CN116340625B - Course recommendation method and device combining learning state fitness and course collocation degree - Google Patents
Course recommendation method and device combining learning state fitness and course collocation degree Download PDFInfo
- Publication number
- CN116340625B CN116340625B CN202310270566.5A CN202310270566A CN116340625B CN 116340625 B CN116340625 B CN 116340625B CN 202310270566 A CN202310270566 A CN 202310270566A CN 116340625 B CN116340625 B CN 116340625B
- Authority
- CN
- China
- Prior art keywords
- course
- knowledge
- student
- collocation
- target
- 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 25
- 238000000605 extraction Methods 0.000 claims abstract description 72
- 239000011159 matrix material Substances 0.000 claims abstract description 45
- 230000003993 interaction Effects 0.000 claims abstract description 44
- 238000003062 neural network model Methods 0.000 claims description 33
- 230000006870 function Effects 0.000 claims description 16
- 238000010276 construction Methods 0.000 claims description 11
- 230000006698 induction Effects 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 6
- 238000000547 structure data Methods 0.000 claims description 6
- 230000004913 activation Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 4
- 239000013598 vector Substances 0.000 claims description 4
- 230000004069 differentiation Effects 0.000 claims description 3
- 230000003542 behavioural effect Effects 0.000 description 10
- 230000006399 behavior Effects 0.000 description 7
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000009193 crawling Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012552 review Methods 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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Educational Technology (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Educational Administration (AREA)
- Computational Linguistics (AREA)
- Animal Behavior & Ethology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a course recommendation method and a device combining learning state fitness and course collocation, comprising the following steps: identifying a course recommendation platform to be recommended, acquiring course data of the course recommendation platform, performing ternary knowledge extraction on the course data to obtain a ternary extraction group, and constructing a knowledge graph of the course recommendation platform according to the ternary extraction group; identifying the knowledge state level of a target student to be recommended by a course, identifying the interest preference of the target student, and constructing a student portrait of the target student according to the knowledge state level and the interest preference; acquiring candidate courses of a course recommendation platform, constructing an interaction matrix of a target student about the candidate courses, determining collocation courses in a knowledge graph based on the interaction matrix and the student portraits, and calculating recommendation scores of the target student about the collocation courses; and determining a recommended course of the target student according to the recommendation score. The method and the device can improve accuracy of course recommendation.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a course recommendation method and device combining learning state fitness and course collocation degree.
Background
Along with the development and popularization of the Internet, the form of Internet plus education is continuously upgraded, the on-line education breaks through the time limit and the space limit of the traditional on-line education, and provides education and learning resources with more flexible forms and richer contents for students and lifelong learners.
How to generate personalized learning resource recommendations for learners based on learning state fitness and course collocation degree of learners in massive learning resources is an important problem to be solved at present . At present, most course recommendation mainly considers interest preference of learners, and selects recommended learning courses by utilizing a collaborative filtering algorithm without considering learning ability level of the learners and logic relation of a knowledge system, so that accuracy of course recommendation is low, and personalized requirements of the learners cannot be met.
Disclosure of Invention
The invention provides a course recommendation method and a course recommendation device combining learning state fitness and course collocation, and mainly aims to improve accuracy of course recommendation.
In order to achieve the above object, the course recommendation method combining learning state fitness and course collocation degree provided by the present invention includes:
Identifying a course recommendation platform to be recommended, acquiring course data of the course recommendation platform, performing ternary knowledge extraction on the course data to obtain a ternary extraction group, and constructing a knowledge graph of the course recommendation platform according to the ternary extraction group;
identifying a knowledge state level of a target student to be recommended by a course, identifying interest preference of the target student, and constructing a student portrait of the target student according to the knowledge state level and the interest preference;
acquiring a candidate course of the course recommendation platform, constructing an interaction matrix of the target student about the candidate course, determining a collocation course in the knowledge graph based on the interaction matrix and the student portrait, and calculating a recommendation score of the target student about the collocation course by using a pre-constructed knowledge graph deep neural network model;
and determining a recommended course of the target student according to the recommended score.
Optionally, the performing ternary knowledge extraction on the course data to obtain a ternary extraction group includes:
performing conceptual induction on the course data to obtain induction structure data, performing entity extraction on the induction structure data to obtain extracted entity data, and performing relation extraction on the entity data to obtain extracted relation data;
Performing attribute extraction on the extracted entity data and the extracted relation data respectively to obtain entity extraction attributes and relation extraction attributes, and updating the extracted entity data and the extracted relation data according to the entity extraction attributes and the relation extraction attributes to obtain updated entity data and updated relation data;
the triad is determined based on the updated entity data and the updated relationship data.
Optionally, the constructing a knowledge graph of the course recommendation platform according to the ternary extraction group includes:
extracting course names in the entity data of the ternary extraction group, and inquiring post-repair courses of the course names in a pre-constructed course learning sequence relation;
and constructing a sequence relation between the course entity corresponding to the course name and the post-repair course, and constructing a knowledge graph of the course recommendation platform according to the sequence relation and the ternary extraction group.
Optionally, the identifying the knowledge state level of the target student to be curriculum recommended includes:
identifying courses to be recommended and course categories thereof corresponding to the target students, constructing multi-level scoring questions with ordered steps corresponding to the course categories, configuring step scores of the multi-level scoring questions, and constructing a capacity value level table according to the multi-level scoring questions and the step scores;
Respectively calculating the front step pairing probability and the back step pairing probability of any adjacent step of the multi-level scoring questions of the target students in the capability value level table;
and determining the knowledge category level of the target student corresponding to the course category by utilizing a preset probability threshold according to the front step pairing probability and the back step pairing probability, and determining the knowledge state level of the target student according to the knowledge category level.
