CN106779921A - Recommend method and device - Google Patents
Recommend method and device Download PDFInfo
- Publication number
- CN106779921A CN106779921A CN201611081633.5A CN201611081633A CN106779921A CN 106779921 A CN106779921 A CN 106779921A CN 201611081633 A CN201611081633 A CN 201611081633A CN 106779921 A CN106779921 A CN 106779921A
- Authority
- CN
- China
- Prior art keywords
- commodity
- user profile
- information
- recognition
- neural network
- 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
- G06F16/90—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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Databases & Information Systems (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of recommendation method, comprise the following steps:User profile is obtained, user profile includes browsing record and chat record;Extract the merchandise news in user profile;The treatment of the Recognition with Recurrent Neural Network that merchandise news is passed through into training in advance forms commodity and scores;Calculate the similarity that commodity scoring is scored with the commodity that commodity score in storehouse;Commercial product recommending is carried out according to similarity.Invention additionally discloses a kind of recommendation apparatus.Through the above way, the present invention can solve the problems, such as that collaborative filtering autgmentability is poor, improve the actual effect and accuracy recommended.
Description
Technical field
It is more particularly to a kind of to recommend method and device the present invention relates to big data field.
Background technology
With the development of ecommerce, increasing people carries out the purchase of commodity using e-commerce platform, in purchase
During, e-commerce platform would generally be recommended user, to improve the buying experience of user.Current proposed algorithm master
Have based on demographic recommendation, content-based recommendation, collaborative filtering recommending etc., wherein, collaborative filtering has base
In the method in field(Method based on memory), hidden semantic model, the Random Walk Algorithm based on figure etc..
When number of users and commodity number reach certain amount, current proposed algorithm can all have serious scalability to ask
Topic, recommendation it is effective poor, and proposed algorithm is generally based only on user browsing behavior and recommended, and recommends the data being based on
Single, the accuracy of recommendation is poor.The scalability problem of proposed algorithm how is avoided, the effective and accurate of recommendation is improved
Property, it is to improve one of user's buying experience problem demanding prompt solution at present.
The content of the invention
Recommend method and device the present invention solves the technical problem of one kind is provided, it is possible to resolve collaborative filtering expands
The problem of malleability difference, improves the actual effect and accuracy recommended.
In order to solve the above technical problems, the present invention provides a kind of recommendation method, comprise the following steps:Obtain user profile,
User profile includes browsing record and chat record;Extract the merchandise news in user profile;By merchandise news by instruction in advance
The treatment of experienced Recognition with Recurrent Neural Network forms commodity scoring;Calculate commodity scoring similar to what the commodity in commodity scoring storehouse scored
Degree;Commercial product recommending is carried out according to similarity.
Wherein, merchandise news includes one or more of:Goods purchase information, articles storage information, commodity share letter
Breath, comment on commodity information.
Wherein, the Recognition with Recurrent Neural Network of training in advance be with merchandise news be input, commodity scoring for output circulation god
Through network.
Wherein, commodity scoring storehouse is the place of the Recognition with Recurrent Neural Network that the merchandise news in user profile is passed through into training in advance
Manage the commodity scoring storehouse for being formed.
Wherein, commercial product recommending is the recommendation of wrist-watch information.
In order to solve the above technical problems, the present invention provides a kind of recommendation apparatus, including:Acquisition module, for obtaining user
Information, user profile includes browsing record and chat record;Extraction module, for extracting the merchandise news in user profile;Place
Reason module, the treatment of the Recognition with Recurrent Neural Network for merchandise news to be passed through into training in advance forms commodity and scores;Computing module, uses
In the similarity for calculating the commodity scoring in commodity scoring and commodity scoring storehouse;Recommending module, for entering to do business according to similarity
Product are recommended.
Wherein, merchandise news includes one or more of:Goods purchase information, articles storage information, commodity share letter
Breath, comment on commodity information.
Wherein, the Recognition with Recurrent Neural Network of training in advance be with merchandise news be input, commodity scoring for output circulation god
Through network.
Wherein, commodity scoring storehouse is the place of the Recognition with Recurrent Neural Network that the merchandise news in user profile is passed through into training in advance
Manage the commodity scoring storehouse for being formed.
Wherein, commercial product recommending is the recommendation of wrist-watch information.
The beneficial effects of the invention are as follows:The situation of prior art is different from, the detailed process of recommendation method of the invention is:
User profile is obtained first, and the user profile includes browsing record and chat record, and extracts the letter of the commodity in the user profile
Breath, the treatment of the Recognition with Recurrent Neural Network that the merchandise news that then will be extracted passes through training in advance forms commodity and scores, and calculates the business
Point similarity scored with the commodity that commodity score in storehouse is judged, commercial product recommending is carried out finally according to similarity.Wherein, similarity
Calculating and commercial product recommending using based on commodity collaborative filtering.Through the above way, Recognition with Recurrent Neural Network and cooperateed with
Filter algorithm is combined, it is possible to resolve the problem of collaborative filtering autgmentability difference, improves the actual effect recommended, and for circulation nerve
Its weights is carried out artificial appropriate regulation by network, can further improve the actual effect of recommendation.In recommendation process, the use being based on
Family information includes browsing record and chat record, and substantial amounts of data can improve the accuracy of recommendation.
Brief description of the drawings
Fig. 1 is the schematic flow sheet of the embodiment of recommendation method one of the present invention;
Fig. 2 is the structural representation of the embodiment of recommendation apparatus of the present invention.
Specific embodiment
The present invention is described in detail with reference to the accompanying drawings and examples.
Fig. 1 is referred to, Fig. 1 is the schematic flow sheet of the embodiment of recommendation method one of the present invention, as shown in figure 1, including following
Step:
S11, obtains user profile, and user profile includes browsing record and chat record.
The present embodiment method realized by commodity transaction platform, when user uses the platform, commercial product recommending is carried out to user.
In recommendation process, the information of user is obtained first, user profile is user's information on the internet, such as browse record, chat
Its record etc..
S12, extracts the merchandise news in user profile.
For user profile, merchandise news therein need to be extracted, wherein, merchandise news includes one or more of:Business
Product purchase information, articles storage information, commodity sharing information, comment on commodity information.For merchandise news, other can also be included
Content, is not defined here.
S13, the treatment of the Recognition with Recurrent Neural Network that merchandise news is passed through into training in advance forms commodity and scores.
Deep learning(Deep Learning)It is a field for closely artificial intelligence, its motivation in machine learning
It is to set up, simulate the neutral net that human brain is analyzed study.And neutral net is that one kind of people's cranial nerve work is simplified
Living model, simulation human brain is to the contact between neuron and the regulation process of intensity.
Recognition with Recurrent Neural Network(Recurrent Neural Networks, RNN)Directed circulation is introduced, it can be to above
Information is remembered and is applied to during current output calculates, i.e., the node between hidden layer has a connection, and hidden layer is defeated
Enter the not only output including input layer, also including the output of last moment hidden layer, therefore, Recognition with Recurrent Neural Network can process defeated
The problem of forward-backward correlation between entering.
In the present embodiment, the Recognition with Recurrent Neural Network of training in advance be with merchandise news be input, commodity scoring for output
Recognition with Recurrent Neural Network.And the Recognition with Recurrent Neural Network is in the training process, set automatic learning rules, add manual intervention because
Element.
In the present embodiment, by the Recognition with Recurrent Neural Network of training in advance to the merchandise news in user profile at
Reason, forms commodity scoring.Wherein, commodity scoring is score value, and the corresponding commodity of score value correspondence, commodity herein are specially
Wrist-watch brand and/or wrist-watch model, for the commodity scoring that merchandise news is formed, its quantity can be one or more.
S14, calculates the similarity that commodity scoring is scored with the commodity that commodity score in storehouse.
In the present embodiment, commodity scoring storehouse is the circulation nerve that the merchandise news in user profile is passed through into training in advance
The commodity scoring storehouse that the treatment of network is formed.
S15, commercial product recommending is carried out according to similarity.
In the present embodiment, the calculating of similarity and the recommendation of commodity are using the collaborative filtering based on commodity.Wherein,
Commercial product recommending is the recommendation of wrist-watch information.
In the present embodiment, the merchandise news of extraction is the information relevant with wrist-watch.
Fig. 2 is referred to, Fig. 2 is the structural representation of the embodiment of recommendation apparatus of the present invention, as shown in Fig. 2 including:Obtain
Module 21, extraction module 22, processing module 23, computing module 24 and recommending module 25.
