CN112347348A - Teaching resource recommendation model training method - Google Patents
Teaching resource recommendation model training method Download PDFInfo
- Publication number
- CN112347348A CN112347348A CN202011186065.1A CN202011186065A CN112347348A CN 112347348 A CN112347348 A CN 112347348A CN 202011186065 A CN202011186065 A CN 202011186065A CN 112347348 A CN112347348 A CN 112347348A
- Authority
- CN
- China
- Prior art keywords
- resources
- recommendation
- resource
- model
- teaching
- 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 37
- 238000012549 training Methods 0.000 title claims abstract description 36
- 230000006399 behavior Effects 0.000 claims abstract description 31
- 238000010801 machine learning Methods 0.000 claims abstract description 16
- 238000004422 calculation algorithm Methods 0.000 claims description 14
- 230000000694 effects Effects 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 238000007635 classification algorithm Methods 0.000 claims description 3
- 238000003066 decision tree Methods 0.000 claims description 3
- 238000007637 random forest analysis Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 2
- 230000007246 mechanism Effects 0.000 abstract description 4
- 230000002708 enhancing effect Effects 0.000 abstract description 2
- 238000000605 extraction Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012954 risk control Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a teaching resource recommendation model training method, S1, selecting a certain amount of teachers belonging to the science subject of target resource T resources to recommend; s2, collecting behavior data of each subject teacher aiming at the target resource, and training a machine learning model ExtraModel; s3, recommending the target resource according to the model in the step S2; s4, continuing to train the model; s5, repeating the steps S3 and S4 for a period of time T1, and finishing after the time is over, wherein the invention relates to the technical field of online education. The teaching resource recommendation model training method can realize that the existing recommendation model can effectively support smooth release of new resources, can quickly improve the exposure rate of the new resources, quickly screens out the good resources, can establish a benign resource updating mechanism, and well achieves the aim of enhancing the recommendation capability of the new teaching resources in a basic model through auxiliary model training based on a specified data set.
Description
Technical Field
The invention relates to the technical field of online education, in particular to a teaching resource recommendation model training method.
Background
With the deep development of education informatization, the number of teaching resources on the Internet shows exponential rapid growth, and the types of the teaching resources are more diversified. Meanwhile, the recommendation system widely applied to e-commerce, social websites and the like is gradually applied to the field of education, and personalized recommendation of teaching resources can be achieved to a certain extent.
The current recommendation method usually performs model training based on large-scale data accumulated in the system, and then is applied to personalized recommendation. These approaches tend to ignore the following important issues: (1) when the system is initially operated or a new user/new resource is added, the system cannot be recommended in the recommendation system due to lack of historical behavior records, so that the problems of cold start and the like are caused; (2) along with the continuous updating of the teaching resources developed in times, the current recommendation of the teaching resources lacks an updating mechanism, the old resources are often positioned at the top of the recommendation, the new resources are not recommended to users, the smooth off-shelf of the old resources are not facilitated, and the whole resource library cannot be updated and iterated effectively and can not grow continuously; (3) the method has high requirements on the quality of resources, the correctness of consciousness forms and the like in an education scene, and the issuing and recommendation of the current resources are usually directly issued in full aiming at target users, so that great risks are generated.
Referring to a chinese patent, a resource recommendation system and method based on a network learning environment (application No. CN201710799698.1 publication No. CN107590232A) the present invention includes: the system comprises a data acquisition module, a user multi-dimensional feature vector and score vector extraction module, a score credibility vector extraction module and a learning resource recommendation module. According to the method, a user group similar to the target user is screened out by utilizing the idea of collaborative filtering, and the scoring and recommendation of the learning resources are carried out by combining the similarity between the similar user group and the target user and the confidence level of the scoring of the user, so that the scoring of the learning resources has user pertinence and scoring objectivity, and therefore, the personalized and high-quality learning resources are recommended for the user.
In the prior art, a large-scale data set is required to be utilized to form a user multi-dimensional feature vector and a user scoring credibility vector, so that personalized recommendation is further performed. The technology depends on the existing data, cannot solve the cold start problem of new resources, cannot effectively recommend new high-quality resources to users, and is not beneficial to update iteration of new and old resources.
Referring to a Chinese patent, the invention discloses a personalized recommendation system and a recommendation method for network teaching resources (application number: CN201410093793.6 publication number: CN 103886054A). The system comprises: the data construction module is used for constructing teacher behavior data, teacher model data, course model data and resource model data; the offline data processing module is used for initializing and adjusting the course model data and the resource model data, deducing the identity of the teacher by using the teacher behavior data, calculating the association degree between resources according to the teacher behavior data, calculating the similarity between the resources according to the resource model data, and calculating the association degree between the courses and the resources according to the resource model data and the course model data; and the online recommendation module is used for recommending the resource online by utilizing the association degree among the resources, the similarity among the resources, the association degree between the courses and the resources and the dynamic description of the teacher, recommending a resource label according to the feedback of the teacher to the recommended resource, and transmitting the behavior data of the teacher to the teacher behavior data of the data construction module through UI interaction.
In the prior art, a recommendation method based on content and tags is adopted, new content can extract initialized tags according to content features, and then the tags of the content are filtered and expanded through teacher behavior records, so that inaccuracy of the content recommendation method in initial keyword extraction is reduced. The method can avoid the influence of the cold start of the new content on the recommendation system, but the smooth release of the new content can not be realized, the initial label is extracted from the new content, the system can push the resource to all user interfaces related to the label according to the initial label, and if the extraction of the initial label is inaccurate or the quality of the content has problems, the negative influence caused by the content is maximized, and the risk control is not facilitated.
In the prior art, the current teaching resource application system has a background management system of resources, and can solve the cold start problem and the update problem of partial resources in a manual mode: aiming at the new resources, a recommendation index can be manually set, a default value is given for a recommendation algorithm, and the new resources are recommended to a user interface; and for the old resources, the invalid resources can be marked in batches for batch off-shelf, and are not recommended to the user.
In the prior art, recommendation indexes or initialization data need to be set manually, personal subjective will is not objective, and accurate recommendation indexes are difficult to set for each resource aiming at huge resources; the old resources are useless resources, and still exert great value for special users or special scenes, so that the mode of the old resources is extreme.
Therefore, a new teaching resource recommendation model training method is needed, which can train the existing recommendation model and make it have the following new capabilities: (1) the method can effectively support the smooth release of the new resources, can quickly improve the exposure rate of the new resources, and quickly screen out the good resources; (2) a benign resource updating mechanism can be established, and the problem that the resource library cannot be updated and iterated effectively is solved.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides a teaching resource recommendation model training method, which solves the problem that how to avoid the situation that stock teaching resources are always at the top of recommendation and new resources are not recommended all the time, namely how to improve the exposure rate of the new resources through a certain strategy and enable good new resources to be screened out quickly.
(II) technical scheme
In order to achieve the purpose, the invention is realized by the following technical scheme: a teaching resource recommendation model training method specifically comprises the following steps:
s1, selecting a certain number of target resources T and disciplines to which the resources belong, and randomly selecting a certain number of N1 discipline teachers to recommend;
the selection of the target resources is mainly to verify the effects of the resources in a small range on the premise of excluding the specific current capability of the base model BaseModel.
As the resources must be used by the user, i.e., the discipline teacher, to generate the usage data and the model training data. In the step, the selection of the teacher in the department of science is randomly selected in the recommendation background, the specific number is different according to the scale and the characteristics of different platforms, and the patent is not particularly limited.
The recommendation of resources is also based on random users, and is also from the target resources.
S2, collecting behavior data of each subject teacher aiming at target resources, and training a machine learning model ExtraModel only aiming at the new resources through a machine learning recommendation algorithm;
s3, expanding the number of N1 in the step S1, and recommending the target resources according to the model in the step S2;
s4, collecting teacher behavior data in the step S3, and continuing to train machine learning models aiming at the new resources; putting the teacher behavior data in the step S3 into a base model BaseModel for training;
s5, repeating the steps S3 and S4 for a period of time T1And when the time is over, the process is finished.
Preferably, the target resource in step S1 is a newly stocked resource or an inventory resource, and is not particularly limited in the present invention.
Preferably, with the teacher behavior data for the target resource in step S1, the teacher behavior data can be used to train a recommendation model for teaching resources, and the machine learning recommendation algorithm in step S2 is one of a random forest algorithm, a decision tree algorithm, or a k-nearest neighbor classification algorithm, which is not limited in the present invention.
Preferably, with the recommendation model for the target teaching resource in step S2, the number of N1 continues to be expanded, and the expansion mode is still random selection, but the recommendation in step S2 is no longer random recommendation, but the association degree of the teacher individual feature, the course knowledge point and the teaching resource is calculated according to the ExtraModel model in step S2, and the recommendation is performed according to the level of the association degree.
Preferably, the teacher behavior data in step S3 is collected continuously, and the ExtraModel is trained continuously to enhance the screening capability and recommendation capability of the model on the target resources, so that good target resources can be recommended better, and the teacher behavior data in step S3 has a certain scale, so that the teacher behavior data needs to be put into the base model BaseModel for training.
Preferably, the steps S3 and S4 are required to last for a period of time T1And the target teaching resources can be exposed and applied in a certain user scale, so that the recommendation capability of BaseModel on the target teaching resources is updated.
Preferably, in the step S5, the time T is reached1Then, the ExtraModel is discarded, and a new resource lacking the use data can be quickly recommended according to the effect through the assistance of the ExtraModel.
(III) advantageous effects
The invention provides a teaching resource recommendation model training method. Compared with the prior art, the method has the following beneficial effects: the teaching resource recommendation model training method specifically comprises the following steps: s1, selecting a certain number of target resources T and disciplines to which the resources belong, and randomly selecting a certain number of N1 discipline teachers to recommend; s2, collecting behavior data of each subject teacher aiming at target resources, and training a machine learning model ExtraModel only aiming at the new resources through a machine learning recommendation algorithm; s3, expanding the number of N1 in the step S1, and recommending the target resources according to the model in the step S2; s4, collecting teacher behavior data in the step S3, and continuing to train machine learning models aiming at the new resources; putting the teacher behavior data in the step S3 into a base model BaseModel for training; s5, repeating the steps S3 and S4 for a period of time T1After the time is over, the method can realize that the existing recommendation model can effectively support smooth release of new resources, can quickly improve the exposure rate of the new resources, quickly screens out good resources, can establish a benign resource updating mechanism, solves the problem that a resource library cannot effectively update iteration, and well achieves the aim of enhancing the recommendation capability of new teaching resources in a basic model through auxiliary model training based on a specified data set.
Drawings
FIG. 1 is a flow chart of model training according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, an embodiment of the present invention provides a technical solution: a teaching resource recommendation model training method specifically comprises the following steps:
s1, selecting a certain number of target resources T and disciplines to which the resources belong, and randomly selecting a certain number of N1 discipline teachers to recommend;
the selection of the target resources is mainly to verify the effects of the resources in a small range on the premise of excluding the specific current capability of the base model BaseModel.
As the resources must be used by the user, i.e., the discipline teacher, to generate the usage data and the model training data. In the step, the selection of the teacher in the department of science is randomly selected in the recommendation background, the specific number is different according to the scale and the characteristics of different platforms, and the patent is not particularly limited.
The recommendation of resources is also based on random users, and is also from the target resources.
S2, collecting behavior data of each subject teacher aiming at target resources, and training a machine learning model ExtraModel only aiming at the new resources through a machine learning recommendation algorithm;
s3, expanding the number of N1 in the step S1, and recommending the target resources according to the model in the step S2;
s4, collecting teacher behavior data in the step S3, and continuing to train machine learning models aiming at the new resources; putting the teacher behavior data in the step S3 into a base model BaseModel for training;
s5, repeating the steps S3 and S4 for a period of time T1And when the time is over, the process is finished.
In the embodiment of the present invention, the target resource in step S1 is a newly warehoused resource or an inventory resource, and is not particularly limited in the present invention.
In the embodiment of the present invention, with the teacher behavior data for the target resource in step S1, the data can be used to train a recommendation model for teaching resources, and the machine learning recommendation algorithm in step S2 is one of a random forest algorithm, a decision tree algorithm, or a k-nearest neighbor classification algorithm, which is not limited in the present invention.
In the embodiment of the invention, the recommendation model for the target teaching resources in the step S2 is provided, the number of N1 is continuously expanded, and the expansion mode is still random selection, but the recommendation in the step S2 is not random recommendation any more, but the association degree of the individual characteristics of the teacher, the course knowledge points and the teaching resources is calculated according to the ExtraModel model in the step S2, and the recommendation is performed according to the association degree.
In the embodiment of the present invention, the teacher behavior data in step S3 is continuously collected, and the ExtraModel is continuously trained to enhance the screening ability and recommendation ability of the model for the target resource, so that the good target resource can be better recommended, and the teacher behavior data in step S3 has a certain scale, so that the data needs to be put into the base model BaseModel for training.
In the embodiment of the present invention, the steps S3 and S4 are required to last for a period of time T1And the target teaching resources can be exposed and applied in a certain user scale, so that the recommendation capability of BaseModel on the target teaching resources is updated.
In step S5, the time T is reached1Then, the ExtraModel is discarded, and a new resource lacking the use data can be quickly recommended according to the effect through the assistance of the ExtraModel.
And those not described in detail in this specification are well within the skill of those in the art.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (7)
1. A teaching resource recommendation model training method is characterized by comprising the following steps: the method specifically comprises the following steps:
s1, selecting a certain number of target resources T and disciplines to which the resources belong, and randomly selecting a certain number of N1 discipline teachers to recommend;
s2, collecting behavior data of each subject teacher aiming at target resources, and training a machine learning model ExtraModel only aiming at the new resources through a machine learning recommendation algorithm;
s3, expanding the number of N1 in the step S1, and recommending the target resources according to the model in the step S2;
s4, collecting teacher behavior data in the step S3, and continuing to train machine learning models aiming at the new resources; putting the teacher behavior data in the step S3 into a base model BaseModel for training;
s5, repeating the steps S3 and S4 for a period of time T1And when the time is over, the process is finished.
2. The teaching resource recommendation model training method of claim 1, wherein: the target resource in the step S1 is a newly stocked resource or an inventory resource.
3. The teaching resource recommendation model training method of claim 1, wherein: with the teacher behavior data for the target resource in step S1, the teacher behavior data can be used to train a recommendation model for teaching resources, and the machine learning recommendation algorithm in step S2 is one of a random forest algorithm, a decision tree algorithm, or a k-nearest neighbor classification algorithm.
4. The teaching resource recommendation model training method of claim 1, wherein: with the recommendation model for the target teaching resource in step S2, the number of N1 continues to be expanded, and the expansion mode is still random selection, but the recommendation in step S2 is no longer random recommendation, but the association degree between the teacher individual feature, the course knowledge point and the teaching resource is calculated according to the ExtraModel model in step S2, and the recommendation is performed according to the level of the association degree.
5. The teaching resource recommendation model training method of claim 1, wherein: continuing to collect teacher behavior data in the step S3, and performing continuous training on the ExtraModel to enhance the filtering capability and recommendation capability of the model on the target resource.
6. The teaching resource recommendation model training method of claim 1, wherein: the steps S3 and S4 are required to last for a period of time T1And the target teaching resources can be exposed and applied in a certain user scale, so that the recommendation capability of BaseModel on the target teaching resources is updated.
7. The teaching resource recommendation model training method of claim 1, wherein: in the step S5, the time T is reached1Then, the ExtraModel is discarded, and a new resource lacking the use data can be quickly recommended according to the effect through the assistance of the ExtraModel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011186065.1A CN112347348A (en) | 2020-10-30 | 2020-10-30 | Teaching resource recommendation model training method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011186065.1A CN112347348A (en) | 2020-10-30 | 2020-10-30 | Teaching resource recommendation model training method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112347348A true CN112347348A (en) | 2021-02-09 |
Family
ID=74356609
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011186065.1A Pending CN112347348A (en) | 2020-10-30 | 2020-10-30 | Teaching resource recommendation model training method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112347348A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103336793A (en) * | 2013-06-09 | 2013-10-02 | 中国科学院计算技术研究所 | Personalized paper recommendation method and system thereof |
| CN106097204A (en) * | 2016-06-24 | 2016-11-09 | 北京航空航天大学 | A kind of work commending system towards cold start-up User and recommendation method |
| CN106127506A (en) * | 2016-06-13 | 2016-11-16 | 浙江大学 | A kind of recommendation method solving commodity cold start-up problem based on Active Learning |
| WO2020191282A2 (en) * | 2020-03-20 | 2020-09-24 | Futurewei Technologies, Inc. | System and method for multi-task lifelong learning on personal device with improved user experience |
-
2020
- 2020-10-30 CN CN202011186065.1A patent/CN112347348A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103336793A (en) * | 2013-06-09 | 2013-10-02 | 中国科学院计算技术研究所 | Personalized paper recommendation method and system thereof |
| CN106127506A (en) * | 2016-06-13 | 2016-11-16 | 浙江大学 | A kind of recommendation method solving commodity cold start-up problem based on Active Learning |
| CN106097204A (en) * | 2016-06-24 | 2016-11-09 | 北京航空航天大学 | A kind of work commending system towards cold start-up User and recommendation method |
| WO2020191282A2 (en) * | 2020-03-20 | 2020-09-24 | Futurewei Technologies, Inc. | System and method for multi-task lifelong learning on personal device with improved user experience |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103024017B (en) | A kind of social networks important goal and Community Group recognition methods | |
| CN106250438B (en) | Zero-citation article recommendation method and system based on random walk model | |
| CN109582864A (en) | Course recommended method and system based on big data science and changeable weight adjustment | |
| CN109635291A (en) | A kind of recommended method of fusion score information and item contents based on coorinated training | |
| CN108920648B (en) | Cross-modal matching method based on music-image semantic relation | |
| CN106951471B (en) | SVM-based label development trend prediction model construction method | |
| CN103034963B (en) | A kind of service selection system and system of selection based on correlation | |
| CN106326413A (en) | Personalized video recommending system and method | |
| CN110880019A (en) | Method for adaptively training target domain classification model through unsupervised domain | |
| CN105069129B (en) | Adaptive multi-tag Forecasting Methodology | |
| CN111626616A (en) | Crowdsourcing task recommendation method | |
| CN108874960A (en) | Curriculum video proposed algorithm based on noise reduction self-encoding encoder mixed model in a kind of on-line study | |
| CN107391577B (en) | Work label recommendation method and system based on expression vector | |
| CN104239496A (en) | Collaborative filtering method based on integration of fuzzy weight similarity measurement and clustering | |
| CN101968798A (en) | Community recommendation method based on on-line soft constraint LDA algorithm | |
| CN108595526B (en) | Resource recommendation method and device | |
| CN109559152A (en) | A kind of network marketing method, system and computer storage medium | |
| CN108268613A (en) | Tour schedule generation method, electronic equipment and storage medium based on semantic analysis | |
| CN111475739A (en) | Heterogeneous social network user anchor link identification method based on meta-path | |
| CN106202515A (en) | A kind of Mobile solution based on sequence study recommends method and commending system thereof | |
| CN110059251B (en) | Collaborative filtering recommendation method based on multi-relation implicit feedback confidence | |
| CN112347348A (en) | Teaching resource recommendation model training method | |
| CN113051468A (en) | Movie recommendation method and system based on knowledge graph and reinforcement learning | |
| CN111966921A (en) | Community identification method and system based on user scene | |
| CN110990662A (en) | Domain expert selection method based on citation network and scientific research cooperation network |
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 | ||
| CB02 | Change of applicant information |
Address after: Zhongjiao Yunzhi, 3 / F, Zhongjiao cloud group, RONGTONG science and Technology Industrial Park, No. 35, Huayuan East Road, Mudanyuan District, Beijing 100088 Applicant after: Zhongjiao Yunzhi Digital Technology Co.,Ltd. Address before: 100094 Yunzhi, No.15, North 1st Street, Zhongguancun, Haidian District, Beijing Applicant before: Zhongjiao Yunzhi Digital Technology Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 100191 zhongjiaoyun, integrated innovation industrial park, No. 35 Huayuan East Road, Haidian District, Beijing Applicant after: Zhongjiao Yunzhi Digital Technology Co.,Ltd. Address before: Zhongjiao Yunzhi, 3 / F, Zhongjiao cloud group, RONGTONG science and Technology Industrial Park, No. 35, Huayuan East Road, Mudanyuan District, Beijing 100088 Applicant before: Zhongjiao Yunzhi Digital Technology Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Zhao Ziying Inventor after: Zhou Jing Inventor after: Yin Dongliang Inventor before: Zhou Jing Inventor before: Zhao Ziying Inventor before: Yin Dongliang |
|
| CB03 | Change of inventor or designer information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210209 |
|
| RJ01 | Rejection of invention patent application after publication |