CN112395403B - Knowledge graph-based question and answer method, system, electronic equipment and medium - Google Patents
Knowledge graph-based question and answer method, system, electronic equipment and medium Download PDFInfo
- Publication number
- CN112395403B CN112395403B CN202011384225.3A CN202011384225A CN112395403B CN 112395403 B CN112395403 B CN 112395403B CN 202011384225 A CN202011384225 A CN 202011384225A CN 112395403 B CN112395403 B CN 112395403B
- Authority
- CN
- China
- Prior art keywords
- knowledge
- question
- graph
- weak
- points
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000012360 testing method Methods 0.000 claims abstract description 57
- 239000013598 vector Substances 0.000 claims description 36
- 239000000463 material Substances 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000013459 approach Methods 0.000 claims description 3
- 238000012887 quadratic function Methods 0.000 description 8
- 238000010276 construction Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006698 induction Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000029087 digestion Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
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
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Educational Administration (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Educational Technology (AREA)
- Mathematical Physics (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Quality & Reliability (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a knowledge graph-based question answering method, a knowledge graph-based question answering system, electronic equipment and a knowledge graph-based question answering medium, and belongs to the technical field of network intelligent education. The question answering method comprises the following steps: acquiring a user question and extracting keywords; determining a target object corresponding to the user question in a corpus; retrieving and establishing a target knowledge graph associated with the target object in the basic knowledge graph; and outputting feedback information according to the target knowledge graph. The establishment of the basic knowledge graph needs to collect personalized data of each examination of students; calculating the personalized mastery degree corresponding to each knowledge point according to the personalized data; according to the personalized mastery, carrying out hierarchical division on the knowledge points and outputting a hierarchical division result; and establishing the basic knowledge graph according to the hierarchical division result. According to the invention, students can conduct self-reinforcement according to weak knowledge points, including course learning or test question training, so that accurate promotion is realized, and the weak knowledge points are effectively eliminated.
Description
Technical Field
The invention belongs to the technical field of network intelligent education, and particularly relates to a question answering method, a question answering system, electronic equipment and a question answering medium based on a knowledge graph.
Background
Under the background of Internet and education, along with the continuous promotion of national education informatization, the continuous accumulation and deep mining of education data are increasingly prominent in the driving effect of large data in the aspects of constructing novel teaching ecology, improving the assistance teaching structure and reconstructing the teaching flow.
In the traditional teaching environment, a teacher uniformly issues homework by taking a class as a unit, and the students can directly and uniformly apply teaching regardless of the digestion and acceptance of knowledge, so that the problem that the existing students feel homework difficultly when the homework is simple and the homework difficultly when the students feel homework is solved, and the matching degree of homework and the knowledge level of the students is not high, so that the teacher cannot avoid deviation when grasping the teaching quality of the class, and cannot accurately position the individualized learning condition of each student. Therefore, under the mode of homogeneous teaching, the learning enthusiasm of students is difficult to mobilize, the students cannot be differentiated and layered according to the knowledge level of each student, the learning interest of the students is low, and the learning efficiency is low.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, and provides a question-answering method, a question-answering system, electronic equipment and a question-answering medium based on a knowledge graph, which solve the adverse effect on the homogeneous teaching of students in the prior art.
In order to achieve the above object, in a first aspect, the present invention provides a knowledge graph-based question answering method, which includes the following steps:
step S1: acquiring a user question and extracting keywords;
step S2: determining a target object corresponding to the user question in a corpus;
step S3: retrieving and establishing a target knowledge graph associated with the target object in the basic knowledge graph;
step S4: and outputting feedback information according to the target knowledge graph.
Further, in step S2:
Generating question-answer pairs based on a set template according to the triples in the knowledge graph;
each question-answer pair comprises a set question sentence and a set answer, word segmentation and vectorization are carried out on the set question sentences to obtain set word vectors corresponding to the set question sentences, and a corpus is built according to the set word vectors;
Performing word segmentation and vectorization on the user question to obtain a user word vector;
Comparing and calculating the user word vector and the set word vector, and determining a target object according to the similarity; the target object comprises N question-answer pairs, wherein N is a natural number which is greater than or equal to 1.
Further, when the set questions and the user questions are subjected to vectorization, the texts of the set questions and the user questions are subjected to distributed vectorization representation, and word2vec models are used for calculating word vectors corresponding to each set question and each user question.
Further, in the corpus, the question-answer pairs store question-answer information corresponding to the question-answer pairs, the question-answer information comprises fifty-dimensional word vectors of the set question sentences and set answer information corresponding to the set question sentences, and the question-answer information forms the corpus.
Further, according to the types of the triplet relation in the knowledge graph, manual question-answer pairs are input into the corpus.
Further, when the user word vector and the set word vector are subjected to comparison calculation, calculating a cosine value of an included angle formed between the user word vector and the set word vector, and judging the similarity of the user question and the set question according to the cosine value, wherein the closer the cosine value is to 1, the higher the similarity of the user question and the set question is; the closer the cosine value is to 0, the lower the similarity between the user question and the set question.
Further, before step S3, a basic knowledge graph is first established, which includes the following steps:
step S31: collecting personalized data of each examination of students;
step S32: calculating the personalized mastery degree corresponding to each knowledge point according to the personalized data;
step S33: according to the personalized mastery, carrying out hierarchical division on the knowledge points and outputting a hierarchical division result;
Step S34: and establishing the basic knowledge graph according to the hierarchical division result.
Further, the personalized data comprises at least one item of examination time information, examination question information, examination paper information or examination score information, the examination paper information comprises at least one item of belonging subjects, examination paper types, examination paper names, examination paper full score values and original subject information, and the original subject information comprises at least one item of belonging subjects, associated chapters, associated knowledge points, capability layers of subjects themselves, subject applicable types, subject difficulty coefficients, test subject stems and answers, subject scores, subject years, regions, sources, examination points, analysis and point scores.
Further, in step S32, the personalized mastery is calculated by the following method:
f= [ (a1+a2+a3+ ] +an)/(n ]. Times.g, wherein f is the individuation grasping degree of the knowledge point, g is the importance degree of the knowledge point, a1, a2, a3...an is the 1 st, 2 nd, 3 rd..n and the corresponding question score value of the knowledge point, n is the wrong question number of the knowledge point;
the topic score value a is obtained by the following method: Wherein a is the question scoring value, b is the test question full scoring value, x% is the weight of the test question full scoring value, c is the test question distinction degree, y% is the weight of the test question distinction degree, d is the difference value between the personal scoring rate of the knowledge points and the class scoring rate, z% is the weight of the scoring rate difference value, p is the difficulty coefficient, the range of the difficulty coefficient p is 0-1, and the more difficult the value of the difficulty coefficient p approaches 0, the greater the difficulty is;
the test question distinguishing degree c is obtained by the following method: c= (v 1-v 2)/b, wherein v1 is the average score of the examination score of 20% before the score ranking, and v2 is the average score of the examination score of 20% after the score ranking;
The knowledge point importance degree g is obtained by the following method: g=70%i+30%j, where i is the degree of mastery of the knowledge points required by the outline students, and j is the percentage of all the topic scores related to the knowledge points in the test paper to the total score.
Further, in step S33, the hierarchy dividing result includes a weak knowledge point hierarchy and a dominant knowledge point hierarchy, the knowledge points are in one-to-one correspondence with the individuation grasping degree, the individuation grasping degree is compared with a set weak knowledge point threshold and dominant knowledge point threshold, a knowledge point corresponding to the individuation grasping degree smaller than the weak knowledge point threshold is defined as a weak knowledge point, the weak knowledge point is divided into weak knowledge point hierarchies, a knowledge point corresponding to the individuation grasping degree larger than the dominant knowledge point threshold is defined as a dominant knowledge point, and the dominant knowledge point is divided into dominant knowledge point hierarchies.
Further, in step S34, the basic knowledge-graph includes a weak knowledge-graph and/or a dominant knowledge-graph;
marking the personalized mastery degree of each weak knowledge point in the set original knowledge map according to the weak knowledge point level information, and establishing a weak knowledge map;
And marking the personalized mastery degree of each dominant knowledge point in the set original knowledge map according to the level information of the dominant knowledge points, and establishing the dominant knowledge map.
Further, the original knowledge graph is determined based on teaching materials and teaching auxiliary materials of discipline authority, and the relation is determined according to knowledge point concepts and encyclopedia information frames; the weak knowledge graph further comprises a plurality of relationships among weak knowledge points; the dominant knowledge graph also includes relationships between a plurality of dominant knowledge points.
Further, the feedback information comprises at least one of a weak knowledge graph, a dominant knowledge graph, a weak knowledge point course and a weak knowledge point test question.
Further, after the practice of the weak knowledge point test questions is performed, the steps S31 to S34 are repeated, and the basic knowledge graph is updated.
Further, collecting wrong questions of each set of weak knowledge point test questions, and optimizing a construction algorithm of the weak knowledge point test questions according to the wrong questions so as to recommend the test questions with high similarity to the wrong questions.
In a second aspect, the present invention provides a system applied to the question-answering method, including:
An acquisition unit configured to acquire a user question, extract a keyword;
a judging unit configured to determine a target object corresponding to the user question in a corpus;
a generation unit configured to retrieve and establish a target knowledge-graph associated with the target object in a base knowledge-graph;
and the feedback unit is configured to output feedback information according to the target knowledge graph.
In a third aspect, the present invention provides an electronic device, including a processor and a memory, where the memory stores at least one instruction, at least one program, a code set, or an instruction set, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the knowledge-graph-based question-answering method described above.
In a fourth aspect, the present invention provides a computer readable storage medium having stored thereon computer instructions which when executed by a processor perform the steps of the above method.
The invention has the beneficial effects that:
1. According to the invention, the personalized data of each examination of students are analyzed and processed, the personalized mastering degree of each knowledge point is calculated, then all knowledge points are hierarchically divided, weak knowledge points and dominant knowledge points are identified, the personalized mastering degree is combined in an original knowledge graph to be marked, a weak knowledge graph and/or dominant knowledge graph corresponding to the weak knowledge points is formed, the students can clearly know the personalized mastering degree of each knowledge point according to the students from visual pictures, knowledge weaknesses of the students and other knowledge points related to the knowledge points can be found according to the weak knowledge graph, a knowledge network is formed, and the knowledge points are not searched one by one, so that the efficiency of induction and finishing of the students is improved;
2. The invention realizes interaction with students based on knowledge graphs, the students only need to input user questions comprising the questioning knowledge points, namely, the user questions are automatically compared with set questions in a corpus in similarity, N question-answer pairs with highest similarity are determined, the corresponding part of the basic knowledge graphs is reversely checked by the target object to form a target knowledge graph with the questioning knowledge points of the students, students or parents or teachers can intuitively see the mastering degree of the students on the knowledge points, so that different users can conveniently and clearly know the individualized learning mastering level of the students, and the next educational learning policy is determined;
3. The invention can also output weak knowledge point courses and weak knowledge point test questions simultaneously, so that students can autonomously conduct self-reinforcement on weak knowledge points of the students, including learning of courses or exercise of test questions, accurate promotion is achieved, weak knowledge points are effectively eliminated, the knowledge graph and the weak knowledge point test questions can be self-optimized and updated according to each time of problem making conditions of the students, synchronous update of knowledge graph and actual knowledge grasping level of the students is achieved, and a construction algorithm of the weak knowledge point test questions is optimized, so that the students can overcome difficulties.