Optionally, the calculating the pre-step pairing probability of the target student in any adjacent step of the multi-level scoring title in the capability value level table includes:
calculating the previous step pairing probability of the target student in any adjacent step of multi-level scoring topics in the capability value level table by using the following formula:
wherein p is ijk Representing the probability of the ith target student doing the previous step of the kth step of the jth multi-level scoring title in the capability value level table, alpha j Index, θ, representing the differentiation of the j-th multi-level scoring title i Representing the knowledge ability, beta, of the ith target student j Represents the overall average difficulty of the j-th multi-level scoring topic in the capability value level table, d v The difficulty of the v step of the j-th multi-level scoring question is represented, v represents the sequence number of the step of the multi-level scoring question, m represents the step score of the step of the multi-level scoring question, and K represents the highest step score of the multi-level scoring question.
Optionally, the determining, according to the previous pairing probability and the subsequent pairing probability, a knowledge category level of the target student corresponding to the course category by using a preset probability threshold includes:
respectively obtaining a pre-step score and a post-step score of the course category, wherein the pre-step score and the post-step score correspond to each other, when the pre-step score is larger than the probability threshold, judging that the knowledge category level is not lower than the pre-step score, and marking a first judging state of the knowledge category level;
when the probability of the later step pair is smaller than the probability threshold, judging that the knowledge category level is not higher than the later step score, and marking a second judging state of the knowledge category level;
and determining the knowledge category level of the target student corresponding to the course category according to the first judging state and the second judging state.
Optionally, the determining a collocation course in the knowledge graph based on the interaction matrix and the student portrait includes:
identifying target students and candidate courses corresponding to the interaction matrix, acquiring matrix elements of each target student in the interaction matrix, which are equal to a preset interaction value, and identifying the candidate courses corresponding to the matrix elements;
Acquiring interest preferences of each target student in the student portrait, and identifying course categories corresponding to the interest preferences;
screening courses belonging to the course category from the candidate courses, inquiring post-repair courses of the screening courses in a knowledge graph, and determining collocation courses in the knowledge graph according to the post-repair courses.
Optionally, the calculating, by using the pre-constructed knowledge-graph deep neural network model, a recommendation score of the target student about the collocation course includes:
acquiring a knowledge graph corresponding to the knowledge graph depth neural network model, acquiring a student knowledge graph corresponding to the knowledge graph of the target student, and identifying a ternary extraction group corresponding to the student knowledge graph, wherein the ternary extraction group comprises entity data and relationship data;
calculating the interest degree and the normalized interest degree of the target students on the relation data by using the following formula:
wherein,representing the interest degree of a target student on the relation data, g representing an interest degree function, u representing the target student, e representing entity data of a student knowledge graph, r representing the relation data, < + >>Representing the normalized interestingness of the target students to the relationship data, v representing the historical viewing courses of the target students, N (v) representing the set of the historical viewing courses of the target students, exp representing the natural exponential function symbol;
Calculating the neighborhood expression value of the collocation course according to the normalized interestingness and the entity data by using the following formula:
wherein,neighborhood expression values representing collocation courses, +.>Representing the normalized interest level of the target student in the relationship data, v representing the historical viewing lessons of the target student, and N (v) representing the set of the historical viewing lessons of the target student;
and calculating the recommended score of the target student on the collocation course by utilizing a pre-constructed knowledge-graph deep neural network model according to the neighborhood expression value and the collocation course.
Optionally, the calculating, according to the neighborhood expression value and the matching course, a recommendation score of the target student about the matching course by using a pre-constructed knowledge-graph deep neural network model includes:
calculating a recommendation score of the target student on the collocation course by using the following formula:
wherein,the recommendation score of the target students on the collocation courses is represented, sigma represents an activation function, W represents a weight matrix of the knowledge graph deep neural network model, v represents entity data of the collocation courses, and +.>Course of representing collocationB represents the bias vector of the knowledge-graph deep neural network model.
In order to solve the above problems, the present invention further provides a course recommendation device combining learning state fitness and course collocation, the device comprising:
the knowledge graph construction module is used for identifying a course recommendation platform to be recommended, acquiring course data of the course recommendation platform, carrying out ternary knowledge extraction on the course data to obtain a ternary extraction group, and constructing a knowledge graph of the course recommendation platform according to the ternary extraction group;
the student portrait construction module is used for identifying the knowledge state level of a target student to be recommended by a course, identifying the interest preference of the target student and constructing the student portrait of the target student according to the knowledge state level and the interest preference;
the recommendation score calculation module is used for obtaining candidate courses of the course recommendation platform, constructing an interaction matrix of the target students about the candidate courses, determining collocation courses in the knowledge graph based on the interaction matrix and the student portrait, and calculating recommendation scores of the target students about the collocation courses by utilizing a pre-constructed knowledge graph deep neural network model;
and the recommended course determining module is used for determining the recommended course of the target student according to the recommended score.
It can be seen that, in the embodiment of the present invention, a specific application scenario of course recommendation can be determined by identifying a course recommendation platform to be recommended for a course, entity characteristics, attribute characteristics and relationship characteristics of a course can be obtained by acquiring course data of the course recommendation platform, basic core elements of a subsequent construction knowledge graph can be determined by performing ternary knowledge extraction on the course data, and a front-back structural relationship between courses can be revealed by constructing the knowledge graph of the course recommendation platform according to the ternary extraction group; secondly, the embodiment of the invention can provide basis for the subsequent course recommended to the knowledge learning capability of the target students by identifying the knowledge state level of the target students to be recommended, the character preference of the target students can be identified to obtain the recommended courses suitable for the subsequent recommendation, the student image of the target students can be constructed according to the knowledge state level and the interest preference to determine the two-dimensional student characteristics of the target students on the knowledge level and the interest preference so as to improve the matching degree of the subsequent recommended courses, the initial course object of the target courses to be recommended can be obtained by obtaining the candidate courses of the recommendation platform, and the interaction relation between the target students and the candidate courses can be obtained by constructing the interaction matrix of the target students about the candidate courses; further, according to the embodiment of the invention, the matching course in the knowledge graph can be determined by combining the learning state fitness of the student and the course matching degree based on the interaction matrix and the student image, so that accurate recommendation of the course can be realized, the recommendation score of the target student on the matching course can be calculated by utilizing the pre-built knowledge graph deep neural network model, the recommendation fitness of the matching course can be determined, and the final recommendation course of the target student can be determined by combining the learning state fitness and the course matching degree with the course knowledge graph according to the recommendation score, so that the accuracy of course recommendation is improved. Therefore, the course recommendation method and the course recommendation device combining the learning state fitness and the course collocation degree can improve accuracy of course recommendation.
Drawings
FIG. 1 is a flow chart of a course recommendation method combining learning status fitness and course collocation provided by an embodiment of the invention;
FIG. 2 is a schematic diagram of a course recommendation device combining learning status fitness and course collocation provided in an embodiment of the invention;
the achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The embodiment of the invention provides a course recommendation method combining learning state fitness and course collocation. The execution subject of the course recommendation method combining learning state fitness and course collocation degree includes, but is not limited to, at least one of a server, a terminal and the like capable of being configured to execute the method provided by the embodiment of the invention. In other words, the course recommendation method combining learning state fitness and course collocation degree may be performed by software or hardware installed in a terminal device or a server device, where the software may be a blockchain platform. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.
Referring to fig. 1, a flow chart of a course recommendation method combining learning status fitness and course collocation degree according to an embodiment of the invention is shown. In the embodiment of the invention, the course recommendation method combining learning state fitness and course collocation degree comprises the following steps:
s1, identifying a course recommendation platform to be recommended, acquiring course data of the course recommendation platform, performing ternary knowledge extraction on the course data to obtain a ternary extraction group, and constructing a knowledge graph of the course recommendation platform according to the ternary extraction group.
According to the embodiment of the invention, the specific application scene of course recommendation can be determined by identifying the course recommendation platform to be recommended, the recommendation platform can be obtained through a data script, and the data script can be compiled and identified through JS script language. According to the embodiment of the invention, the physical characteristics, the attribute characteristics and the relation characteristics of the courses can be obtained by acquiring the course data of the course recommendation platform, and the course data can be obtained by crawling from the course recommendation platform through a crawler technology.
Further, the embodiment of the invention can determine the basic core elements of the subsequent knowledge graph construction by carrying out ternary knowledge extraction on the course data. Wherein, the ternary extraction group is the basic unit and core of the knowledge graph, and is formed by an entity-relation-entity form.
Further, as an optional embodiment of the present invention, the performing ternary knowledge extraction on the course data to obtain a ternary extraction group includes: performing conceptual induction on the course data to obtain induction structure data, performing entity extraction on the induction structure data to obtain extracted entity data, and performing relation extraction on the entity data to obtain extracted relation data; performing attribute extraction on the extracted entity data and the extracted relation data respectively to obtain entity extraction attributes and relation extraction attributes, and updating the extracted entity data and the extracted relation data according to the entity extraction attributes and the relation extraction attributes to obtain updated entity data and updated relation data; the triad is determined based on the updated entity data and the updated relationship data.
Further, according to the embodiment of the invention, the knowledge graph of the course recommendation platform is constructed according to the ternary extraction group, so that the front-back structural relationship between courses can be revealed. The knowledge graph is a structured semantic knowledge base and is used for describing concepts and interrelationships thereof in a physical world in a symbol form, wherein a basic composition unit of the knowledge graph is an entity-relation-entity triplet, and the entities and related attribute-value pairs thereof are mutually connected through the relation to form a netlike knowledge structure.
Further, as an optional embodiment of the present invention, the constructing a knowledge graph of the course recommendation platform according to the ternary extraction set includes: extracting course names in the entity data of the ternary extraction group, and inquiring post-repair courses of the course names in a pre-constructed course learning sequence relation; and constructing a sequence relation between the course entity corresponding to the course name and the post-repair course, and constructing a knowledge graph of the course recommendation platform according to the sequence relation and the ternary extraction group. The pre-constructed course learning sequence relationship refers to a state of interaction and interaction between things formulated according to a course teaching outline and a successive course maintenance relationship.
S2, identifying a knowledge state level of a target student to be recommended by a course, identifying interest preference of the target student, and constructing a student portrait of the target student according to the knowledge state level and the interest preference;
according to the embodiment of the invention, the knowledge state level of the target student to be curriculum recommended is identified, so that a basis can be provided for the subsequent curriculum recommended to be suitable for the knowledge learning capability of the target student.