The function of above-mentioned each module is specific as follows:
Acquisition module 21 is used to obtain user profile, and user profile includes browsing record and chat record;Extraction module 22 is used for
Extract the merchandise news in user profile;Processing module 23 is used for the Recognition with Recurrent Neural Network that merchandise news is passed through into training in advance
Treatment forms commodity scoring;Computing module 24 is used to calculate the similarity that commodity scoring is scored with the commodity that commodity score in storehouse;
Recommending module 25 is used to carry out commercial product recommending according to similarity.
In the present embodiment, during recommendation, acquisition module 21 obtains the information of user first, and user profile is user in interconnection
Online information, such as browses record, chat record.For the user profile for obtaining, extraction module 22 extracts commodity therein
Information.Wherein, merchandise news includes one or more of:Goods purchase information, articles storage information, commodity sharing information,
Comment on commodity information.For merchandise news, other guide can also be included, be not defined here.
In the present embodiment, the Recognition with Recurrent Neural Network of training in advance be with merchandise news be input, commodity scoring for output
Recognition with Recurrent Neural Network.And the Recognition with Recurrent Neural Network is in the training process, set automatic learning rules, add manual intervention because
Element.
In the present embodiment, by the Recognition with Recurrent Neural Network of training in advance to the merchandise news in user profile at
Reason, forms commodity scoring.Wherein, commodity scoring is score value, and the corresponding commodity of score value correspondence, commodity herein are specially
Wrist-watch brand and/or wrist-watch model, for the commodity scoring that merchandise news is formed, its quantity can be one or more.
In the present embodiment, commodity scoring storehouse is the circulation nerve that the merchandise news in user profile is passed through into training in advance
The commodity scoring storehouse that the treatment of network is formed.
In the present embodiment, the calculating of similarity and the recommendation of commodity are using the collaborative filtering based on commodity.Wherein,
Commercial product recommending is the recommendation of wrist-watch information.
In the present embodiment, the merchandise news of extraction is the information relevant with wrist-watch.
In sum, Recognition with Recurrent Neural Network of the present invention and collaborative filtering are combined, it is possible to resolve collaborative filtering expands
The problem of malleability difference, improves the actual effect recommended, and for Recognition with Recurrent Neural Network, its weights is carried out with artificial appropriate regulation, can
Further improve the actual effect recommended.In recommendation process, the user profile being based on includes browsing record and chat record, largely
Data can improve the accuracy of recommendation.
Recommendation method of the invention more meets the thinking habit of user, during recommendation, introduces Recognition with Recurrent Neural Network, can depth digging
Between pick user and user, the internal association between user and commodity, can more accurately recommended user's commodity interested.
Embodiments of the invention are the foregoing is only, the scope of the claims of the invention is not thereby limited, it is every to utilize this hair
Equivalent structure or equivalent flow conversion that bright specification and accompanying drawing content are made, or directly or indirectly it is used in other related skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of recommendation method, it is characterised in that comprise the following steps:
User profile is obtained, the user profile includes browsing record and chat record;
Extract the merchandise news in the user profile;
The treatment of the Recognition with Recurrent Neural Network that the merchandise news is passed through into training in advance forms commodity and scores;
Calculate the similarity that the commodity scoring is scored with the commodity that commodity score in storehouse;
Commercial product recommending is carried out according to the similarity.
2. recommendation method according to claim 1, it is characterised in that the merchandise news includes one or more of:
Goods purchase information, articles storage information, commodity sharing information, comment on commodity information.
3. recommendation method according to claim 2, it is characterised in that the Recognition with Recurrent Neural Network of the training in advance is with business
The Recognition with Recurrent Neural Network that product information is input, commodity scoring is output.
4. recommendation method according to claim 3, it is characterised in that the commodity scoring storehouse is by the business in user profile
The commodity scoring storehouse that the treatment of the Recognition with Recurrent Neural Network that product information passes through training in advance is formed.
5. recommendation method according to claim 4, it is characterised in that the commercial product recommending is the recommendation of wrist-watch information.
6. a kind of recommendation apparatus, it is characterised in that including:
Acquisition module, for obtaining user profile, the user profile includes browsing record and chat record;
Extraction module, for extracting the merchandise news in the user profile;
Processing module, the treatment of the Recognition with Recurrent Neural Network for the merchandise news to be passed through into training in advance forms commodity and scores;
Computing module, for calculating the similarity that the commodity scoring is scored with the commodity that commodity score in storehouse;
Recommending module, for carrying out commercial product recommending according to the similarity.
7. recommendation apparatus according to claim 6, it is characterised in that the merchandise news includes one or more of:
Goods purchase information, articles storage information, commodity sharing information, comment on commodity information.
8. recommendation apparatus according to claim 7, it is characterised in that the Recognition with Recurrent Neural Network of the training in advance is with business
The Recognition with Recurrent Neural Network that product information is input, commodity scoring is output.
9. recommendation apparatus according to claim 8, it is characterised in that the commodity scoring storehouse is by the business in user profile
The commodity scoring storehouse that the treatment of the Recognition with Recurrent Neural Network that product information passes through training in advance is formed.
10. recommendation apparatus according to claim 9, it is characterised in that the commercial product recommending is the recommendation of wrist-watch information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611081633.5A CN106779921A (en) | 2016-11-30 | 2016-11-30 | Recommend method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611081633.5A CN106779921A (en) | 2016-11-30 | 2016-11-30 | Recommend method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106779921A true CN106779921A (en) | 2017-05-31 |
Family
ID=58901462
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611081633.5A Pending CN106779921A (en) | 2016-11-30 | 2016-11-30 | Recommend method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106779921A (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107507054A (en) * | 2017-07-24 | 2017-12-22 | 哈尔滨工程大学 | A kind of proposed algorithm based on Recognition with Recurrent Neural Network |
CN107527236A (en) * | 2017-08-10 | 2017-12-29 | 云南财经大学 | A kind of collaborative filtering recommending method and commending system based on market effect |
CN107645559A (en) * | 2017-09-30 | 2018-01-30 | 广东美的制冷设备有限公司 | Household electrical appliances information-pushing method, server, mobile terminal and storage medium |
CN107688602A (en) * | 2017-07-22 | 2018-02-13 | 长沙兔子代跑网络科技有限公司 | A kind of method and device that generation race client is excavated according to chat content |
CN108564414A (en) * | 2018-04-23 | 2018-09-21 | 帷幄匠心科技(杭州)有限公司 | Method of Commodity Recommendation based on behavior under line and system |
CN108876526A (en) * | 2018-06-06 | 2018-11-23 | 北京京东尚科信息技术有限公司 | Method of Commodity Recommendation, device and computer readable storage medium |
CN108921649A (en) * | 2018-06-13 | 2018-11-30 | 苏州若依玫信息技术有限公司 | A kind of screening type e-commerce system based on Internet of Things |
CN109815309A (en) * | 2018-12-21 | 2019-05-28 | 航天信息股份有限公司 | A kind of user information recommended method and system based on personalization |
CN109993544A (en) * | 2017-12-29 | 2019-07-09 | 北京京东尚科信息技术有限公司 | Data processing method, system, computer system and computer readable storage medium |
CN110458637A (en) * | 2019-06-19 | 2019-11-15 | 中国平安财产保险股份有限公司 | Product method for pushing and its relevant device neural network based |
CN113095908A (en) * | 2021-04-22 | 2021-07-09 | 深圳正品创想科技有限公司 | Information processing method, server and information processing system |
CN113450188A (en) * | 2021-06-29 | 2021-09-28 | 平安养老保险股份有限公司 | Product similarity matching method and device, computer equipment and storage medium |
US11361364B2 (en) | 2018-03-09 | 2022-06-14 | Boe Technology Group Co., Ltd. | Shopping recommendation method, client, and server |
-
2016
- 2016-11-30 CN CN201611081633.5A patent/CN106779921A/en active Pending
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107688602A (en) * | 2017-07-22 | 2018-02-13 | 长沙兔子代跑网络科技有限公司 | A kind of method and device that generation race client is excavated according to chat content |
CN107507054A (en) * | 2017-07-24 | 2017-12-22 | 哈尔滨工程大学 | A kind of proposed algorithm based on Recognition with Recurrent Neural Network |
CN107527236A (en) * | 2017-08-10 | 2017-12-29 | 云南财经大学 | A kind of collaborative filtering recommending method and commending system based on market effect |
CN107645559B (en) * | 2017-09-30 | 2020-10-09 | 广东美的制冷设备有限公司 | Household appliance information pushing method, server, mobile terminal and storage medium |
CN107645559A (en) * | 2017-09-30 | 2018-01-30 | 广东美的制冷设备有限公司 | Household electrical appliances information-pushing method, server, mobile terminal and storage medium |
CN109993544A (en) * | 2017-12-29 | 2019-07-09 | 北京京东尚科信息技术有限公司 | Data processing method, system, computer system and computer readable storage medium |
US11361364B2 (en) | 2018-03-09 | 2022-06-14 | Boe Technology Group Co., Ltd. | Shopping recommendation method, client, and server |
CN108564414A (en) * | 2018-04-23 | 2018-09-21 | 帷幄匠心科技(杭州)有限公司 | Method of Commodity Recommendation based on behavior under line and system |
CN108876526A (en) * | 2018-06-06 | 2018-11-23 | 北京京东尚科信息技术有限公司 | Method of Commodity Recommendation, device and computer readable storage medium |
CN108921649A (en) * | 2018-06-13 | 2018-11-30 | 苏州若依玫信息技术有限公司 | A kind of screening type e-commerce system based on Internet of Things |
CN109815309A (en) * | 2018-12-21 | 2019-05-28 | 航天信息股份有限公司 | A kind of user information recommended method and system based on personalization |
CN110458637A (en) * | 2019-06-19 | 2019-11-15 | 中国平安财产保险股份有限公司 | Product method for pushing and its relevant device neural network based |
CN113095908A (en) * | 2021-04-22 | 2021-07-09 | 深圳正品创想科技有限公司 | Information processing method, server and information processing system |
CN113450188A (en) * | 2021-06-29 | 2021-09-28 | 平安养老保险股份有限公司 | Product similarity matching method and device, computer equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106779921A (en) | Recommend method and device | |
Li et al. | Confiding in and listening to virtual agents: The effect of personality | |
CN111784455B (en) | Article recommendation method and recommendation equipment | |
US20190122121A1 (en) | Method and system for generating individual microdata | |
Hacker et al. | Matchin: eliciting user preferences with an online game | |
Obadă | Flow theory and online marketing outcomes: A critical literature review | |
US11809985B2 (en) | Algorithmic apparel recommendation | |
CN109146626B (en) | Fashionable garment matching recommendation method based on user dynamic interest analysis | |
Mowlabocus | Gay men and the pornification of everyday life | |
Hui et al. | Using anonymity and communal efforts to improve quality of crowdsourced feedback | |
CN106779922A (en) | Recommend method and device | |
Paraschos et al. | Game difficulty adaptation and experience personalization: A literature review | |
US20150174493A1 (en) | Automated content curation and generation of online games | |
CN107423335A (en) | A kind of negative sample system of selection for single class collaborative filtering problem | |
Qi et al. | A user experience study on short video social apps based on content recommendation algorithm of artificial intelligence | |
Kim | Why Should GUI Designers Create Visual Novelties?: The Mechanisms of First Impression Formation in User Experience: The Mechanisms of First Impression Formation in User Experience | |
Wątróbski et al. | Integration of eye-tracking based studies into e-commerce websites evaluation process with eQual and TOPSIS methods | |
CN104050298B (en) | A kind of subscriber segmentation method based on LDA topic model algorithms | |
CN106779923A (en) | Recommend method and device | |
Leiva et al. | Modeling how different user groups perceive webpage aesthetics | |
CN110555210A (en) | product feature analysis method based on user viewpoint and emotion score | |
Wang et al. | Testing the moderating effects of toolkits and user communities in personalization: The case of social networking service | |
Baffa et al. | Dealing with the emotions of non player characters | |
CN102866997B (en) | The treating method and apparatus of user data | |
Song et al. | User modeling using user preference and user life pattern based on personal bio data and SNS data |
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: 511430, No. 60, north of Panyu Avenue, Dashi street, Guangzhou, Guangdong, Panyu District Applicant after: Guangzhou Polytron Technologies Inc Address before: 103 Tianhe District, Guangzhou Tianfu Road, No. 1, room 11, room 510000, Guangdong Applicant before: Guangzhou Polytron Technologies Inc |
|
CB02 | Change of applicant information | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170531 |
|
RJ01 | Rejection of invention patent application after publication |