Drawings
The invention will be further described with reference to the accompanying drawings, in which embodiments do not constitute any limitation of the invention, and other drawings can be obtained by one of ordinary skill in the art without inventive effort from the following drawings.
Fig. 1 is a schematic flow chart of a knowledge-based question-answering method in embodiment 1.
Fig. 2 is a schematic diagram of a flow chart of establishing a basic knowledge graph in embodiment 1 according to the knowledge graph-based question-answering method provided by the invention.
FIG. 3 is a schematic diagram of a weak knowledge graph in example 1 of a knowledge graph-based question answering method
Detailed Description
The following description of the embodiments of the present invention will be made apparent and fully in view of the accompanying drawings, in which some, but not all embodiments of the invention are shown. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
Example 1:
Referring to fig. 1, the embodiment provides a knowledge graph-based question-answering method, which includes the following steps:
step S1: acquiring a user question and extracting keywords;
step S2: determining a target object corresponding to a user question in a corpus;
step S3: retrieving and establishing a target knowledge graph associated with the target object in the basic knowledge graph;
step S4: and outputting feedback information according to the target knowledge graph.
It should be noted that, the method can be used by students, teachers and parents together, the user only needs to input a question, the question contains knowledge points which the students want to query, that is, the knowledge points are analyzed and compared with information in a corpus to determine a corresponding target object, the target object already contains relevant information of the knowledge points of the users, a target knowledge map associated with the knowledge points is selected from basic knowledge maps, and finally feedback information is output according to the target knowledge map, and the pushed feedback information has pertinence and accuracy because the target knowledge map already contains relevant information of the knowledge points of the users.
In the above method, the most important is two aspects, the first aspect is how to effectively establish the question-answering mechanism in step S2, so that the pushed feedback information meets the requirement of the user; the second aspect is how the basic knowledge-graph is built up and how the personalized data of the student is embodied in the basic knowledge-graph in step S3.
Next, the first aspect will be described, and in this embodiment, in step S2:
generating question-answer pairs based on a set template according to the triples in the knowledge graph;
Each question-answer pair comprises a set question sentence and a set answer, wherein the set question sentences and the set answers are preset and have a one-to-one correspondence, word segmentation and vectorization are carried out on the set question sentences to obtain set word vectors corresponding to the set question sentences, and a corpus is constructed according to the set word vectors;
Word segmentation and vectorization are carried out on the user question to obtain a user word vector;
comparing and calculating the user word vector and the set word vector, and determining a target object according to the similarity; the target object comprises N question-answer pairs, wherein N is a natural number greater than or equal to 1.
As a preferred mode, when vectorization processing is carried out on the set questions and the user questions, the texts of the set questions and the user questions are carried out with distributed vectorization representation, and word2vec models are used for calculating word vectors corresponding to each set question and each user question.
In this embodiment, in the corpus, the question-answer pairs store question-answer information corresponding to the question-answer pairs, where the question-answer information includes fifty-dimensional word vectors of set question sentences and set answer information corresponding to the set question sentences, and the question-answer information forms the corpus, so that data connection from the user word vectors to the set answer information is realized through the corpus.
Additionally, according to the types of the triplet relation in the knowledge graph, manual question-answer pairs can be input into the corpus, so that the information in the corpus can be artificially and purposefully added or modified.
As a preferred mode, when the user word vector and the set word vector are compared and calculated, calculating the cosine value of an included angle formed between the user word vector and the set word vector, and judging the similarity of the user question and the set question according to the cosine value, wherein the closer the cosine value is to 1, the higher the similarity of the user question and the set question is; the closer the cosine value is to 0, the lower the similarity between the user question and the set question; and selecting the N cosine values which are arranged at the front in the result closest to 1, determining N set questions corresponding to the cosine values, and setting answer information corresponding to the set questions to finish the selection of the target object.
Referring to fig. 3, up to now, the target object already includes related information of knowledge points that the user wants to know, and N set questions are selected, firstly, accuracy is improved, secondly, other knowledge points closely related to the most similar knowledge points are determined, because the knowledge points do not exist alone, the knowledge points are all in one point in a network, and there is a close relationship between the knowledge points, for example, search for a "quadratic function", but knowledge points related to the knowledge points, such as a plane rectangular coordinate system, a unitary quadratic equation, and the like, are also possible factors affecting the grasping degree of the "quadratic function", so that the N set questions and the set answer information thereof can form a knowledge point path or a knowledge point area relationship network, and each knowledge point is in series connection to let the user know weaknesses of students.
In order to realize the question-answering mechanism, a basic knowledge graph with knowledge mastering and differentiating information of students needs to be established at the back, and the basic knowledge graph can determine the personalized mastery degree of each knowledge point for each student according to the personalized data of each student.
The second aspect is described below as to how the basic knowledge graph is created and how the personalized data of the student is embodied in the basic knowledge graph.
Referring to fig. 2, in the present embodiment, before step S3, a basic knowledge graph is established, which includes the following steps:
step S31: collecting personalized data of each examination of students;
step S32: calculating the personalized mastery degree corresponding to each knowledge point according to the personalized data;
Step S33: according to the personalized mastery degree, carrying out hierarchical division on the knowledge points and outputting a hierarchical division result;
step S34: and establishing a basic knowledge graph according to the hierarchical division result.
It should be noted that, each examination of the student generates corresponding personalized data, and the data includes the data of the student in the examination, and reflects the relevant performance of the student in the examination; more specifically, the personalized data includes at least one item of examination time information, examination test question information, examination paper information or examination score information, the examination time information includes a date of examination, a time point before and after the examination, total time spent per question, examination time, and the like, the examination test paper information includes at least one item of belonging subject, test paper type, test paper name, test paper full score and original subject information, and the original subject information includes at least one item of belonging subject, associated chapter (subject, grade, unit, text), associated knowledge point, capability level to which the subject itself belongs, subject application type, subject difficulty coefficient, subject matter stem and answer, subject score, subject year, region, source, test point, analysis, and point score; of course, the personalized data may also include other information representative of information related to the current examination.
In the present embodiment, after the personalized data is collected, in step S32, the personalized mastery degree is calculated by the following method:
f= [ (a1+a2+a3+ ] +an)/(n ]. Times.g, wherein f is the individuation grasping degree of the knowledge points, g is the importance degree of the knowledge points, a1, a2, a3...an is the question score value corresponding to the 1 st, 2 nd and 3 rd..n and the knowledge points, and n is the wrong number of questions of the knowledge points;
the topic score value a is obtained by the following method: Wherein a is a question scoring value, b is a test question full scoring value, x% is a weight of the test question full scoring value, c is a test question distinction degree, y% is a weight of the test question distinction degree, d is a difference value between a personal scoring rate of a knowledge point and a class scoring rate, z% is a weight of the scoring rate difference value, p is a difficulty coefficient, the difficulty coefficient p ranges from 0 to 1, and the more the value of the difficulty coefficient p approaches 0, the greater the difficulty is;
The test question distinguishing degree c is obtained by the following method: c= (v 1-v 2)/b, wherein v1 is average score of 20% of the first-ranking scores, and v2 is average score of 20% of the last-ranking scores;
The knowledge point importance g is obtained by the following method: g=70%i+30%j, wherein i is the degree of knowledge of the outline requiring the student to grasp the knowledge points, and j is the percentage of all the topic scores of the relevant knowledge points in the test paper to the total score.
As one embodiment, the weight x% of the full score value of the test question, the weight y% of the division of the test question and the weight z% of the difference value of the score are added to be 1, i.e., x% + y% + z% = 1. According to the examination condition, defining: the weight of the full score of the test question is x% = 25%, the weight of the differential score of the test question is y% = 35%, and the weight of the differential score is z% = 40%.
In the examination, 26 questions are all divided into 120 points, 6 questions are all included in the questions containing a certain knowledge point, the questions account for 33% of the total score, and the outline requires the students to grasp the knowledge point to 80%. Wherein:
the 1 st title is fully divided into 3 points, the difficulty coefficient is 0.9, the class score is 92%, and the score of the title of the student is 100%.
The 2 nd title is divided into 3 points, the difficulty coefficient is 0.88, the class score rate is 90%, and the score rate of the title of the student is 0.
The 3 rd title is fully divided into 3 points, the difficulty coefficient is 0.85, the class score rate is 89%, and the score rate of the student on the title is 100%.
The 4 th title is fully divided into 6 points, the difficulty coefficient is 0.75, the class score is 64%, and the score of the student is 83%.
The 5 th title is fully divided into 10 points, the difficulty coefficient is 0.6, the class score rate is 48%, and the score rate of the student on the title is 60%.
The 6 th title is fully divided into 15 parts, the difficulty coefficient is 0.2, the class score is 19%, and the score of the title of the student is 10%.
Calculating the distinguishing degree of the six topics to obtain:
The 1 st question is divided into 3 points, the high group average score is 3 points, the low group average score is 0 point, and the question is divided into three points ；
The 2 nd title is divided into 3 points, the high group average score is 3 points, the low group average score is 0 point, the title is divided into three points；
The 3 rd title is divided into 3 points, the high group average score is 3 points, the low group average score is 0 point, the title is divided into three points；
The 4 th question is divided into 6 points, the high group average score is 4.5 points, the low group average score is 2.5 points, and the questions are classified into the following categories；
The 5 th question is fully divided into 10 points, the high group average score is 8.8 points, the low group average score is 2.4 points, and the question is classified into the following categories；
The 6 th question is divided into 15 points, the high group average score is 12.8 points, the low group average score is 2.8 points, and the question is divided into the following points。
Additionally, the outline requires that the student grasp the knowledge point with i=80%, and all the topic scores of the relevant knowledge points in the test paper account for the percentage j=33% of the total score, so g=70% ×80% +30% ×33% = 0.659.
The score value a1 of the above-mentioned title is obtained from the above-mentioned contents as follows:
the remaining calculated 5-topic score values are respectively:
a2=0.024；
a3=0.274；
a4=0.443；
a5=1.045；
a6=4.061。
The student can simulate the examination to grasp the knowledge points in the learning period as follows:
f＝[(a1+a2+a3+...+a6)÷6]×g=[(0.252+0.024+0.274+0.443+1.045+4.061)÷6]×0.659≈0.67。
And finally, combining the mastery degree data of the knowledge points with the mastery degree data of other knowledge points to establish and perfect a weak knowledge graph.
As a preferred manner, in step S33, the hierarchy dividing result includes a weak knowledge point hierarchy and a dominant knowledge point hierarchy, knowledge points are in one-to-one correspondence with the personalized mastery degree, the personalized mastery degree is compared with a set weak knowledge point threshold and dominant knowledge point threshold, the personalized mastery degree is sequentially arranged from small to large according to the numerical value, the weak knowledge point threshold and the dominant knowledge point threshold are respectively taken as demarcation points in the number sequence, wherein the personalized mastery degree smaller than the weak knowledge point threshold is separated, the knowledge point corresponding to the personalized mastery degree is defined as the weak knowledge point, and the weak knowledge point is divided into the weak knowledge point hierarchy; and separating out personalized mastery degrees larger than the threshold value of the dominant knowledge points, defining the knowledge points corresponding to the personalized mastery degrees as dominant knowledge points, and dividing the dominant knowledge points into dominant knowledge point levels. Therefore, through quantitative numerical comparison, all knowledge points appearing in the examination paper are separated and extracted to obtain weak knowledge points and dominant knowledge points.
Further, in step S34, the basic knowledge-graph includes a weak knowledge-graph and/or a dominant knowledge-graph;
marking the personalized mastery degree of each weak knowledge point in the set original knowledge map according to the weak knowledge point level information, and establishing a weak knowledge map;
And marking the personalized mastery degree of each dominant knowledge point in the set original knowledge map according to the level information of the dominant knowledge points, and establishing the dominant knowledge map.
The weak knowledge graph and the dominant knowledge graph are both built in the original knowledge graph, all knowledge points are marked, the weak knowledge points and the dominant knowledge points are distinguished, the individuation grasping degree of the weak knowledge points and the dominant knowledge points is respectively marked, and the graphs of related paths or networks are formed according to the connection between the knowledge points.
In this embodiment, the original knowledge graph is determined based on teaching materials and teaching materials of discipline authority, and relationships are determined according to knowledge point concepts and encyclopedia information frames, wherein each knowledge point concept has a plurality of examples, each example has a corresponding information frame in encyclopedia, and the important relationships under the knowledge points are obtained by integrating the information frame relationships of the plurality of examples under the same knowledge point; the weak knowledge graph comprises a plurality of relationships among weak knowledge points; the dominant knowledge graph includes relationships between a plurality of dominant knowledge points.
As a preferred mode, after the target knowledge graph is determined, feedback information is required to be output, wherein the feedback information comprises at least one of a weak knowledge graph, a dominant knowledge graph, a weak knowledge point course and a weak knowledge point test question.
In this embodiment, after the exercise of the weak knowledge point test questions is performed, the steps S31 to S34 are repeated to update the basic knowledge graph, so that the basic knowledge graph is updated in real time, and the knowledge level synchronization with the students is ensured.
In this embodiment, the wrong questions of each set of weak knowledge point test questions are collected to form a wrong question book, and the building algorithm of the weak knowledge point test questions is optimized according to the wrong questions so as to recommend the test questions with high similarity to the wrong questions, so that the questions are more targeted, higher in quality and more humanized when the relevant connection of the weak knowledge points is carried out next time.
Referring to fig. 1 to 3, after a basic knowledge graph is established, when a user question is acquired, a target object is determined by comparing a user word vector with a set word vector, the target object includes knowledge point information, searching is performed on the basic knowledge graph through the knowledge point to find a target knowledge graph corresponding to the target object, and feedback information corresponding to the target knowledge graph including a weak knowledge graph, a weak knowledge point course or a weak knowledge point test question is output according to the level of the knowledge point included in the target object. Therefore, the user can obtain information related to the problematic knowledge points which the student wants to query, especially when learning difficulties such as a quadratic function are encountered, namely a weak knowledge map related to the quadratic function can appear, the weak knowledge map may be sequentially connected with a plurality of knowledge points along the quadratic function, and can be divided into a first-level relevant knowledge point, a second-level relevant knowledge point and the like according to the connection relation, besides seeing the personalized mastery degree in the object of the quadratic function, the personalized mastery degree of the rest relevant knowledge points related to the quadratic function can be seen, and real problems can be found on the path, such as a plane rectangular coordinate system, a unitary quadratic equation, factorization and a unitary first-order equation which are sequentially connected with the quadratic function, only the personalized mastery degree of the plane rectangular coordinate system, the factorization and the unitary first-order equation is relatively high, so that the knowledge point is called as the weak knowledge point only the unitary second-order equation is lost, just because the user can see the weak point by utilizing the connection between the knowledge points, the weak point of the student can overcome, the attack point efficiency and the students can be improved, and the parents can learn the students and the parents can clearly benefit.
Example 2:
This embodiment 2 provides a system applied to the question-answering method in the above embodiment 1, including:
The acquisition unit is configured to acquire a user question and extract keywords;
the judging unit is configured to determine a target object corresponding to the user question in the corpus;
A generation unit configured to retrieve and establish a target knowledge-graph associated with the target object in the basic knowledge-graph;
and the feedback unit is configured to output feedback information according to the target knowledge graph.
It should be noted that the system can be used by students, teachers and parents together, when the students, teachers and parents input knowledge points which want to be queried, the acquisition unit extracts keywords from the user question, the judgment unit determines a target object corresponding to the user question in the corpus, the target object already contains relevant information of the user knowledge points, the generation unit retrieves and builds a target knowledge map associated with the target object from the basic knowledge map, and finally the feedback unit outputs feedback information according to the target knowledge map, and the pushed feedback information has pertinence and accuracy because the target knowledge map already contains relevant information of the user knowledge points.
Example 3:
Embodiment 3 provides an electronic device, including a processor and a memory, where the memory stores at least one instruction, at least one program, a code set, or an instruction set, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the knowledge-graph-based question-answering method in embodiment 1.
Example 4:
this embodiment 4 provides a computer readable storage medium having stored thereon computer instructions which when executed by a processor perform the steps of the method of embodiment 1 described above.
The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. A typical implementation device is a computer, which may be in the form of a personal computer, laptop computer, cellular telephone, camera phone, smart phone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or a combination of any of these devices.
In a typical configuration, a computer includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer 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, read only compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic disk storage, quantum memory, graphene-based storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by the computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
Compared with the prior art, the method and the device for analyzing and processing the personalized data of each examination of the students, calculate the personalized mastering degree of each knowledge point, then conduct hierarchical division on all knowledge points, identify weak knowledge points and dominant knowledge points, mark the personalized mastering degree in the original knowledge map, form the weak knowledge map and/or dominant knowledge map corresponding to the weak knowledge points, enable the students to clearly know the personalized mastering degree of the students on each knowledge point from visual pictures, find out own knowledge weaknesses and other knowledge points related to the knowledge weaknesses according to the weak knowledge map, form a knowledge network, and do not search for the weak knowledge points one by one, so that the efficiency of induction and arrangement of the students is improved;
The invention realizes interaction with students based on knowledge graphs, the students only need to input user questions comprising the questioning knowledge points, namely, the user questions are automatically compared with set questions in a corpus in similarity, N question-answer pairs with highest similarity are determined, the corresponding part of the basic knowledge graphs is reversely checked by the target object to form a target knowledge graph with the questioning knowledge points of the students, students or parents or teachers can intuitively see the mastering degree of the students on the knowledge points, so that different users can conveniently and clearly know the individualized learning mastering level of the students, and the next educational learning policy is determined;
The invention can also output weak knowledge point courses and weak knowledge point test questions simultaneously, so that students can autonomously conduct self-reinforcement on weak knowledge points of the students, including learning of courses or exercise of test questions, accurate promotion is achieved, weak knowledge points are effectively eliminated, the knowledge graph and the weak knowledge point test questions can be self-optimized and updated according to each time of problem making conditions of the students, synchronous update of knowledge graph and actual knowledge grasping level of the students is achieved, and a construction algorithm of the weak knowledge point test questions is optimized, so that the students can overcome difficulties.
Finally, it should be emphasized that the present invention is not limited to the above-described embodiments, but is merely preferred embodiments of the invention, and any modifications, equivalents, improvements, etc. within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (14)
1. The question answering method based on the knowledge graph is used by students, teachers and parents together and is characterized by comprising the following steps:
step S1: acquiring a user question and extracting keywords;
step S2: determining a target object corresponding to the user question in a corpus;
step S3: retrieving and establishing a target knowledge graph associated with the target object in the basic knowledge graph;
step S4: outputting feedback information according to the target knowledge graph;
Before step S3, a basic knowledge graph is established, which comprises the following steps:
step S31: collecting personalized data of each examination of students;
step S32: calculating the personalized mastery degree corresponding to each knowledge point according to the personalized data;
step S33: according to the personalized mastery, carrying out hierarchical division on the knowledge points and outputting a hierarchical division result;
step S34: establishing the basic knowledge graph according to the hierarchical division result;
the feedback information comprises at least one of a weak knowledge graph, a dominant knowledge graph, a weak knowledge point course and a weak knowledge point test question;
repeating the steps S31 to S34 after the weak knowledge point test questions are exercised, and updating the basic knowledge graph;
collecting wrong questions of each set of weak knowledge point test questions, and optimizing a building algorithm of the weak knowledge point test questions according to the wrong questions so as to recommend the test questions with high similarity to the wrong questions.
2. The knowledge-based question-answering method according to claim 1, wherein in step S2:
Generating question-answer pairs based on a set template according to the triples in the knowledge graph;
each question-answer pair comprises a set question sentence and a set answer, word segmentation and vectorization are carried out on the set question sentences to obtain set word vectors corresponding to the set question sentences, and a corpus is built according to the set word vectors;
Performing word segmentation and vectorization on the user question to obtain a user word vector;
Comparing and calculating the user word vector and the set word vector, and determining a target object according to the similarity; the target object comprises N question-answer pairs, wherein N is a natural number which is greater than or equal to 1.
3. The knowledge graph-based question-answering method according to claim 2, wherein when the set questions and the user questions are vectorized, the texts of the set questions and the user questions are distributed and vectorized, and word2vec models are used to calculate word vectors corresponding to each set question and each user question.
4. A knowledge-graph-based question-answering method according to claim 3, wherein in the corpus, the question-answer pairs store question-answer information corresponding thereto, the question-answer information including fifty-dimensional word vectors of the set question sentences and set answer information corresponding to the set question sentences, the question-answer information constituting the corpus.
5. The knowledge-based question-answering method according to claim 4, wherein manual question-answer pairs are input into the corpus according to the types of triplet relationships in the knowledge-based graph.
6. The knowledge graph-based question-answering method according to claim 5, wherein when comparing the user word vector and the set word vector, a cosine value of an included angle formed between the user word vector and the set word vector is calculated, and the similarity of the user question and the set question is judged according to the cosine value, wherein the closer the cosine value is to 1, the higher the similarity of the user question and the set question is; the closer the cosine value is to 0, the lower the similarity between the user question and the set question.
7. The knowledge-graph-based question and answer method of claim 6, wherein the personalized data includes at least one of examination time information, examination question information, examination paper information, or examination performance information, the examination paper information includes at least one of a subject of interest, a type of examination paper, a name of examination paper, a full score of a test question, and original question information including at least one of a subject of interest, an associated chapter, an associated knowledge point, a level of capability to which the subject itself belongs, a subject application type, a subject difficulty coefficient, a subject stem and answer, a subject score, a subject year, a region, a source, a test point, an analysis, and a point of comment.
8. The knowledge-graph-based question-answering method according to claim 7, wherein in step S32, the personalized mastery is calculated by:
f= [ (a1+a2+a3+ ] +an)/(n ]. Times.g, wherein f is the individuation grasping degree of the knowledge point, g is the importance degree of the knowledge point, a1, a2, a3...an is the 1 st, 2 nd, 3 rd..n and the corresponding question score value of the knowledge point, n is the wrong question number of the knowledge point;
the topic score value a is obtained by the following method: Wherein a is the question scoring value, b is the test question full scoring value, x% is the weight of the test question full scoring value, c is the test question distinction degree, y% is the weight of the test question distinction degree, d is the difference value between the personal scoring rate of the knowledge points and the class scoring rate, z% is the weight of the scoring rate difference value, p is the difficulty coefficient, the range of the difficulty coefficient p is 0-1, and the more difficult the value of the difficulty coefficient p approaches 0, the greater the difficulty is;
the test question distinguishing degree c is obtained by the following method: c= (v 1-v 2)/b, wherein v1 is the average score of the examination score of 20% before the score ranking, and v2 is the average score of the examination score of 20% after the score ranking;
The knowledge point importance degree g is obtained by the following method: g=70%i+30%j, where i is the degree of mastery of the knowledge points required by the outline students, and j is the percentage of all the topic scores related to the knowledge points in the test paper to the total score.
9. The knowledge graph-based question-answering method according to claim 8, wherein in step S33, the hierarchy classification result includes a weak knowledge point hierarchy and a dominant knowledge point hierarchy, the knowledge points are in one-to-one correspondence with the personalized mastery degrees, the personalized mastery degrees are compared with the set weak knowledge point threshold and dominant knowledge point threshold, the knowledge points corresponding to the personalized mastery degrees smaller than the weak knowledge point threshold are defined as weak knowledge points, the weak knowledge points are classified into weak knowledge point hierarchies, the knowledge points corresponding to the personalized mastery degrees larger than the dominant knowledge point threshold are defined as dominant knowledge points, and the dominant knowledge points are classified into dominant knowledge point hierarchies.
10. A knowledge-based question-answering method according to claim 9, wherein in step S34, the basic knowledge-graph includes a weak knowledge-graph and/or a dominant knowledge-graph;
marking the personalized mastery degree of each weak knowledge point in the set original knowledge map according to the weak knowledge point level information, and establishing a weak knowledge map;
And marking the personalized mastery degree of each dominant knowledge point in the set original knowledge map according to the level information of the dominant knowledge points, and establishing the dominant knowledge map.
11. The knowledge-based question-answering method according to claim 10, wherein the original knowledge graph is determined based on teaching materials teaching assistance materials of discipline authorities, and the relationship is determined according to knowledge point concepts and encyclopedia information frames; the weak knowledge graph further comprises a plurality of relationships among weak knowledge points; the dominant knowledge graph also includes relationships between a plurality of dominant knowledge points.
12. A system for applying the question-answering method according to any one of claims 1 to 11, comprising:
An acquisition unit configured to acquire a user question, extract a keyword;
a judging unit configured to determine a target object corresponding to the user question in a corpus;
a generation unit configured to retrieve and establish a target knowledge-graph associated with the target object in a base knowledge-graph;
and the feedback unit is configured to output feedback information according to the target knowledge graph.
13. An electronic device comprising a processor and a memory, wherein the memory stores at least one instruction, at least one program, code set, or instruction set that is loaded and executed by the processor to implement the knowledge-graph-based question-answering method according to any one of claims 1 to 11.
14. A computer readable storage medium having stored thereon computer instructions, which when executed by a processor, implement the steps of the method of any of claims 1 to 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011384225.3A CN112395403B (en) | 2020-11-30 | 2020-11-30 | Knowledge graph-based question and answer method, system, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011384225.3A CN112395403B (en) | 2020-11-30 | 2020-11-30 | Knowledge graph-based question and answer method, system, electronic equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112395403A CN112395403A (en) | 2021-02-23 |
| CN112395403B true CN112395403B (en) | 2024-06-11 |
Family
ID=74604050
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011384225.3A Active CN112395403B (en) | 2020-11-30 | 2020-11-30 | Knowledge graph-based question and answer method, system, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112395403B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112908067B (en) * | 2021-03-09 | 2022-09-23 | 浙江创课网络科技有限公司 | Student homework distribution system based on multi-dimensional layering mechanism |
| CN113806550A (en) * | 2021-04-15 | 2021-12-17 | 京东科技控股股份有限公司 | Generation method and device of personalized knowledge graph and computer equipment |
| CN113221540A (en) * | 2021-06-03 | 2021-08-06 | 天闻数媒科技（湖南）有限公司 | Knowledge point identification method, device, equipment and storage medium |
| CN113435737B (en) * | 2021-06-24 | 2023-06-16 | 窦昕 | Evaluation method of Chinese ability evaluation system |
| CN113407678B (en) * | 2021-06-30 | 2023-08-01 | 竹间智能科技（上海）有限公司 | Knowledge graph construction method, device and equipment |
| CN115438152B (en) * | 2022-09-14 | 2023-04-07 | 北方工业大学 | Simple answer scoring method and system based on multi-neural network and knowledge graph |
| CN116933870A (en) * | 2023-09-15 | 2023-10-24 | 浪潮软件股份有限公司 | Method, system and device for arranging elastic operation based on knowledge graph |
| CN117672027B (en) * | 2024-02-01 | 2024-04-30 | 青岛培诺教育科技股份有限公司 | VR teaching method, device, equipment and medium |
| CN118246719A (en) * | 2024-05-30 | 2024-06-25 | 成都在线支点教育科技有限公司 | Automatic online education course distribution system and distribution method based on cloud computing |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105868313A (en) * | 2016-03-25 | 2016-08-17 | 浙江大学 | Mapping knowledge domain questioning and answering system and method based on template matching technique |
| CN110704746A (en) * | 2019-10-10 | 2020-01-17 | 江苏曲速教育科技有限公司 | Method and system for recommending test questions according to strong and weak knowledge point analysis results |
| CN111506721A (en) * | 2020-04-22 | 2020-08-07 | 福州大学 | Question-answering system and construction method for domain knowledge graph |
| CN111753098A (en) * | 2020-06-23 | 2020-10-09 | 陕西师范大学 | Teaching method and system based on cross-media dynamic knowledge graph |
-
2020
- 2020-11-30 CN CN202011384225.3A patent/CN112395403B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105868313A (en) * | 2016-03-25 | 2016-08-17 | 浙江大学 | Mapping knowledge domain questioning and answering system and method based on template matching technique |
| CN110704746A (en) * | 2019-10-10 | 2020-01-17 | 江苏曲速教育科技有限公司 | Method and system for recommending test questions according to strong and weak knowledge point analysis results |
| CN111506721A (en) * | 2020-04-22 | 2020-08-07 | 福州大学 | Question-answering system and construction method for domain knowledge graph |
| CN111753098A (en) * | 2020-06-23 | 2020-10-09 | 陕西师范大学 | Teaching method and system based on cross-media dynamic knowledge graph |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112395403A (en) | 2021-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112395403B (en) | Knowledge graph-based question and answer method, system, electronic equipment and medium | |
| CN107230174B (en) | Online interactive learning system and method based on network | |
| CN109359215B (en) | Video intelligent pushing method and system | |
| CN110941723A (en) | Method, system and storage medium for constructing knowledge graph | |
| CN112184500A (en) | Extraclass learning tutoring system based on deep learning and knowledge graph and implementation method | |
| CN108509439B (en) | Algebra teaching system | |
| CN117150151B (en) | Wrong question analysis and test question recommendation system and method based on large language model | |
| WO2022170985A1 (en) | Exercise selection method and apparatus, and computer device and storage medium | |
| US20160019802A1 (en) | Neural adaptive learning device and neural adaptive learning method using realtional concept map | |
| CN113851020A (en) | Self-adaptive learning platform based on knowledge graph | |
| Brown | Going back or going forward? Tensions in the formulation of a new National Curriculum in mathematics | |
| Salahli et al. | Concept Based Approach for Adaptive Personalized Course Learning System. | |
| Agarwal et al. | Autoeval: A nlp approach for automatic test evaluation system | |
| CN116595188A (en) | Educational knowledge graph system based on artificial intelligence and big data | |
| Xie et al. | Virtual reality primary school mathematics teaching system based on GIS data fusion | |
| CN115544268A (en) | Construction and application method of teaching and employment auxiliary knowledge map | |
| Alobed et al. | A comparative analysis of Euclidean, Jaccard and Cosine similarity measure and arabic wordnet for automated arabic essay scoring | |
| Álvarez et al. | Semantics and service technologies for the automatic generation of online MCQ tests | |
| CN109871430A (en) | A kind of method, apparatus, electronic equipment and the storage medium of intelligent recognition text | |
| Kumar et al. | Identification and addressal of knowledge gaps in students | |
| CN111813919A (en) | MOOC course evaluation method based on syntactic analysis and keyword detection | |
| Xue-jun et al. | Design of Personalized Learning System for Military Vocational Education Based on Big Data | |
| CN112084345B (en) | Teaching guiding method and system combining body of course and teaching outline | |
| Li | Multimodal Teaching of College English Based on Similarity | |
| da Silva et al. | Adaptation in educational hypermedia based on the classification of the user profile |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Country or region after: China Address after: 519000 room 367, floor 1, Zone C, building 24, Gangwan 1 science and Technology Innovation Park, Jintang Road, Tangjiawan Town, high tech Zone, Zhuhai, Guangdong Province (centralized office area) Applicant after: GUANGDONG GUOLI EDUCATION TECHNOLOGY Co.,Ltd. Address before: 519000 room 105-40499, No.6 Baohua Road, Hengqin New District, Zhuhai City, Guangdong Province (centralized office area) Applicant before: GUANGDONG GUOLI EDUCATION TECHNOLOGY Co.,Ltd. Country or region before: China |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |