CN116362331A - Knowledge point filling method based on man-machine cooperation construction knowledge graph - Google Patents
Knowledge point filling method based on man-machine cooperation construction knowledge graph Download PDFInfo
- Publication number
- CN116362331A CN116362331A CN202310135279.3A CN202310135279A CN116362331A CN 116362331 A CN116362331 A CN 116362331A CN 202310135279 A CN202310135279 A CN 202310135279A CN 116362331 A CN116362331 A CN 116362331A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- knowledge graph
- resources
- man
- video
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000010276 construction Methods 0.000 title claims abstract description 20
- 239000000463 material Substances 0.000 claims description 39
- 238000005516 engineering process Methods 0.000 claims description 20
- 239000013598 vector Substances 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 238000003058 natural language processing Methods 0.000 claims description 5
- 239000000284 extract Substances 0.000 claims description 4
- 239000012634 fragment Substances 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 238000011982 device technology Methods 0.000 abstract 1
- 238000012015 optical character recognition Methods 0.000 description 6
- 239000000047 product Substances 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 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
- 238000010586 diagram Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9035—Filtering based on additional data, e.g. user or group profiles
-
- 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
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Animal Behavior & Ethology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a knowledge point filling method based on man-machine cooperation construction of a knowledge graph, and relates to the technical field of higher education. The method comprises the following steps: creating a knowledge graph through a device technology, and adding content into a knowledge graph resource package; recommending the resources related to the knowledge points through the names of the knowledge points in the created knowledge graph. According to the invention, two creation modes of the tree-shaped knowledge graph and the net-shaped knowledge graph are supported, so that different knowledge graph construction requirements of teachers can be met; the method has the advantages that a rich multi-mode teaching resource library is provided, and proper educational resources are actively recommended for knowledge points created by teachers, so that man-machine cooperation is realized, and the efficiency and accuracy of the teachers in constructing knowledge maps are improved; the method provides safe and reliable multi-user collaborative construction and result sharing of the knowledge patterns, can realize simultaneous online editing of the knowledge patterns by multiple teachers, shares the knowledge pattern results to student users, and guides students to learn online.
Description
Technical Field
The invention belongs to the technical field of higher education, and particularly relates to a knowledge point filling method based on human-computer cooperation construction of a knowledge graph.
Background
The knowledge graph is a key resource of education informatization in the 2.0 era, and the development and application of the knowledge graph provide strong power and good opportunity for comprehensively realizing education modernization; the knowledge graph can be regarded as a knowledge network graph consisting of knowledge points and knowledge relations, and subject knowledge and teaching resource entities are required to be linked in a standardized mode, so that effective organization of online education resources is realized;
in order to facilitate the manual construction of the knowledge graph, tools with better interaction experience, such as XMIND installed locally and Processon used on line for webpages, are easy to operate and convenient for teachers to quickly construct the knowledge graph; if the knowledge graph is applied to the teaching process in the higher education field, the knowledge graph not only reflects strict and correct knowledge points and knowledge relations, but also needs to provide rich and accurate teaching resources, and organizes massive multi-mode teaching resources in the form of knowledge points, such as aliases and descriptions of the knowledge points, pictures, audios, videos, teaching materials, network resources, test questions and the like;
therefore, not only is a teacher required to complete the construction work of the knowledge graph, but also the resources of each knowledge point are required to be supplemented and perfected, but the existing tool not only supports the teacher to upload the existing local files, but also is difficult to supplement other resources, has a certain limitation, and the teacher cannot search or recommend the proper teaching resources in a rich teaching resource library; meanwhile, whether XMIND of a local edition or Processon of a webpage edition is adopted, knowledge maps can not be constructed in an online cooperative manner by multiple teachers by constructing a form of a virtual teaching and research team;
the existing XMind, processOn and other knowledge graph editing software has the defects that multi-mode teaching resources cannot be filled, a rich teaching resource library cannot be provided for users, proper teaching resources cannot be recommended, multi-user online collaborative construction of the knowledge graph cannot be realized, and the manufacturing speed and the rich degree of the knowledge graph are severely limited; aiming at the problems, the invention constructs a knowledge point filling method based on man-machine cooperation to construct a knowledge graph.
Disclosure of Invention
The invention aims to provide a knowledge point filling method for constructing a knowledge graph based on man-machine cooperation, which aims to solve the technical problems in the background technology.
In order to solve the technical problems, the invention is realized by the following technical scheme:
the invention relates to a knowledge point filling method based on man-machine cooperation construction of a knowledge graph, which comprises the following steps:
creating a knowledge graph, and adding content into a knowledge graph resource package;
recommending the resources related to the knowledge points through the names of the knowledge points in the created knowledge graph.
Further, the creating of the knowledge graph is to create a tree-shaped knowledge graph through a front-end DOM technology.
Further, the creating of the knowledge graph is to create a net-shaped knowledge graph through svg technology.
Further, the recommending the knowledge point related resource includes:
the method comprises the steps of carrying out vectorization representation on knowledge points, teaching materials and video resources by adopting BERT (binary automatic repeat request) processed by natural language and related variant algorithms thereof, carrying out normalization processing on vectors, obtaining semantic cosine similarity by inner products of the knowledge points, the teaching materials and the video, and respectively sequencing the video resources and the teaching materials resources according to the semantic cosine similarity.
Further, the sorting the video resources and the teaching material resources according to the similarity includes:
the semantic cosine similarity scores of different resources in the sorting process need to be adjusted and considered according to attribute weights, and the formula is as follows:
wherein score item Score for gross rank stage total similarity calculation x Weight for each attribute score x Is attribute ofAnd (5) weighting.
Further, the obtaining the semantic cosine similarity through the inner product of the knowledge points, the teaching materials and the video includes:
for teaching material resources, calculating a semantic cosine similarity score according to the long text attribute of the small-section content and the short text attribute of the chapter name;
for video resources, a semantic cosine similarity score is calculated from the video name, the lesson chapter to which it belongs, and the short text attribute of the key frame OCR.
Further, the recommending the knowledge point related resource includes:
recommending relevant resources, wherein a recommended user selects teaching materials in a resource package and resource fragments contained in courses; when the highest scoring resource content score does not reach the threshold or the threshold number of resource contents is small, the recommendation is made based on all shared resources except the user selected resource package.
Further, the method further comprises the following steps:
for a certain knowledge point, when receiving recommended resources which are decided to be cited by a user, linking the knowledge point with all recommended resources which are decided to be cited by the user; when the user decides not to refer to the recommended resources, the knowledge point does not mount any recommended resources;
and when receiving that the knowledge points are shared by the user to the sharing target, issuing all the quoted recommended resources of the knowledge points and the links thereof to the sharing target.
Further, the content added in the knowledge graph resource package is natural language processing audio, video and teaching materials, and the video and the teaching materials are processed.
Further, the processing video extracts audio from the course video through an automatic voice recognition technology and converts the audio into characters, and simultaneously, the characters appearing in the video are recognized and all stored in a corpus;
and processing the teaching materials, extracting the characters from the teaching materials shared by the teacher through an OCR character recognition technology, and storing the characters in a corpus.
The invention has the following beneficial effects:
according to the invention, two creation modes of the tree-shaped knowledge graph and the net-shaped knowledge graph are supported, so that different knowledge graph construction requirements of teachers can be met; the method has the advantages that a rich multi-mode teaching resource library is provided, and proper educational resources are actively recommended for knowledge points created by teachers, so that man-machine cooperation is realized, and the efficiency and accuracy of the teachers in constructing knowledge maps are improved; the method provides safe and reliable multi-user collaborative construction and result sharing of the knowledge patterns, can realize simultaneous online editing of the knowledge patterns by multiple teachers, shares the knowledge pattern results to student users, and guides students to learn online.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of the structure of the present invention;
FIG. 2 is a schematic flow chart of the knowledge graph of the present invention;
FIG. 3 is a schematic flow chart of the knowledge of the present invention;
fig. 4 is a flow chart of the method of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Embodiment one:
referring to fig. 1-3, the present invention is a knowledge point filling method based on man-machine collaboration knowledge graph construction.
Firstly, when a knowledge graph is created, a tree-shaped knowledge graph and a net-shaped knowledge graph can be created; adding video, teaching materials and other contents into the map resource package; the platform processes the resources such as video, teaching materials and the like into text forms and stores the text forms in a database;
then, after the user creates a knowledge point in the knowledge graph, the platform recommends the alias, definition, video, teaching material and network resource related to the knowledge point according to the name of the knowledge point; the platform adopts a natural language processing bert algorithm and variants thereof to carry out vectorization representation on knowledge points, teaching materials and video resources, the vectors are normalized, and then semantic cosine similarity can be obtained through inner products of the knowledge points, the teaching materials and the video, the semantic cosine similarity is used as one of ordering reference attributes, and the video resources and the teaching materials resources are respectively ordered according to the semantic similarity;
wherein different types of resource handling apply different variants, such as Chinese-Bert-WWM (video), XLNET (book), electric (video), for converting a text into a vector, representing the text with this vector;
the knowledge point vectors are multiplied by the teaching materials and the video vectors to obtain inner products, and the inner products are obtained by the step of obtaining the cosine similarity among the vectors because the vectors are normalized before;
the vector representations of different resources, which possibly have a plurality of attributes, have certain differences in the attribute fields contained in the vector representations, so that the semantic cosine similarity score of the vector representations needs to be adjusted and considered according to the attribute weights in the sorting process; the total similarity of the coarse row stage calculates a score item Score for each attribute x And attribute weight x The maximum value is obtained after multiplication:
the weight values of different fields in the formula are obtained by solving marked data;
for teaching material resources, calculating a semantic cosine similarity score mainly according to a long text attribute, such as a small-section content, and a short text attribute, such as a chapter name; for video resources, calculating a semantic cosine similarity score according to short text attributes such as video names, belonging course chapters, key frame OCRs and the like; in the recommending process, recommending the teaching materials and resource fragments contained in courses selected by the user in the resource package preferentially; if the resource content score with the highest score in the first step does not reach the threshold value or the number of the resource contents reaching the threshold value is small, recommending all shared resources except the resource package selected by the user in the intelligent tree official network; in addition, considering the diversity requirement of recommendation results in part of scenes, clustering candidate sets based on distance in the recommendation process, and outputting data in a plurality of classes according to service requirements;
the alias and description recommendation of the knowledge points are obtained by using a sequence labeling model of a BERT+CRF (conditional random field ) structure, the part of speech (noun, verb, predicate, graduated word, etc.) of each word in the text is obtained, and the dependency relationship among the words is obtained by using an open source analysis algorithm based on transfer.
Knowledge points are extracted from the text correctly based on the dependency relationship between the extracted parts of speech and the vocabulary, for example, a transmission control protocol can effectively ensure the transmission of a message, and a transmission control protocol is extracted correctly instead of a control protocol or a transmission control. After the complete word is obtained, extracting alias and description information corresponding to the knowledge points from the text by assistance of regular expression and other rules, sorting according to the information such as the occurrence frequency of the alias and description in the whole text, and recommending the result to the user.
The user (teacher) can view the recommended resource and its source corresponding to the knowledge point and decide not to refer or refer to the recommended resource by the user (teacher). If a reference is determined (all or part of the content of the recommended resource may be referenced), the recommended resource of the reference should be mounted on the knowledge point. Meanwhile, the system links the knowledge points with all recommended resources which are decided to be quoted by the user;
while the user is editing the knowledge point, the rest of teacher users can edit other knowledge points at the same time. When the user (teacher) decides not to refer, then the knowledge point does not mount any recommended resources.
Finally, the knowledge graph constructed by the user (teacher) can be shared with students, and the students can learn various contents of the knowledge points based on the knowledge graph. When the system receives that the user shares the knowledge point to a sharing target (student), the knowledge point and all the quoted recommended resources linked with the knowledge point are issued to the sharing target.
Example two
The contents of the first embodiment are supplemented:
the node for creating the tree-shaped knowledge graph by the user is supported by utilizing the front-end DOM technology, and the node for creating the net-shaped knowledge graph by the user is supported by utilizing the svg technology.
In this embodiment, the front-end DOM technique and the svg technique are both the prior art, and the nodes of the tree-like knowledge graph can be created by the user through the front-end DOM technique or the svg technique.
And then, carrying out data integration and processing on rich teaching resources in a system teaching resource library, processing resources such as audio, video and teaching materials based on natural language, recommending resources with proper knowledge points to a user by using a recommendation technology, extracting audio from a course video and converting the audio into characters by an automatic voice recognition technology when processing the video, and simultaneously recognizing the characters appearing in the video and storing the characters in a corpus. When the teaching materials are processed, the teaching materials shared by teachers are extracted into characters through an OCR character recognition technology, and the characters are stored in a corpus. After a teacher user establishes a knowledge point, based on natural language processing, word segmentation technology and the like, the knowledge point related information such as aliases and definitions can be recommended in a corpus, and suitable video clips, teaching material clips, other network resources and the like can be recommended for the teacher user, so that the teacher can review and edit the recommended teaching resources, and the human-computer collaborative knowledge map construction is realized. After the teacher finishes knowledge graph making, the teacher can generate links by using encryption technology to share the links with other teacher users and student users. The method comprises the steps of carrying out a first treatment on the surface of the
In this embodiment, the automatic speech recognition technology and the OCR text recognition technology are both existing mature technologies, and the automatic speech recognition technology extracts text from speech and the OCR technology extracts text from pictures.
The two embodiments described above are in use:
in the construction process of the tree-shaped knowledge graph or the net-shaped knowledge graph, a plurality of teachers can cooperate and divide work, the invention can automatically search the existing online education resource library, intelligently recommend multi-mode teaching resources related to knowledge points for the teachers, such as aliases, definitions, teaching videos, electronic teaching materials, network resources, topics and the like, and the teachers can quote and edit recommended related contents. Through man-machine cooperation based on artificial intelligence, the efficiency of a teacher for filling multi-mode resources for knowledge points of a knowledge graph can be obviously improved;
the teacher can be allowed to fill corresponding teaching resources for the knowledge points in the knowledge graph, and the teacher can actively search and fill appropriate teaching resources in a massive and numerous resource library through artificial intelligence, so that the human-computer collaborative knowledge graph construction is realized. Meanwhile, the system supports the establishment of a virtual teaching and research team, and realizes the online collaborative construction of a knowledge graph for multiple teacher users. Finally, the teacher can release the constructed knowledge graph to student users, and the students can learn various teaching resources of knowledge points on line based on the knowledge graph.
In the description of the present specification, the descriptions of the terms "one embodiment," "example," "specific example," and the like, mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The preferred embodiments of the invention disclosed above are intended only to assist in the explanation of the invention. The preferred embodiments are not exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof.
Claims (10)
1. A knowledge point filling method based on man-machine cooperation construction knowledge graph is characterized by comprising the following steps:
creating a knowledge graph, and adding content into a knowledge graph resource package;
recommending the resources related to the knowledge points through the names of the knowledge points in the created knowledge graph.
2. The knowledge point filling method based on man-machine cooperation to construct a knowledge graph according to claim 1, wherein the creating of the knowledge graph is to create a tree-shaped knowledge graph through a front-end DOM technique.
3. The knowledge point filling method based on man-machine cooperation construction of a knowledge graph according to claim 1, wherein the creating of the knowledge graph is to create a net-shaped knowledge graph by svg technology.
4. The knowledge point filling method based on man-machine cooperation to construct a knowledge graph according to claim 1, wherein the recommending the knowledge point related resource comprises:
the method comprises the steps that a BERT and related variant algorithms of natural language processing are adopted to carry out vectorization representation on knowledge points, teaching materials and video resources, and vectors are normalized;
and obtaining the semantic cosine similarity through the inner products of the knowledge points, the teaching materials and the video, and respectively sequencing the video resources and the teaching material resources according to the semantic cosine similarity.
5. The knowledge point filling method based on man-machine cooperation to construct a knowledge graph according to claim 4, wherein the sorting the video resources and the teaching material resources according to the similarity includes:
the semantic cosine similarity scores of different resources in the sorting process need to be adjusted and considered according to attribute weights, and the formula is as follows:
wherein score item Score for gross rank stage total similarity calculation x Weight for each attribute score x Is an attribute weight.
6. The knowledge point filling method based on man-machine cooperation to construct a knowledge graph according to claim 5, wherein the semantic cosine similarity is obtained by the inner product of knowledge points, teaching materials and videos, and the method comprises the following steps:
for teaching material resources, calculating a semantic cosine similarity score according to the long text attribute of the small-section content and the short text attribute of the chapter name;
for video resources, a semantic cosine similarity score is calculated from the video name, the lesson chapter to which it belongs, and the short text attribute of the key frame OCR.
7. The knowledge point filling method based on man-machine cooperation to construct a knowledge graph according to claim 1, wherein the recommending the knowledge point related resource comprises:
recommending relevant resources, wherein a recommended user selects teaching materials in a resource package and resource fragments contained in courses;
when the highest scoring resource content score does not reach the threshold or the threshold number of resource contents is small, the recommendation is made based on all shared resources except the user selected resource package.
8. The knowledge point filling method based on man-machine cooperation construction knowledge graph according to claim 1, further comprising:
for a certain knowledge point, when receiving recommended resources which are decided to be cited by a user, linking the knowledge point with all recommended resources which are decided to be cited by the user; when the user decides not to refer to the recommended resources, the knowledge point does not mount any recommended resources;
and when receiving that the knowledge points are shared by the user to the sharing target, issuing all the quoted recommended resources of the knowledge points and the links thereof to the sharing target.
9. The knowledge point filling method based on man-machine cooperation to construct a knowledge graph according to claim 1, wherein the content added in the knowledge graph resource package is natural language processing audio, video and teaching materials, and the video and the teaching materials are processed.
10. The knowledge point filling method based on man-machine cooperation to construct a knowledge graph according to claim 9, wherein the processing video extracts audio from the course video and converts the audio into characters through an automatic voice recognition technology, and simultaneously recognizes the characters appearing in the video and stores the characters in a corpus;
and processing the teaching materials, extracting the characters from the teaching materials shared by the teacher through an OCR character recognition technology, and storing the characters in a corpus.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310135279.3A CN116362331A (en) | 2023-02-17 | 2023-02-17 | Knowledge point filling method based on man-machine cooperation construction knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310135279.3A CN116362331A (en) | 2023-02-17 | 2023-02-17 | Knowledge point filling method based on man-machine cooperation construction knowledge graph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116362331A true CN116362331A (en) | 2023-06-30 |
Family
ID=86931280
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310135279.3A Pending CN116362331A (en) | 2023-02-17 | 2023-02-17 | Knowledge point filling method based on man-machine cooperation construction knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116362331A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117473963A (en) * | 2023-12-26 | 2024-01-30 | 西昌学院 | Teaching text knowledge labeling method and system for intelligent education |
-
2023
- 2023-02-17 CN CN202310135279.3A patent/CN116362331A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117473963A (en) * | 2023-12-26 | 2024-01-30 | 西昌学院 | Teaching text knowledge labeling method and system for intelligent education |
| CN117473963B (en) * | 2023-12-26 | 2024-04-12 | 西昌学院 | Teaching text knowledge labeling method and system for intelligent education |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108681574B (en) | Text abstract-based non-fact question-answer selection method and system | |
| CN109960786A (en) | Chinese Measurement of word similarity based on convergence strategy | |
| CN107247751B (en) | LDA topic model-based content recommendation method | |
| CN112214593A (en) | Question and answer processing method and device, electronic equipment and storage medium | |
| CN102955848A (en) | Semantic-based three-dimensional model retrieval system and method | |
| CN110929045B (en) | Construction method and system of poetry-semantic knowledge map | |
| CN113157885B (en) | Efficient intelligent question-answering system oriented to knowledge in artificial intelligence field | |
| CN111143672A (en) | Expert specialty scholars recommendation method based on knowledge graph | |
| CN113505209A (en) | Intelligent question-answering system for automobile field | |
| CN112685550B (en) | Intelligent question-answering method, intelligent question-answering device, intelligent question-answering server and computer readable storage medium | |
| WO2024011813A1 (en) | Text expansion method and apparatus, device, and medium | |
| CN117077792B (en) | Knowledge graph-based method and device for generating prompt data | |
| CN111460145A (en) | Learning resource recommendation method, device and storage medium | |
| CN112434142A (en) | Method for marking training sample, server, computing equipment and storage medium | |
| CN111553138B (en) | Auxiliary writing method and device for standardizing content structure document | |
| CN116541493A (en) | Interactive response method, device, equipment and storage medium based on intention recognition | |
| CN116362331A (en) | Knowledge point filling method based on man-machine cooperation construction knowledge graph | |
| CN111199151A (en) | Data processing method and data processing device | |
| CN112749556B (en) | Multi-language model training method and device, storage medium and electronic equipment | |
| CN110750632B (en) | Improved Chinese ALICE intelligent question-answering method and system | |
| CN113761887A (en) | Matching method and device based on text processing, computer equipment and storage medium | |
| CN114372454A (en) | Text information extraction method, model training method, device and storage medium | |
| CN117473034A (en) | Interactive text processing method and device, electronic equipment and storage medium | |
| CN115617974A (en) | Dialogue processing method, device, equipment and storage medium | |
| CN112085985B (en) | Student answer automatic scoring method for English examination translation questions |
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 |