CN112101567A - Automatic modeling method and device based on artificial intelligence - Google Patents
Automatic modeling method and device based on artificial intelligence Download PDFInfo
- Publication number
- CN112101567A CN112101567A CN202010965902.4A CN202010965902A CN112101567A CN 112101567 A CN112101567 A CN 112101567A CN 202010965902 A CN202010965902 A CN 202010965902A CN 112101567 A CN112101567 A CN 112101567A
- Authority
- CN
- China
- Prior art keywords
- model
- model training
- training scheme
- scheme
- training
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 23
- 238000012549 training Methods 0.000 claims abstract description 182
- 238000012986 modification Methods 0.000 claims description 22
- 230000004048 modification Effects 0.000 claims description 22
- 238000003058 natural language processing Methods 0.000 claims description 9
- 238000013519 translation Methods 0.000 claims description 8
- 230000000007 visual effect Effects 0.000 claims description 8
- 238000002372 labelling Methods 0.000 claims description 6
- 238000010801 machine learning Methods 0.000 abstract description 10
- 230000000694 effects Effects 0.000 description 3
- 241000282414 Homo sapiens Species 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000007786 learning performance Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06F16/35—Clustering; Classification
- G06F16/355—Class or cluster creation or modification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Databases & Information Systems (AREA)
- Machine Translation (AREA)
Abstract
In order to solve the problem that the existing machine learning modeling threshold is high, the automatic modeling method and device based on artificial intelligence are provided, and the threshold of machine learning modeling is reduced. An automated modeling method based on artificial intelligence, comprising: generating a model training scheme selection page, wherein each selectable model training scheme in the model training scheme selection page is associated with an algorithm model suitable for the model training scheme; acquiring a target model training scheme selected by a user from a model training scheme selection page; obtaining a training sample; and training the algorithm model associated with the target model training scheme according to the training samples to generate the target model required by the user. By implementing the artificial intelligence-based automatic modeling method or adopting the artificial intelligence-based automatic modeling device for modeling, the threshold of machine learning modeling can be reduced.
Description
Technical Field
The disclosure relates to the field of modeling, in particular to an automatic modeling method and device based on artificial intelligence.
Background
In a typical machine learning application, a practitioner must perform algorithm selection and hyper-parameter optimization to maximize the predictive performance of the machine learning model. However, the related steps exceed the capability of non-experts, so that the threshold of machine learning modeling is high, and the popularization of machine learning modeling is not facilitated.
Disclosure of Invention
In order to solve at least one of the above technical problems, the present disclosure provides an automated modeling method and apparatus based on artificial intelligence, which reduces the threshold of machine learning modeling.
In a first aspect of the disclosure, an automated modeling method based on artificial intelligence includes:
generating a model training scheme selection page, wherein each selectable model training scheme in the model training scheme selection page is associated with an algorithm model suitable for the model training scheme;
acquiring a target model training scheme selected by a user from a model training scheme selection page;
obtaining a training sample;
and training the algorithm model associated with the target model training scheme according to the training samples to generate the target model required by the user.
Optionally, the method includes:
determining a model type and an algorithm model suitable for the model type according to the content to be identified by the model;
and generating a model training scheme of the model class according to the model class, and associating the model training scheme of the model class with the algorithm model suitable for the model class.
Optionally, the model training scheme in the model training scheme selection page includes one or more than two of the following model training schemes: a natural language processing model training scheme, a visual model training scheme, a translation model training scheme, a numerical analysis model training scheme and a multimedia model training scheme.
Optionally, the obtaining of the training sample includes:
acquiring a characteristic data set;
labeling the unlabeled characteristic data in the characteristic data set;
and taking all the labeled characteristic data as training samples.
Optionally, the method includes:
displaying the characteristic data and the labels thereof in the training sample;
acquiring label modification data of the characteristic data;
and modifying the label of the characteristic data corresponding to the label modification data according to the label modification data.
In a second aspect of the disclosure, an automated modeling apparatus based on artificial intelligence comprises:
the page generation module is used for generating a model training scheme selection page, and each selectable model training scheme in the model training scheme selection page is associated with an algorithm model suitable for the model training scheme;
the scheme acquisition module is used for acquiring a target model training scheme selected by a user from the model training scheme selection page;
the sample acquisition module is used for acquiring a training sample;
and the model generation module is used for training the algorithm model associated with the target model training scheme according to the training sample so as to generate the target model required by the user.
Optionally, the apparatus further comprises:
the model type determining module is used for determining the type of the model and an algorithm model suitable for the type of the model according to the content to be identified by the model;
and the association module is used for generating a model training scheme of the model category according to the model category and associating the model training scheme of the model category with the algorithm model suitable for the model category.
Optionally, the model training scheme in the model training scheme selection page includes one or more than two of the following model training schemes: a natural language processing model training scheme, a visual model training scheme, a translation model training scheme, a numerical analysis model training scheme and a multimedia model training scheme.
Optionally, obtaining a training sample includes:
acquiring a characteristic data set;
labeling the unlabeled characteristic data in the characteristic data set;
and taking all the labeled characteristic data as training samples.
Optionally, the apparatus further comprises:
and the label modification module is used for displaying the characteristic data and the labels thereof in the training samples, acquiring the label modification data of the characteristic data, and modifying the labels of the characteristic data corresponding to the label modification data according to the label modification data.
Has the advantages that: the corresponding algorithm model can be automatically matched and calculated according to the model training scheme selected by the user and the imported training sample, and the target model required by the user is generated, so that the user who learns related professional knowledge by using the inorganic device can also model, and the modeling threshold is reduced.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the disclosure and together with the description serve to explain the principles of the disclosure.
FIG. 1 is a flow diagram of a method for automated modeling based on artificial intelligence in one embodiment of the present application;
FIG. 2 is a block diagram of an automated modeling apparatus based on artificial intelligence in one embodiment of the present application.
Detailed Description
The present disclosure will be described in further detail with reference to the drawings and embodiments. It is to be understood that the specific embodiments described herein are for purposes of illustration only and are not to be construed as limitations of the present disclosure. It should be further noted that, for the convenience of description, only the portions relevant to the present disclosure are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
The execution subject can be adjusted according to specific cases, such as a server, an electronic device, a computer, and the like.
Referring to fig. 1, an automated modeling method based on artificial intelligence includes:
102, acquiring a target model training scheme selected by a user from a model training scheme selection page;
and 104, training the algorithm model associated with the target model training scheme according to the training sample to generate the target model required by the user.
Taking the method executed in the computer as an example, when the user needs to model, the user only needs to select the required model training scheme from the model training scheme selection page and import the corresponding training sample, and the computer can automatically match and calculate the corresponding algorithm model according to the model training scheme selected by the user and the imported training sample to generate the target model required by the user, so that the user who does not learn the relevant professional knowledge by the machine can model, and the modeling threshold of the user is reduced.
It will be appreciated that in the context of machine learning, a hyper-parameter is a parameter that is set to a value prior to the start of the learning process, and not parameter data obtained through training. In general, the hyper-parameters need to be optimized, and a group of optimal hyper-parameters is selected for the learning machine, so as to improve the learning performance and effect. In the application, the algorithm model related to the model training scheme and suitable for the model training scheme is also preset with the hyper-parameters of the corresponding algorithm model, so that the user modeling of the inorganic machine learning related professional knowledge is facilitated.
In an alternative embodiment, the automated modeling method based on artificial intelligence further comprises:
determining a model type and an algorithm model suitable for the model type according to the content to be identified by the model;
and generating a model training scheme of the model class according to the model class, and associating the model training scheme of the model class with the algorithm model suitable for the model class.
According to the technical scheme in the embodiment, different model types and algorithm models suitable for the model types are determined; the model training schemes of different categories are associated with applicable algorithm models, the number of the model training schemes is reduced, and the user can conveniently select the number of the target model training schemes.
The model category may include one or more than two of the following model schemes: the model training scheme can comprise one or more than two of the following model training schemes: a natural language processing model training scheme, a visual model training scheme, a translation model training scheme, a numerical analysis model training scheme and a multimedia model training scheme.
The natural language processing model aims to automatically classify texts or classify the texts according to the existing labels or deeply analyze the content of the articles and output the subject multi-level classification of the articles, the corresponding confidence coefficient and the like.
Visual models, intended to recognize and understand content in images, including image classification, object detection, OCR recognition, etc.;
a translation model, which aims to simulate the understanding of human beings to natural language by using human language and return the result expected by users, such as translating English into Chinese;
the numerical analysis model aims at analyzing numerical data, including predictive analysis and personalized recommendation.
A multimedia model, which is intended to determine user behavior by applying a prediction function based on media material; including user behavior analysis and prediction from audio or video.
The relevant contents of the model can be displayed in a natural language processing model training scheme so as to be convenient for a user to understand.
In an alternative embodiment, obtaining the training samples comprises:
acquiring a characteristic data set;
labeling the unlabeled characteristic data in the characteristic data set;
and taking all the labeled characteristic data as training samples.
Specifically, the unlabeled feature data in the feature data set can be displayed, so that a user can label the unlabeled feature data.
The imported feature data set contains the feature data which is not labeled, and the computer can display the feature data which is not labeled so as to provide the label of the feature data input by the user and generate the labeled feature data; ensure that the training samples can be used to train the model.
The feature data set may be derived from a plurality of data sources, including a relational data source, a distributed file data source, a distributed hive data source, a distributed hbase data source, a non-relational data source, and the like.
The characteristic data can be text, picture labels, multimedia and the like.
The user may label the displayed unlabeled feature data to form a label, for example, the user may label the displayed unlabeled feature data by means of picture classification, target physics delineation, text classification, and the like to form a label.
In an alternative embodiment, the method comprises:
displaying the characteristic data and the labels thereof in the training sample;
acquiring label modification data of the characteristic data;
and modifying the label of the characteristic data corresponding to the label modification data according to the label modification data.
And when the user checks the displayed characteristic data and the label thereof, judging whether an error label or an unsuitable label exists, and modifying the label when the error label or the unsuitable label exists so as to enable the generated target model to be more accurate.
In an optional embodiment, when the algorithm model associated with the target model training scheme is trained according to the training sample, the detailed information of the training is displayed, including the hyper-parameter configuration, the training progress, the training log, the evaluation information and the like.
In an alternative embodiment, after the target model is obtained through training, the target model can be deployed on a server for a user to use online and show details of model recognition.
In an optional implementation mode, the method comprises the steps of obtaining sample data input by a user, obtaining characteristic data and a label in the sample data, and judging a model training scheme selected by the user according to the characteristic data and the label. Judging whether the characteristic data is a numerical value, a video, an audio or an image; if the model training scheme is video or audio, judging that the model training scheme selected by the user is a multimedia model training scheme, if the model training scheme is a numerical value, judging that the model training scheme selected by the user is a numerical value analysis model training scheme, and if the model training scheme is an image, judging that the model training scheme selected by the user is a visual model training scheme; if the label is the character, judging whether the label is the character or the classification, if the label is the character, judging that the model training scheme selected by the user is a translation model training scheme, and if the label is the classification, judging that the model training scheme selected by the user is a natural language processing model training scheme.
Referring to fig. 2, an automated modeling apparatus based on artificial intelligence includes:
a page generation module 201, configured to generate a model training scheme selection page, where each selectable model training scheme in the model training scheme selection page is associated with an algorithm model applicable to the model training scheme;
a scheme obtaining module 202, configured to obtain a target model training scheme selected by a user from the model training scheme selection page;
a sample obtaining module 203, configured to obtain a training sample;
and the model generating module 204 is configured to train the algorithm model associated with the target model training scheme according to the training sample to generate the target model required by the user.
In an alternative embodiment, the apparatus further comprises:
the model type determining module is used for determining the type of the model and an algorithm model suitable for the type of the model according to the content to be identified by the model;
and the association module is used for generating a model training scheme of the model category according to the model category and associating the model training scheme of the model category with the algorithm model suitable for the model category.
In an alternative embodiment, the model training scenario in the model training scenario selection page includes one or more of the following model training scenarios: a natural language processing model training scheme, a visual model training scheme, a translation model training scheme, a numerical analysis model training scheme and a multimedia model training scheme.
In an alternative embodiment, obtaining training samples comprises:
acquiring a characteristic data set;
labeling the unlabeled characteristic data in the characteristic data set;
and taking all the labeled characteristic data as training samples.
In an alternative embodiment, the apparatus further comprises:
and the label modification module is used for displaying the characteristic data and the labels thereof in the training samples, acquiring the label modification data of the characteristic data, and modifying the labels of the characteristic data corresponding to the label modification data according to the label modification data.
The principle and effect of the automatic modeling device based on artificial intelligence can refer to the principle and effect of the automatic modeling method based on artificial intelligence, and the description is not repeated here.
In the description herein, reference to the description of the terms "one embodiment/mode," "some embodiments/modes," "example," "specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment/mode or example is included in at least one embodiment/mode or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to be the same embodiment/mode or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments/modes or examples. Furthermore, the various embodiments/aspects or examples and features of the various embodiments/aspects or examples described in this specification can be combined and combined by one skilled in the art without conflicting therewith.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
It will be understood by those skilled in the art that the foregoing embodiments are merely for clarity of illustration of the disclosure and are not intended to limit the scope of the disclosure. Other variations or modifications may occur to those skilled in the art, based on the foregoing disclosure, and are still within the scope of the present disclosure.
Claims (10)
1. An automated modeling method based on artificial intelligence, comprising:
generating a model training scheme selection page, wherein each selectable model training scheme in the model training scheme selection page is associated with an algorithm model suitable for the model training scheme;
acquiring a target model training scheme selected by a user from the model training scheme selection page;
obtaining a training sample;
and training the algorithm model associated with the target model training scheme according to the training sample to generate the target model required by the user.
2. The method for automated modeling based on artificial intelligence of claim 1, wherein the method comprises:
determining a model type and an algorithm model suitable for the model type according to the content to be identified by the model;
and generating a model training scheme of the model class according to the model class, and associating the model training scheme of the model class with the algorithm model suitable for the model class.
3. The method of claim 1, wherein the model training solutions in the model training solution selection page comprise one or more of the following model training solutions: a natural language processing model training scheme, a visual model training scheme, a translation model training scheme, a numerical analysis model training scheme and a multimedia model training scheme.
4. The method of claim 1, wherein the obtaining training samples comprises:
acquiring a characteristic data set;
labeling the unlabeled characteristic data in the characteristic data set;
and taking all the labeled characteristic data as training samples.
5. The method of claim 4, wherein after the training samples are obtained, the method comprises:
displaying the feature data and the labels thereof in the training sample;
acquiring label modification data of the characteristic data;
and modifying the label of the characteristic data corresponding to the label modification data according to the label modification data.
6. An automated modeling apparatus based on artificial intelligence, comprising:
the page generation module is used for generating a model training scheme selection page, and each selectable model training scheme in the model training scheme selection page is associated with an algorithm model suitable for the model training scheme;
the scheme acquisition module is used for acquiring a target model training scheme selected by a user from the model training scheme selection page;
the sample acquisition module is used for acquiring a training sample;
and the model generation module is used for training the algorithm model associated with the target model training scheme according to the training sample so as to generate the target model required by the user.
7. The automated modeling apparatus based on artificial intelligence of claim 6, further comprising:
the model type determining module is used for determining the type of the model and an algorithm model suitable for the type of the model according to the content to be identified by the model;
and the association module is used for generating a model training scheme of the model category according to the model category and associating the model training scheme of the model category with the algorithm model suitable for the model category.
8. The device of claim 6, wherein the model training solutions in the model training solution selection page comprise one or more of the following model training solutions: a natural language processing model training scheme, a visual model training scheme, a translation model training scheme, a numerical analysis model training scheme and a multimedia model training scheme.
9. The automated modeling apparatus based on artificial intelligence of claim 6, wherein obtaining training samples comprises:
acquiring a characteristic data set;
labeling the unlabeled characteristic data in the characteristic data set;
and taking all the labeled characteristic data as training samples.
10. The automated modeling apparatus based on artificial intelligence of claim 9, wherein the apparatus further comprises:
and the label modification module is used for displaying the feature data and the labels thereof in the training samples, acquiring the label modification data of the feature data, and modifying the labels of the feature data corresponding to the label modification data according to the label modification data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010965902.4A CN112101567A (en) | 2020-09-15 | 2020-09-15 | Automatic modeling method and device based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010965902.4A CN112101567A (en) | 2020-09-15 | 2020-09-15 | Automatic modeling method and device based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112101567A true CN112101567A (en) | 2020-12-18 |
Family
ID=73758605
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010965902.4A Pending CN112101567A (en) | 2020-09-15 | 2020-09-15 | Automatic modeling method and device based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112101567A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113139332A (en) * | 2021-03-31 | 2021-07-20 | 联想(北京)有限公司 | Automatic model construction method, device and equipment |
| CN115223424A (en) * | 2022-03-23 | 2022-10-21 | 北京好奇星教育科技有限公司 | Programming method and device and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109145981A (en) * | 2018-08-17 | 2019-01-04 | 上海非夕机器人科技有限公司 | Deep learning automation model training method and equipment |
| CN109325541A (en) * | 2018-09-30 | 2019-02-12 | 北京字节跳动网络技术有限公司 | Method and apparatus for training pattern |
| CN109635918A (en) * | 2018-10-30 | 2019-04-16 | 银河水滴科技（北京）有限公司 | The automatic training method of neural network and device based on cloud platform and preset model |
| US20190205791A1 (en) * | 2016-09-21 | 2019-07-04 | Equifax Inc. | Transforming attributes for training automated modeling systems |
| CN111160569A (en) * | 2019-12-30 | 2020-05-15 | 第四范式（北京）技术有限公司 | Application development method and device based on machine learning model and electronic equipment |
-
2020
- 2020-09-15 CN CN202010965902.4A patent/CN112101567A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190205791A1 (en) * | 2016-09-21 | 2019-07-04 | Equifax Inc. | Transforming attributes for training automated modeling systems |
| CN109145981A (en) * | 2018-08-17 | 2019-01-04 | 上海非夕机器人科技有限公司 | Deep learning automation model training method and equipment |
| CN109325541A (en) * | 2018-09-30 | 2019-02-12 | 北京字节跳动网络技术有限公司 | Method and apparatus for training pattern |
| CN109635918A (en) * | 2018-10-30 | 2019-04-16 | 银河水滴科技（北京）有限公司 | The automatic training method of neural network and device based on cloud platform and preset model |
| CN111160569A (en) * | 2019-12-30 | 2020-05-15 | 第四范式（北京）技术有限公司 | Application development method and device based on machine learning model and electronic equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113139332A (en) * | 2021-03-31 | 2021-07-20 | 联想(北京)有限公司 | Automatic model construction method, device and equipment |
| CN115223424A (en) * | 2022-03-23 | 2022-10-21 | 北京好奇星教育科技有限公司 | Programming method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11721230B2 (en) | Personalized learning system and method for the automated generation of structured learning assets based on user data | |
| CN110807126B (en) | Method, device, storage medium and equipment for converting article into video | |
| US20180366013A1 (en) | System and method for providing an interactive visual learning environment for creation, presentation, sharing, organizing and analysis of knowledge on subject matter | |
| Pal et al. | A semi-automatic metadata extraction model and method for video-based e-learning contents | |
| CN109949637B (en) | Automatic answering method and device for objective questions | |
| CN111524578B (en) | Psychological assessment device, method and system based on electronic psychological sand table | |
| US10936684B2 (en) | Automatically generating instructions from tutorials for search and user navigation | |
| CN112307773B (en) | Automatic generation method of custom problem data of machine reading understanding system | |
| CN110968708A (en) | Method and system for labeling education information resource attributes | |
| US20150026184A1 (en) | Methods and systems for content management | |
| CN112101567A (en) | Automatic modeling method and device based on artificial intelligence | |
| CN116049367A (en) | Visual-language pre-training method and device based on non-supervision knowledge enhancement | |
| CN116091836A (en) | Multi-mode visual language understanding and positioning method, device, terminal and medium | |
| CN114218379B (en) | Attribution method for question answering incapacity of intelligent question answering system | |
| CN109408175B (en) | Real-time interaction method and system in general high-performance deep learning calculation engine | |
| CN113259763B (en) | Teaching video processing method and device and electronic equipment | |
| Ciurez et al. | Automatic categorization of educational videos according to learning styles | |
| Angrave et al. | Creating tiktoks, memes, accessible content, and books from engineering videos? first solve the scene detection problem | |
| Valentini | Developing AVT corpora for a quantitative approach to language transfer in cinematic products | |
| Pal et al. | Enhanced metadata modelling and extraction methods to acquire contextual pedagogical information from e-learning contents for personalised learning systems | |
| Atef et al. | Automatic Identification and Extraction of Adaptive Learning Objects from Traditional Courseware | |
| CN113158644B (en) | Retrieval lattice and implicit emotion recognition method based on multitask learning | |
| US20240086452A1 (en) | Tracking concepts within content in content management systems and adaptive learning systems | |
| CN112801829B (en) | Method and device for correlation of test question prediction network model | |
| CN117454891A (en) | Seal domain information extraction method based on pre-training model |
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 |