CN117033665B - Method and device for aligning map knowledge points with video - Google Patents
Method and device for aligning map knowledge points with video Download PDFInfo
- Publication number
- CN117033665B CN117033665B CN202311280036.5A CN202311280036A CN117033665B CN 117033665 B CN117033665 B CN 117033665B CN 202311280036 A CN202311280036 A CN 202311280036A CN 117033665 B CN117033665 B CN 117033665B
- Authority
- CN
- China
- Prior art keywords
- vector
- knowledge
- text
- knowledge point
- teaching 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 23
- 239000013598 vector Substances 0.000 claims abstract description 133
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000010276 construction Methods 0.000 claims description 11
- 239000000463 material Substances 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 6
- 101710129069 Serine/threonine-protein phosphatase 5 Proteins 0.000 description 17
- 101710199542 Serine/threonine-protein phosphatase T Proteins 0.000 description 17
- 229920000470 poly(p-phenylene terephthalate) polymer Polymers 0.000 description 17
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—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
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/7844—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using original textual content or text extracted from visual content or transcript of audio data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention discloses a method and a device for aligning map knowledge points with videos, and belongs to the technical field of Internet. An alignment method of map knowledge points and videos comprises the following steps: acquiring a teaching video, and identifying text content marked with a time stamp in the teaching video; calculating a first vector of each sentence of text in the text content; acquiring knowledge points of courses corresponding to the teaching video; constructing an initial knowledge graph based on the knowledge points; calculating a second vector for each knowledge point; determining corresponding teaching video information for each knowledge point according to the matching values of the first vector and the second vector; and associating corresponding teaching video information for each knowledge point on the initial knowledge map to generate a final knowledge map. The invention realizes the rapid alignment of the knowledge points and the video explanation content.
Description
Technical Field
The invention belongs to the technical field of Internet, and particularly relates to an alignment method and device for map knowledge points and videos.
Background
In the teaching field, a teacher needs to prepare a teaching plan PPT, then explain the teaching plan PPT one by one according to knowledge points, recording and broadcasting equipment of a school can acquire teaching videos of the teacher and store the teaching videos of the teacher into a resource management platform, and students can grasp the conditions according to the knowledge points in a knowledge graph to find corresponding teaching videos of the lesson for review when reviewing after the lessons. When the map builder searches the video according to a certain knowledge point, the map builder does not know which video resource in the resource platform corresponding to the knowledge point and the specific time point in the video of the lesson, and can only search the lesson explanation video segments of the knowledge point by adopting a mode of fuzzy search and watching the video one by one. The existing products on the market can only generate a knowledge graph according to a teaching outline in a specific format, then manually associate classroom video resources corresponding to each knowledge point with time points, and finally complete the construction of the course knowledge graph. This approach of determining knowledge points based on manually looking up classroom video assets and watching the videos one by one is extremely inefficient.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a method and a device for aligning map knowledge points with videos.
The aim of the invention is realized by the following technical scheme: an alignment method of map knowledge points and videos comprises the following steps:
acquiring a teaching video, and identifying text content marked with a time stamp in the teaching video;
calculating a first vector of each sentence of text in the text content;
acquiring knowledge points of courses corresponding to the teaching video;
constructing an initial knowledge graph based on the knowledge points;
calculating a second vector for each knowledge point;
determining corresponding teaching video information for each knowledge point according to the matching values of the first vector and the second vector;
and associating corresponding teaching video information for each knowledge point on the initial knowledge map to generate a final knowledge map.
Further, acquiring the teaching video, and identifying text content with a timestamp in the teaching video, including:
acquiring a teaching video;
identifying a PPT with a time point in the teaching video;
and identifying the text content on the PPT to obtain the text content with the timestamp.
Further, obtaining knowledge points of courses corresponding to the teaching video includes:
acquiring a Word-format teaching outline of the teaching video corresponding to the course or a catalog photo of the electronic teaching material;
and extracting knowledge points from the teaching outline or directory photos.
Further, the first vector and the second vector are calculated by the same vector algorithm.
Further, determining corresponding teaching video information for each knowledge point according to the matching values of the first vector and the second vector includes:
calculating the matching value of each first vector and all second vectors respectively;
and determining a plurality of corresponding texts for each knowledge point according to the matching value, and determining teaching video information corresponding to the texts as video information corresponding to the knowledge points.
Further, determining a plurality of corresponding texts for each knowledge point according to the matching value, including:
for each knowledge point, determining the text corresponding to the first vectors with the highest matching values of the second vectors of the knowledge point as the text corresponding to the knowledge point.
Further, the teaching video information corresponding to each knowledge point includes an ID of the teaching video corresponding to the knowledge point and a start-stop time of the text corresponding to the knowledge point in the teaching video to which the text belongs.
An alignment device for map knowledge points and videos, comprising:
the text recognition module is used for acquiring the teaching video and recognizing text content marked with a time stamp in the teaching video;
the knowledge point acquisition module is used for acquiring knowledge points of courses corresponding to the teaching video;
the initial knowledge graph construction module is used for constructing an initial knowledge graph based on the knowledge points;
the vector calculation module is used for calculating a first vector of each sentence of text in the text content and calculating a second vector of each knowledge point;
the teaching video information determining module is used for determining corresponding teaching video information for each knowledge point according to the matching values of the first vector and the second vector;
and the final knowledge graph construction module is used for generating a final knowledge graph for associating the corresponding teaching video information with each knowledge point on the initial knowledge graph.
Further, the knowledge point acquisition module is further configured to: acquiring a Word-format teaching outline of the teaching video corresponding to the course or a catalog photo of the electronic teaching material; and extracting knowledge points from the teaching outline or directory photos.
Further, the teaching video information determining module is further configured to: calculating the matching value of each first vector and all second vectors respectively; and determining a plurality of corresponding texts for each knowledge point according to the matching value, and determining teaching video information corresponding to the texts as video information corresponding to the knowledge points.
The beneficial effects of the invention are as follows:
(1) According to the method, the number of matched videos is greatly reduced through the course ID fields in the catalogue attribute carried by the videos, and the map construction speed is higher;
(2) According to the method, the PPT resources in the video are identified for matching, so that the PPT resources can be accurately associated to the time point;
(3) The matching process is fully automatic, manual intervention is not needed, and precious human resources are saved; the map database is adopted to store knowledge points, so that mass data can be stored;
(4) The method adopts the exclusive vector calculation model algorithm aiming at different languages, so that the vector matching degree is higher;
(5) The invention stores the constructed knowledge graph by adopting the graph database, and displays the real world relationship more intuitively and naturally than the traditional relational database;
(6) The invention adopts the map database to support high-efficiency association inquiry;
(7) The invention provides a method for quickly aligning knowledge points with video explanation content, which reduces the time of a knowledge graph builder in searching videos and watching the videos one by one to confirm the time of the knowledge points in and out, and the graph builder only needs to confirm whether the content between the time of the videos in and out is accurate or not, so that more time and energy are put on business.
Drawings
FIG. 1 is a flow chart of a method for aligning knowledge points of a map with a video according to the present invention;
fig. 2 is a block diagram of an alignment device for map knowledge points and video according to the present invention.
Detailed Description
The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments, and it is apparent that the described embodiments are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by a person skilled in the art without any inventive effort, are intended to be within the scope of the present invention, based on the embodiments of the present invention.
Referring to fig. 1 to 2, the present invention provides a method and apparatus for aligning knowledge points of a map with a video:
the first aspect of the present embodiment provides a method for aligning a map knowledge point with a video, as shown in fig. 1, which includes steps S100 to S700. It should be noted that, the numbers of the steps in this embodiment do not indicate that all the steps must be performed in the order of the numbers, for example, some steps may be performed simultaneously, or some steps after the numbers may be performed before the steps before the numbers.
And S100, acquiring the teaching video, and identifying text content marked with a time stamp in the teaching video.
In some embodiments, capturing the instructional video and identifying the time-stamped text content in the instructional video includes: acquiring a teaching video; identifying a PPT with a time point in the teaching video; and recognizing the text content on the PPT by utilizing OCR to obtain the text content with the timestamp.
Specifically, firstly, a teaching video is acquired, then all PPTs contained in the teaching video are identified, the PPT is identified, meanwhile, the corresponding time point of each page of PPT in the teaching video is identified (namely, the time corresponding to each page of PPT when displayed in the teaching video is, for example, the time point corresponding to a page of PPT is the 5 th to 6 th minutes of the teaching video when displayed in the 5 th to 6 th minutes of the teaching video), then the text content in each page of PPT is identified by utilizing an OCR technology, and the time point of the text content in each page of PPT in the teaching video is the same as the time point of the page of PPT in the teaching video, so that the text content with a timestamp is obtained.
And S200, calculating a first vector of each text in the text content.
Specifically, firstly, sentence dividing is performed on text content of each page, and then, a first vector of each sentence of text is calculated respectively. In general, the first vector of each text sentence is calculated by the existing vector algorithm.
And S300, acquiring knowledge points of courses corresponding to the teaching video.
In some embodiments, obtaining knowledge points of the corresponding course of the teaching video includes: acquiring a Word-format teaching outline of the teaching video corresponding to the course or a catalog photo of the electronic teaching material; and extracting knowledge points from the teaching outline or directory photos.
In the embodiment, knowledge points are automatically acquired according to the input teaching outline and the catalogue photo of the electronic teaching material, manual input is not needed, the efficiency of knowledge graph construction is improved, and the workload of a knowledge graph constructor is reduced.
And S400, constructing an initial knowledge graph based on the knowledge points.
And S500, calculating a second vector of each knowledge point.
In general, the second vector for each knowledge point is calculated by an existing vector algorithm.
In this embodiment, the same vector algorithm is used for calculating the first vector and the second vector.
And S600, determining corresponding teaching video information for each knowledge point according to the matching values of the first vector and the second vector.
The teaching video information corresponding to the knowledge points comprises the ID of the teaching video corresponding to the knowledge points and the start and stop time of the text corresponding to the knowledge points in the teaching video. In this step, each knowledge point is associated with a corresponding teaching video according to the matching values of the first vector and the second vector, that is, the teaching video corresponding to each knowledge point and the specific start-stop time in the teaching video are found.
In some embodiments, corresponding teaching video information is determined for each knowledge point according to the matching values of the first vector and the second vector, including step S610 and step S620.
And S610, respectively calculating the matching value of each first vector and all second vectors.
Specifically, the matching value calculation is carried out on the first vector corresponding to each sentence of text in the teaching video and the second vector of all knowledge points under the course corresponding to the teaching video.
And S620, determining a plurality of corresponding texts for each knowledge point according to the matching value, and determining teaching video information corresponding to the texts as video information corresponding to the knowledge points.
For example, for a certain knowledge point, one or more first vectors with highest matching values with the second vectors of the knowledge point are screened, then texts corresponding to the screened first vectors are truly texts corresponding to the knowledge point, then teaching video information corresponding to the texts is determined to be teaching video information corresponding to the knowledge point, wherein video information corresponding to each sentence of texts comprises an ID of a teaching video to which the sentence of texts belongs and start and stop time of the sentence of texts in the teaching video to which the sentence of texts belongs.
The text corresponding to each knowledge point can be one sentence or multiple sentences, and the specific number is determined according to the actual requirement, for example, each knowledge point corresponds to three sentences of text.
And S700, associating corresponding teaching video information for each knowledge point on the initial knowledge map to generate a final knowledge map.
In this embodiment, when the user clicks each knowledge point in the final knowledge graph, the corresponding teaching video may be opened, and the user may automatically position the knowledge point to the corresponding starting position in the teaching video for playing. When a certain knowledge point is associated with multiple teaching videos, after clicking the knowledge point in a final knowledge map, presenting all teaching videos associated with the knowledge point to a user, and after the user selects the teaching video to be watched, automatically positioning the teaching video to the corresponding initial position of the knowledge point in the teaching video for playing.
In some embodiments, after calculating the first vector of each sentence of text, storing the first vector of each sentence of text, the ID of the teaching video to which the sentence of text belongs, and the start-stop time of the sentence of text in the teaching video to which the sentence of text belongs (the time point of the teaching video when a sentence of text starts to be displayed is the start time of the sentence of text, and the time point of the teaching video when the sentence of text ends to be displayed is the end time of the sentence of text) as a teaching record in a MySQL database; in general, the start and stop time of each sentence of text on the same page PPT in the affiliated teaching video is the same. After the second vector of each knowledge point is calculated, the second vector is stored in a vector database. When the matching values of the first vector and the second vector are calculated, respectively calculating the matching value of each first vector in the teaching video and the second vector of all knowledge points in the course corresponding to the teaching video in a vector database, screening out the second vector with the highest matching value with the first vector, and then adding a corresponding knowledge point mark for the first vector in a MySQL database to obtain the knowledge point corresponding to the first vector mark (the knowledge point corresponding to the first vector is the knowledge point corresponding to the second vector with the highest matching value with the first vector). When determining the corresponding text for a certain knowledge point, screening one or more first vectors with highest second vector matching values of the knowledge point, and determining the text corresponding to the first vectors as the text corresponding to the knowledge point. Generally, the number of knowledge points in a course is far less than the number of sentences of texts in the teaching video, so that the calculation amount can be reduced and the calculation efficiency can be improved by adopting the matching value calculation method in the embodiment.
In some embodiments, for a certain knowledge point under a course, when the number of texts currently corresponding to the knowledge point reaches a preset upper limit, if a text with a higher matching value appears, replacing one text with a lowest matching value in all texts currently corresponding to the knowledge point with the text with the higher matching value. The second aspect of the present embodiment provides an alignment device for a map knowledge point and a video, as shown in fig. 2, which includes a text recognition module, a knowledge point acquisition module, an initial knowledge map construction module, a vector calculation module, a teaching video information determination module, and a final knowledge map construction module.
The text recognition module is used for acquiring the teaching video and recognizing text content marked with a time stamp in the teaching video;
and the knowledge point acquisition module is used for acquiring knowledge points of courses corresponding to the teaching video.
And the initial knowledge graph construction module is used for constructing an initial knowledge graph based on the knowledge points.
And the vector calculation module is used for calculating a first vector of each sentence of text in the text content and calculating a second vector of each knowledge point.
And the teaching video information determining module is used for determining corresponding teaching video information for each knowledge point according to the matching values of the first vector and the second vector.
And the final knowledge graph construction module is used for generating a final knowledge graph for associating the corresponding teaching video information with each knowledge point on the initial knowledge graph.
In some embodiments, the knowledge point acquisition module is further to: acquiring a Word-format teaching outline of the teaching video corresponding to the course or a catalog photo of the electronic teaching material; and extracting knowledge points from the teaching outline or directory photos.
In some embodiments, the teaching video information determination module is further configured to: calculating the matching value of each first vector and all second vectors respectively; determining a plurality of corresponding texts for each knowledge point according to the matching value, and determining teaching video information corresponding to the texts as video information corresponding to the knowledge point
It should be noted that, for convenience and brevity, a person skilled in the art will clearly understand that, for the specific working process of the system or apparatus described above, reference may be made to the corresponding process in the foregoing method embodiment, and the description will not be repeated here.
The foregoing is merely a preferred embodiment of the invention, and it is to be understood that the invention is not limited to the form disclosed herein but is not to be construed as excluding other embodiments, but is capable of numerous other combinations, modifications and environments and is capable of modifications within the scope of the inventive concept, either as taught or as a matter of routine skill or knowledge in the relevant art. And that modifications and variations which do not depart from the spirit and scope of the invention are intended to be within the scope of the appended claims.
Claims (5)
1. The method for aligning the map knowledge points with the video is characterized by comprising the following steps of:
acquiring a teaching video, and identifying text content marked with a time stamp in the teaching video;
calculating a first vector of each sentence of text in the text content;
acquiring knowledge points of courses corresponding to the teaching video;
constructing an initial knowledge graph based on the knowledge points;
calculating a second vector for each knowledge point;
determining corresponding teaching video information for each knowledge point according to the matching values of the first vector and the second vector;
associating corresponding teaching video information for each knowledge point on the initial knowledge graph to generate a final knowledge graph;
acquiring the teaching video, identifying text content marked with a time stamp in the teaching video, and comprising:
acquiring a teaching video;
identifying a PPT with a time point in the teaching video;
identifying text content on the PPT to obtain text content with a timestamp mark;
determining corresponding teaching video information for each knowledge point according to the matching values of the first vector and the second vector, including:
calculating the matching value of each first vector and all second vectors respectively;
determining a plurality of corresponding texts for each knowledge point according to the matching value, and determining teaching video information corresponding to the texts as video information corresponding to the knowledge points;
determining a plurality of corresponding texts for each knowledge point according to the matching value, wherein the method comprises the following steps:
for each knowledge point, determining texts corresponding to a plurality of first vectors with highest matching values of second vectors of the knowledge point as texts corresponding to the knowledge point;
the teaching video information corresponding to each knowledge point comprises an ID of the teaching video corresponding to the knowledge point and the start-stop time of a text corresponding to the knowledge point in the teaching video to which the text belongs;
after calculating the first vector of each sentence of text, storing the first vector of each sentence of text, the ID of the teaching video to which the sentence of text belongs and the start-stop time of the sentence of text in the teaching video to which the sentence of text belongs as a teaching record into a MySQL database; the start and stop time of each sentence of text on the same page PPT in the affiliated teaching video is the same; after calculating the second vector of each knowledge point, storing the second vector into a vector database; when the matching values of the first vector and the second vector are calculated, respectively carrying out matching value calculation on each first vector in the teaching video and the second vector of all knowledge points in the course corresponding to the teaching video in a vector database, screening out the second vector with the highest matching value with the first vector, and then adding a corresponding knowledge point mark for the first vector in a MySQL database to obtain the knowledge point corresponding to the first vector mark; when determining a corresponding text for a certain knowledge point, screening one or more first vectors with highest second vector matching values of the knowledge point, and determining the text corresponding to the first vectors as the text corresponding to the knowledge point;
and for a certain knowledge point under a course, when the number of texts currently corresponding to the knowledge point reaches a preset upper limit, if a text with a higher matching value appears, replacing one text with the lowest matching value in all texts currently corresponding to the knowledge point with the text with the higher matching value.
2. The method for aligning knowledge points of a map with a video according to claim 1, wherein obtaining knowledge points of a corresponding course of the teaching video comprises:
acquiring a Word-format teaching outline of the teaching video corresponding to the course or a catalog photo of the electronic teaching material;
and extracting knowledge points from the teaching outline or directory photos.
3. The method of claim 1, wherein the first vector and the second vector are calculated by the same vector algorithm.
4. An alignment device for a map knowledge point and a video is characterized by comprising:
the text recognition module is used for acquiring the teaching video and recognizing text content marked with a time stamp in the teaching video;
the knowledge point acquisition module is used for acquiring knowledge points of courses corresponding to the teaching video;
the initial knowledge graph construction module is used for constructing an initial knowledge graph based on the knowledge points;
the vector calculation module is used for calculating a first vector of each sentence of text in the text content and calculating a second vector of each knowledge point;
the teaching video information determining module is used for determining corresponding teaching video information for each knowledge point according to the matching values of the first vector and the second vector;
the final knowledge graph construction module is used for generating a final knowledge graph for associating the corresponding teaching video information with each knowledge point on the initial knowledge graph;
the teaching video information determining module is further used for: calculating the matching value of each first vector and all second vectors respectively; determining a plurality of corresponding texts for each knowledge point according to the matching value, and determining teaching video information corresponding to the texts as video information corresponding to the knowledge points;
acquiring the teaching video, identifying text content marked with a time stamp in the teaching video, and comprising: acquiring a teaching video; identifying a PPT with a time point in the teaching video; identifying text content on the PPT to obtain text content with a timestamp mark;
determining a plurality of corresponding texts for each knowledge point according to the matching value, wherein the method comprises the following steps: for each knowledge point, determining texts corresponding to a plurality of first vectors with highest matching values of second vectors of the knowledge point as texts corresponding to the knowledge point;
the teaching video information corresponding to each knowledge point comprises an ID of the teaching video corresponding to the knowledge point and the start-stop time of a text corresponding to the knowledge point in the teaching video to which the text belongs;
after calculating the first vector of each sentence of text, storing the first vector of each sentence of text, the ID of the teaching video to which the sentence of text belongs and the start-stop time of the sentence of text in the teaching video to which the sentence of text belongs as a teaching record into a MySQL database; the start and stop time of each sentence of text on the same page PPT in the affiliated teaching video is the same; after calculating the second vector of each knowledge point, storing the second vector into a vector database; when the matching values of the first vector and the second vector are calculated, respectively carrying out matching value calculation on each first vector in the teaching video and the second vector of all knowledge points in the course corresponding to the teaching video in a vector database, screening out the second vector with the highest matching value with the first vector, and then adding a corresponding knowledge point mark for the first vector in a MySQL database to obtain the knowledge point corresponding to the first vector mark; when determining a corresponding text for a certain knowledge point, screening one or more first vectors with highest second vector matching values of the knowledge point, and determining the text corresponding to the first vectors as the text corresponding to the knowledge point;
and for a certain knowledge point under a course, when the number of texts currently corresponding to the knowledge point reaches a preset upper limit, if a text with a higher matching value appears, replacing one text with the lowest matching value in all texts currently corresponding to the knowledge point with the text with the higher matching value.
5. The device for aligning knowledge points of a map with a video according to claim 4, wherein the knowledge point acquisition module is further configured to: acquiring a Word-format teaching outline of the teaching video corresponding to the course or a catalog photo of the electronic teaching material; and extracting knowledge points from the teaching outline or directory photos.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311280036.5A CN117033665B (en) | 2023-10-07 | 2023-10-07 | Method and device for aligning map knowledge points with video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311280036.5A CN117033665B (en) | 2023-10-07 | 2023-10-07 | Method and device for aligning map knowledge points with video |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117033665A CN117033665A (en) | 2023-11-10 |
| CN117033665B true CN117033665B (en) | 2024-01-09 |
Family
ID=88641348
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311280036.5A Active CN117033665B (en) | 2023-10-07 | 2023-10-07 | Method and device for aligning map knowledge points with video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117033665B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109274913A (en) * | 2018-10-17 | 2019-01-25 | 北京竞业达数码科技股份有限公司 | A kind of video intelligent slice clipping method and system |
| CN111046194A (en) * | 2019-12-31 | 2020-04-21 | 重庆和贯科技有限公司 | Method for constructing multi-mode teaching knowledge graph |
| CN111429768A (en) * | 2020-03-17 | 2020-07-17 | 安徽爱学堂教育科技有限公司 | Knowledge point splitting and integrating method and system based on teaching recording and broadcasting |
| CN111462554A (en) * | 2020-04-22 | 2020-07-28 | 浙江蓝鸽科技有限公司 | Online classroom video knowledge point identification method and device |
| CN111898441A (en) * | 2020-06-30 | 2020-11-06 | 华中师范大学 | Online course video resource content identification and evaluation method and intelligent system |
| CN112261477A (en) * | 2020-10-22 | 2021-01-22 | 新东方教育科技集团有限公司 | Video processing method and device, training method and storage medium |
| CN113840109A (en) * | 2021-09-23 | 2021-12-24 | 杭州海宴科技有限公司 | Classroom audio and video intelligent note taking method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111738041A (en) * | 2019-09-30 | 2020-10-02 | 北京沃东天骏信息技术有限公司 | Video segmentation method, device, equipment and medium |
-
2023
- 2023-10-07 CN CN202311280036.5A patent/CN117033665B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109274913A (en) * | 2018-10-17 | 2019-01-25 | 北京竞业达数码科技股份有限公司 | A kind of video intelligent slice clipping method and system |
| CN111046194A (en) * | 2019-12-31 | 2020-04-21 | 重庆和贯科技有限公司 | Method for constructing multi-mode teaching knowledge graph |
| CN111429768A (en) * | 2020-03-17 | 2020-07-17 | 安徽爱学堂教育科技有限公司 | Knowledge point splitting and integrating method and system based on teaching recording and broadcasting |
| CN111462554A (en) * | 2020-04-22 | 2020-07-28 | 浙江蓝鸽科技有限公司 | Online classroom video knowledge point identification method and device |
| CN111898441A (en) * | 2020-06-30 | 2020-11-06 | 华中师范大学 | Online course video resource content identification and evaluation method and intelligent system |
| CN112261477A (en) * | 2020-10-22 | 2021-01-22 | 新东方教育科技集团有限公司 | Video processing method and device, training method and storage medium |
| CN113840109A (en) * | 2021-09-23 | 2021-12-24 | 杭州海宴科技有限公司 | Classroom audio and video intelligent note taking method |
Non-Patent Citations (2)
| Title |
|---|
| Process analysis of teachers’ self-regulated learning patterns in technological pedagogical content knowledge development;Lingyun Huang et al.;《Computers & Education》;1-15 * |
| 面向智能教育的多模态课程知识图谱建构与应用研究;金灵巧 等;《中国新通信》;119-121 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117033665A (en) | 2023-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109359215B (en) | Video intelligent pushing method and system | |
| CN109598995B (en) | Intelligent teaching system based on Bayesian knowledge tracking model | |
| WO2021000909A1 (en) | Curriculum optimisation method, apparatus, and system | |
| CN109698920B (en) | Follow teaching system based on internet teaching platform | |
| CN109460488B (en) | Auxiliary teaching method and system | |
| CN103605706A (en) | Knowledge map based resource retrieval method | |
| CN112115301B (en) | Video annotation method and system based on classroom notes | |
| CN108121715B (en) | Character labeling method and character labeling device | |
| CN110554995A (en) | Deep learning model management method and system | |
| CN103714094A (en) | Equipment and method for recognizing objects in video | |
| CN110753256B (en) | Video playback method and device, storage medium and computer equipment | |
| CN109785691B (en) | Method and system for assisting learning through terminal | |
| US20190272769A1 (en) | Information processing device, information processing method, and non-transitory computer readable medium storing information processing program | |
| Dang et al. | MOOC-KG: A MOOC knowledge graph for cross-platform online learning resources | |
| CN106874382A (en) | A kind of teaching resource sharing system | |
| CN105930490A (en) | Intelligent selecting system for teaching resources | |
| CN113034319A (en) | User behavior data processing method and device in teaching management, electronic equipment and storage medium | |
| CN114202978A (en) | Intelligent training method and system based on big data | |
| CN117033665B (en) | Method and device for aligning map knowledge points with video | |
| CN111488330A (en) | Digital network teaching system for medical examination morphology | |
| CN114139053A (en) | Lifelong learning resource intelligent pushing system based on credit bank and big data analysis | |
| CN111818278A (en) | Teaching video acquisition and retrieval system and method | |
| CN112115275A (en) | Knowledge graph construction method and system for math tutoring question-answering system | |
| CN112347354B (en) | Courseware management method for intelligent education | |
| CN112257438B (en) | Language knowledge processing method and device with association mechanism |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |