CN109885772A - The education content personalized recommendation system of knowledge based map - Google Patents
The education content personalized recommendation system of knowledge based map Download PDFInfo
- Publication number
- CN109885772A CN109885772A CN201910147126.4A CN201910147126A CN109885772A CN 109885772 A CN109885772 A CN 109885772A CN 201910147126 A CN201910147126 A CN 201910147126A CN 109885772 A CN109885772 A CN 109885772A
- Authority
- CN
- China
- Prior art keywords
- user
- module
- portrait
- knowledge
- search engine
- 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.)
- Withdrawn
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The education content personalized recommendation system of knowledge based map, including search engine and knowledge mapping module, user behavior logging modle, user's portrait module, in, user behavior logging modle records the operation of user in a search engine, the various actions of user are passed into user's portrait module, knowledge mapping module establishes user's portrait and knowledge point portrait, knowledge mapping module draws a portrait module according to knowledge point portrait module and user to ensure the content of personalized recommendation while meet the personal preference and teaching logic of user, semantic understanding module in search engine technique, semantic-based sequence is carried out for recommendation results, recommendation results itself are finally made more to meet the demand of user.The technology of the present invention level is constituted simply, solves cold start-up, can recommend both to have met individual subscriber hobby, meet the content of teaching logic again, the sequence of recommendation is optimized, so that sequence more meets the natural language expressing of user, to be more suitable for educating the application of scene.
Description
Technical field
The present invention relates to educational system applied technical field, the education content of especially a kind of knowledge based map is personalized
Recommender system.
Background technique
Recommender system be it is a kind of user's coordinate indexing content, the system recommending and be presented to user, be conducive to user and obtain
To relevant information.In practical application, when the content quantity occurred on internet is more and more, type becomes increasingly complex the case where
When, user would have to the data and search result in face of magnanimity, and user needs to take a lot of time from these magnanimity at this time
As a result the content retrieval that oneself is really needed in comes out, this process can spend user's many times, in this case, just
Be born recommender system, and the task of recommender system is exactly to connect between user and information, saves the time of user and improves
Search efficiency creates value for user.In recent years, recommender system is widely used in the every aspect of internet, including
The numerous areas such as commercial product recommending, personalized advertisement are recommended, news is recommended, the trill being commonly used such as people, Taobao, head today
Just there is the application of a large amount of recommender systems in the products such as item, bean cotyledon film review.
Unquestionably, when data and number of users largely increase, the complexity of recommender system and technological challenge can increase on an equal basis
It is long.In the prior art, the difference of data is used according to recommender system, the recommender system algorithm of mainstream can be divided into collaborative filtering
Proposed algorithm (Collaborative Filtering Recommendation) is based on commending contents algorithm (Content-
) and three kinds of mixing proposed algorithm basedRecommendation.Wherein, collaborative filtering do not need to be obtained ahead of time user or
The characteristic of article, the historical behavior data for only relying upon user model user, to recommend for user;Association
It mainly include the collaborative filtering based on user, the collaborative filtering based on article and hidden semantic model etc. with filter algorithm;It cooperateed with
Filter algorithm is main disadvantage is that need to be modeled according to the behavior of user, for new user, there are cold start-ups can not
The problem of effectively recommending.Basic thought based on commending contents algorithm is to recommend object similar with his interested content for user
Product, such as user like class books of pursuing a goal with determination, then system directly can recommend such books for him, such as " Xiao Shenke's
Redeem ", this process does not need to provide the historical behavior data of user, can well solve cold start-up problem;Based on content
The critical issue of proposed algorithm is modeled to user interest profile and article characteristics, and main method includes vector space mould
Type, linear classification, linear regression etc.;It is based on the shortcomings that commending contents algorithm, needs that use is provided previously based on commending contents
The characteristic at family and article is difficult that the content of article is accurately classified and described in preprocessing process, in data
In the case that amount is very big, pretreatment efficiency can be very low.In mixed recommendation, it will use a variety of proposed algorithms, for example use base
Cold start-up and the behavioral data Sparse Problems that new user is solved the problems, such as in the proposed algorithm of interior perhaps label, it is certain having
User behavior data after, according to the needs of business scenario it is comprehensive using UserCF, ItemCF, matrix decomposition or other recommend to calculate
Method carries out off-line calculation and model training, comprehensive by social network data, Time Correlation Data, the geodata of acquisition user etc.
It closes and considers to be recommended, guarantee the personalization of recommended engine, improve the robustness of recommended engine, real-time, diversity and new
Newness;The disadvantage is that, due to needing asking for the complexity that there is the system of increasing using mixed model and cost in mixed recommendation
Topic.
Furthermore existing various proposed algorithms are mainly based upon the recommendation system of the contents such as commodity, single video, audio application
System is developed, and in the case where educating scene, the content of courses and resource are then different from above-mentioned content, and teaching resource and knowledge point have
Inherent logic, such as want learning knowledge point A, be desirable to the basis of knowledge point B or knowledge point C, be similar to such
Logic and rule can be found everywhere in the recommendation of education content, and these above-mentioned common proposed algorithm systems, there is no for
Such case is specifically optimized, and can not recommend both to meet teaching logic rule for academics and students preferably under scene of imparting knowledge to students
Then, and it is able to satisfy the content of users ' individualized requirement.Recommendation is in sequence, and existing recommender system without considering language enough
There is content of recommendation itself and do not meet the real demand of user's enquirement in the demand of reason and good sense solution.
Summary of the invention
In order to overcome in the prior art, single recommender system can not handle cold start-up, in the case that data volume is very big, pre- place
Inefficiency is managed, the mixed model of mixed recommendation has that complicated and at high cost and existing recommender system is being recommended
When do not account for teaching logic, recommendation sequence on do not account for user semantic understand, be not suitable for education scene application
Drawback is established the present invention provides by introducing knowledge mapping (chart database) technology and semantic understanding search engine technique etc.
One technological layer constitutes novel recommender system model that is simple, while not having cold start-up problem, solves conventional recommendation calculation
Single model can not handle cold start-up in method, in the case that data volume is very big, pretreatment low efficiency and mixed model there is knot
Structure complexity cost too high problem in the case that recommendation itself meets individual subscriber preference, joined examining for teaching logic
Amount allows to recommend not only to have met individual subscriber hobby, but also meets the content of teaching logic, is managed using the semanteme in search engine
Solution technology optimizes the sequence of recommendation, so that sequence more meets the natural language expressing of user, to be more suitable for educational park
The education content personalized recommendation system of the knowledge based map of scape application.
The technical solution adopted by the present invention to solve the technical problems is:
The education content personalized recommendation system of knowledge based map, it is characterised in that including search engine and knowledge mapping mould
Block, user behavior logging modle, user's portrait module, search engine and knowledge mapping module, user behavior logging modle, user
Portrait module is mounted in the application software in intelligent terminal internet device, and in, user behavior logging modle record is used
The various actions of user are passed to user's portrait module by the operation of family in a search engine, and knowledge mapping module establishes user
Portrait and knowledge point portrait, knowledge mapping module draw a portrait module according to knowledge point portrait module and user to ensure that personalization pushes away
The content recommended while the personal preference for meeting user and teaching logic, the semantic understanding module in search engine technique, for pushing away
It recommends result and carries out semantic-based sequence, recommendation results itself is finally made more to meet the demand of user.
The operation of the user behavior logging modle record user in a search engine, the various actions of user are passed to
User draws a portrait after module, and user's portrait module can establish corresponding user's portrait according to user behavior in knowledge mapping module,
Due to the characteristic of knowledge mapping module, it is not necessary to additionally carry out complicated modeling for user interest profile and article characteristics, know
Know in map module, the preference of user is expressed with node, relationship, limit, mutual distance.
There is the knowledge point portrait established in knowledge mapping module the distribution of teaching knowledge point itself and teaching to patrol
Data are collected, when being recommended using knowledge mapping module, module is drawn a portrait in knowledge point can be with user's portrait module while work
Make, it is ensured that content of recommendation itself is to meet the teaching logic of knowledge point.
The knowledge point portrait module is preset in knowledge mapping module, is made in advance by staff and faculty.
In the application, when user is in a search engine there are no when any operation excessively, user's portrait module is not joined
With recommendation, but the content for meeting teaching logic is recommended by knowledge point portrait module, while by semantic understanding module according to user
Input meet for content semantic personalized ordering.
The medicine have the advantages that the present invention is in application, when user inputs various relevant data by search engine
Afterwards, user behavior logging modle will record the operation of user in a search engine, and the various actions of user are passed to user and are drawn
As module, knowledge mapping module draws a portrait module according to knowledge point portrait module and user to ensure the content of personalized recommendation simultaneously
Meet the personal preference and teaching logic of user, and the semantic understanding module in search engine technique, for recommendation results energy
Semantic-based sequence is carried out, recommendation results itself is finally made more to meet the demand of user, when reducing the search of user
Between.The technology of the present invention level constitute it is simple, while the problem of be not cold-started, solve in conventional recommendation algorithm single model without
Method processing cold start-up, in the case that data volume is very big, pretreatment low efficiency and mixed model have that structure is complicated cost be too high
The problem of, in the case that recommendation itself meets individual subscriber preference, it joined considering for teaching logic, allow to recommend
Not only met individual subscriber hobby, but also meet teaching logic content optimize and push away using the semantic understanding technology in search engine
The sequence of content is recommended, so that sequence more meets the natural language expressing of user, to be more suitable for educating the application of scene.Based on upper
It states, so the present invention has extremely broad application prospect.
Detailed description of the invention
The present invention is described further below in conjunction with drawings and examples.
Fig. 1 is block architecture diagram of the present invention.
Specific embodiment
Shown in Fig. 1, the education content personalized recommendation system of knowledge based map, including search engine and knowledge mapping
Module (chart database), user behavior logging modle, user's portrait module, search engine and knowledge mapping module, user behavior
Logging modle, user's portrait module are mounted in the application in intelligent terminal internet device (PC machine, tablet computer, mobile phone etc.)
Software, in, user behavior logging modle records the operation of user in a search engine, and the various actions of user are passed to
User's portrait module, knowledge mapping module establish user's portrait and knowledge point portrait, and knowledge mapping module is drawn a portrait according to knowledge point
Module and user draw a portrait module to ensure the content of personalized recommendation while meet the personal preference and teaching logic of user, search
Semantic understanding module in engine technique carries out semantic-based sequence for recommendation results, finally makes recommendation results itself
More meet the demand of user.
Shown in Fig. 1, user behavior logging modle records the operation of user in a search engine, by the various actions of user
After passing to user's portrait module, user's portrait module can establish corresponding user according to user behavior in knowledge mapping module
Portrait, due to the characteristic of knowledge mapping module (chart database), it is not necessary to additionally be carried out for user interest profile and article characteristics
Complicated modeling is expressed the preference of user with node, relationship, limit, mutual distance, reduces biography in knowledge mapping
In system recommender system the modeling that is more troublesome and build the set that Schema(is database object) time of layer, ensuring effect
In the case of, reduce complexity.
Shown in Fig. 1, the knowledge point established in knowledge mapping module portrait (including before and after the study of knowledge point, knowledge
Level etc. between point) distribution with teaching knowledge point itself and teaching logical data, using knowledge mapping module into
Row recommend when, knowledge point portrait module can and user draw a portrait module work at the same time, it is ensured that content of recommendation itself is to meet
The teaching logic of knowledge point.Knowledge point portrait module is preset in knowledge mapping module, is shifted to an earlier date by staff and faculty
Production.
Shown in Fig. 1, in, when user is in a search engine there are no when any operation excessively, user draws a portrait mould
Block is not involved in recommendation, but recommends the content for meeting teaching logic by knowledge point portrait module, while by semantic understanding module root
Content is carried out to meet semantic personalized ordering according to the input of user, it is cold thus to solve the single recommender system data of tradition
The problem of starting.
