the flexibility of the platform is higher.
F5, supporting various forms of search. The user can search for the problem in the form of characters, pictures or voice so as to improve the efficiency of searching for the problem.
F6, correcting and prompting the user for input. The prompting and error correction functions of the search engine become necessary options nowadays, and the system also supports prompting and error correction of user input when the user inputs. If the user may misspell the word "Python" into "Python," the platform alerts the user that the misspelling occurred. If the user inputs the word "c", the system will also automatically match the name of the knowledge point related to "c" to prompt, such as "c language".
F7, and the data volume of the relevant platform for answering the user question is proportional. The off-site search in the navigation bar shows that the problem is in proportion to the data volume of platforms such as a known platform, a hundredth platform, a V2ex platform, a CSDN platform, a blog garden platform, a personal blog platform and the like.
The invention also provides a knowledge graph-based PEC course question-answering robot for autonomous learning, which comprises the following components:
the knowledge acquisition module is used for acquiring a knowledge data packet provided by a teacher end, wherein the knowledge data packet comprises knowledge point data and problem processing data;
the data processing module is used for cleaning the knowledge data packet, extracting knowledge point data in the knowledge data packet as a first part of data and storing the first part of data into the neo4j database, and extracting processing problem data in the knowledge data packet as a second part of data and storing the second part of data into the elastic search database;
the knowledge graph building module is used for calling the Neo4j database and the elastic search database to build a knowledge graph through the Neo4j technology;
the keyword acquisition module is used for acquiring keywords input by a user in a search engine;
the answer matching module is used for analyzing the keywords to obtain a current question and extracting an answer which is matched with the current question before a first threshold value from an elastic search database;
and the display module is used for displaying the answers and the corresponding knowledge graph according to the sequence of the matching degree from high to low.
When the robot runs, data of the platform is compiled by a professional teacher in a school, and is uploaded to a background of the platform for data cleaning through an excel file shown in the attached drawing 1, and the data cleaning is divided into three parts:
a first part: establishing a relation between knowledge point data one by one, wherein the relation between the knowledge points comprises the following steps: the method comprises the following steps of (1) subject- [ knowledge points ] - [ detailed knowledge points ] - [ small sections in subject chapters ]. The knowledge point relation of the part can be displayed when the students search for problems later, so that the students can learn more deeply.
A second part: and processing a question part in the Excel file, wherein the question part comprises a question, a question option, a question answer, a subject to which the question belongs and knowledge points contained in the question, and the knowledge points are respectively stored in a search engine database, and when a student searches, data return is carried out in two parts. The first part is that the data with high matching degree with the problem is returned to the background for processing and then displayed for the user; and the second part is to integrate and analyze the inquired knowledge point data to obtain a knowledge graph of the corresponding knowledge point and return the knowledge graph.
And a third part: the using condition can be seen in fig. 2, after the teacher uploads Excel data, the background automatically cleans the data and stores the data into the corresponding knowledge point attribute. When the students search, the background receives corresponding nouns, the corresponding nouns are inquired in the background knowledge map database, corresponding explanations and data of knowledge points with the connection of the nouns are found to construct a knowledge map, and the knowledge map is returned to solve the answers for the students. Besides seeing the explanation of the noun, the student can also find the knowledge point connected with the noun to learn autonomously, thereby improving the autonomous learning ability of the student.
When students search for questions, the specific situation can be seen in the attached figure 1, and in the aspect of question return: after receiving the problem data, the background analyzes the problem, compares the problem with the problem in the search engine database, arranges the scores of the matching similarity from high to low through calculation, and returns the scores according to the arrangement sequence, so that students can find the question which best meets the requirements of the students to learn. In terms of problem-related knowledge-graphs: after the problem is collected, analyzing knowledge points contained in the problem, constructing sentences for inquiring a database, returning the knowledge graph corresponding to the problem and displaying the knowledge graph on a page for a student to check.
As shown in fig. 3, when the student does not find a satisfactory answer, the student firstly notifies the relevant teacher to update the data through the system, and meanwhile, the student can perform off-site search through an "off-site search" module in the platform to obtain popular answers of each current large question answering platform, and shows the proportion comparison of the current search answering source platform on the right.
On the basis, aiming at the aspect of intelligent question answering, the knowledge graph is used for displaying the knowledge point tree, the key words of the question are classified according to the knowledge points in the knowledge point tree, all questions matched with a certain knowledge point in the course are displayed layer by layer, and the missing of the knowledge are convenient to check, digest and absorb; and as the types of the problems in the field of education subjects are numerous, the entity names in the knowledge base are mostly proper nouns, and the system adopts a semantic analysis method to construct a question-answering system of the knowledge base, the user experience is optimized.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing module, or each of the modules may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.
The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium and can implement the steps of the above-described method embodiments when the computer program is executed by a processor. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or robot capable of carrying said computer program code, a recording medium, a usb disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a Random Access Memory (RAM), an electrical carrier wave signal, a telecommunication signal, a software distribution medium, etc. It should be noted that the computer readable medium includes content that can be suitably increased or decreased according to the requirements of legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunication signals according to legislation and patent practice.
While the present invention has been described in considerable detail and with particular reference to a few illustrative embodiments thereof, it is not intended to be limited to any such details or embodiments or any particular embodiments, but it is to be construed as effectively covering the intended scope of the invention by providing a broad, potential interpretation of such claims in view of the prior art with reference to the appended claims. Furthermore, the foregoing describes the invention in terms of embodiments foreseen by the inventor for which an enabling description was available, notwithstanding that insubstantial modifications of the invention, not presently foreseen, may nonetheless represent equivalent modifications thereto.
The above description is only a preferred embodiment of the present invention, and the present invention is not limited to the above embodiment, and the present invention shall fall within the protection scope of the present invention as long as the technical effects of the present invention are achieved by the same means. The invention is capable of other modifications and variations in its technical solution and/or its implementation, within the scope of protection of the invention.
Claims (10)
1. The knowledge graph-based PEC course question-answering method facing autonomous learning is characterized by comprising the following steps of:
acquiring a knowledge data packet provided by a teacher end, wherein the knowledge data packet comprises knowledge point data and problem processing data;
carrying out data cleaning on the knowledge data packet, extracting knowledge point data in the knowledge data packet as a first part of data, storing the first part of data into a neo4j database, extracting problem processing data in the knowledge data packet as a second part of data, and storing the second part of data into an elastic search database;
calling the Neo4j database and the elastic search database to construct a knowledge graph by the Neo4j technology;
acquiring a keyword input by a user in a search engine;
analyzing the key words to obtain a current question, and extracting answers which are matched with the current question before a first threshold value from an elastic search database;
and displaying the answers and the corresponding knowledge graph according to the sequence of the matching degree from high to low.
2. The PEC course question-answering method oriented to autonomous learning based on knowledge graph according to claim 1, wherein the knowledge data packet is an Excel file provided by a teacher, the knowledge data includes an explanation of a proper noun related to teaching, and the processing problem data includes a problem and a knowledge point corresponding to the problem.
3. The knowledge-graph-based PEC course question-answering method for oriented autonomous learning according to claim 1, wherein the method for acquiring the keywords input by the user and the search engine comprises directly acquiring a text input by the user, converting the text into a text according to voice information of the user, and converting the text into a text according to picture information provided by the user.
4. The knowledge-graph-based PEC course question-answering method oriented to autonomous learning according to claim 2, wherein the data washing process specifically comprises the following two parts,
a first part: establishing a relation between knowledge point data one by one, wherein the relation between the knowledge points comprises the following steps: the method comprises the following steps of (1) providing disciplines- [ knowledge points ] -knowledge points which are equivalent to discipline chapters, (ii) providing knowledge points which are equivalent to discipline chapters- [ detailed knowledge points ] -detailed knowledge points which are equivalent to subsections in the discipline chapters, wherein the knowledge point relation of the part can be displayed when a student searches for problems later, so that the student can learn more deeply;
a second part: processing the problem processing data in the Excel file, wherein the part comprises topics, topic options, topic answers, subjects to which the topics belong and knowledge points included by the topics are respectively stored in an elastic search database.
5. The knowledge-graph-based PEC course question-answering method for autonomous learning, according to claim 1, further comprising displaying contents related to a certain node of the knowledge graph when a user controls a mouse pointer to move to the certain node, and controlling a display interface to jump to a question interface corresponding to the node when the user clicks the certain node.
6. The knowledge-graph-based PEC course question-answering method facing autonomous learning according to claim 3, further comprising performing keyword prompting according to the keywords input by the user when the keyword is input by the user, and performing guidance prompting to the user when the keyword input by the user has misspelling.
7. The knowledge-graph-based PEC course question-answering method facing autonomous learning according to claim 1, further comprising recording and pushing a current question obtained by parsing a keyword input by a user to the teacher side when the current question cannot be matched in the elastic search database, obtaining a reply content of the teacher side, associating the reply content with the current question as a new knowledge point, and storing the new knowledge point in the elastic search database to update the elastic search database.
8. The knowledge-graph-based PEC course question-answering method facing autonomous learning according to claim 7, further comprising receiving an off-site search channel and presenting the results of the off-site search to the user when the current question parsed from the keywords input by the user cannot be matched in the elastic search database.
9. The PEC course question-answering method based on knowledge graph oriented autonomous learning of claim 8, wherein the platforms accessed by the off-site search include, but are not limited to, Anzhi, Baidu, V2ex, CSDN, blog garden, personal blog, and when the results of the off-site search are presented to the user, the number of the platforms obtained by the off-site search according to the current question is calculated and presented in the form of a pie chart.
10. Knowledge graph-based PEC course question-answering robot facing autonomous learning is characterized by comprising the following components:
the knowledge acquisition module is used for acquiring a knowledge data packet provided by a teacher end, wherein the knowledge data packet comprises knowledge point data and problem processing data;
the data processing module is used for cleaning the knowledge data packet, extracting knowledge point data in the knowledge data packet as a first part of data and storing the first part of data into the neo4j database, and extracting processing problem data in the knowledge data packet as a second part of data and storing the second part of data into the elastic search database;
the knowledge graph building module is used for calling the Neo4j database and the elastic search database to build a knowledge graph through the Neo4j technology;
the keyword acquisition module is used for acquiring keywords input by a user in a search engine;
the answer matching module is used for analyzing the keywords to obtain a current question and extracting an answer which is matched with the current question before a first threshold value from an elastic search database;
and the display module is used for displaying the answers and the corresponding knowledge graph according to the sequence of the matching degree from high to low.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110778263.5A CN113609265A (en) | 2021-07-09 | 2021-07-09 | Knowledge graph-based PEC course question-answering method and robot for autonomous learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110778263.5A CN113609265A (en) | 2021-07-09 | 2021-07-09 | Knowledge graph-based PEC course question-answering method and robot for autonomous learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113609265A true CN113609265A (en) | 2021-11-05 |
Family
ID=78304323
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110778263.5A Pending CN113609265A (en) | 2021-07-09 | 2021-07-09 | Knowledge graph-based PEC course question-answering method and robot for autonomous learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113609265A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023159650A1 (en) * | 2022-02-28 | 2023-08-31 | Microsoft Technology Licensing, Llc | Mining and visualizing related topics in knowledge base |
-
2021
- 2021-07-09 CN CN202110778263.5A patent/CN113609265A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023159650A1 (en) * | 2022-02-28 | 2023-08-31 | Microsoft Technology Licensing, Llc | Mining and visualizing related topics in knowledge base |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108345690B (en) | Intelligent question and answer method and system | |
| US20200301954A1 (en) | Reply information obtaining method and apparatus | |
| CN111475623A (en) | Case information semantic retrieval method and device based on knowledge graph | |
| CN102262634A (en) | Automatic questioning and answering method and system | |
| CN104133817A (en) | Online community interaction method and device and online community platform | |
| CN109902087B (en) | Data processing method and device for questions and answers and server | |
| CN112163077A (en) | Domain-oriented question-answering knowledge graph construction method | |
| CN110929045B (en) | Construction method and system of poetry-semantic knowledge map | |
| CN113342958B (en) | Question-answer matching method, text matching model training method and related equipment | |
| CN112507139B (en) | Knowledge graph-based question and answer method, system, equipment and storage medium | |
| CN105677872A (en) | Question searching method and device and learning equipment | |
| CN103593412A (en) | Tree-structure-based question answering system and method | |
| CN113468300B (en) | Intelligent message processing system and method based on WeChat interaction | |
| Chaudhri et al. | Question generation from a knowledge base | |
| CN112506945A (en) | Self-adaptive learning guiding method and system based on knowledge graph | |
| CN114186983B (en) | Video interview multidimensional scoring method, system, computer equipment and storage medium | |
| CN113609265A (en) | Knowledge graph-based PEC course question-answering method and robot for autonomous learning | |
| US10275487B2 (en) | Demographic-based learning in a question answering system | |
| CN114707000A (en) | Knowledge graph-based question-answer library generation method and device, electronic equipment and storage medium | |
| KR101794547B1 (en) | System and Method for Automatically generating of personal wordlist and learning-training word | |
| CN117312509A (en) | Knowledge base question-answering method and device based on large language model under massive information | |
| CN117271799A (en) | Knowledge graph-based multi-round question answering method and system | |
| CN114328846B (en) | Intelligent customer service response system and method for policy consultation in colleges and universities | |
| CN116595188A (en) | Educational knowledge graph system based on artificial intelligence and big data | |
| CN115640403A (en) | Knowledge management and control method and device based on knowledge graph |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |