CN114911949A - Course knowledge graph construction method and system - Google Patents
Course knowledge graph construction method and system Download PDFInfo
- Publication number
- CN114911949A CN114911949A CN202210467173.9A CN202210467173A CN114911949A CN 114911949 A CN114911949 A CN 114911949A CN 202210467173 A CN202210467173 A CN 202210467173A CN 114911949 A CN114911949 A CN 114911949A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- teaching
- outline
- unit
- graph
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 238000010276 construction Methods 0.000 title claims abstract description 15
- 239000013598 vector Substances 0.000 claims abstract description 16
- 238000010586 diagram Methods 0.000 claims description 69
- 230000011218 segmentation Effects 0.000 claims description 36
- 238000000034 method Methods 0.000 claims description 31
- 238000013461 design Methods 0.000 claims description 16
- 238000004458 analytical method Methods 0.000 claims description 15
- 238000000605 extraction Methods 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000001228 spectrum Methods 0.000 claims description 6
- 238000013500 data storage Methods 0.000 claims description 2
- 238000004590 computer program Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000003058 natural language processing Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 239000000969 carrier Substances 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Educational Technology (AREA)
- Educational Administration (AREA)
- Artificial Intelligence (AREA)
- Animal Behavior & Ethology (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (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)
- Devices For Executing Special Programs (AREA)
Abstract
The invention discloses a course knowledge graph construction method and a system, wherein an outline knowledge graph is generated according to a teaching outline and a preset weight value; generating a teaching plan knowledge graph according to the teaching plan; establishing vector representation among knowledge points by taking core knowledge points in the outline knowledge graph as root nodes; calculating the similarity between vectors of entities in the outline knowledge graph and the teaching plan knowledge graph by using a cosine similarity formula; if the similarity is larger than or equal to a set threshold value, the entity is considered to be the same entity, the knowledge points in the teaching plan knowledge graph are taken as the standard, the course knowledge points are determined, and the sub-graph taking the knowledge points in the teaching plan knowledge graph as the root nodes is stored in the corresponding position of the course knowledge graph; if the similarity is smaller than a set threshold value, the entity is considered to be different, and subgraphs taking the two entities as root nodes are respectively stored in corresponding positions of the course knowledge graph; and integrating to form a complete course knowledge graph. The invention realizes the automatic construction of the course knowledge graph depending on the teaching outline and the teaching plan.
Description
Technical Field
The invention relates to the technical field of natural language processing, in particular to a course knowledge graph construction method and system.
Background
The knowledge map is a series of different graphs for displaying the relationship between the knowledge development process and the structure, and is used for describing knowledge resources and carriers thereof by using a visualization technology, and mining, analyzing, constructing, drawing and displaying knowledge and the mutual relationship between the knowledge resources and the carriers.
Natural language processing is an important direction in the fields of computer science and artificial intelligence. It studies various theories and methods that enable efficient communication between humans and computers using natural language. Natural language processing is a science integrating linguistics, computer science, mathematics and the whole body.
In the prior art, there are generally two ways for constructing a knowledge graph: one is knowledge expansion based on the existing general knowledge graph, which is generally used for searching encyclopedia knowledge; another method requires the user to define and construct the knowledge graph in advance, and the method needs top-level design of experts and is generally suitable for professional fields (such as the power industry).
When the course knowledge graph is constructed, the first mode depends on the general knowledge graph, so that the mode cannot be adopted; the second method is very dependent on the top-level design of experts, and simultaneously, a large amount of manpower is needed to participate in entity extraction, relationship judgment, entity disambiguation and the like, and the knowledge graph is not updated timely, so that the actual application effect is poor.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, provides a course knowledge graph construction method and a system, and solves the problems that the current course knowledge graph construction is too dependent on expert personnel, and the actual application effect is poor.
In order to solve the technical problems, the invention is realized by adopting the following technical scheme:
in a first aspect, the invention provides a course knowledge graph construction method, which comprises the following steps:
generating a schema knowledge graph according to the teaching schema and a preset weight value;
generating a teaching plan knowledge map according to the teaching plan;
establishing vector representation among knowledge points by taking core knowledge points in the outline knowledge graph as root nodes;
calculating the similarity between vectors of entities in the outline knowledge graph and the teaching plan knowledge graph by using a cosine similarity formula;
if the similarity is larger than or equal to a set threshold value, the entity is considered to be the same entity, the knowledge points in the teaching plan knowledge graph are taken as the standard, the course knowledge points are determined, and the subgraph taking the node as the root node is stored in the corresponding position of the course knowledge graph;
if the similarity is smaller than a set threshold value, the entity is considered to be different, and subgraphs taking the two entities as root nodes are respectively stored in corresponding positions of the course knowledge graph;
and integrating to form a complete course knowledge graph.
With reference to the first aspect, further, a method for generating a schema knowledge graph according to a teaching schema and a preset weight value includes:
removing the contents of non-knowledge points in the teaching outline to form a teaching target and a unit teaching design outline document;
designing outline documents according to a teaching outline, a teaching target and unit teaching to form an outline top-level knowledge point tree diagram and an outline teaching unit knowledge point tree diagram, and integrating the outline top-level knowledge point tree diagram and the outline teaching unit knowledge point tree diagram to form an outline knowledge point tree diagram;
setting corresponding weight values for the knowledge points of the outline knowledge point tree graph according to the unit weight, the importance of the knowledge points and the dependency relationship to form an attribute relationship;
completing the establishment of the relation between the knowledge points according to the attribute relation to form an outline knowledge point-attribute-knowledge point triple;
and integrating the outline knowledge point tree graph, the attribute relation and the outline knowledge point-attribute-knowledge point triple, and storing to generate the outline knowledge graph.
With reference to the first aspect, further, the method for forming the outline knowledge point tree includes:
determining a schematic top-level knowledge point tree diagram according to the teaching target and the unit names and teaching arrangement sequence in the unit teaching design schematic document;
performing word segmentation and semantic analysis on the teaching content corresponding to each teaching unit name in the teaching outline, acquiring unit knowledge points, and forming an outline teaching unit knowledge point tree diagram;
and integrating the schema top-level knowledge point tree diagram and the schema teaching unit knowledge point tree diagram according to the teaching unit structure and the order in the teaching schema to form the schema knowledge point tree diagram.
With reference to the first aspect, further, a method for generating a teaching plan knowledge graph according to a teaching plan includes:
removing the contents of non-knowledge points in the teaching plan to form teaching plan documents in unit class;
forming a unit class time knowledge point tree graph according to the unit class time teaching plan document;
forming a teaching plan unit knowledge point tree diagram according to the unit class time knowledge point tree diagram and the outline top-level knowledge point tree diagram;
establishing a relation between teaching plan knowledge points to form a teaching plan knowledge point-attribute-knowledge point triple;
and integrating the unit class time knowledge point tree graph and the teaching plan knowledge point-attribute-knowledge point triplets, and storing to generate the teaching plan knowledge graph.
With reference to the first aspect, further, the method for forming a unit time knowledge point tree includes:
performing word segmentation and text analysis on teaching contents, teaching key points and teaching difficult point contents according to unit names and the class time arrangement sequence in the unit class time teaching plan document, and determining knowledge points in each class time;
dividing the knowledge points in each class into key knowledge points, difficult knowledge points and general knowledge points, and respectively giving weights to the key knowledge points, the difficult knowledge points and the general knowledge points to form a unit class knowledge point tree diagram.
With reference to the first aspect, further, the core knowledge points are core knowledge points of an outline top-level knowledge point tree diagram in an outline knowledge graph.
With reference to the first aspect, further, the outline knowledge graph and the teaching plan knowledge graph are stored according to an RDF data format.
In a second aspect, the present invention provides a course knowledge graph building system, comprising:
the outline knowledge graph generation module: the system is used for generating an outline knowledge graph according to the teaching outline and a preset weight value;
the teaching plan knowledge map generation module: the teaching plan knowledge graph is generated according to the teaching plan;
the course knowledge graph generation module: the method is used for establishing vector representation among knowledge points by taking core knowledge points in the outline knowledge graph as root nodes; calculating the similarity between vectors of entities in the outline knowledge graph and the teaching plan knowledge graph by using a cosine similarity formula; if the similarity is larger than or equal to a set threshold value, the entity is considered to be the same entity, the knowledge points in the teaching plan knowledge graph are taken as the standard, the course knowledge points are determined, and the subgraph taking the node as the root node is stored in the corresponding position of the course knowledge graph; if the similarity is smaller than a set threshold value, the entity is considered to be different, and subgraphs taking the two entities as root nodes are respectively stored in corresponding positions of the course knowledge graph; and integrating to form a complete course knowledge graph.
With reference to the second aspect, further, the outline knowledge graph generation module includes:
outline preprocessing unit: the method is used for removing the contents of non-knowledge points in the teaching outline to form a teaching target and a unit teaching design outline document;
acquiring outline knowledge points: the method comprises the steps of determining a schematic top-level knowledge point tree diagram according to teaching targets and unit names and teaching arrangement sequence in a unit teaching design schematic document; performing word segmentation and semantic analysis on teaching contents corresponding to each teaching unit name in the teaching outline to obtain unit knowledge points to form an outline teaching unit knowledge point tree diagram; integrating the schema top knowledge point tree diagram and the schema teaching unit knowledge point tree diagram according to the teaching unit structure and the order in the teaching schema to form a schema knowledge point tree diagram;
setting outline knowledge point weight value unit: the system is used for setting corresponding weight values for the knowledge points of the outline knowledge point tree graph according to the unit weight, the importance and the dependency relationship of the knowledge points to form an attribute relationship;
establishing a knowledge point relational database unit: the system is used for completing the establishment of the relationship between the knowledge points according to the attribute relationship to form an outline knowledge point-attribute-knowledge point triple;
generating a preset outline knowledge point spectrum unit: and the data storage unit is used for storing and generating the outline knowledge map according to the data generated by the outline knowledge point acquisition unit, the outline knowledge point weight value setting unit and the knowledge point relation base establishment unit.
With reference to the second aspect, further, the teaching plan knowledge graph generating module includes:
a teaching plan preprocessing unit: the teaching plan file is used for removing the contents of non-knowledge points in the teaching plan and forming a teaching plan file in unit class;
a unit class time knowledge point extraction unit: the system is used for determining the knowledge points of each class according to the unit names and the class arrangement sequence in the unit class time teaching plan document to form a unit class time knowledge point tree diagram;
establishing a lesson knowledge point relational database unit: the teaching plan unit knowledge point tree graph is formed according to the unit class time knowledge point tree graph and the outline top-level knowledge point tree graph, and meanwhile, the relation between teaching plan knowledge points is established to form a teaching plan knowledge point-attribute-knowledge point triple;
and a teaching plan knowledge point spectrum generating unit: and the teaching plan knowledge graph is stored and generated according to the data generated by the unit class time knowledge point extraction unit and the unit for establishing the class time knowledge point relational database.
Compared with the prior art, the invention has the following beneficial effects: generating an outline knowledge graph according to the teaching outline and a preset weight value, and generating a teaching plan knowledge graph according to the teaching plan; knowledge point entities in the two knowledge maps are vectorized, and the course knowledge maps are constructed after the similarity is calculated, so that the course knowledge maps can be constructed without depending on the general knowledge maps or top-level design of professionals, the automatic construction of the course knowledge maps depending on teaching outlines and teaching plans is realized, and teachers and students can help to sort out the content and the association relation of the knowledge points of the courses.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flowchart of a course knowledge graph building method according to an embodiment of the present invention;
fig. 2 is a schematic block diagram of a course knowledge graph building system according to a second embodiment of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
The first embodiment is as follows:
as shown in fig. 1, which is a flowchart of a course knowledge graph building method provided in an embodiment of the present invention, the flowchart only shows a logical order of the method described in this embodiment, and in other possible embodiments of the present invention, the steps shown or described may be completed in an order different from that shown in fig. 1 without conflict. The construction method specifically comprises the following steps:
step A: generating an outline knowledge graph according to the teaching outline and a preset weight value;
and B: generating a teaching plan knowledge graph according to the teaching plan;
and C: and taking core knowledge points in the outline knowledge graph as root nodes, establishing vector representation among the knowledge points, and comparing and analyzing vector expressions of entities in the outline knowledge graph and the teaching plan knowledge graph to generate the course knowledge graph.
The method for comparing and analyzing the vector expressions of the entities in the outline knowledge graph and the teaching plan knowledge graph specifically comprises the following steps:
calculating the similarity between vectors of entities in the outline knowledge graph and the teaching plan knowledge graph by using a cosine similarity formula;
if the similarity is larger than or equal to a set threshold value, the entity is considered to be the same entity, the knowledge points in the teaching plan knowledge graph are taken as the standard, the course knowledge points are determined, and the sub-graph taking the knowledge points in the teaching plan knowledge graph as the root nodes is stored in the corresponding position of the course knowledge graph;
if the similarity is smaller than the set threshold, the two entities are considered to be different entities, and the subgraphs taking the two entities as root nodes are respectively stored in corresponding positions of the course knowledge graph.
It should be noted that, when the outline knowledge graph is generated according to the teaching outline and the preset weight value, the teaching outline needs to be preprocessed, including removing the content of non-knowledge points in the teaching outline, where the non-knowledge points in the teaching outline include, but are not limited to: course code, school hours, school score, class start period, class use, department affiliated, course team, applicable specialty, etc. By preprocessing the teaching outline, teaching targets and unit teaching design outline documents can be formed.
The set threshold value may be selected to be 0.8 in the embodiment of the present invention.
Step aa: and designing an outline document according to the teaching outline, the teaching target and the unit teaching to form an outline top-level knowledge point tree diagram and an outline teaching unit knowledge point tree diagram, and integrating the outline top-level knowledge point tree diagram and the outline teaching unit knowledge point tree diagram to form the outline knowledge point tree diagram. The method specifically comprises the following steps:
determining a schematic top-level knowledge point tree diagram according to the teaching target and the unit names and teaching arrangement sequence in the unit teaching design schematic document; the core knowledge points in the step C are the core knowledge points of the schema top-level knowledge point tree diagram in the schema knowledge graph;
performing word segmentation and semantic analysis on the teaching content corresponding to each teaching unit name in the teaching outline to obtain unit knowledge points and form an outline teaching unit knowledge point tree diagram;
and integrating the schema top-level knowledge point tree diagram and the schema teaching unit knowledge point tree diagram according to the teaching unit structure and the order in the teaching schema to form the schema knowledge point tree diagram.
Step ab: setting corresponding weight values for the knowledge points of the outline knowledge point tree graph according to the unit weight, the importance of the knowledge points and the dependency relationship to form an attribute relationship;
for example: in the "natural language processing" course outline, the course is divided into 6 units including natural language and mathematics, Chinese analysis technology application, part of speech tagging and named entity recognition, keyword extraction algorithm and corpus, syntactic analysis and text vectorization, and emotion analysis, and the corresponding unit weights are 16.6%, 16.7%, 20.8% and 12.5%, respectively. Taking a Chinese analysis technology application unit as an example, the unit knowledge points obtained by performing word segmentation and semantic analysis on the teaching content corresponding to the unit name according to the step aa comprise 6 knowledge points of Chinese word segmentation, regular word segmentation, statistical word segmentation, mixed word segmentation, jieba and high-frequency word extraction, and according to course teaching arrangement, the main content of the unit is Chinese word segmentation, so that Chinese word segmentation is the key point, and the importance is set as 1. The Chinese word segmentation comprises regular word segmentation, statistical word segmentation, mixed word segmentation, jieba and high-frequency word extraction, so that the knowledge point regular word segmentation, the statistical word segmentation, the mixed word segmentation, the jieba and the high-frequency word extraction belong to the knowledge point Chinese word segmentation, and are 0.1, 0.2, 0.1, 0.4 and 0.2 in sequence according to importance. Therefore, the Chinese word segmentation technology applies the unit outline tree diagram as three layers, and the three layers are the first layer from top to bottom in sequence: chinese word segmentation technology application, second layer: chinese word segmentation, third layer: regular word segmentation, statistical word segmentation, mixed word segmentation, jieba and high-frequency word extraction, wherein the upper layer comprises a lower layer with neighbor. The weights extracted by the knowledge point Chinese word segmentation, the rule word segmentation, the statistical word segmentation, the mixed word segmentation, the jieba and the high-frequency word segmentation are 16.7% by 1, 16.7% by 0.1, 16.7% by 0.2, 16.7% by 0.1, 16.7% by 0.4 and 16.7% by 0.2 in sequence.
Step ac: completing the establishment of the relation between the knowledge points according to the attribute relation to form an outline knowledge point-attribute-knowledge point triple;
step ad: and integrating the outline knowledge point tree graph, the attribute relation and the outline knowledge point-attribute-knowledge point triple, and storing to generate the outline knowledge graph.
In the embodiment of the present invention, when the teaching plan knowledge graph is generated according to the teaching plan, the content of the non-knowledge points in the teaching plan needs to be removed first, which includes but is not limited to: and removing the contents of non-knowledge points such as course codes, general hours, course responsible persons, lessee teachers, teaching modes, evaluation modes, course resources and the like in the teaching plan so as to form a unit class time teaching plan document.
Step ba: according to the unit class hour teaching plan document, a unit class hour knowledge point tree diagram can be formed, and the method specifically comprises the following steps: performing word segmentation and text analysis on teaching contents, teaching key points and teaching difficult point contents according to unit names and the class time arrangement sequence in the unit class time teaching plan document, and determining knowledge points in each class time; dividing the knowledge points in each class into key knowledge points, difficult knowledge points and general knowledge points, and respectively giving weights to the key knowledge points, the difficult knowledge points and the general knowledge points to form a unit class knowledge point tree diagram.
In the embodiments of the present invention, the important knowledge points generally refer to: the knowledge points which the students must master are the core knowledge in the course of a unit, and the weight of the knowledge points can be set to be 1; difficult knowledge points generally refer to: teaching difficulties and new contents in unit class and knowledge points with certain fall from knowledge points mastered by students can be set to be 0.8; the general knowledge points generally refer to: the weight of other knowledge points needing to be mastered except key knowledge points and difficult knowledge points in the unit class time can be set to be 0.5.
Step bb: forming a teaching plan unit knowledge point tree diagram according to the unit class time knowledge point tree diagram and the outline top-level knowledge point tree diagram;
step bc: establishing a relation between teaching plan knowledge points to form a teaching plan knowledge point-attribute-knowledge point triple;
step bd: and integrating the unit class time knowledge point tree graph and the teaching plan knowledge point-attribute-knowledge point triplets, and storing to generate the teaching plan knowledge graph.
In the embodiment of the invention, the outline knowledge graph and the teaching plan knowledge graph can be stored according to an RDF data format. RDF (resource Description Framework) is a markup language for describing Web resources. RDF is an XML (subset of standard universal markup language) application that handles metadata, i.e. "data describing data" or "information describing information". For example: the contents of the book are data of the book, and the name of the author, the address of the publishing house, or copyright information is metadata of the book. The division of data and metadata is not absolute, and some data may be handled as data or metadata, for example, the name of an author may be handled as data rather than metadata.
According to the construction method provided by the embodiment of the invention, an outline knowledge graph is generated according to the teaching outline and the preset weight value, and a teaching plan knowledge graph is generated according to the teaching plan; knowledge point entities in the two knowledge maps are vectorized, and the course knowledge maps are constructed after the similarity is calculated, so that the course knowledge maps can be constructed without depending on the general knowledge maps or top-level design of professionals, the course knowledge maps can be automatically constructed depending on teaching outlines and teaching plans, and teachers and students can help to sort out the content and the association relation of the knowledge points of the courses.
The second embodiment:
as shown in fig. 2, the system for building a course knowledge graph according to an embodiment of the present invention may be used to implement the building method according to the first embodiment, where the building system includes:
the outline knowledge graph generation module: the system is used for generating an outline knowledge graph according to the teaching outline and a preset weight value;
a teaching plan knowledge map generation module: the teaching plan knowledge graph is generated according to the teaching plan;
the course knowledge graph generation module: the method is used for establishing vector representation among knowledge points by taking core knowledge points in the outline knowledge graph as root nodes; calculating the similarity between vectors of entities in the outline knowledge graph and the teaching plan knowledge graph by using a cosine similarity formula; if the similarity is larger than or equal to a set threshold value, the entity is considered to be the same entity, the knowledge points in the teaching plan knowledge graph are taken as the standard, the course knowledge points are determined, and the subgraph taking the node as the root node is stored in the corresponding position of the course knowledge graph; if the similarity is smaller than a set threshold value, the entity is considered to be different, and subgraphs taking the two entities as root nodes are respectively stored in corresponding positions of the course knowledge graph; and integrating to form a complete course knowledge graph.
As an embodiment of the invention, the outline knowledge graph generation module comprises an outline preprocessing unit, an outline knowledge point acquisition unit, an outline knowledge point weight value setting unit, a knowledge point relation base establishing unit and a preset outline knowledge point graph generation unit;
the outline preprocessing unit removes the contents of non-knowledge points such as course codes, the number of times of learning, the scores of the learning, the period of starting a course, the class of use, the department to which the course belongs, the course team, the applicable specialty and the like in the outline to form a teaching target and a unit teaching design outline document.
The outline knowledge point acquisition unit determines an outline top knowledge point tree diagram according to a teaching target, unit names in unit teaching design outline documents and a teaching arrangement sequence;
the outline knowledge point acquisition unit carries out word segmentation and semantic analysis on the teaching content corresponding to each teaching unit name in the teaching outline to acquire unit knowledge points to form an outline teaching unit knowledge point tree diagram;
the outline knowledge point acquisition unit integrates the outline top-level knowledge point dendrogram and the outline teaching unit knowledge point dendrogram according to the structure and the sequence of the teaching units in the teaching outline to form an outline knowledge point dendrogram;
the outline knowledge point weight value setting unit is connected with the outline knowledge point obtaining unit and is used for setting corresponding weight values for the knowledge points of the outline knowledge point dendrogram according to the unit weight, the importance and the subordination relation of the knowledge points to form an attribute relation;
the establishing knowledge point relation base unit is connected with the setting outline knowledge point weight value unit and is used for completing the establishment of the relation between the knowledge points according to the set weight value and forming an outline knowledge point-attribute-knowledge point triple;
the generating preset outline knowledge point spectrum unit is connected with the establishing knowledge point relational database unit and is used for storing and generating the outline knowledge map according to the data generated by the acquiring outline knowledge point unit, the setting outline knowledge point weight value unit and the establishing knowledge point relational database unit and the RDF data format.
As an embodiment of the invention, the teaching plan knowledge map generation module is connected with the outline knowledge map generation module and comprises a teaching plan preprocessing unit, a unit class hour knowledge point extraction unit, a class hour knowledge point relation base establishment unit and a teaching plan knowledge point map generation unit.
The teaching plan preprocessing unit removes the contents of non-knowledge points such as course codes, overall school hours, course responsible persons, lessee teachers, teaching modes, evaluation modes, course resources and the like in the teaching plan to form a teaching plan document in the course of the unit.
The unit class time knowledge point extracting unit carries out word segmentation and text analysis on teaching contents, teaching key points and teaching difficult point contents according to unit names and class time arrangement sequences in unit class time teaching plan documents to determine knowledge points of each class time, wherein the weight of the key knowledge points can be set to be 1, the weight of the difficult knowledge points can be set to be 0.8, and the weight of the general knowledge points can be set to be 0.5, so that a unit class time knowledge point tree graph is formed.
The teaching time knowledge point relation base establishing unit and the teaching time knowledge point extracting unit are connected with the outline knowledge map generating module to obtain outline knowledge point units, a teaching plan unit knowledge point tree map is formed according to the unit teaching time knowledge point tree map and the outline top knowledge point tree map, and meanwhile, the establishment of the relation among teaching plan knowledge points is completed, and a teaching plan knowledge point-attribute-knowledge point triple is formed;
the teaching plan knowledge point spectrum generating unit is connected with the lesson-time knowledge point relational database establishing unit and used for storing and generating the teaching plan knowledge map according to the RDF data format according to the data generated by the lesson-time knowledge point extracting unit and the lesson-time knowledge point relational database establishing unit.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A course knowledge graph construction method is characterized by comprising the following steps:
generating an outline knowledge graph according to the teaching outline and a preset weight value;
generating a teaching plan knowledge graph according to the teaching plan;
establishing vector representation among knowledge points by taking core knowledge points in the outline knowledge graph as root nodes;
calculating the similarity between vectors of entities in the outline knowledge graph and the teaching plan knowledge graph by using a cosine similarity formula;
if the similarity is larger than or equal to a set threshold value, the entity is considered to be the same entity, the knowledge points in the teaching plan knowledge graph are taken as the standard, the course knowledge points are determined, and the sub-graph taking the knowledge points in the teaching plan knowledge graph as the root nodes is stored in the corresponding position of the course knowledge graph;
if the similarity is smaller than a set threshold value, the entity is considered to be different, and subgraphs taking the two entities as root nodes are respectively stored in corresponding positions of the course knowledge graph;
and integrating to form a complete course knowledge graph.
2. The method of claim 1, wherein the step of generating the outline knowledge graph according to the teaching outline and the preset weight value comprises:
removing the contents of non-knowledge points in the teaching outline to form a teaching target and a unit teaching design outline document;
designing outline documents according to a teaching outline, a teaching target and unit teaching to form an outline top-level knowledge point tree diagram and an outline teaching unit knowledge point tree diagram, and integrating the outline top-level knowledge point tree diagram and the outline teaching unit knowledge point tree diagram to form an outline knowledge point tree diagram;
setting corresponding weight values for the knowledge points of the outline knowledge point tree graph according to the unit weight, the importance of the knowledge points and the dependency relationship to form an attribute relationship;
completing the establishment of the relation between the knowledge points according to the attribute relation to form an outline knowledge point-attribute-knowledge point triple;
and integrating the outline knowledge point tree graph, the attribute relation and the outline knowledge point-attribute-knowledge point triple, and storing to generate the outline knowledge graph.
3. The method of constructing a lesson knowledge-graph as claimed in claim 2, wherein the method of forming the outline knowledge-point tree-graph includes:
determining a schematic top-level knowledge point tree diagram according to the teaching target and the unit names and teaching arrangement sequence in the unit teaching design schematic document;
performing word segmentation and semantic analysis on the teaching content corresponding to each teaching unit name in the teaching outline to obtain unit knowledge points and form an outline teaching unit knowledge point tree diagram;
and integrating the schema top-level knowledge point tree diagram and the schema teaching unit knowledge point tree diagram according to the teaching unit structure and the order in the teaching schema to form the schema knowledge point tree diagram.
4. The course knowledge graph construction method of claim 3, wherein the method for generating a teaching plan knowledge graph from a teaching plan comprises:
removing the contents of non-knowledge points in the teaching plan to form teaching plan documents in unit class;
forming a unit class time knowledge point tree graph according to the unit class time teaching plan document;
forming a teaching plan unit knowledge point tree diagram according to the unit class time knowledge point tree diagram and the outline top-level knowledge point tree diagram;
establishing a relation between teaching plan knowledge points to form a teaching plan knowledge point-attribute-knowledge point triple;
and integrating the unit class time knowledge point tree graph and the teaching plan knowledge point-attribute-knowledge point triplets, and storing to generate the teaching plan knowledge graph.
5. The method of constructing a lesson knowledge-graph as claimed in claim 4, wherein the step of forming a unit time knowledge point tree-graph comprises:
performing word segmentation and text analysis on teaching contents, teaching key points and teaching difficult point contents according to unit names and the class time arrangement sequence in the unit class time teaching plan document, and determining knowledge points in each class time;
dividing the knowledge points in each class into key knowledge points, difficult knowledge points and general knowledge points, and respectively giving weights to the key knowledge points, the difficult knowledge points and the general knowledge points to form a unit class knowledge point tree diagram.
6. The course knowledge graph construction method of claim 2, wherein the core knowledge points are core knowledge points of an outline top-level knowledge point tree in an outline knowledge graph.
7. The curriculum knowledge graph construction method of any of claims 1 to 6, wherein the outline knowledge graph and the teaching plan knowledge graph are both stored in RDF data format.
8. A course knowledge graph building system, the building system comprising:
the outline knowledge graph generation module: the system is used for generating an outline knowledge graph according to the teaching outline and a preset weight value;
a teaching plan knowledge map generation module: the teaching plan knowledge graph is generated according to the teaching plan;
the course knowledge graph generation module: the method is used for establishing vector representation among knowledge points by taking core knowledge points in the outline knowledge graph as root nodes; calculating the similarity between vectors of entities in the outline knowledge graph and the teaching plan knowledge graph by using a cosine similarity formula; if the similarity is larger than or equal to a set threshold value, the entity is considered to be the same entity, the knowledge points in the teaching plan knowledge graph are taken as the standard, the course knowledge points are determined, and the subgraph taking the node as the root node is stored in the corresponding position of the course knowledge graph; if the similarity is smaller than a set threshold value, the entity is considered to be different, and subgraphs taking the two entities as root nodes are respectively stored in corresponding positions of the course knowledge graph; and integrating to form a complete course knowledge graph.
9. The course knowledge graph building system of claim 8, wherein the outline knowledge graph generating module comprises:
outline preprocessing unit: the method is used for removing the contents of non-knowledge points in the teaching outline to form a teaching target and a unit teaching design outline document;
acquiring outline knowledge points: the method comprises the steps of determining a schematic top-level knowledge point tree diagram according to teaching targets and unit names and teaching arrangement sequence in a unit teaching design schematic document; performing word segmentation and semantic analysis on teaching contents corresponding to each teaching unit name in the teaching outline to obtain unit knowledge points to form an outline teaching unit knowledge point tree diagram; integrating the schema top knowledge point tree diagram and the schema teaching unit knowledge point tree diagram according to the teaching unit structure and the order in the teaching schema to form a schema knowledge point tree diagram;
setting outline knowledge point weight value unit: the system is used for setting corresponding weight values for the knowledge points of the outline knowledge point tree graph according to the unit weight, the importance and the dependency relationship of the knowledge points to form an attribute relationship;
establishing a knowledge point relational database unit: the system is used for completing the establishment of the relationship between the knowledge points according to the attribute relationship to form an outline knowledge point-attribute-knowledge point triple;
generating a preset outline knowledge point spectrum unit: and the data storage unit is used for storing and generating the outline knowledge map according to the data generated by the outline knowledge point acquisition unit, the outline knowledge point weight value setting unit and the knowledge point relation base establishing unit.
10. The course knowledge graph building system of claim 9, wherein the teaching plan knowledge graph generating module comprises:
a teaching plan preprocessing unit: the teaching plan file is used for removing the contents of non-knowledge points in the teaching plan and forming a teaching plan file in unit class;
a unit class time knowledge point extraction unit: the system is used for determining the knowledge points of each class according to the unit names and the class arrangement sequence in the unit class time teaching plan document to form a unit class time knowledge point tree diagram;
establishing a lesson knowledge point relational database unit: the teaching plan unit knowledge point tree graph is formed according to the unit class time knowledge point tree graph and the outline top-level knowledge point tree graph, and meanwhile, the relation between teaching plan knowledge points is established to form a teaching plan knowledge point-attribute-knowledge point triple;
and a teaching plan knowledge point spectrum generating unit: the system is used for storing and generating the teaching plan knowledge map according to the data generated by the unit class time knowledge point extraction unit and the unit for establishing the class time knowledge point relational database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210467173.9A CN114911949A (en) | 2022-04-29 | 2022-04-29 | Course knowledge graph construction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210467173.9A CN114911949A (en) | 2022-04-29 | 2022-04-29 | Course knowledge graph construction method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114911949A true CN114911949A (en) | 2022-08-16 |
Family
ID=82764376
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210467173.9A Withdrawn CN114911949A (en) | 2022-04-29 | 2022-04-29 | Course knowledge graph construction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114911949A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117349478A (en) * | 2023-10-08 | 2024-01-05 | 国网江苏省电力有限公司经济技术研究院 | Resource data reconstruction integration system based on digital transformation enterprise |
| CN117874251A (en) * | 2024-01-09 | 2024-04-12 | 北京华乐思教育科技有限公司 | Knowledge structure automatic generation system and method |
-
2022
- 2022-04-29 CN CN202210467173.9A patent/CN114911949A/en not_active Withdrawn
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117349478A (en) * | 2023-10-08 | 2024-01-05 | 国网江苏省电力有限公司经济技术研究院 | Resource data reconstruction integration system based on digital transformation enterprise |
| CN117349478B (en) * | 2023-10-08 | 2024-05-24 | 国网江苏省电力有限公司经济技术研究院 | Resource data reconstruction integration system based on digital transformation enterprise |
| CN117874251A (en) * | 2024-01-09 | 2024-04-12 | 北京华乐思教育科技有限公司 | Knowledge structure automatic generation system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111259653B (en) | Knowledge graph question-answering method, system and terminal based on entity relationship disambiguation | |
| CN102262634B (en) | Automatic questioning and answering method and system | |
| CN111488465A (en) | Knowledge graph construction method and related device | |
| CN110990590A (en) | Dynamic financial knowledge map construction method based on reinforcement learning and transfer learning | |
| CN111475623A (en) | Case information semantic retrieval method and device based on knowledge graph | |
| CN109325040B (en) | FAQ question-answer library generalization method, device and equipment | |
| CN108664599B (en) | Intelligent question-answering method and device, intelligent question-answering server and storage medium | |
| CN114911949A (en) | Course knowledge graph construction method and system | |
| CN103927358A (en) | Text search method and system | |
| CN111143672B (en) | Knowledge graph-based professional speciality scholars recommendation method | |
| CN111767385A (en) | Intelligent question and answer method and device | |
| CN103885933A (en) | Method and equipment for evaluating text sentiment | |
| CN111797222A (en) | Course knowledge graph construction method, device, terminal and storage medium | |
| CN112163097A (en) | Military knowledge graph construction method and system | |
| CN111651569B (en) | Knowledge base question-answering method and system in electric power field | |
| CN105335510A (en) | Text data efficient searching method | |
| CN116561264A (en) | Knowledge graph-based intelligent question-answering system construction method | |
| CN116821373A (en) | Map-based prompt recommendation method, device, equipment and medium | |
| CN105160046A (en) | Text-based data retrieval method | |
| CN114911893A (en) | Method and system for automatically constructing knowledge base based on knowledge graph | |
| Chen et al. | A synergistic framework for geographic question answering | |
| CN117196042B (en) | Semantic reasoning method and terminal for learning target in education universe | |
| CN110750632B (en) | Improved Chinese ALICE intelligent question-answering method and system | |
| CN117010373A (en) | Recommendation method for category and group to which asset management data of power equipment belong | |
| CN117216221A (en) | Intelligent question-answering system based on knowledge graph and construction method |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220816 |