Shown in Fig. 1, the present invention in application, after user inputs various relevant search data by search engine,
User behavior logging modle will record the operation of user in a search engine, and the various actions of user are passed to user's portrait mould
Block, knowledge mapping module draw a portrait module according to knowledge point portrait module and user to ensure the content of personalized recommendation while meet
The personal preference and teaching logic (knowledge mapping module is user's recommendation) of user, and the semanteme in search engine technique
Understanding Module can be carried out semantic-based sequence for recommendation results, recommendation results itself finally made more to meet the need of user
It asks, reduces the search time of user.The technology of the present invention level constitutes simple, while the problem of be not cold-started, solves
Single model can not handle cold start-up in conventional recommendation algorithm, in the case that data volume is very big, pretreatment low efficiency, and mixing
Model has that structure is complicated, and cost is too high, in the case that recommendation itself meets individual subscriber preference, joined religion
Considering for logic is learned, allows to recommend not only to have met individual subscriber hobby, but also meet the content of teaching logic, utilizes search engine
In semantic understanding technology, the sequence of recommendation is optimized, so that sequence more meets the natural language expressing of user, thus more
It is suitble to the application of education scene.Based on above-mentioned, so the present invention has extremely broad application prospect.
Shown in Fig. 1, the knowledge mapping module (chart database) that the present invention applies is the database of NoSQL(non-relational)
One seed type of database, the relation information between its Graphics Application theory storage entity;Most common example is exactly community network
In interpersonal relationship.There is relevant database for storing the effect of " relationship type " data and bad, there is inquiry
It is complicated, slowly, beyond expected disadvantage, and the unique design of graphic data base (knowledge mapping module) exactly compensates for this and lacks
It falls into, therefore can effectively meet actual needs.In a graphic data base, there are two types of most important compositions, nodal set and connection
The relationship (some is also referred to as bubble and arrow) of node, nodal set is exactly a series of set of nodes in figure, is comparatively close to relationship
Most-often used table in database, and relationship is then the specific composition of graphic data base." figure " word in chart database refers to
Be figure (node and relationship), rather than picture, " figure " word refer to the graphic form storage entity of node and relationship it
Between relation information.
Basic principles and main features and advantages of the present invention of the invention have been shown and described above, for this field skill
For art personnel, it is clear that the present invention is limited to the details of above-mentioned exemplary embodiment, and without departing substantially from spirit or base of the invention
In the case where eigen, the present invention can be realized in other specific forms.It therefore, in all respects, should all be by reality
Apply example and regard exemplary as, and be non-limiting, the scope of the present invention by appended claims rather than above description
It limits, it is intended that including all changes that fall within the meaning and scope of the equivalent elements of the claims in the present invention.
Any reference signs in the claims should not be construed as limiting the involved claims.
In addition, it should be understood that although this specification is described in terms of embodiments, but not each embodiment is only wrapped
Containing an independent technical solution, this description of the specification is merely for the sake of clarity, and those skilled in the art should
It considers the specification as a whole, the technical solutions in the various embodiments may also be suitably combined, forms those skilled in the art
The other embodiments being understood that.
Claims (5)
1. the education content personalized recommendation system of knowledge based map, it is characterised in that including search engine and knowledge mapping mould
Block, user behavior logging modle, user's portrait module, search engine and knowledge mapping module, user behavior logging modle, user
Portrait module is mounted in the application software in intelligent terminal internet device, and in, user behavior logging modle record is used
The various actions of user are passed to user's portrait module by the operation of family in a search engine, and knowledge mapping module establishes user
Portrait and knowledge point portrait, knowledge mapping module draw a portrait module according to knowledge point portrait module and user to ensure that personalization pushes away
The content recommended while the personal preference for meeting user and teaching logic, the semantic understanding module in search engine technique, for pushing away
It recommends result and carries out semantic-based sequence, recommendation results itself is finally made more to meet the demand of user.
2. the education content personalized recommendation system of knowledge based map according to claim 1, it is characterised in that user
Behavior record module records the operation of user in a search engine, after the various actions of user are passed to user's portrait module,
User's portrait module can establish corresponding user's portrait according to user behavior in knowledge mapping module, due to knowledge mapping module
Characteristic, it is not necessary to additionally user interest profile and article characteristics are carried out with complicated modeling, in knowledge mapping module, with section
Point, relationship, limit, mutual distance express the preference of user.
3. the education content personalized recommendation system of knowledge based map according to claim 1, it is characterised in that knowing
Know distribution and teaching logical data that the knowledge point portrait established in map module has teaching knowledge point itself, utilizes knowledge
When map module is recommended, knowledge point portrait module can be worked at the same time with user's portrait module, it is ensured that the content of recommendation
It itself is the teaching logic for meeting knowledge point.
4. the education content personalized recommendation system of knowledge based map according to claim 1, it is characterised in that knowledge
Point portrait module is preset in knowledge mapping module, is made in advance by staff and faculty.
5. the education content personalized recommendation system of knowledge based map according to claim 1, it is characterised in that application
In, when user is in a search engine there are no when any operation excessively, user's portrait module is not involved in recommendation, but by knowledge
Point portrait module recommends the content for meeting teaching logic, while content is carried out according to the input of user by semantic understanding module
Meet semantic personalized ordering.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910147126.4A CN109885772A (en) | 2019-02-27 | 2019-02-27 | The education content personalized recommendation system of knowledge based map |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910147126.4A CN109885772A (en) | 2019-02-27 | 2019-02-27 | The education content personalized recommendation system of knowledge based map |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109885772A true CN109885772A (en) | 2019-06-14 |
Family
ID=66929727
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910147126.4A Withdrawn CN109885772A (en) | 2019-02-27 | 2019-02-27 | The education content personalized recommendation system of knowledge based map |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109885772A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110555112A (en) * | 2019-08-22 | 2019-12-10 | 桂林电子科技大学 | interest point recommendation method based on user positive and negative preference learning |
CN112559874A (en) * | 2020-12-21 | 2021-03-26 | 周欢 | User recommendation method based on intelligent education |
CN112966092A (en) * | 2020-11-25 | 2021-06-15 | 安徽教育网络出版有限公司 | Knowledge graph personalized semantic recommendation method based on basic education |
CN113076428A (en) * | 2021-03-19 | 2021-07-06 | 北京沃东天骏信息技术有限公司 | Method and device for generating book list |
CN113722601A (en) * | 2021-09-07 | 2021-11-30 | 南方电网数字电网研究院有限公司 | Power measurement information recommendation method and device, computer equipment and storage medium |
CN113889209A (en) * | 2021-09-26 | 2022-01-04 | 浙江禾连网络科技有限公司 | Recommendation system and storage medium for health management service products |
CN114780785A (en) * | 2022-06-23 | 2022-07-22 | 新缪斯(深圳)音乐科技产业发展有限公司 | Music teaching recommendation method and system based on knowledge graph |
CN116342340A (en) * | 2023-03-31 | 2023-06-27 | 上海毅学堂智能科技有限公司 | Personalized education system and method based on multi-version teaching material knowledge graph |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104516904A (en) * | 2013-09-29 | 2015-04-15 | 北大方正集团有限公司 | Key knowledge point recommendation method and system |
CN107085803A (en) * | 2017-03-31 | 2017-08-22 | 弘成科技发展有限公司 | The individualized teaching resource recommendation system of knowledge based collection of illustrative plates and capability comparison |
CN109191929A (en) * | 2018-09-25 | 2019-01-11 | 上海优谦智能科技有限公司 | The intellectual education system of knowledge based map |
-
2019
- 2019-02-27 CN CN201910147126.4A patent/CN109885772A/en not_active Withdrawn
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104516904A (en) * | 2013-09-29 | 2015-04-15 | 北大方正集团有限公司 | Key knowledge point recommendation method and system |
CN107085803A (en) * | 2017-03-31 | 2017-08-22 | 弘成科技发展有限公司 | The individualized teaching resource recommendation system of knowledge based collection of illustrative plates and capability comparison |
CN109191929A (en) * | 2018-09-25 | 2019-01-11 | 上海优谦智能科技有限公司 | The intellectual education system of knowledge based map |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110555112A (en) * | 2019-08-22 | 2019-12-10 | 桂林电子科技大学 | interest point recommendation method based on user positive and negative preference learning |
CN110555112B (en) * | 2019-08-22 | 2022-07-15 | 桂林电子科技大学 | Interest point recommendation method based on user positive and negative preference learning |
CN112966092A (en) * | 2020-11-25 | 2021-06-15 | 安徽教育网络出版有限公司 | Knowledge graph personalized semantic recommendation method based on basic education |
CN112559874A (en) * | 2020-12-21 | 2021-03-26 | 周欢 | User recommendation method based on intelligent education |
CN112559874B (en) * | 2020-12-21 | 2023-05-16 | 南京康裕数字科技有限公司 | User recommendation method based on intelligent education |
CN113076428A (en) * | 2021-03-19 | 2021-07-06 | 北京沃东天骏信息技术有限公司 | Method and device for generating book list |
CN113722601A (en) * | 2021-09-07 | 2021-11-30 | 南方电网数字电网研究院有限公司 | Power measurement information recommendation method and device, computer equipment and storage medium |
CN113889209A (en) * | 2021-09-26 | 2022-01-04 | 浙江禾连网络科技有限公司 | Recommendation system and storage medium for health management service products |
CN114780785A (en) * | 2022-06-23 | 2022-07-22 | 新缪斯(深圳)音乐科技产业发展有限公司 | Music teaching recommendation method and system based on knowledge graph |
CN114780785B (en) * | 2022-06-23 | 2022-09-13 | 新缪斯(深圳)音乐科技产业发展有限公司 | Music teaching recommendation method and system based on knowledge graph |
CN116342340A (en) * | 2023-03-31 | 2023-06-27 | 上海毅学堂智能科技有限公司 | Personalized education system and method based on multi-version teaching material knowledge graph |
CN116342340B (en) * | 2023-03-31 | 2023-10-17 | 上海毅学堂智能科技有限公司 | Personalized education system and method based on multi-version teaching material knowledge graph |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109885772A (en) | The education content personalized recommendation system of knowledge based map | |
Fan et al. | The application of computer graphics processing in visual communication design | |
Galvagno et al. | Mapping creative tourism research: Reviewing the field and outlining future directions | |
CN104951518B (en) | One kind recommends method based on the newer context of dynamic increment | |
Bailey et al. | Speak to the eyes: The history and practice of information visualization | |
Gao et al. | Optimization analysis and implementation of online wisdom teaching mode in cloud classroom based on data mining and processing | |
Jörgensen | Access to pictorial material: A review of current research and future prospects | |
CN107193882A (en) | Why not query answer methods based on figure matching on RDF data | |
CN111291191A (en) | Radio and television knowledge graph construction method and device | |
CN110309271A (en) | Intelligent knowledge study and question and answer technology | |
CN117171191A (en) | Intelligent search engine system and method in material vertical field | |
Li | A Recommendation Model for College English Digital Teaching Resources Using Collaborative Filtering and Few‐Shot Learning Technology | |
Xu | Packaging design method of modern cultural and creative products based on rough set theory | |
CN115409025A (en) | Marketing text creation method, device and equipment | |
Luo | Digital Art Design Effectiveness Model System Based on K‐Medoids Algorithm | |
Chen | Study on the innovative development of digital media art in the context of artificial intelligence | |
Li | Based on data mining technology in distance education system applied research | |
Xiong | [Retracted] Comparative Analysis of Chinese Culture and Hong Kong, Macao, and Taiwan Culture in the Field of Public Health Based on the CNN Model | |
CN103383693A (en) | Method and system for improving information exchange success rate | |
Luo et al. | [Retracted] A Visual Comprehensive Evaluation of Cultural and Creative Industry Projects Based on Improved Literature Measurement Method | |
CN114036444B (en) | Interactive digital teaching material system based on big data | |
CN113868322B (en) | Semantic structure analysis method, device and equipment, virtualization system and medium | |
Chang | Museum and cultural products co-creation brand value: Taking the innovative cultural products of Ningbo Port Museum as an example | |
Jiang | Research on the Innovative Strategy of Teaching Advertising Design Based on Data Visualization | |
Deng et al. | [Retracted] Application of Deep Learning Algorithm in Web Page Advertising Design Style |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190614 |
|
WW01 | Invention patent application withdrawn after publication |