Further, as an optional embodiment of the present invention, the identifying a knowledge state level of the target student to be curriculum recommended includes: identifying courses to be recommended and course categories thereof corresponding to the target students, constructing multi-level scoring questions with ordered steps corresponding to the course categories, configuring step scores of the multi-level scoring questions, and constructing a capacity value level table according to the multi-level scoring questions and the step scores; respectively calculating the front step pairing probability and the back step pairing probability of any adjacent step of the multi-level scoring questions of the target students in the capability value level table; and determining the knowledge category level of the target student corresponding to the course category by utilizing a preset probability threshold according to the front step pairing probability and the back step pairing probability, and determining the knowledge state level of the target student according to the knowledge category level.
Optionally, the calculating the pre-step pairing probability of the target student in any adjacent step of the multi-level scoring title in the capability value level table includes:
calculating the previous step pairing probability of the target student in any adjacent step of multi-level scoring topics in the capability value level table by using the following formula:
wherein p is ijk Representing the probability of the ith target student doing the previous step of the kth step of the jth multi-level scoring title in the capability value level table, alpha j Index, θ, representing the differentiation of the j-th multi-level scoring title i Representing the knowledge ability, beta, of the ith target student j Represents the overall average difficulty of the j-th multi-level scoring topic in the capability value level table, d v The difficulty of the v step of the j-th multi-level scoring question is represented, v represents the sequence number of the step of the multi-level scoring question, m represents the step score of the step of the multi-level scoring question, and K represents the highest step score of the multi-level scoring question.
Optionally, the determining, according to the previous pairing probability and the subsequent pairing probability, a knowledge category level of the target student corresponding to the course category by using a preset probability threshold includes: respectively obtaining a pre-step score and a post-step score of the course category, wherein the pre-step score and the post-step score correspond to each other, when the pre-step score is larger than the probability threshold, judging that the knowledge category level is not lower than the pre-step score, and marking a first judging state of the knowledge category level; when the probability of the later step pair is smaller than the probability threshold, judging that the knowledge category level is not higher than the later step score, and marking a second judging state of the knowledge category level; and determining the knowledge category level of the target student corresponding to the course category according to the first judging state and the second judging state.
Further, the embodiment of the invention can obtain the preference of the target student by identifying the character preference of the target student so as to be suitable for the recommended course of the follow-up recommendation.
Further, as an alternative embodiment of the present invention, the identifying interest preferences of the target student includes: acquiring a course recommendation platform and course data corresponding to the target students, acquiring historical course behaviors of the target students on the course recommendation platform, and identifying behavior interest indexes of the historical course behaviors; and calculating the behavioral interest score of the historical course behavior according to the behavioral interest index, and determining the interest preference of the target student according to the behavioral interest score.
Optionally, the behavioral interest index for identifying the historical course behavior may be identified by detecting a viewing duration, a number of clicks, a review rate, a single viewing duration, etc. in the historical course behavior. The calculation of the behavioral interest score of the historical course behavior according to the behavioral interest indicators can be realized by quantifying each behavioral interest indicator and weighting and summing according to the weight parameters of the preset behavioral interest indicators. And determining the interest preference of the target student according to the behavioral interest score, wherein the behavioral interest score reaching a preset interest score threshold corresponds to the class category in the class data as the interest preference of the target student.
Further, according to the embodiment of the invention, the two-dimensional student characteristics of the target students on the knowledge level and the interest preference can be determined by constructing the student portraits of the target students according to the knowledge state level and the interest preference, so that the matching degree of the follow-up recommended courses is improved. The student portrait can be constructed by carrying out abstract labeling processing on basic information, knowledge state level and interest preference of the target student and analyzing the logic hierarchical relationship of the abstract label.
S3, acquiring candidate courses of the course recommendation platform, constructing an interaction matrix of the target students about the candidate courses, determining collocation courses in the knowledge graph based on the interaction matrix and the student portraits, and calculating recommendation scores of the target students about the collocation courses by using a pre-constructed knowledge graph deep neural network model.
According to the embodiment of the invention, the initial course object of the course to be recommended can be obtained by obtaining the candidate course of the course recommendation platform, the candidate course can be obtained through a data script, and the data script can be compiled through a JS script language.
Further, according to the embodiment of the invention, the interaction relation between the target student and the candidate course can be obtained by constructing the interaction matrix of the target student about the candidate course. The interaction matrix refers to a matrix of interaction relations between a target student and candidate courses.
Further, as an alternative embodiment of the present invention, the constructing the interaction matrix of the target student with respect to the candidate courses includes:
constructing an interaction matrix of the target student about the candidate courses using the following formula:
wherein G represents the interaction matrix of the target students about the candidate courses, i represents the serial numbers of the target students, and j represents the serial numbers of the candidate courses.
Furthermore, according to the embodiment of the invention, the matching courses in the knowledge graph are determined based on the interaction matrix and the student portrait, so that accurate recommendation of courses can be realized by combining the learning state fitness of students and the course matching degree.
Further, as an optional embodiment of the present invention, the determining a collocation course in the knowledge-graph based on the interaction matrix and the student portrait includes: identifying target students and candidate courses corresponding to the interaction matrix, acquiring matrix elements of each target student in the interaction matrix, which are equal to a preset interaction value, and identifying the candidate courses corresponding to the matrix elements; acquiring interest preferences of each target student in the student portrait, and identifying course categories corresponding to the interest preferences; screening courses belonging to the course category from the candidate courses, inquiring post-repair courses of the screening courses in a knowledge graph, and determining collocation courses in the knowledge graph according to the post-repair courses. Wherein, the preset interaction value is generally set according to an interaction matrix, and is set to 1 in the present invention.
Further, according to the embodiment of the invention, the recommendation suitability of the collocation course can be determined by calculating the recommendation score of the target student on the collocation course by using the pre-constructed knowledge graph deep neural network model.
Further, as an optional embodiment of the present invention, the calculating, using the pre-constructed knowledge-graph deep neural network model, a recommendation score of the target student with respect to the collocation course includes:
acquiring a knowledge graph corresponding to the knowledge graph depth neural network model, acquiring a student knowledge graph corresponding to the knowledge graph of the target student, and identifying a ternary extraction group corresponding to the student knowledge graph, wherein the ternary extraction group comprises entity data and relationship data;
calculating the interest degree and the normalized interest degree of the target students on the relation data by using the following formula:
wherein,representing the interest degree of a target student on the relation data, g representing an interest degree function, u representing the target student, e representing entity data of a student knowledge graph, r representing the relation data, < + >>Representing the normalized interestingness of the target students to the relationship data, v representing the historical viewing courses of the target students, N (v) representing the set of the historical viewing courses of the target students, exp representing the natural exponential function symbol;
Calculating the neighborhood expression value of the collocation course according to the normalized interestingness and the entity data by using the following formula:
wherein,neighborhood expression values representing collocation courses, +.>Representing the normalized interest level of the target student in the relationship data, v representing the historical viewing lessons of the target student, and N (v) representing the set of the historical viewing lessons of the target student;
and calculating the recommended score of the target student on the collocation course by utilizing a pre-constructed knowledge-graph deep neural network model according to the neighborhood expression value and the collocation course.
Optionally, the calculating, according to the neighborhood expression value and the matching course, a recommendation score of the target student about the matching course by using a pre-constructed knowledge-graph deep neural network model includes:
calculating a recommendation score of the target student on the collocation course by using the following formula:
wherein,the recommendation score of the target students on the collocation courses is represented, sigma represents an activation function, W represents a weight matrix of the knowledge graph deep neural network model, v represents entity data of the collocation courses, and +.>And b represents the bias vector of the knowledge-graph deep neural network model.
And S4, determining a recommended course of the target student according to the recommended score.
According to the method and the device for recommending the students, the recommended courses of the target students are determined according to the recommended scores, and the final recommended courses of the target students can be determined through combining the learning state fitness and the course collocation degree with the course knowledge graph, so that the accuracy of course recommendation is improved.
Further, as an optional embodiment of the present invention, the determining, according to the recommendation score, a recommended course of the target student may be used as a final recommended course by determining a collocation course corresponding to a recommendation score not less than a preset score threshold.
It can be seen that, in the embodiment of the present invention, a specific application scenario of course recommendation can be determined by identifying a course recommendation platform to be recommended for a course, entity characteristics, attribute characteristics and relationship characteristics of a course can be obtained by acquiring course data of the course recommendation platform, basic core elements of a subsequent construction knowledge graph can be determined by performing ternary knowledge extraction on the course data, and a front-back structural relationship between courses can be revealed by constructing the knowledge graph of the course recommendation platform according to the ternary extraction group; secondly, the embodiment of the invention can provide basis for the subsequent course recommended to the knowledge learning capability of the target students by identifying the knowledge state level of the target students to be recommended, the character preference of the target students can be identified to obtain the recommended courses suitable for the subsequent recommendation, the student image of the target students can be constructed according to the knowledge state level and the interest preference to determine the two-dimensional student characteristics of the target students on the knowledge level and the interest preference so as to improve the matching degree of the subsequent recommended courses, the initial course object of the target courses to be recommended can be obtained by obtaining the candidate courses of the recommendation platform, and the interaction relation between the target students and the candidate courses can be obtained by constructing the interaction matrix of the target students about the candidate courses; further, according to the embodiment of the invention, the matching course in the knowledge graph can be determined by combining the learning state fitness of the student and the course matching degree based on the interaction matrix and the student image, so that accurate recommendation of the course can be realized, the recommendation score of the target student on the matching course can be calculated by utilizing the pre-built knowledge graph deep neural network model, the recommendation fitness of the matching course can be determined, and the final recommendation course of the target student can be determined by combining the learning state fitness and the course matching degree with the course knowledge graph according to the recommendation score, so that the accuracy of course recommendation is improved. Therefore, the course recommendation method and the course recommendation device combining the learning state fitness and the course collocation degree can improve accuracy of course recommendation.
Fig. 2 is a functional block diagram of a course recommendation device according to the present invention combining learning status fitness and course collocation.
The course recommendation device 100 combining learning state fitness and course collocation degree can be installed in an electronic device. Depending on the functions implemented, the course recommendation device combining learning state fitness and course collocation degree may include a knowledge graph construction module 101, a student portrait construction module 102, a recommendation score calculation module 103, and a recommendation course determination module 104. The module according to the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.
In the present embodiment, the functions concerning the respective modules/units are as follows:
the knowledge graph construction module 101 is configured to identify a course recommendation platform to be recommended, obtain course data of the course recommendation platform, perform ternary knowledge extraction on the course data to obtain a ternary extraction group, and construct a knowledge graph of the course recommendation platform according to the ternary extraction group;
The student portrait construction module 102 is used for identifying the knowledge state level of a target student to be recommended by a course, identifying the interest preference of the target student, and constructing the student portrait of the target student according to the knowledge state level and the interest preference;
the recommendation score calculating module 103 is configured to obtain a candidate course of the course recommendation platform, construct an interaction matrix of the target student about the candidate course, determine a matching course in the knowledge graph based on the interaction matrix and the student portrait, and calculate a recommendation score of the target student about the matching course by using a pre-constructed knowledge graph deep neural network model;
the recommended course determining module 104 is configured to determine a recommended course of the target student according to the recommendation score.
In detail, the modules in the course recommendation device 100 combining learning state fitness and course matching degree in the embodiment of the present invention use the same technical means as the course recommendation method combining learning state fitness and course matching degree described in fig. 1, and can generate the same technical effects, which is not described herein.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (8)
1. The course recommendation method combining the learning state fitness and the course collocation degree is characterized by comprising the following steps:
identifying a course recommendation platform to be recommended, acquiring course data of the course recommendation platform, performing ternary knowledge extraction on the course data to obtain a ternary extraction group, and constructing a knowledge graph of the course recommendation platform according to the ternary extraction group;
identifying a knowledge state level of a target student to be recommended by a course, identifying interest preference of the target student, and constructing a student portrait of the target student according to the knowledge state level and the interest preference;
acquiring a candidate course of the course recommendation platform, constructing an interaction matrix of the target student about the candidate course, determining a collocation course in the knowledge graph based on the interaction matrix and the student portrait, and calculating a recommendation score of the target student about the collocation course by using a pre-constructed knowledge graph deep neural network model;
The calculating the recommendation score of the target student about the collocation course by using the pre-constructed knowledge graph deep neural network model comprises the following steps:
acquiring a knowledge graph corresponding to the knowledge graph depth neural network model, acquiring a student knowledge graph corresponding to the knowledge graph of the target student, and identifying a ternary extraction group corresponding to the student knowledge graph, wherein the ternary extraction group comprises entity data and relationship data;
calculating the interest degree and the normalized interest degree of the target students on the relation data by using the following formula:
wherein,representing the interest degree of a target student on the relation data, g representing an interest degree function, u representing the target student, e representing entity data of a student knowledge graph, r representing the relation data, < + >>Representing the normalized interestingness of the target students to the relationship data, v representing the historical viewing courses of the target students, N (v) representing the set of the historical viewing courses of the target students, exp representing the natural exponential function symbol;
calculating the neighborhood expression value of the collocation course according to the normalized interestingness and the entity data by using the following formula:
wherein,neighborhood expression values representing collocation courses, +.>Representing the normalized interest level of the target student in the relationship data, v representing the historical viewing lessons of the target student, and N (v) representing the set of the historical viewing lessons of the target student;
Calculating a recommendation score of the target student on the collocation course by using a pre-constructed knowledge-graph deep neural network model according to the neighborhood expression value and the collocation course;
calculating a recommendation score of the target student on the collocation course by using a pre-constructed knowledge-graph deep neural network model according to the neighborhood expression value and the collocation course, wherein the recommendation score comprises the following steps:
calculating a recommendation score of the target student on the collocation course by using the following formula:
wherein,the recommendation score of the target students on the collocation courses is represented, sigma represents an activation function, W represents a weight matrix of the knowledge graph deep neural network model, v represents entity data of the collocation courses, and +.>Representing neighborhood expression values of collocation courses, b representsBias vector of knowledge-graph deep neural network model;
and determining a recommended course of the target student according to the recommended score.
2. The course recommendation method combining learning state fitness and course collocation degree according to claim 1, wherein the performing ternary knowledge extraction on the course data to obtain a ternary extraction group comprises:
performing conceptual induction on the course data to obtain induction structure data, performing entity extraction on the induction structure data to obtain extracted entity data, and performing relation extraction on the entity data to obtain extracted relation data;
Performing attribute extraction on the extracted entity data and the extracted relation data respectively to obtain entity extraction attributes and relation extraction attributes, and updating the extracted entity data and the extracted relation data according to the entity extraction attributes and the relation extraction attributes to obtain updated entity data and updated relation data;
the triad is determined based on the updated entity data and the updated relationship data.
3. The course recommendation method combining learning state fitness and course collocation degree according to claim 1, wherein the constructing a knowledge graph of the course recommendation platform according to the ternary extraction group comprises:
extracting course names in the entity data of the ternary extraction group, and inquiring post-repair courses of the course names in a pre-constructed course learning sequence relation;
and constructing a sequence relation between the course entity corresponding to the course name and the post-repair course, and constructing a knowledge graph of the course recommendation platform according to the sequence relation and the ternary extraction group.
4. The course recommendation method combining learning state fitness and course collocation degree according to claim 1, wherein the identifying the knowledge state level of the target student to be course recommended comprises:
Identifying courses to be recommended and course categories thereof corresponding to the target students, constructing multi-level scoring questions with ordered steps corresponding to the course categories, configuring step scores of the multi-level scoring questions, and constructing a capacity value level table according to the multi-level scoring questions and the step scores;
respectively calculating the front step pairing probability and the back step pairing probability of any adjacent step of the multi-level scoring questions of the target students in the capability value level table;
and determining the knowledge category level of the target student corresponding to the course category by utilizing a preset probability threshold according to the front step pairing probability and the back step pairing probability, and determining the knowledge state level of the target student according to the knowledge category level.
5. The course recommendation method combining learning state fitness and course collocation of claim 4, wherein calculating the pre-step pairing probabilities for the target student at any adjacent step of multi-level scoring topics in the capacity value level table comprises:
calculating the previous step pairing probability of the target student in any adjacent step of multi-level scoring topics in the capability value level table by using the following formula:
Wherein p is ijk Representing the probability of the ith target student doing the previous step of the kth step of the jth multi-level scoring title in the capability value level table, alpha j Index, θ, representing the differentiation of the j-th multi-level scoring title i Representing the knowledge ability, beta, of the ith target student j Represents the overall average difficulty of the j-th multi-level scoring topic in the capability value level table, d v Representing the difficulty of the jth step of the jth multi-level scoring topic, v representing the step of the multi-level scoring topicThe number of steps, m, represents the step score of the multi-level scoring topic, and K represents the highest step score of the multi-level scoring topic.
6. The course recommendation method combining learning state fitness and course collocation degree according to claim 4, wherein determining the knowledge category level of the target student corresponding to the course category by using a preset probability threshold according to the preceding step pair probability and the following step pair probability comprises:
respectively obtaining a pre-step score and a post-step score of the course category, wherein the pre-step score and the post-step score correspond to each other, when the pre-step score is larger than the probability threshold, judging that the knowledge category level is not lower than the pre-step score, and marking a first judging state of the knowledge category level;
When the probability of the later step pair is smaller than the probability threshold, judging that the knowledge category level is not higher than the later step score, and marking a second judging state of the knowledge category level;
and determining the knowledge category level of the target student corresponding to the course category according to the first judging state and the second judging state.
7. The course recommendation method combining learning state fitness and course collocation degree of claim 1, wherein the determining a collocation course in the knowledge-graph based on the interaction matrix and the student representation comprises:
identifying target students and candidate courses corresponding to the interaction matrix, acquiring matrix elements of each target student in the interaction matrix, which are equal to a preset interaction value, and identifying the candidate courses corresponding to the matrix elements;
acquiring interest preferences of each target student in the student portrait, and identifying course categories corresponding to the interest preferences;
screening courses belonging to the course category from the candidate courses, inquiring post-repair courses of the screening courses in a knowledge graph, and determining collocation courses in the knowledge graph according to the post-repair courses.
8. Course recommendation device combining learning state fitness and course collocation degree, which is characterized in that the device comprises:
the knowledge graph construction module is used for identifying a course recommendation platform to be recommended, acquiring course data of the course recommendation platform, carrying out ternary knowledge extraction on the course data to obtain a ternary extraction group, and constructing a knowledge graph of the course recommendation platform according to the ternary extraction group;
the student portrait construction module is used for identifying the knowledge state level of a target student to be recommended by a course, identifying the interest preference of the target student and constructing the student portrait of the target student according to the knowledge state level and the interest preference;
the recommendation score calculation module is used for obtaining candidate courses of the course recommendation platform, constructing an interaction matrix of the target students about the candidate courses, determining collocation courses in the knowledge graph based on the interaction matrix and the student portrait, and calculating recommendation scores of the target students about the collocation courses by utilizing a pre-constructed knowledge graph deep neural network model;
the calculating the recommendation score of the target student about the collocation course by using the pre-constructed knowledge graph deep neural network model comprises the following steps:
Acquiring a knowledge graph corresponding to the knowledge graph depth neural network model, acquiring a student knowledge graph corresponding to the knowledge graph of the target student, and identifying a ternary extraction group corresponding to the student knowledge graph, wherein the ternary extraction group comprises entity data and relationship data;
calculating the interest degree and the normalized interest degree of the target students on the relation data by using the following formula:
wherein,representing the interest degree of a target student on the relation data, g representing an interest degree function, u representing the target student, e representing entity data of a student knowledge graph, r representing the relation data, < + >>Representing the normalized interestingness of the target students to the relationship data, v representing the historical viewing courses of the target students, N (v) representing the set of the historical viewing courses of the target students, exp representing the natural exponential function symbol;
calculating the neighborhood expression value of the collocation course according to the normalized interestingness and the entity data by using the following formula:
wherein,neighborhood expression values representing collocation courses, +.>Representing the normalized interest level of the target student in the relationship data, v representing the historical viewing lessons of the target student, and N (v) representing the set of the historical viewing lessons of the target student;
Calculating a recommendation score of the target student on the collocation course by using a pre-constructed knowledge-graph deep neural network model according to the neighborhood expression value and the collocation course;
calculating a recommendation score of the target student on the collocation course by using a pre-constructed knowledge-graph deep neural network model according to the neighborhood expression value and the collocation course, wherein the recommendation score comprises the following steps:
calculating a recommendation score of the target student on the collocation course by using the following formula:
wherein,the recommendation score of the target students on the collocation courses is represented, sigma represents an activation function, W represents a weight matrix of the knowledge graph deep neural network model, v represents entity data of the collocation courses, and +.>Representing neighborhood expression values of collocation courses, and b represents bias vectors of the knowledge-graph deep neural network model;
and the recommended course determining module is used for determining the recommended course of the target student according to the recommended score.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310270566.5A CN116340625B (en) | 2023-03-15 | 2023-03-15 | Course recommendation method and device combining learning state fitness and course collocation degree |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310270566.5A CN116340625B (en) | 2023-03-15 | 2023-03-15 | Course recommendation method and device combining learning state fitness and course collocation degree |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116340625A CN116340625A (en) | 2023-06-27 |
| CN116340625B true CN116340625B (en) | 2024-04-05 |
Family
ID=86892464
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310270566.5A Active CN116340625B (en) | 2023-03-15 | 2023-03-15 | Course recommendation method and device combining learning state fitness and course collocation degree |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116340625B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116797052A (en) * | 2023-08-25 | 2023-09-22 | 之江实验室 | Resource recommendation method, device, system and storage medium based on programming learning |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2333746A1 (en) * | 2009-12-04 | 2011-06-15 | D.R.E.A.M. Italia S.c.a.f. | System and process for evaluating, updating and certifying students' learning |
| CN105005701A (en) * | 2015-07-24 | 2015-10-28 | 成都康赛信息技术有限公司 | Personalized recommendation method based on attributes and scores |
| CN109919810A (en) * | 2019-01-22 | 2019-06-21 | 山东科技大学 | Student's modeling and personalized course recommended method in on-line study system |
| CN110609960A (en) * | 2019-09-25 | 2019-12-24 | 华中师范大学 | Learning resource recommendation method and device, data processing equipment and storage medium |
| CN111460249A (en) * | 2020-02-24 | 2020-07-28 | 桂林电子科技大学 | Personalized learning resource recommendation method based on learner preference modeling |
| CN111831831A (en) * | 2020-07-17 | 2020-10-27 | 广东金融学院 | Knowledge graph-based personalized learning platform and construction method thereof |
| WO2021033208A1 (en) * | 2019-08-21 | 2021-02-25 | Heuristix Digital Technologies Private Limited | Recommendation system for learning and method thereof |
| CN115098770A (en) * | 2022-06-07 | 2022-09-23 | 桂林电子科技大学 | Online course recommendation method integrating reinforcement learning and knowledge graph link propagation |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100190142A1 (en) * | 2009-01-28 | 2010-07-29 | Time To Know Ltd. | Device, system, and method of automatic assessment of pedagogic parameters |
-
2023
- 2023-03-15 CN CN202310270566.5A patent/CN116340625B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2333746A1 (en) * | 2009-12-04 | 2011-06-15 | D.R.E.A.M. Italia S.c.a.f. | System and process for evaluating, updating and certifying students' learning |
| CN105005701A (en) * | 2015-07-24 | 2015-10-28 | 成都康赛信息技术有限公司 | Personalized recommendation method based on attributes and scores |
| CN109919810A (en) * | 2019-01-22 | 2019-06-21 | 山东科技大学 | Student's modeling and personalized course recommended method in on-line study system |
| WO2021033208A1 (en) * | 2019-08-21 | 2021-02-25 | Heuristix Digital Technologies Private Limited | Recommendation system for learning and method thereof |
| CN110609960A (en) * | 2019-09-25 | 2019-12-24 | 华中师范大学 | Learning resource recommendation method and device, data processing equipment and storage medium |
| CN111460249A (en) * | 2020-02-24 | 2020-07-28 | 桂林电子科技大学 | Personalized learning resource recommendation method based on learner preference modeling |
| CN111831831A (en) * | 2020-07-17 | 2020-10-27 | 广东金融学院 | Knowledge graph-based personalized learning platform and construction method thereof |
| CN115098770A (en) * | 2022-06-07 | 2022-09-23 | 桂林电子科技大学 | Online course recommendation method integrating reinforcement learning and knowledge graph link propagation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116340625A (en) | 2023-06-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112784608B (en) | Test question recommending method and device, electronic equipment and storage medium | |
| CN107403398A (en) | A kind of English education internet platform and its application method | |
| CN116340625B (en) | Course recommendation method and device combining learning state fitness and course collocation degree | |
| CN113342958B (en) | Question-answer matching method, text matching model training method and related equipment | |
| CN111552773A (en) | Method and system for searching key sentence of question or not in reading and understanding task | |
| WO2021210992A9 (en) | Systems and methods for determining entity attribute representations | |
| CN111563158A (en) | Text sorting method, sorting device, server and computer-readable storage medium | |
| CN112084413A (en) | Information recommendation method and device and storage medium | |
| CN115577185A (en) | Muting course recommendation method and device based on mixed reasoning and mesopic group decision | |
| CN110929169A (en) | Position recommendation method based on improved Canopy clustering collaborative filtering algorithm | |
| Lin | Learning information recommendation based on text vector model and support vector machine | |
| CN112165639B (en) | Content distribution method, device, electronic equipment and storage medium | |
| CN111443973B (en) | Filling method, device and equipment of remark information and storage medium | |
| CN115049397A (en) | Method and device for identifying risk account in social network | |
| CN115131052A (en) | Data processing method, computer equipment and storage medium | |
| CN111930908A (en) | Answer recognition method and device based on artificial intelligence, medium and electronic equipment | |
| CN116756281A (en) | Knowledge question-answering method, device, equipment and medium | |
| CN115934899A (en) | IT industry resume recommendation method and device, electronic equipment and storage medium | |
| CN115631008B (en) | Commodity recommendation method, device, equipment and medium | |
| CN114722280A (en) | User portrait based course recommendation method, device, equipment and storage medium | |
| CN115131058A (en) | Account identification method, device, equipment and storage medium | |
| CN114896975A (en) | Online education intelligent teaching-aid-oriented autonomous evolution method and system | |
| CN112818084B (en) | Information interaction method, related device, equipment and computer readable medium | |
| CN111897943A (en) | Session record searching method and device, electronic equipment and storage medium | |
| CN110765108A (en) | False message early detection method based on crowd-sourcing data fusion |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20240205 Address after: Room 319, 2nd Floor, Building 109, Phase II, Yijinghuating, No. 289 Guanshan Avenue, Hongshan District, Wuhan City, Hubei Province, 430000 Applicant after: Wuhan Boao Pengcheng Technology Investment Co.,Ltd. Country or region after: Zhong Guo Address before: Wuhan Boao Pengcheng Education Technology Co., Ltd., No. 289 Guanshan Avenue, Hongshan District, Wuhan City, Hubei Province, 430000 Applicant before: Wuhan Boao Pengcheng Education Technology Co.,Ltd. Country or region before: Zhong Guo |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |