CN109359215A - Video intelligent method for pushing and system - Google Patents
Video intelligent method for pushing and system Download PDFInfo
- Publication number
- CN109359215A CN109359215A CN201811465037.6A CN201811465037A CN109359215A CN 109359215 A CN109359215 A CN 109359215A CN 201811465037 A CN201811465037 A CN 201811465037A CN 109359215 A CN109359215 A CN 109359215A
- Authority
- CN
- China
- Prior art keywords
- video
- examination question
- knowledge
- student
- examination
- 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.)
- Granted
Links
Classifications
-
- 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 kind of video intelligent method for pushing and system, method adds examination question attribute tags to the examination question comprising steps of acquisition typing examination question；Examination question portrait is established to examination question, on the basis of the examination question attribute tags, the text semantic network of knowledge based map is established to examination question text；The analysis of student's learning outcome Check and weak item big data analysis obtain student and learn feelings portrait；Acquire instructional video, respectively in instructional video image and voice analyze, and to instructional video be marked video portrait label；Construct knowledge mapping；Building push model and video push.Video intelligent method for pushing and system of the invention pushing video while pushing examination question, video is the knowledge point explanation video recorded, the automatic processing analysis for carrying out picture and audio, obtain corresponding examination question, realization examination question is associated with video, student obtains the video explanation of corresponding knowledge point while obtaining push examination question.
Description
Technical field
The present invention relates to computers and technical field of data processing, more particularly, to a kind of video intelligent method for pushing
And system.
Background technique
With the development of internet, education sector before 10 years just promote long-distance education, by internet virtual classroom come
Realize long-distance video give lessons, electronic document it is shared, thus allow teacher and student formed on network it is a kind of give lessons with learn it is mutual
It is dynamic；And the arriving in present 4G epoch allows more convenient study not only by bulky computer, as long as one can have
The logical mobile phone of big flow is promoted by the fast network of 4G, can be more easily directly online by palms tools such as mobile phones
Study, and wireless network becomes the daily interaction of people more effectively.
The prior art discloses the examination question method for pushing and system of a kind of associated video, this method comprises: believing according to attribute
Breath marks examination question attribute information to video data marking video attribute information, and to examination question, and attribute information includes: grade, section
Mesh, version and chapters and sections；According to Video attribute information and examination question attribute information, video data and examination question are formed into mapping and closed
System；The Video attribute information for extracting the currently playing video data of student matches corresponding examination question according to mapping relations；According to
Default push rule, is pushed to student for corresponding examination question.
Video data and examination question are associated by the prior art, can be pushed and be matched according to the Video attribute information of video data
The examination question of set, so that student carries out targetedly consolidating practice.
But student receive other situations examination question push when, such as based on mistake topic etc. examination questions push etc., still without needle
Video explanation to property.
Summary of the invention
In view of this, the present invention provides a kind of video intelligent method for pushing and systems, comprising steps of
Typing examination question is acquired, examination question attribute tags are added to the examination question, the examination question attribute tags include: subject, version
Sheet, grade, chapters and sections and knowledge point determine that the core knowledge point of examination question and correlated knowledge point form examination according to examination question attribute tags
Exam pool, wherein the core knowledge point is the knowledge point that the examination question is mainly investigated, and the correlated knowledge point is in the examination question
The knowledge point relevant to the core knowledge point investigated；
Examination question portrait is established to examination question, on the basis of the examination question attribute tags, knowledge based is established to examination question text
The text semantic network of map；
The analysis of student's learning outcome Check and weak item big data analysis obtain student and learn feelings portrait: passing through student
It takes an exam to the examination question in test item bank and operation practice, from branch, overall ranking fluction analysis student's study schedule, study
Completeness and knowledge point master degree；Learning level, the student class by big data analysis student's subject in its class
In the teaching level of its grade, the student school in its regional teaching level situation, the student location teaching level situation,
Face and answer situation are examined in conjunction with the knowledge point of student examination, operation, online exercise, in conjunction with difficulty of knowledge points, the school province
It goes through past feelings of examining and precisely analyzes the study break-through point for being suitble to student to show progress；
Acquire instructional video, respectively in instructional video image and voice analyze, and instructional video is marked
Remember video portrait label；
Knowledge mapping is constructed, comprising steps of
Entity link, to voice, examination question text in video carry out the name Entity recognition based on BiLSTM+CRF algorithm into
Row entity extracts, and the entity after extraction links the same entity information on different sub- knowledge mappings, uses
CoLink unsupervised learning frame realizes entity link；
Extract knowledge mapping feature: the TranD algorithm of knowledge based TuPu method study carries out knowledge mapping feature extraction,
The context substance feature of entity, accurately portrays the entity；
Building push model and video push, comprising steps of
Knowledge based map establishes consistency or relevance between student, examination question and instructional video, utilizes knowledge mapping
It was found that the associated path between different type entity, the degree of correlation of the weight propagation algorithm computational entity node based on iteration；To
Raw, examination question and instructional video carry out Feature Semantics association；Student, examination question and instructional video are found out based on Manifold algorithm
Potential association finds out the semantic association between different labels using DN-DBpedia corpus combination ESA model；
Based on convolutional neural networks and attention Mechanism establishing examination question and video push algorithm；Region-by-region, is learned teaching material version
School, grade's progress, combining with teaching quality, student learn feelings portrait, knowledge point difficulty, knowledge point examination frequency, in conjunction with knowledge point
Map comprehensive matching, matching mention point strategy, formulate and propose a point rate, mention the optimal video of point difficulty and pushed；
By the learning data of classmate, the accurate follow-up teaching rhythm and pace of moving things is learned feelings portrait and having matched in conjunction with student and is mentioned point
Strategy carries out video push；
Precisely matching pushes high-quality elite school's essence topic after the completion of video study, consolidates learning effect, verifying Grasping level, accordingly
Data backflow student learns feelings portrait.
Preferably, the acquisition instructional video, respectively analyzes image and voice, and instructional video is marked
Video draw a portrait label, further for,
Speech recognition is carried out to the audio-frequency unit of instructional video, while recording speech recognition result, to speech recognition knot
Fruit carries out knowledge based map and carries out knowledge extraction, obtains instructional video knowledge keyword, while recording corresponding video playing
Position；
Image recognition is carried out to instructional video image section, recognition of face, optical character identification and formula is carried out respectively and knows
Not, recognition of face goes out the teacher's information in video；It is extracted, is extracted by the knowledge that optical character identification carries out knowledge based map
Knowledge point in video image and knowledge keyword out；Type video is explained for examination question, it includes examination question that optical character identification, which goes out,
Stem, answer and the text information parsed；Formulas solutions go out LaTex formula and formula structure type in video image；
The semantic analysis that knowledge based map is carried out to speech recognition result and text in picture information analyzes teaching field
Scape, the teaching scene include knowledge point range, instructional video knowledge keyword and the video type of teaching, wherein video class
Type includes examination question explanation type and knowledge point explanation type；The semanteme of knowledge based map is established to examination question attribute, examination question text
Relationship；
Marking video label, label include teaching knowledge point range, video type, teacher's information, knowledge keyword and
The video semanteme relationship of its video location, LaTex formula and formula structure type and knowledge based map, works as video type
When explaining type for examination question, label further includes examination question stem, answer and parsing.
Preferably, the learning data by classmate, precisely follow-up teaching the rhythm and pace of moving things, in conjunction with student learn feelings portrait and
It has matched and has mentioned point strategy, carried out a video push, further to establish and be associated with examination question by the chained address of the video, simultaneously
It is pushed to student.
Preferably, further includes: after student receives chained address and the examination question of video, call player to video
The instructional video stored in chained address plays out.
The invention also discloses a kind of video intelligent supplying systems, including examination question acquires equipment, instructional video acquires equipment,
Store equipment, student learns feelings statistical module, processor, building knowledge mapping module and building push model and video push
Module, wherein
The examination question acquires equipment, is connected with the processor, for acquiring typing examination question, and is sent to the processing
Device；
The instructional video acquires equipment, is connected with the processor, for acquiring instructional video, is sent to the place
Manage device；
The student learns feelings statistical module, is connected with the storage equipment, by student to the examination question in test item bank into
Row examination and operation practice, are slapped from branch, overall ranking fluction analysis student's study schedule, study completeness and knowledge point
Degree of holding；By big data analysis student's subject the learning level of its class, the student class its grade teaching water
Flat, the student school in conjunction with student examination, makees in its regional teaching level situation, the student location teaching level situation
Industry, online exercise knowledge point examination face and answer situation, go through in conjunction with difficulty of knowledge points, the school province and precisely analyze toward examining feelings
It is suitble to student show the study break-through point of progress, obtains student and learn feelings portrait and feed back to storing equipment and storing；
The processor is connected with examination question acquisition equipment, instructional video acquisition equipment and storage equipment respectively, right
The examination question adds examination question attribute tags, and the examination question attribute tags include: subject, version, grade, chapters and sections and knowledge point, root
Determine that the core knowledge point of examination question and correlated knowledge point form test item bank according to examination question attribute tags, wherein the core knowledge point
It is the knowledge point that the examination question is mainly investigated, the correlated knowledge point is investigating in the examination question with the core knowledge point phase
Examination question portrait is established to examination question in the knowledge point of pass, on the basis of the examination question attribute tags, establishes to examination question text and is based on knowing
Know the text semantic network of map, and test item bank and examination question portrait are sent to storage equipment and stored；Teaching is regarded respectively
Image and voice in frequency are analyzed, and video portrait label is marked to instructional video, are sent to storage equipment and are carried out
Storage；
The building knowledge mapping module pushes model and video push module phase with the storage equipment, building respectively
Connection is used for entity link, carries out voice, examination question text in the video of storage equipment storage based on BiLSTM+CRF algorithm
Entity recognition is named to carry out entity extraction, the entity after extraction carries out the same entity information on different sub- knowledge mappings
Link realizes entity link using CoLink unsupervised learning frame；Extract knowledge mapping feature: knowledge based TuPu method
The TranD algorithm of habit carries out knowledge mapping feature extraction, and the context substance feature of entity accurately carves the entity
It draws；
The building push model and video push module, are connected with the building knowledge mapping module, knowledge based
Map establishes consistency or relevance between student, examination question and instructional video, finds different type entity using knowledge mapping
Between associated path, the degree of correlation of the weight propagation algorithm computational entity node based on iteration；To student, examination question and teaching view
Frequency carries out Feature Semantics association；The potential association that student, examination question and instructional video are found out based on Manifold algorithm, utilizes DN-
DBpedia corpus combination ESA model finds out the semantic association between different labels；It is built based on convolutional neural networks and attention mechanism
Vertical examination question and video push algorithm；Region-by-region, teaching material version, school, grade's progress, combining with teaching quality, student learn feelings portrait,
Knowledge point difficulty, knowledge point examination frequency, in conjunction with knowledge point map comprehensive matching, matching mentions a point strategy, and formulation proposes a point rate, mentions
Point optimal video of difficulty is pushed；By the learning data of classmate, precisely the follow-up teaching rhythm and pace of moving things, is learned in conjunction with student
Feelings, which are drawn a portrait and matched, mentions a point strategy, carries out video push, by the chained address of the video and examination question, while being pushed to
It is raw.
Preferably, the examination question acquisition equipment is scanner or camera, and the instructional video acquisition equipment is camera.
Preferably, the storage equipment is cloud storage or physical store.
Preferably, in the processor respectively in instructional video image and voice analyze, and to instructional video
Be marked video portrait label, further for,
Speech recognition is carried out to the audio-frequency unit of instructional video, while recording speech recognition result, to speech recognition knot
Fruit carries out knowledge based map and carries out knowledge extraction, obtains instructional video knowledge keyword, while recording corresponding video playing
Position；
Image recognition is carried out to instructional video image section, recognition of face, optical character identification and formula is carried out respectively and knows
Not, recognition of face goes out the teacher's information in video；It is extracted, is extracted by the knowledge that optical character identification carries out knowledge based map
Knowledge point in video image and knowledge keyword out；Type video is explained for examination question, it includes examination question that optical character identification, which goes out,
Stem, answer and the text information parsed；Formulas solutions go out LaTex formula and formula structure type in video image；
The semantic analysis that knowledge based map is carried out to speech recognition result and text in picture information analyzes teaching field
Scape, the teaching scene include knowledge point range, instructional video knowledge keyword and the video type of teaching, wherein video class
Type includes examination question explanation type and knowledge point explanation type；The semanteme of knowledge based map is established to examination question attribute, examination question text
Relationship；
Marking video label, label include teaching knowledge point range, video type, teacher's information, knowledge keyword and
The video semanteme relationship of its video location, LaTex formula and formula structure type and knowledge based map, works as video type
When explaining type for examination question, label further includes examination question stem, answer and parsing.
It preferably, further include that player calls the player pair after student receives chained address and the examination question of video
The instructional video stored in the chained address of video plays out.
Video is associated with by the present invention with examination question, when pushing examination question simultaneously pushing video.
Compared with prior art, video intelligent method for pushing provided by the invention and system, at least realizing following has
Beneficial effect:
Video intelligent method for pushing and system of the invention pushing video while pushing examination question, video are knowing for recording
Know point explanation video, the automatic processing analysis for carrying out picture and audio obtains corresponding examination question, realizes the pass of examination question and video
Connection, student obtain the video explanation of corresponding knowledge point while obtaining push examination question.
Certainly, implementing any of the products of the present invention specific needs while must not reach all the above technical effect.
By referring to the drawings to the detailed description of exemplary embodiment of the present invention, other feature of the invention and its
Advantage will become apparent.
Detailed description of the invention
It is combined in the description and the attached drawing for constituting part of specification shows the embodiment of the present invention, and even
With its explanation together principle for explaining the present invention.
Fig. 1 is video intelligent method for pushing flow chart in embodiment 1；
Fig. 2 is video intelligent supplying system structural schematic diagram in embodiment 2；
Fig. 3 is video intelligent supplying system structural schematic diagram in embodiment 3.
Specific embodiment
Carry out the various exemplary embodiments of detailed description of the present invention now with reference to attached drawing.It should also be noted that unless in addition having
Body explanation, the unlimited system of component and the positioned opposite of step, numerical expression and the numerical value otherwise illustrated in these embodiments is originally
The range of invention.
Be to the description only actually of at least one exemplary embodiment below it is illustrative, never as to the present invention
And its application or any restrictions used.
Technology, method and apparatus known to person of ordinary skill in the relevant may be not discussed in detail, but suitable
In the case of, the technology, method and apparatus should be considered as part of specification.
It is shown here and discuss all examples in, any occurrence should be construed as merely illustratively, without
It is as limitation.Therefore, other examples of exemplary embodiment can have different values.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, then in subsequent attached drawing does not need that it is further discussed.
Embodiment 1:
In conjunction with Fig. 1, a kind of video intelligent method for pushing is present embodiments provided, specifically includes the following steps:
Step 101: acquisition typing examination question adds examination question attribute tags to the examination question, and the examination question attribute tags include:
Subject, version, grade, chapters and sections and knowledge point determine the core knowledge point and correlated knowledge point of examination question according to examination question attribute tags
Form test item bank, wherein the core knowledge point is the knowledge point that the examination question is mainly investigated, and the correlated knowledge point is described
The knowledge point relevant to the core knowledge point investigated in examination question；
The mode for acquiring typing examination question network can be acquired after editor by the way of uploading, can also be using scanning
The mode that instrument uploads after being scanned.
Step 102: examination question portrait being established to examination question, on the basis of the examination question attribute tags, examination question text is established
The text semantic network of knowledge based map；
Step 103: the analysis of student's learning outcome Check and weak item big data analysis obtain student and learn feelings portrait:
It is taken an exam by student to the examination question in test item bank and operation is practiced, learnt from branch, the overall ranking fluction analysis student
Progress, study completeness and knowledge point master degree；By big data analysis student's subject its class learning level,
The student class is taught in the teaching level of its grade, the student school in its regional teaching level situation, the student location
Level condition is learned, face and answer situation are examined in conjunction with the knowledge point of student examination, operation, online exercise, in conjunction with knowledge point hardly possible
Degree, the school province go through past feelings of examining and precisely analyze the study break-through point for being suitble to student to show progress；
Step 104: acquisition instructional video, respectively in instructional video image and voice analyze, and to teaching regard
Video portrait label is marked in frequency；
It is uploaded after recording instructional video by camera, instructional video here can be specifically for some knowledge point
, specifically instructional video is to be also possible to based on core knowledge point for examination question explanation.
Specifically, the method for step 104 is as follows:
Speech recognition is carried out to the audio-frequency unit of instructional video, while recording speech recognition result, to speech recognition knot
Fruit carries out knowledge based map and carries out knowledge extraction, obtains instructional video knowledge keyword, while recording corresponding video playing
Position；
Image recognition is carried out to instructional video image section, recognition of face, optical character identification and formula is carried out respectively and knows
Not, recognition of face goes out the teacher's information in video；It is extracted, is extracted by the knowledge that optical character identification carries out knowledge based map
Knowledge point in video image and knowledge keyword out；Type video is explained for examination question, it includes examination question that optical character identification, which goes out,
Stem, answer and the text information parsed；Formulas solutions go out LaTex formula and formula structure type in video image；
The semantic analysis that knowledge based map is carried out to speech recognition result and text in picture information analyzes teaching field
Scape, the teaching scene include knowledge point range, instructional video knowledge keyword and the video type of teaching, wherein video class
Type includes examination question explanation type and knowledge point explanation type；The semanteme of knowledge based map is established to examination question attribute, examination question text
Relationship；
Marking video label, label include teaching knowledge point range, video type, teacher's information, knowledge keyword and
The video semanteme relationship of its video location, LaTex formula and formula structure type and knowledge based map, works as video type
When explaining type for examination question, label further includes examination question stem, answer and parsing.
Step 105: building knowledge mapping, specific as follows:
Entity link, to voice, examination question text in video carry out the name Entity recognition based on BiLSTM+CRF algorithm into
Row entity extracts, and the entity after extraction links the same entity information on different sub- knowledge mappings, uses
CoLink unsupervised learning frame realizes entity link；
Extract knowledge mapping feature: the TranD algorithm of knowledge based TuPu method study carries out knowledge mapping feature extraction,
The context substance feature of entity, accurately portrays the entity；
Step 106: building push model and video push, comprising steps of
The step of building push model: knowledge based map establish consistency between student, examination question and instructional video or
Relevance finds the associated path between different type entity using knowledge mapping, and the weight propagation algorithm based on iteration calculates real
The degree of correlation of body node；Feature Semantics association is carried out to student, examination question and instructional video；Find out based on Manifold algorithm
Raw, examination question and instructional video potential association, finds out the language between different labels using DN-DBpedia corpus combination ESA model
Justice association；
Based on convolutional neural networks and attention Mechanism establishing examination question and video push algorithm；
The step of video push: region-by-region, teaching material version, school, grade's progress, combining with teaching quality, student learn feelings and draw
Picture, knowledge point difficulty, knowledge point are taken an examination frequency, and in conjunction with knowledge point map comprehensive matching, matching mentions a point strategy, are formulated and are mentioned point
Rate mentions the optimal video of point difficulty and is pushed；
By the learning data of classmate, the accurate follow-up teaching rhythm and pace of moving things is learned feelings portrait and having matched in conjunction with student and is mentioned point
Strategy carries out video push；
Precisely matching pushes high-quality elite school's essence topic after the completion of video study, consolidates learning effect, verifying Grasping level, accordingly
Data backflow student learns feelings portrait.
The learning data by classmate, precisely the follow-up teaching rhythm and pace of moving things, learns feelings portrait in conjunction with student and has matched
Strategy is mentioned point, a video push is carried out, further to establish and be associated with examination question by the chained address of the video, be pushed to simultaneously
Student.
After further comprising the steps of: chained address and the examination question that student receives video, call player to video certainly
Chained address in store instructional video play out.
The present invention can have following several application scenarios:
1, the video push under student's mistake topic scene:
Feelings portrait, examination question portrait matching video portrait are learned based on student, most matched examination question explanation video is retrieved and pushes away
Give student.
2, the examination question push under student's weakness knowledge point:
Based on student's portrait, learn weak knowledge point analysis as a result, retrieving most matched knowledge point explanation video and pushing away
Give student.
3, the study practice examination question push after instructional video study:
Based on student's portrait, video portrait, retrieves most matched examination question and be pushed to student.Occur in video knowledge point or
When knowledge keyword, most matched examination question or knowledge point explanation will be retrieved based on student's portrait, knowledge point or knowledge keyword
Video is simultaneously pushed to student.
Embodiment 2:
In conjunction with Fig. 2, a kind of video intelligent supplying system, including examination question acquisition equipment 201, teaching view are present embodiments provided
Frequency acquisition equipment 202, storage equipment 205, student learn feelings statistical module 203, processor 204, building knowledge mapping module 206,
And building pushes model and video push module 207, wherein
The examination question acquires equipment 201, is connected with the processor 204, for acquiring typing examination question, and is sent to institute
State processor 204；
The instructional video acquires equipment 202, is connected with the processor 204, for acquiring instructional video, is sent to
The processor 204；
The student learns feelings statistical module 203, is connected with the storage equipment 205, by student in test item bank
Examination question takes an exam and operation practice, from branch, overall ranking fluction analysis student's study schedule, study completeness and knows
Know point master degree；By big data analysis student's subject in the learning level of its class, the student class in its grade
Teaching level, the student school examine in its regional teaching level situation, the student location teaching level situation in conjunction with student
Examination, operation, the knowledge point examination face of online exercise and answer situation, go through smart toward feelings are examined in conjunction with difficulty of knowledge points, the school province
Standard, which is analyzed, is suitble to student show the study break-through point of progress, obtains student and learn feelings portrait and feed back to storing equipment 205 and storing；
The processor 204, acquires equipment 201 with the examination question respectively and instructional video acquisition equipment 202 is connected, right
The examination question adds examination question attribute tags, and the examination question attribute tags include: subject, version, grade, chapters and sections and knowledge point, root
Determine that the core knowledge point of examination question and correlated knowledge point form test item bank according to examination question attribute tags, wherein the core knowledge point
It is the knowledge point that the examination question is mainly investigated, the correlated knowledge point is investigating in the examination question with the core knowledge point phase
Examination question portrait is established to examination question in the knowledge point of pass, on the basis of the examination question attribute tags, establishes to examination question text and is based on knowing
Know the text semantic network of map, and test item bank and examination question portrait are sent to storage equipment 205 and stored；Respectively to teaching
Image and voice in video are analyzed, and video portrait label is marked to instructional video, are sent to storage equipment 205
It is stored；
The building knowledge mapping module 206 pushes model and video push with the storage equipment 205, building respectively
Module 207 is connected, and is used for entity link, and voice, examination question text are based in the video stored to storage equipment 205
The name Entity recognition of BiLSTM+CRF algorithm carries out entity extraction, and the entity after extraction will be on different sub- knowledge mappings
Same entity information is linked, and realizes entity link using CoLink unsupervised learning frame；Extract knowledge mapping feature: base
Knowledge mapping feature extraction, the context substance feature of entity, to the reality are carried out in the TranD algorithm of knowledge mapping feature learning
Body is accurately portrayed；
The building push model and video push module 207, are connected with the building knowledge mapping module 206, structure
Build push model: knowledge based map establishes the consistency or relevance between student, examination question and instructional video, utilizes knowledge
Map finds the associated path between different type entity, the degree of correlation of the weight propagation algorithm computational entity node based on iteration；
Feature Semantics association is carried out to student, examination question and instructional video；Student, examination question and teaching view are found out based on Manifold algorithm
The potential association of frequency finds out the semantic association between different labels using DN-DBpedia corpus combination ESA model；Based on convolution mind
Through network and attention Mechanism establishing examination question and video push algorithm；Region-by-region, teaching material version, school, grade's progress, in conjunction with religion
Quality, student feelings portrait, knowledge point difficulty, knowledge point examination frequency are learned, in conjunction with knowledge point map comprehensive matching, matching is mentioned
Point strategy, formulation propose a point rate, mention the optimal video of point difficulty and pushed；By the learning data of classmate, precisely with
Into the teaching rhythm and pace of moving things, learns feelings portrait in conjunction with student and matched and mention point strategy, a progress video push, by the chained address of the video
With examination question, while it being pushed to student.
The examination question acquisition equipment 201 is scanner or camera, and the instructional video acquisition equipment 202 is camera.
The storage equipment 205 is cloud storage or physical store.
In the processor 204 respectively in instructional video image and voice analyze, and to instructional video carry out
Marking video draw a portrait label, further for,
Speech recognition is carried out to the audio-frequency unit of instructional video, while recording speech recognition result, to speech recognition knot
Fruit carries out knowledge based map and carries out knowledge extraction, obtains instructional video knowledge keyword, while recording corresponding video playing
Position；
Image recognition is carried out to instructional video image section, recognition of face, optical character identification and formula is carried out respectively and knows
Not, recognition of face goes out the teacher's information in video；It is extracted, is extracted by the knowledge that optical character identification carries out knowledge based map
Knowledge point in video image and knowledge keyword out；Type video is explained for examination question, it includes examination question that optical character identification, which goes out,
Stem, answer and the text information parsed；Formulas solutions go out LaTex formula and formula structure type in video image；
The semantic analysis that knowledge based map is carried out to speech recognition result and text in picture information analyzes teaching field
Scape, the teaching scene include knowledge point range, instructional video knowledge keyword and the video type of teaching, wherein video class
Type includes examination question explanation type and knowledge point explanation type；The semanteme of knowledge based map is established to examination question attribute, examination question text
Relationship；
Marking video label, label include teaching knowledge point range, video type, teacher's information, knowledge keyword and
The video semanteme relationship of its video location, LaTex formula and formula structure type and knowledge based map, works as video type
When explaining type for examination question, label further includes examination question stem, answer and parsing.
Embodiment 3,
On the basis of embodiment 2, the video intelligent supplying system in the present embodiment further includes player 208, Xue Shengjie
After the chained address and the examination question that receive video, call the player 208 to the instructional video stored in the chained address of video
It plays out.
Through the foregoing embodiment it is found that video intelligent method for pushing provided by the invention and system, at least realize as follows
The utility model has the advantages that
Video intelligent method for pushing and system of the invention pushing video while pushing examination question, video are knowing for recording
Know point explanation video, the automatic processing analysis for carrying out picture and audio obtains corresponding examination question, realizes the pass of examination question and video
Connection, student obtain the video explanation of corresponding knowledge point while obtaining push examination question.
Although some specific embodiments of the invention are described in detail by example, the skill of this field
Art personnel it should be understood that example above merely to being illustrated, the range being not intended to be limiting of the invention.The skill of this field
Art personnel are it should be understood that can without departing from the scope and spirit of the present invention modify to above embodiments.This hair
Bright range is defined by the following claims.
Claims (9)
1. a kind of video intelligent method for pushing, which is characterized in that comprising steps of
Typing examination question is acquired, examination question attribute tags are added to the examination question, the examination question attribute tags include: subject, version, year
Grade, chapters and sections and knowledge point determine that the core knowledge point of examination question and correlated knowledge point form test item bank according to examination question attribute tags,
Wherein, the core knowledge point is the knowledge point that the examination question is mainly investigated, and the correlated knowledge point is investigated in the examination question
Knowledge point relevant to the core knowledge point；
Examination question portrait is established to examination question, on the basis of the examination question attribute tags, knowledge based map is established to examination question text
Text semantic network；
The analysis of student's learning outcome Check and weak item big data analysis obtain student and learn feelings portrait: by student to examination
Examination question in exam pool takes an exam and operation practice, completes from branch, overall ranking fluction analysis student's study schedule, study
Degree and knowledge point master degree；By big data analysis student's subject in the learning level of its class, the student class at it
The teaching level of grade, the student school in its regional teaching level situation, the student location teaching level situation, in conjunction with
Student examination, operation, the knowledge point examination face of online exercise and answer situation, go through past in conjunction with difficulty of knowledge points, the school province
It examines feelings and precisely analyzes the study break-through point for being suitble to student to show progress；
Acquire instructional video, respectively in instructional video image and voice analyze, and view is marked to instructional video
Frequency portrait label；
Knowledge mapping is constructed, comprising steps of
Entity link carries out the name Entity recognition based on BiLSTM+CRF algorithm to voice, examination question text in video and carries out in fact
Body extracts, and the entity after extraction links the same entity information on different sub- knowledge mappings, using CoLink without
Supervised learning frame realizes entity link；
Extract knowledge mapping feature: the TranD algorithm of knowledge based TuPu method study carries out knowledge mapping feature extraction, entity
Context substance feature, which is accurately portrayed；
Building push model and video push, comprising steps of
Knowledge based map establishes consistency or relevance between student, examination question and instructional video, is found using knowledge mapping
Associated path between different type entity, the degree of correlation of the weight propagation algorithm computational entity node based on iteration；To student, examination
Topic and instructional video carry out Feature Semantics association；The potential of student, examination question and instructional video is found out based on Manifold algorithm
Association, finds out the semantic association between different labels using DN-DBpedia corpus combination ESA model；
Based on convolutional neural networks and attention Mechanism establishing examination question and video push algorithm；Region-by-region, teaching material version, school,
Grade's progress, combining with teaching quality, student learn feelings portrait, knowledge point difficulty, knowledge point examination frequency, in conjunction with knowledge point map
Comprehensive matching, matching mention point strategy, formulate and propose a point rate, mention the optimal video of point difficulty and pushed；
By the learning data of classmate, the accurate follow-up teaching rhythm and pace of moving things, in conjunction with student learn feelings portrait and having matched mention it is point tactful,
Carry out video push；
Precisely matching pushes high-quality elite school's essence topic after the completion of video study, consolidates learning effect, verifying Grasping level, corresponding data
The student that flows back learns feelings portrait.
2. video intelligent method for pushing according to claim 1, which is characterized in that the acquisition instructional video is right respectively
Image and voice are analyzed, and to instructional video be marked video portrait label, further for,
Speech recognition is carried out to the audio-frequency unit of instructional video, while recording speech recognition result, to speech recognition result into
Row knowledge based map carries out knowledge extraction, obtains instructional video knowledge keyword, while recording corresponding video playing position；
Image recognition is carried out to instructional video image section, carries out recognition of face, optical character identification and formulas solutions respectively,
Recognition of face goes out the teacher's information in video；It is extracted, is extracted by the knowledge that optical character identification carries out knowledge based map
Knowledge point and knowledge keyword in video image；Type video is explained for examination question, it includes examination question topic that optical character identification, which goes out,
The text information of dry, answer and parsing；Formulas solutions go out LaTex formula and formula structure type in video image；
The semantic analysis that knowledge based map is carried out to speech recognition result and text in picture information, analyzes teaching scene,
The teaching scene includes knowledge point range, instructional video knowledge keyword and the video type of teaching, wherein video type packet
Include examination question explanation type and knowledge point explanation type；The semantic relation of knowledge based map is established to examination question attribute, examination question text；
Marking video label, label include knowledge point range, video type, teacher's information, knowledge keyword and its view of teaching
The video semanteme relationship of frequency position, LaTex formula and formula structure type and knowledge based map, when video type is examination
When topic explanation type, label further includes examination question stem, answer and parsing.
3. video intelligent method for pushing according to claim 1, which is characterized in that the study number by classmate
According to, the accurate follow-up teaching rhythm and pace of moving things, learn feelings portrait in conjunction with student and matched and mention point strategy, carry out a video push, further for, by
The chained address of the video is associated with examination question foundation, while being pushed to student.
4. video intelligent method for pushing according to claim 2, which is characterized in that further include: student receives video
Behind chained address and the examination question, player is called to play out the instructional video stored in the chained address of video.
5. a kind of video intelligent supplying system, which is characterized in that including examination question acquisition equipment, instructional video acquisition equipment, storage
Equipment, student learn feelings statistical module, processor, building knowledge mapping module and building push model and video push module,
Wherein,
The examination question acquires equipment, is connected with the processor, for acquiring typing examination question, and is sent to the processor；
The instructional video acquires equipment, is connected with the processor, for acquiring instructional video, is sent to the processing
Device；
The student learns feelings statistical module, is connected with the storage equipment, is examined by student the examination question in test item bank
Examination and operation practice, from branch, overall ranking fluction analysis student's study schedule, study completeness and knowledge point master degree；
By big data analysis student's subject the learning level of its class, the student class its grade teaching level, should
Student school in its regional teaching level situation, the student location teaching level situation, in conjunction with student examination, operation,
The knowledge point examination face and answer situation of line practice, in conjunction with difficulty of knowledge points, the school province go through toward examine feelings precisely analyze it is suitable
Student shows the study break-through point of progress, obtain student learn feelings portrait feed back to storage equipment store；
The processor is connected, to described respectively with examination question acquisition equipment, instructional video acquisition equipment and storage equipment
Examination question adds examination question attribute tags, and the examination question attribute tags include: subject, version, grade, chapters and sections and knowledge point, according to examination
Topic attribute tags determine that the core knowledge point of examination question and correlated knowledge point form test item bank, wherein the core knowledge point is institute
State the knowledge point that examination question is mainly investigated, the correlated knowledge point be investigated in the examination question it is relevant to the core knowledge point
Knowledge point establishes examination question portrait to examination question, on the basis of the examination question attribute tags, establishes knowledge based figure to examination question text
The text semantic network of spectrum, and test item bank and examination question portrait are sent to storage equipment and stored；Respectively in instructional video
Image and voice analyzed, and to instructional video be marked video portrait label, be sent to storage equipment stored；
The building knowledge mapping module is connected with the storage equipment, building push model and video push module respectively,
For entity link, the name based on BiLSTM+CRF algorithm is carried out to voice, examination question text in the video of storage equipment storage
Entity recognition carries out entity extraction, and the same entity information on different sub- knowledge mappings is carried out chain by the entity after extraction
It connects, realizes entity link using CoLink unsupervised learning frame；Extract knowledge mapping feature: knowledge based TuPu method study
TranD algorithm carry out knowledge mapping feature extraction, the context substance feature of entity accurately portrays the entity；
The building push model and video push module, are connected with the building knowledge mapping module, knowledge based map
The consistency or relevance between student, examination question and instructional video are established, using between knowledge mapping discovery different type entity
Associated path, the degree of correlation of the weight propagation algorithm computational entity node based on iteration；To student, examination question and instructional video into
The association of row Feature Semantics；The potential association that student, examination question and instructional video are found out based on Manifold algorithm, utilizes DN-
DBpedia corpus combination ESA model finds out the semantic association between different labels；It is built based on convolutional neural networks and attention mechanism
Vertical examination question and video push algorithm；Region-by-region, teaching material version, school, grade's progress, combining with teaching quality, student learn feelings portrait,
Knowledge point difficulty, knowledge point examination frequency, in conjunction with knowledge point map comprehensive matching, matching mentions a point strategy, and formulation proposes a point rate, mentions
Point optimal video of difficulty is pushed；By the learning data of classmate, precisely the follow-up teaching rhythm and pace of moving things, is learned in conjunction with student
Feelings, which are drawn a portrait and matched, mentions a point strategy, carries out video push, by the chained address of the video and examination question, while being pushed to
It is raw.
6. video intelligent supplying system according to claim 5, which is characterized in that the examination question acquisition equipment is scanner
Or camera, the instructional video acquisition equipment is camera.
7. video intelligent supplying system according to claim 5, which is characterized in that the storage equipment is cloud storage or object
Reason storage.
8. video intelligent supplying system according to claim 5, which is characterized in that regarded respectively to teaching in the processor
Image and voice in frequency are analyzed, and to instructional video be marked video portrait label, further for,
Speech recognition is carried out to the audio-frequency unit of instructional video, while recording speech recognition result, to speech recognition result into
Row knowledge based map carries out knowledge extraction, obtains instructional video knowledge keyword, while recording corresponding video playing position；
Image recognition is carried out to instructional video image section, carries out recognition of face, optical character identification and formulas solutions respectively,
Recognition of face goes out the teacher's information in video；It is extracted, is extracted by the knowledge that optical character identification carries out knowledge based map
Knowledge point and knowledge keyword in video image；Type video is explained for examination question, it includes examination question topic that optical character identification, which goes out,
The text information of dry, answer and parsing；Formulas solutions go out LaTex formula and formula structure type in video image；
The semantic analysis that knowledge based map is carried out to speech recognition result and text in picture information, analyzes teaching scene,
The teaching scene includes knowledge point range, instructional video knowledge keyword and the video type of teaching, wherein video type packet
Include examination question explanation type and knowledge point explanation type；The semantic relation of knowledge based map is established to examination question attribute, examination question text；
Marking video label, label include knowledge point range, video type, teacher's information, knowledge keyword and its view of teaching
The video semanteme relationship of frequency position, LaTex formula and formula structure type and knowledge based map, when video type is examination
When topic explanation type, label further includes examination question stem, answer and parsing.
9. video intelligent supplying system according to claim 5, which is characterized in that further include player, student receives
Behind the chained address of video and examination question, the player is called to broadcast the instructional video stored in the chained address of video
It puts.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811465037.6A CN109359215B (en) | 2018-12-03 | 2018-12-03 | Video intelligent pushing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811465037.6A CN109359215B (en) | 2018-12-03 | 2018-12-03 | Video intelligent pushing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109359215A true CN109359215A (en) | 2019-02-19 |
| CN109359215B CN109359215B (en) | 2023-08-22 |
Family
ID=65330830
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811465037.6A Active CN109359215B (en) | 2018-12-03 | 2018-12-03 | Video intelligent pushing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109359215B (en) |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110021213A (en) * | 2019-05-14 | 2019-07-16 | 上海乂学教育科技有限公司 | Mathematics preamble learning method in artificial intelligence study |
| CN110196939A (en) * | 2019-04-26 | 2019-09-03 | 上海理工大学 | Text emphasis tagging system and method based on examination question examination point |
| CN110489648A (en) * | 2019-08-15 | 2019-11-22 | 上海乂学教育科技有限公司 | Education resource dynamic pushing method and system |
| CN111061856A (en) * | 2019-06-06 | 2020-04-24 | 北京理工大学 | Knowledge perception-based news recommendation method |
| CN111125339A (en) * | 2019-11-26 | 2020-05-08 | 华南师范大学 | Test question recommendation method based on formal concept analysis and knowledge graph |
| CN111225235A (en) * | 2020-01-16 | 2020-06-02 | 北京合众美华教育投资有限公司 | Method for playing network teaching video |
| CN111597305A (en) * | 2020-05-15 | 2020-08-28 | 法政国际教育投资有限公司 | Entity marking method, entity marking device, computer equipment and storage medium |
| CN111611434A (en) * | 2020-05-19 | 2020-09-01 | 深圳康佳电子科技有限公司 | Online course interaction method and interaction platform |
| CN111626902A (en) * | 2020-05-30 | 2020-09-04 | 苏州才豪电子科技有限公司 | Online education management system and method based on block chain |
| 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 |
| TWI707296B (en) * | 2019-05-09 | 2020-10-11 | 麥奇數位股份有限公司 | Smart teaching consultant generation method, system, equipment and storage medium |
| CN111783709A (en) * | 2020-07-09 | 2020-10-16 | 中国科学技术大学 | Information prediction method and device for education video |
| CN111798138A (en) * | 2020-07-07 | 2020-10-20 | 广州视源电子科技股份有限公司 | Data processing method, computer storage medium and related equipment |
| CN111815274A (en) * | 2020-07-03 | 2020-10-23 | 北京字节跳动网络技术有限公司 | Information processing method and device and electronic equipment |
| CN112163027A (en) * | 2020-09-30 | 2021-01-01 | 华院数据技术(上海)有限公司 | Django and LaTeX-based mathematical test question and paper combining system and method |
| CN112163118A (en) * | 2020-09-28 | 2021-01-01 | 北京爱论答科技有限公司 | Recommended video acquisition method and device for teaching |
| CN112231522A (en) * | 2020-09-24 | 2021-01-15 | 北京奥鹏远程教育中心有限公司 | Online course knowledge tree generation association method |
| CN112287037A (en) * | 2020-10-23 | 2021-01-29 | 大连东软教育科技集团有限公司 | Multi-entity mixed knowledge graph construction method and device and storage medium |
| CN112883226A (en) * | 2021-03-29 | 2021-06-01 | 读书郎教育科技有限公司 | Intelligent classroom learning video recommendation method |
| CN113434036A (en) * | 2021-05-26 | 2021-09-24 | 上海慕知文化传媒有限公司 | AR augmented reality teaching material auxiliary system |
| CN113505238A (en) * | 2021-07-09 | 2021-10-15 | 北京小谛机器人科技有限公司 | Semantic map construction method and device |
| CN113742496A (en) * | 2021-09-10 | 2021-12-03 | 国网江苏省电力有限公司电力科学研究院 | Power knowledge learning system and method based on heterogeneous resource fusion |
| CN114241835A (en) * | 2021-11-17 | 2022-03-25 | 北京执象科技发展有限公司 | Student spoken language quality evaluation method and device |
| CN116501892A (en) * | 2023-05-06 | 2023-07-28 | 广州番禺职业技术学院 | Training knowledge graph construction method based on automatic following system of Internet of things |
| CN116823557A (en) * | 2023-08-30 | 2023-09-29 | 南通四建集团有限公司 | Interactive training management method and system for safety education of construction workers |
| CN116955589A (en) * | 2023-09-19 | 2023-10-27 | 山东山大鸥玛软件股份有限公司 | Intelligent proposition method, system, proposition terminal and storage medium based on teaching material knowledge graph |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013091434A1 (en) * | 2011-12-23 | 2013-06-27 | Liu Zhuochen | Intelligent interaction system for video teaching |
| GB201501437D0 (en) * | 2015-01-28 | 2015-03-11 | Canon Kk | Client-driven push of resources by a server device |
| US20150099256A1 (en) * | 2013-12-17 | 2015-04-09 | Chien Cheng Liu | Intelligent teaching and tutoring test method |
| WO2016112679A1 (en) * | 2015-01-14 | 2016-07-21 | 百度在线网络技术（北京）有限公司 | Method, system and storage medium for realizing intelligent answering of questions |
| CN106951439A (en) * | 2017-02-13 | 2017-07-14 | 广东小天才科技有限公司 | The examination question method for pushing and system of a kind of associated video |
| CN108596472A (en) * | 2018-04-20 | 2018-09-28 | 贵州金符育才教育科技有限公司 | A kind of the artificial intelligence tutoring system and method for natural sciences study |
| CN108664649A (en) * | 2018-05-17 | 2018-10-16 | 深圳习习网络科技有限公司 | Knowledge content method for pushing, device and push server |
| CN108900366A (en) * | 2018-09-26 | 2018-11-27 | 江苏曲速教育科技有限公司 | Uniform data central management system and its management method |
-
2018
- 2018-12-03 CN CN201811465037.6A patent/CN109359215B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013091434A1 (en) * | 2011-12-23 | 2013-06-27 | Liu Zhuochen | Intelligent interaction system for video teaching |
| US20150099256A1 (en) * | 2013-12-17 | 2015-04-09 | Chien Cheng Liu | Intelligent teaching and tutoring test method |
| WO2016112679A1 (en) * | 2015-01-14 | 2016-07-21 | 百度在线网络技术（北京）有限公司 | Method, system and storage medium for realizing intelligent answering of questions |
| GB201501437D0 (en) * | 2015-01-28 | 2015-03-11 | Canon Kk | Client-driven push of resources by a server device |
| CN106951439A (en) * | 2017-02-13 | 2017-07-14 | 广东小天才科技有限公司 | The examination question method for pushing and system of a kind of associated video |
| CN108596472A (en) * | 2018-04-20 | 2018-09-28 | 贵州金符育才教育科技有限公司 | A kind of the artificial intelligence tutoring system and method for natural sciences study |
| CN108664649A (en) * | 2018-05-17 | 2018-10-16 | 深圳习习网络科技有限公司 | Knowledge content method for pushing, device and push server |
| CN108900366A (en) * | 2018-09-26 | 2018-11-27 | 江苏曲速教育科技有限公司 | Uniform data central management system and its management method |
Non-Patent Citations (1)
| Title |
|---|
| 刘一然;骆力明;: "基于知识图谱的学科单选题考点提取研究", 计算机应用研究, no. 06 * |
Cited By (37)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110196939A (en) * | 2019-04-26 | 2019-09-03 | 上海理工大学 | Text emphasis tagging system and method based on examination question examination point |
| TWI707296B (en) * | 2019-05-09 | 2020-10-11 | 麥奇數位股份有限公司 | Smart teaching consultant generation method, system, equipment and storage medium |
| CN110021213A (en) * | 2019-05-14 | 2019-07-16 | 上海乂学教育科技有限公司 | Mathematics preamble learning method in artificial intelligence study |
| CN111061856B (en) * | 2019-06-06 | 2022-05-27 | 北京理工大学 | Knowledge perception-based news recommendation method |
| CN111061856A (en) * | 2019-06-06 | 2020-04-24 | 北京理工大学 | Knowledge perception-based news recommendation method |
| CN110489648A (en) * | 2019-08-15 | 2019-11-22 | 上海乂学教育科技有限公司 | Education resource dynamic pushing method and system |
| 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 |
| CN111125339B (en) * | 2019-11-26 | 2023-05-09 | 华南师范大学 | Test question recommendation method based on formal concept analysis and knowledge graph |
| CN111125339A (en) * | 2019-11-26 | 2020-05-08 | 华南师范大学 | Test question recommendation method based on formal concept analysis and knowledge graph |
| CN111225235A (en) * | 2020-01-16 | 2020-06-02 | 北京合众美华教育投资有限公司 | Method for playing network teaching video |
| CN111597305A (en) * | 2020-05-15 | 2020-08-28 | 法政国际教育投资有限公司 | Entity marking method, entity marking device, computer equipment and storage medium |
| CN111597305B (en) * | 2020-05-15 | 2020-12-22 | 法政国际教育投资有限公司 | Entity marking method, entity marking device, computer equipment and storage medium |
| CN111611434A (en) * | 2020-05-19 | 2020-09-01 | 深圳康佳电子科技有限公司 | Online course interaction method and interaction platform |
| CN111626902A (en) * | 2020-05-30 | 2020-09-04 | 苏州才豪电子科技有限公司 | Online education management system and method based on block chain |
| CN111815274A (en) * | 2020-07-03 | 2020-10-23 | 北京字节跳动网络技术有限公司 | Information processing method and device and electronic equipment |
| CN111798138A (en) * | 2020-07-07 | 2020-10-20 | 广州视源电子科技股份有限公司 | Data processing method, computer storage medium and related equipment |
| CN111783709B (en) * | 2020-07-09 | 2022-09-06 | 中国科学技术大学 | Information prediction method and device for education video |
| CN111783709A (en) * | 2020-07-09 | 2020-10-16 | 中国科学技术大学 | Information prediction method and device for education video |
| CN112231522B (en) * | 2020-09-24 | 2021-09-14 | 北京奥鹏远程教育中心有限公司 | Online course knowledge tree generation association method |
| CN112231522A (en) * | 2020-09-24 | 2021-01-15 | 北京奥鹏远程教育中心有限公司 | Online course knowledge tree generation association method |
| CN112163118A (en) * | 2020-09-28 | 2021-01-01 | 北京爱论答科技有限公司 | Recommended video acquisition method and device for teaching |
| CN112163027B (en) * | 2020-09-30 | 2021-10-22 | 华院计算技术(上海)股份有限公司 | Django and LaTeX-based mathematical test question and paper combining system and method |
| CN112163027A (en) * | 2020-09-30 | 2021-01-01 | 华院数据技术(上海)有限公司 | Django and LaTeX-based mathematical test question and paper combining system and method |
| CN112287037A (en) * | 2020-10-23 | 2021-01-29 | 大连东软教育科技集团有限公司 | Multi-entity mixed knowledge graph construction method and device and storage medium |
| CN112883226A (en) * | 2021-03-29 | 2021-06-01 | 读书郎教育科技有限公司 | Intelligent classroom learning video recommendation method |
| CN112883226B (en) * | 2021-03-29 | 2023-05-26 | 读书郎教育科技有限公司 | Intelligent classroom learning video recommendation method |
| CN113434036A (en) * | 2021-05-26 | 2021-09-24 | 上海慕知文化传媒有限公司 | AR augmented reality teaching material auxiliary system |
| CN113434036B (en) * | 2021-05-26 | 2024-02-20 | 上海慕知文化传媒有限公司 | AR augmented reality teaching material auxiliary system |
| CN113505238A (en) * | 2021-07-09 | 2021-10-15 | 北京小谛机器人科技有限公司 | Semantic map construction method and device |
| CN113742496A (en) * | 2021-09-10 | 2021-12-03 | 国网江苏省电力有限公司电力科学研究院 | Power knowledge learning system and method based on heterogeneous resource fusion |
| CN114241835A (en) * | 2021-11-17 | 2022-03-25 | 北京执象科技发展有限公司 | Student spoken language quality evaluation method and device |
| CN116501892A (en) * | 2023-05-06 | 2023-07-28 | 广州番禺职业技术学院 | Training knowledge graph construction method based on automatic following system of Internet of things |
| CN116501892B (en) * | 2023-05-06 | 2024-03-29 | 广州番禺职业技术学院 | Training knowledge graph construction method based on automatic following system of Internet of things |
| CN116823557A (en) * | 2023-08-30 | 2023-09-29 | 南通四建集团有限公司 | Interactive training management method and system for safety education of construction workers |
| CN116823557B (en) * | 2023-08-30 | 2023-11-17 | 南通四建集团有限公司 | Interactive training management method and system for safety education of construction workers |
| CN116955589A (en) * | 2023-09-19 | 2023-10-27 | 山东山大鸥玛软件股份有限公司 | Intelligent proposition method, system, proposition terminal and storage medium based on teaching material knowledge graph |
| CN116955589B (en) * | 2023-09-19 | 2024-01-30 | 山东山大鸥玛软件股份有限公司 | Intelligent proposition method, system, proposition terminal and storage medium based on teaching material knowledge graph |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109359215B (en) | 2023-08-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109359215A (en) | Video intelligent method for pushing and system | |
| CN107203953B (en) | Teaching system based on internet, expression recognition and voice recognition and implementation method thereof | |
| Ye et al. | Recognizing american sign language gestures from within continuous videos | |
| CN109940627B (en) | Man-machine interaction method and system for picture book reading robot | |
| CN107133303A (en) | Method and apparatus for output information | |
| CN109388700A (en) | A kind of intension recognizing method and system | |
| Temkar et al. | Internet of things for smart classrooms | |
| CN109583429A (en) | A kind of method and device for the middle application topic that corrects an examination paper | |
| CN108648535A (en) | A kind of tutoring system and its operation method based on the mobile terminals VR technology | |
| CN104021326B (en) | A kind of Teaching Methods and foreign language teaching aid | |
| CN110446063A (en) | Generation method, device and the electronic equipment of video cover | |
| CN112163162B (en) | Method for recommending selected courses based on portrait identification, storage medium and electronic equipment | |
| CN111428175A (en) | Micro-expression recognition-based online course recommendation method and related equipment | |
| CN107544956B (en) | Text key point detection method and system | |
| CN109446891A (en) | A kind of interactive learning methods based on image recognition, electronic equipment and storage medium | |
| CN113610680A (en) | AI-based interactive reading material personalized recommendation method and system | |
| WO2022012605A1 (en) | Pre-trained deep neural network model-based user churn prediction system | |
| CN110245253B (en) | Semantic interaction method and system based on environmental information | |
| CN117055724A (en) | Generating type teaching resource system in virtual teaching scene and working method thereof | |
| CN109754653A (en) | A kind of method and system of individualized teaching | |
| CN111985282A (en) | Learning ability training and evaluating system | |
| CN116825288A (en) | Autism rehabilitation course recording method and device, electronic equipment and storage medium | |
| CN109299805B (en) | Artificial intelligence-based online education course request processing method | |
| CN107886791A (en) | A kind of intelligent sharing method and its system based on teaching data | |
| CN115527404A (en) | Artificial intelligence self-adaptation interactive teaching system |
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 |