CN110532344A - Automatic Selected Topic System based on deep neural network model - Google Patents
Automatic Selected Topic System based on deep neural network model Download PDFInfo
- Publication number
- CN110532344A CN110532344A CN201910722781.8A CN201910722781A CN110532344A CN 110532344 A CN110532344 A CN 110532344A CN 201910722781 A CN201910722781 A CN 201910722781A CN 110532344 A CN110532344 A CN 110532344A
- Authority
- CN
- China
- Prior art keywords
- neural network
- network model
- deep neural
- topic
- user
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention relates to a kind of automatic Selected Topic System based on deep neural network model, comprising: user input equipment, for receiving several keywords of user's input;Grade authentication equipment identifies for the bodily form to active user, to obtain the corresponding VIP grade of active user;Data mapping device is connect with the grade authentication equipment, the number of plies of the hidden layer for mapping out the deep neural network model for analysis of selecting a topic based on the corresponding VIP grade of active user;The selected topic executes equipment, it is connect respectively with the user input equipment and the data mapping device, several keywords for being inputted based on user and the deep neural network model for analysis of selecting a topic obtain the thesis topic that the deep neural network model output layer exports.Through the invention, when user's VIP higher grade, the selected topic of acquisition is more convenient for subsequent thesis writing more close to technology itself.
Description
Technical field
The present invention relates to thesis topic selection field more particularly to a kind of automatic selected topic systems based on deep neural network model
System.
Background technique
The selected topic is the first step of thesis writing key, the quality of direct relation paper.As the saying goes: " the good literary half of topic ".Choosing
Thesis topic is selected usually it is noted that the following:
(1) associative learning and reality of work are wanted, profession and research interest according to known to oneself, appropriate selection have theory
With the project of practice significance;
(2) thesis writing is selected a topic preferably small unsuitable big, as long as having oneself one to obtain on academic a certain field or certain point
Opinion, successfully experience or failure lesson or new viewpoint and understanding, have substance in speech, read it is beneficial, so that it may as
The selected topic;
(3) documents and materials to be checked when thesis writing is selected a topic, both can be appreciated that others reaches to the research of this problem
Degree can also use for reference other research achievement to this problem.
It may be noted that the existing relationship of the title of the thesis writing selected topic and paper is not again the same thing.Title is in selected topic base
It is drafted on plinth, is the high level overview of the selected topic, but selected a topic and write and should not be limited by title, sometimes in writing process, choosing
Inscribe unchanged, title several modified variations.
Currently, the selected topic of paper is not limited only to artificial raw mode, it, being capable of basis in some thesis writing assistants
The keyword of user's input is selected a topic automatically, however the grade difference of user that automatic selected topic mode at present does not account for,
The choosing that not only can guarantee that various class users completed the automatic selected topic therefore, it is necessary to one kind but also different brackets user service difference can be embodied
Topic mechanism.
Summary of the invention
To solve the above-mentioned problems, the present invention provides a kind of automatic Selected Topic System based on deep neural network model,
The VIP grade that each user can be obtained under targetedly image recognition mode provides not according to the different VIP grades of user
With the deep neural network model for analysis of selecting a topic of depth to obtain the deep neural network model output layer output
Thesis topic, to not only can guarantee that various class users completed the automatic selected topic but also can embody different brackets user service difference.
According to an aspect of the present invention, a kind of automatic Selected Topic System based on deep neural network model is provided, it is described
System includes:
User input equipment is arranged in writing article terminal, for receiving several keywords of user's input, the number
A keyword is for user i.e. by the selection of the thesis topic of Paper Writing;
Grade authentication equipment is connect with the user input equipment, is identified for the bodily form to active user, to obtain
Obtain the corresponding VIP grade of active user;
Data mapping device is connect with the grade authentication equipment, for based on the corresponding VIP grade mapping of active user
The number of plies for the hidden layer of the deep neural network model for analysis of selecting a topic out;
The selected topic executes equipment, connect respectively with the user input equipment and the data mapping device, for based on use
Several keywords that family inputs and the deep neural network model for analysis of selecting a topic obtain the deep neural network model
The thesis topic of output layer output;
Ethernet connecting interface executes equipment with the selected topic and connect, for based on several keywords from the whole network
One or more bibliography corresponding one including several keywords are retrieved in each reference data base
A or multiple bibliography topics;
Wherein, it is executed in equipment in the selected topic, the input layer of the deep neural network model for analysis of selecting a topic
What is be entered is several keywords;
Wherein, the grade authentication equipment includes image sensing cell, adaptive recursive filtering unit, image enhancing unit
With bodily form recognition unit, described image sensing unit, the adaptive recursive filtering unit, described image enhancement unit and described
Bodily form recognition unit is linked in sequence, and the image sensing that described image sensing unit is used to carry out active user the bodily form operates, with
Obtain corresponding active user's image;
Wherein, it is executed in equipment in the selected topic, uses several keywords and one or more of reference texts
Topic is offered to be trained the deep neural network model for analysis of selecting a topic.
According to another aspect of the present invention, a kind of automatic Topic Selection based on deep neural network model is additionally provided,
The method includes using a kind of such as above-mentioned automatic Selected Topic System based on deep neural network model, for being used according to current
The VIP grade at family gives different thesis topic selection strategies, to realize the user management of distinctiveness.
Wherein, for deep neural network model, the concept of deep learning is derived from the research of artificial neural network.Contain
The multilayer perceptron of more hidden layers is exactly a kind of deep learning structure.Deep learning is more abstracted by combination low-level feature formation
High level indicates attribute classification or feature, to find that the distributed nature of data indicates.
Multilayer neural network refers to that single computation layer perceptron can only solve the problems, such as linear separability, and a large amount of classification problem is
Linearly inseparable.Overcoming the effective way of this limitation of single computation layer perceptron is, draws between input layer and output layer
Enter hidden layer (hidden layer number can be greater than or equal to 1) as input pattern " internal representation ", single computation layer perceptron becomes more
(calculating) layer perceptron.
The concept of deep learning was proposed by Hinton et al. in 2006.It is proposed based on deep Belief Network (DBN) non-supervisory greedy
The layer-by-layer training algorithm of the heart brings hope to solve the relevant optimization problem of deep structure, then proposes that multilayer autocoder is deep
Layer structure.Furthermore the convolutional neural networks that Lecun et al. is proposed are first real multilayered structure learning algorithms, it utilizes space
Relativeness reduces number of parameters to improve training performance.
Deep learning is a new field in machine learning research, and motivation is that foundation, simulation human brain are divided
The neural network of study is analysed, it imitates the mechanism of human brain to explain data, such as image, sound and text.
The present invention needs to have inventive point crucial at following two:
(1) the VIP grade of on-site identification active user gives different thesis topic selection strategies based on different VIP grades,
To realize the user management of distinctiveness;
(2) the trainable deep neural network model for analysis of selecting a topic is introduced to provide different thesis topic selection plans
Slightly.
Detailed description of the invention
Embodiment of the present invention is described below with reference to attached drawing, in which:
Fig. 1 is the structure according to the automatic Selected Topic System based on deep neural network model shown in embodiment of the present invention
Block diagram.
Fig. 2 is the input according to the automatic Selected Topic System based on deep neural network model shown in embodiment of the present invention
Interface schematic diagram.
Fig. 3 is the selected topic according to the automatic Selected Topic System based on deep neural network model shown in embodiment of the present invention
Result schematic diagram.
Specific embodiment
The embodiment of automatic Selected Topic System to of the invention based on deep neural network model below with reference to accompanying drawings
It is described in detail.
The paper used in current thesis writing assistant is selected a topic automatically mechanism or does not account for the rank difference of user
It is different, or only rambunctiously using allow using with do not allow using two kinds of limited ways, can not carry out both can guarantee it is various etc.
Grade user completes the automatic selected topic can embody the technical effect of different brackets user service difference again.
In order to overcome above-mentioned deficiency, the present invention has built a kind of automatic Selected Topic System based on deep neural network model,
It can effectively solve the problem that corresponding technical problem.
Fig. 1 is the structure according to the automatic Selected Topic System based on deep neural network model shown in embodiment of the present invention
Block diagram, the system comprises:
User input equipment is arranged in writing article terminal, for receiving several keywords of user's input, the number
A keyword is for user i.e. by the selection of the thesis topic of Paper Writing;
Grade authentication equipment is connect with the user input equipment, is identified for the bodily form to active user, to obtain
Obtain the corresponding VIP grade of active user;
Data mapping device is connect with the grade authentication equipment, for based on the corresponding VIP grade mapping of active user
The number of plies for the hidden layer of the deep neural network model for analysis of selecting a topic out;
The selected topic executes equipment, connect respectively with the user input equipment and the data mapping device, for based on use
Several keywords that family inputs and the deep neural network model for analysis of selecting a topic obtain the deep neural network model
The thesis topic of output layer output;
Ethernet connecting interface executes equipment with the selected topic and connect, for based on several keywords from the whole network
One or more bibliography corresponding one including several keywords are retrieved in each reference data base
A or multiple bibliography topics;
Wherein, it is executed in equipment in the selected topic, the input layer of the deep neural network model for analysis of selecting a topic
What is be entered is several keywords;
Wherein, the grade authentication equipment includes image sensing cell, adaptive recursive filtering unit, image enhancing unit
With bodily form recognition unit, described image sensing unit, the adaptive recursive filtering unit, described image enhancement unit and described
Bodily form recognition unit is linked in sequence, and the image sensing that described image sensing unit is used to carry out active user the bodily form operates, with
Obtain corresponding active user's image;
Wherein, it is executed in equipment in the selected topic, uses several keywords and one or more of reference texts
Topic is offered to be trained the deep neural network model for analysis of selecting a topic.
Then, continue the automatic Selected Topic System to of the invention based on deep neural network model specific structure carry out into
The explanation of one step.
Can also include: in the automatic Selected Topic System based on deep neural network model
Data storage device executes equipment with the Ethernet connecting interface, the selected topic respectively and the grade identifies
Equipment connection, for storing the corresponding VIP grade of active user.
In the automatic Selected Topic System based on deep neural network model:
The data storage device is also used to store several keywords and one or more of bibliography topics.
In the automatic Selected Topic System based on deep neural network model:
The data storage device is also connect with the data mapping device, for storing the depth mind for the analysis that is used to select a topic
The number of plies of hidden layer through network model.
In the automatic Selected Topic System based on deep neural network model:
The data storage device is one of FLASH flash memory or SDRAM memory.
In the automatic Selected Topic System based on deep neural network model:
The user input equipment is one of touch display screen or push-button array.
In the automatic Selected Topic System based on deep neural network model:
In the grade authentication equipment, the adaptive recursive filtering unit is connect with described image sensing unit, is used
In the adaptive recursive filtering processing of active user's image progress to receiving.
In the automatic Selected Topic System based on deep neural network model:
In the grade authentication equipment, described image enhancement unit is connect with the adaptive recursive filtering unit, is used
The image enhancement processing based on exponential transform is executed in the output data to the adaptive recursive filtering unit.
In the automatic Selected Topic System based on deep neural network model:
In the grade authentication equipment, the bodily form recognition unit is connect with described image enhancement unit, for institute
The identification of the bodily form of the output data execution active user of image enhancing unit is stated, to obtain the corresponding VIP grade of active user;
Wherein, output of the bodily form recognition unit based on each legitimate user's benchmark bodily form to described image enhancement unit
Data execute the identification of the bodily form of active user, to obtain the corresponding VIP grade of active user.
Meanwhile in order to overcome above-mentioned deficiency, the present invention has also built a kind of automatic choosing based on deep neural network model
Topic method is used for root the method includes using a kind of such as above-mentioned automatic Selected Topic System based on deep neural network model
Different thesis topic selection strategies is given, according to the VIP grade of active user to realize the user management of distinctiveness.
Fig. 2 is the input according to the automatic Selected Topic System based on deep neural network model shown in embodiment of the present invention
Interface schematic diagram.
As shown in Fig. 2, carry out undergraduate degree academic dissertation selected topic operation interface in, provide multiple input frames with
Corresponding a variety of keywords are inputted for user, a variety of keywords execute the input parameter of equipment as the selected topic to execute
Automatic selected topic operation.
Wherein, a variety of keywords include colleges and universities' title, major name, tutor's name and pass relevant to paper field
Keyword.
Fig. 3 is the selected topic according to the automatic Selected Topic System based on deep neural network model shown in embodiment of the present invention
Result schematic diagram.
As shown in figure 3, providing 7 candidate Article Titles after the selected topic execution equipment is selected a topic automatically for user's choosing
It selects, for example, user can choose the candidate Article Titles of serial number 2: computer network security is brief talked as this writing just
Formula Article Titles are to be used for subsequent thesis writing.
In addition, deep neural network algorithm, that is, DNN algorithm, is novel in an industry and academia in recent years machine
The popular topic of learning areas.Previous discrimination is successfully improved a significant class by DNN algorithm.
Artificial neural network originate from the forties in last century, first neuron models be nineteen forty-three McCulloch and
What Pitts was proposed, referred to as threshold logic, the function of some logical operations may be implemented in it.Henceforth, nerve net
The research of network is divided into both direction, and one is absorbed in the process of Bioinformatics, referred to as biological neural network;One is absorbed in
In engineer application, referred to as artificial neural network.
Until the proposition of depth networks (deep network) in 2006 and deep learning (deep learning) concept,
Neural network starts to shine the new life of a wheel again.Depth network is exactly profound neural network from literal upper understanding.As for
Why not continue to use pervious term " multilayer neural network ", individual conjecture may be in order to pervious neural network phase region
Point, indicate that this is a new concept.This noun was created by the Geoff Hinton study group of University of Toronto in 2006.
In fact, what this depth network that Hinton study group proposes do not have not from structure and traditional multi-layer perception (MLP)
Together, algorithm is also the same and when doing supervised learning.It is not both uniquely that this network is wanted before doing supervised learning
Unsupervised learning is first done, is then trained the weight that unsupervised learning is acquired as the initial value of supervised learning.This changes
Change corresponds to a reasonable hypothesis in fact.We carry out the number that pre-training obtains to network with P (x) expression with unsupervised learning
According to a kind of expression, (such as BP algorithm) then is trained to network with supervised learning, obtains P (Y | X), wherein Y is output
(such as class label).The hypothesis thinks that the study of P (X) facilitates the study of P (Y | X).This study thinking is relative to simple
Supervised learning for help to reduce the risk of over-fitting because it has not only learnt conditional probability distribution P (Y | X), also
The joint probability distribution of X and Y are learnt.The reason of facilitating deep learning about pre-training, there are also other explanations, wherein most straight
The explanation connect is that pre-training trains network parameter to one group of suitable initial value, can enable cost function from this group of initial value
Reach a lower value, but Erhan's et al. experiments have shown that not necessarily such.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.
In addition, term " first ", " second " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance
Or implicitly indicate the quantity of indicated technical characteristic.Define " first " as a result, the feature of " second " can be expressed or
Implicitly include at least one this feature.
Although the present invention is disclosed as above with embodiment, it is not intended to limit the invention, any technical field
Those of ordinary skill should can make change appropriate and same replacement without departing from the spirit and scope of the present invention.
Therefore protection scope of the present invention should be subject to the range that the claim of this application defined.
Claims (10)
1. a kind of automatic Selected Topic System based on deep neural network model, the system comprises:
User input equipment is arranged in writing article terminal, for receiving several keywords of user's input, several passes
Keyword is for user i.e. by the selection of the thesis topic of Paper Writing;
Grade authentication equipment is connect with the user input equipment, is identified for the bodily form to active user, to be worked as
The corresponding VIP grade of preceding user;
Data mapping device is connect with the grade authentication equipment, for mapping out use based on the corresponding VIP grade of active user
In the number of plies of the hidden layer of the deep neural network model of selected topic analysis;
The selected topic executes equipment, connect respectively with the user input equipment and the data mapping device, for defeated based on user
The several keywords entered and the deep neural network model for analysis of selecting a topic obtain the deep neural network model output
The thesis topic of layer output;
Ethernet connecting interface executes equipment with the selected topic and connect, for based on several keywords from each of the whole network
Retrieved in reference data base one or more bibliography including several keywords it is corresponding one or
Multiple bibliography topics;
Wherein, it is executed in equipment in the selected topic, the input layer of the deep neural network model for analysis of selecting a topic is defeated
What is entered is several keywords;
Wherein, the grade authentication equipment includes image sensing cell, adaptive recursive filtering unit, image enhancing unit and body
Shape recognition unit, described image sensing unit, the adaptive recursive filtering unit, described image enhancement unit and the bodily form
Recognition unit is linked in sequence, and the image sensing that described image sensing unit is used to carry out active user the bodily form operates, to obtain
Corresponding active user's image;
Wherein, it executes in equipment in the selected topic, is inscribed using several keywords and one or more of bibliography
Mesh is trained the deep neural network model for analysis of selecting a topic.
2. the automatic Selected Topic System based on deep neural network model as described in claim 1, which is characterized in that the system
Further include:
Data storage device executes equipment and the grade authentication equipment with the Ethernet connecting interface, the selected topic respectively
Connection, for storing the corresponding VIP grade of active user.
3. the automatic Selected Topic System based on deep neural network model as claimed in claim 2, it is characterised in that:
The data storage device is also used to store several keywords and one or more of bibliography topics.
4. the automatic Selected Topic System based on deep neural network model as claimed in claim 3, it is characterised in that:
The data storage device is also connect with the data mapping device, for storing the depth nerve net for the analysis that is used to select a topic
The number of plies of the hidden layer of network model.
5. the automatic Selected Topic System based on deep neural network model as claimed in claim 4, it is characterised in that:
The data storage device is one of FLASH flash memory or SDRAM memory.
6. the automatic Selected Topic System based on deep neural network model as claimed in claim 5, it is characterised in that:
The user input equipment is one of touch display screen or push-button array.
7. the automatic Selected Topic System based on deep neural network model as claimed in claim 6, it is characterised in that:
In the grade authentication equipment, the adaptive recursive filtering unit is connect with described image sensing unit, for pair
The active user's image received carries out adaptive recursive filtering processing.
8. the automatic Selected Topic System based on deep neural network model as claimed in claim 7, it is characterised in that:
In the grade authentication equipment, described image enhancement unit is connect with the adaptive recursive filtering unit, for pair
The output data of the adaptive recursive filtering unit executes the image enhancement processing based on exponential transform.
9. the automatic Selected Topic System based on deep neural network model as claimed in claim 8, it is characterised in that:
In the grade authentication equipment, the bodily form recognition unit is connect with described image enhancement unit, for the figure
The output data of image intensifying unit executes the identification of the bodily form of active user, to obtain the corresponding VIP grade of active user;
Wherein, the bodily form recognition unit is based on each legitimate user's benchmark bodily form to the output data of described image enhancement unit
The identification of the bodily form of active user is executed, to obtain the corresponding VIP grade of active user.
10. a kind of automatic Topic Selection based on deep neural network model, a kind of such as claim the method includes providing
Any automatic Selected Topic System based on deep neural network model of 1-9, for being given according to the VIP grade of active user
Different thesis topic selection strategy, to realize the user management of distinctiveness.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910722781.8A CN110532344A (en) | 2019-08-06 | 2019-08-06 | Automatic Selected Topic System based on deep neural network model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910722781.8A CN110532344A (en) | 2019-08-06 | 2019-08-06 | Automatic Selected Topic System based on deep neural network model |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110532344A true CN110532344A (en) | 2019-12-03 |
Family
ID=68662221
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910722781.8A Pending CN110532344A (en) | 2019-08-06 | 2019-08-06 | Automatic Selected Topic System based on deep neural network model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110532344A (en) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104598439A (en) * | 2013-10-30 | 2015-05-06 | 阿里巴巴集团控股有限公司 | Title correction method and device of information object and method for pushing information object |
CN105550216A (en) * | 2015-12-03 | 2016-05-04 | 百度在线网络技术(北京)有限公司 | Searching method and device of academic research information and excavating method and device of academic research information |
CN105765566A (en) * | 2013-06-27 | 2016-07-13 | 谷歌公司 | Automatic generation of headlines |
CN106383817A (en) * | 2016-09-29 | 2017-02-08 | 北京理工大学 | Paper title generation method capable of utilizing distributed semantic information |
CN106502985A (en) * | 2016-10-20 | 2017-03-15 | 清华大学 | A kind of neural network modeling approach and device for generating title |
CN107766940A (en) * | 2017-11-20 | 2018-03-06 | 北京百度网讯科技有限公司 | Method and apparatus for generation model |
CN107977363A (en) * | 2017-12-20 | 2018-05-01 | 北京百度网讯科技有限公司 | Title generation method, device and electronic equipment |
CN108647209A (en) * | 2018-05-10 | 2018-10-12 | 北京理工大学珠海学院 | A kind of topic generation method based on mind map |
CN108703505A (en) * | 2018-05-25 | 2018-10-26 | 钱文伟 | Automation computer desk based on user's identification |
CN109918643A (en) * | 2019-01-24 | 2019-06-21 | 平安科技(深圳)有限公司 | A kind of word creation generation method, device, computer equipment and storage medium |
-
2019
- 2019-08-06 CN CN201910722781.8A patent/CN110532344A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105765566A (en) * | 2013-06-27 | 2016-07-13 | 谷歌公司 | Automatic generation of headlines |
CN104598439A (en) * | 2013-10-30 | 2015-05-06 | 阿里巴巴集团控股有限公司 | Title correction method and device of information object and method for pushing information object |
CN105550216A (en) * | 2015-12-03 | 2016-05-04 | 百度在线网络技术(北京)有限公司 | Searching method and device of academic research information and excavating method and device of academic research information |
CN106383817A (en) * | 2016-09-29 | 2017-02-08 | 北京理工大学 | Paper title generation method capable of utilizing distributed semantic information |
CN106502985A (en) * | 2016-10-20 | 2017-03-15 | 清华大学 | A kind of neural network modeling approach and device for generating title |
CN107766940A (en) * | 2017-11-20 | 2018-03-06 | 北京百度网讯科技有限公司 | Method and apparatus for generation model |
CN107977363A (en) * | 2017-12-20 | 2018-05-01 | 北京百度网讯科技有限公司 | Title generation method, device and electronic equipment |
CN108647209A (en) * | 2018-05-10 | 2018-10-12 | 北京理工大学珠海学院 | A kind of topic generation method based on mind map |
CN108703505A (en) * | 2018-05-25 | 2018-10-26 | 钱文伟 | Automation computer desk based on user's identification |
CN109918643A (en) * | 2019-01-24 | 2019-06-21 | 平安科技(深圳)有限公司 | A kind of word creation generation method, device, computer equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
González García et al. | A review of artificial intelligence in the internet of things | |
US20220148191A1 (en) | Image segmentation method and apparatus and storage medium | |
Mayor et al. | A neurocomputational account of taxonomic responding and fast mapping in early word learning. | |
Hoffman et al. | A taxonomy of event-level dimensions: Implications for understanding leadership processes, behavior, and performance | |
CN111415740A (en) | Method and device for processing inquiry information, storage medium and computer equipment | |
Ebrahim et al. | Quantitative and qualitative analysis of time-series classification using deep learning | |
CN109754012A (en) | Entity Semantics relationship classification method, model training method, device and electronic equipment | |
Thiessen et al. | iMinerva: A mathematical model of distributional statistical learning | |
Morente-Molinera et al. | A dynamic group decision making process for high number of alternatives using hesitant Fuzzy Ontologies and sentiment analysis | |
CN108596069A (en) | Neonatal pain expression recognition method and system based on depth 3D residual error networks | |
US20080222064A1 (en) | Processes and Systems for Automated Collective Intelligence | |
Iyer et al. | Neural dynamics of idea generation and the effects of priming | |
Wu et al. | Learning and self-instruction expert system for Yoga | |
Burger et al. | Developing a smart operational research with hybrid practice theories | |
Pan et al. | Deep neural network-based classification model for Sentiment Analysis | |
CN112164476A (en) | Medical consultation conversation generation method based on multitask and knowledge guidance | |
CN106959946A (en) | A kind of text semantic feature generation optimization method based on deep learning | |
Li | Sentiment-enhanced learning model for online language learning system | |
CN116741411A (en) | Intelligent health science popularization recommendation method and system based on medical big data analysis | |
Wang | Fuzzy comprehensive evaluation of physical education based on high dimensional data mining | |
Liang et al. | Knowledge aggregation and intelligent guidance for fragmented learning | |
Dong et al. | [Retracted] An Empirical Study on Application of Machine Learning and Neural Network in English Learning | |
CN117352159A (en) | Method, system and storage medium for evidence-based treatment of difficult and complicated diseases based on electronic medical records | |
Carsetti | Causality, meaningful complexity and embodied cognition | |
Wang et al. | An automatic classification and clustering algorithm for online learning goals based on cognitive thinking |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20211130 Address after: 1501-1, floor 15, No. 19, Chegongzhuang West Road, Haidian District, Beijing 100048 Applicant after: Super Intellectual Property Consultant (Beijing) Co.,Ltd. Address before: 12a-3-110, block D, 12 / F, No. 28, information road, Haidian District, Beijing 100085 Applicant before: Beijing Ruyou Education Technology Co.,Ltd. |
|
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191203 |