CN108921673A - Method of Commodity Recommendation based on big data - Google Patents
Method of Commodity Recommendation based on big data Download PDFInfo
- Publication number
- CN108921673A CN108921673A CN201810779565.2A CN201810779565A CN108921673A CN 108921673 A CN108921673 A CN 108921673A CN 201810779565 A CN201810779565 A CN 201810779565A CN 108921673 A CN108921673 A CN 108921673A
- Authority
- CN
- China
- Prior art keywords
- user
- commodity
- class
- big data
- binary classifier
- 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.)
- Granted
Links
Classifications
-
- 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
-
- 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
Abstract
The invention discloses the Method of Commodity Recommendation based on big data, include the following steps：S1：All commodity are divided into multiple commodity classes according to the type of merchandise；S2：The feature for extracting commodity in the same commodity class carries out SVM machine learning and generates the binary classifier of the commodity class；The quantity of the binary classifier is identical as the quantity of commodity class, and binary classifier and commodity class correspond；S3：From extracting browsing and transaction record characteristic value as user of all users on platform in big data；S4：Clustering is carried out to all users with the characteristic value of user, generates multiple user class.The present invention is based on the Method of Commodity Recommendation of big data, when so that carrying out real-time recommendation during user's use, the operand that system end needs is only the operation of binary classifier, and operand of the binary classifier after formation is very small, the mode for comparing point-to-point recommendation in the prior art, can greatly improve advisory speed.
Description
Technical field
The present invention relates to commercial product recommending technical fields, and in particular to the Method of Commodity Recommendation based on big data.
Background technique
With the fast development of internet, the information explosion formula presented on internet increases.It is purchased in Amazon within 2012
On object website, more than 10,000,000 kinds commodity are provided.The increase of information content reduces the utilization rate of information instead, leads to user more
Difficulty finds the information of oneself needs, information overload phenomenon occurs.It is that solution is this that commodity personalized recommendation, which is generally believed that, at present
Effective information is recommended user by the behavioural habits of analysis user by one of most effective tool of problem, personalized recommendation, is saved
The time for saving user's filter information, also improve the effective rate of utilization of information.
The method that commercial product recommending mainly directly carries out matching comparison using sole user and single commodity at present, for
For the commodity of current types up to ten million easily and up to ten million users, operand can geometry go up again, commodity greatly improved and push away
The operating cost recommended.
Summary of the invention
The technical problem to be solved by the present invention is to current commercial product recommendings mainly using sole user and single commodity
The method for directly carrying out matching comparison, at present easily for the commodity of up to ten million types and up to ten million users, operand meeting
Geometry goes up again, the operating cost of commercial product recommending greatly improved, and it is an object of the present invention to provide the Method of Commodity Recommendation based on big data,
It solves the above problems.
The present invention is achieved through the following technical solutions：
Method of Commodity Recommendation based on big data, includes the following steps：S1：All commodity are divided into according to the type of merchandise
Multiple commodity classes；S2：The feature for extracting commodity in the same commodity class carries out SVM machine learning and generates the binary of the commodity class
Classifier；The quantity of the binary classifier is identical as the quantity of commodity class, and binary classifier and commodity class correspond；
S3：From extracting browsing and transaction record characteristic value as user of all users on platform in big data；S4：With user's
Characteristic value carries out clustering to all users, generates multiple user class；S5：Extract the feature of user in the same user class
It is worth and is weighted and averaged to obtain the characteristic mean of each user class；S6：Bring characteristic mean into each binary classifier；When
When the output result of any one binary classifier is true value, it is equal that the corresponding commodity class of this binary classifier is recommended into this feature
It is worth each of corresponding user class user.
In the prior art, commercial product recommending mainly directly carries out the side of matching comparison using sole user and single commodity
Method, at present easily for the commodity of up to ten million types and up to ten million users, operand can geometry go up again, greatly improved
The operating cost of commercial product recommending.The present invention is in application, be first divided into multiple commodity classes for all commodity according to the type of merchandise, generally
E-commerce platform can all have perfect commodity classification, so what operand do not needed substantially, then extract the same quotient
The feature of commodity carries out SVM machine learning and generates the binary classifier of the commodity class in category, this binary classifier be with
User preferences are corresponding, input information be user characteristic value, output information be true value (true) or falsity (false), this
The work of one step is the equal of the pretreatment that platform carries out；Subsequently from extracting browsing of all users on platform in big data
Characteristic value with transaction record as user, this characteristic value can be the offer of the big data on platform, be also possible to from it
What the big data on his platform obtained, with the development of big data technology, the information sharing of big data platform is more and more flourishing, can
It also can be more and more abundant with the information content of acquisition；Clustering is subsequently carried out to all users with the characteristic value of user, it is raw
At multiple user class, each user class corresponds to a kind of preference, and this preference may correspond to a kind of commodity, it is also possible to corresponding
A variety of commodity, such as user are automobile industry purchaser, his preference may correspond to a variety of commodity such as aluminium, steel, rubber.
In order to position to preference common in user class, characteristic mean is brought into each binary classifier；When any one binary
When the output result of classifier is true value, the corresponding commodity class of this binary classifier is recommended into the corresponding user of this feature mean value
Each of class user, when this allows for carrying out real-time recommendation during user's use, the operand of system end needs
The only operation of binary classifier, and operand of the binary classifier after formation is very small, the comparison prior art
In point-to-point recommendation mode, advisory speed can be greatly improved.
Further, binary classifier described in step S2 uses linear binary classifier.
The present invention is in application, in order to further increase recommendation efficiency, using linear binary classifier.
Further, further comprising the steps of：S7：When platform is added in new user, extract the user's from big data
Browsing and characteristic value of the transaction record as new user；It is worth between new user and all user class according to new user characteristics
Distance, and new user is added and the shortest user class of new user distance.
The present invention is in application, in order to quickly match the preference newly into user, using direct and existing user
The mode that class is compared will be distributed newly into user into carrying out commercial product recommending in existing class, without will newly into user with it is upper
Ten million kind of commodity carries out matching comparison again, effectively increases recommendation efficiency, reduces operand.
Further, distance described in step S7 is COS distance.
Further, step S5 includes the following steps：S51：It is somebody's turn to do according to the characteristic value of user in the same user class
The central point of user class；S52：It is weighted using the inverse of user to user class central point distance as characteristic value of the weight to user
Averagely obtain the characteristic mean of user class.
The present invention is in application, in order to further simplify calculating process, since cluster point has been carried out in user
Analysis forms user class, so inventor obtains the weight of user using the operation mode of central point distance, improves recommendation efficiency,
Operand is reduced, the experience of user is effectively improved.
Further, distance described in step S52 is COS distance.
Compared with prior art, the present invention having the following advantages and benefits：
The present invention is based on the Method of Commodity Recommendation of big data, when so that carrying out real-time recommendation during user's use,
The operand that system end needs is only the operation of binary classifier, and operand of the binary classifier after formation is very
Small, the mode of point-to-point recommendation in the prior art is compared, advisory speed can be greatly improved.
Detailed description of the invention
Attached drawing described herein is used to provide to further understand the embodiment of the present invention, constitutes one of the application
Point, do not constitute the restriction to the embodiment of the present invention.In the accompanying drawings：
Fig. 1 is step schematic diagram of the present invention.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below with reference to embodiment and attached drawing, to this
Invention is described in further detail, and exemplary embodiment of the invention and its explanation for explaining only the invention, are not made
For limitation of the invention.
Embodiment 1
As shown in Figure 1, including the following steps the present invention is based on the Method of Commodity Recommendation of big data：S1：According to the type of merchandise
All commodity are divided into multiple commodity classes；S2：The feature for extracting commodity in the same commodity class carries out SVM machine learning and life
At the binary classifier of the commodity class；The quantity of the binary classifier is identical as the quantity of commodity class, and binary classifier with
Commodity class corresponds；S3：From extracting browsing and transaction record spy as user of all users on platform in big data
Value indicative；S4：Clustering is carried out to all users with the characteristic value of user, generates multiple user class；S5：Extract the same use
It the characteristic value of user and is weighted and averaged to obtain the characteristic mean of each user class in the class of family；S6：Characteristic mean is brought into
Each binary classifier；When the output result of any one binary classifier is true value, by the corresponding quotient of this binary classifier
Category recommends each of the corresponding user class of this feature mean value user.
When the present embodiment is implemented, all commodity are first divided by multiple commodity classes, general electronics quotient according to the type of merchandise
Business platform can all have perfect commodity classification, so what operand do not needed substantially, then extract quotient in the same commodity class
The features of product carries out SVM machine learning and generates the binary classifier of the commodity class, and this binary classifier is and user preferences
Corresponding, input information is the characteristic value of user, and output information is true value (true) or falsity (false), the work of this step
Work is the equal of the pretreatment that platform carries out；Subsequently from extracting browsing of all users on platform and transaction note in big data
The characteristic value as user is recorded, this characteristic value can be the offer of the big data on platform, be also possible to from other platforms
Big data obtain, with the development of big data technology, the information sharing of big data platform is more and more flourishing, can obtain
Information content also can be more and more abundant；Clustering is subsequently carried out to all users with the characteristic value of user, generates multiple use
Family class, each user class correspond to a kind of preference, and this preference may correspond to a kind of commodity, it is also possible to corresponding a variety of quotient
Product, such as user are automobile industry purchaser, his preference may correspond to a variety of commodity such as aluminium, steel, rubber.In order to right
Common preference is positioned in user class, brings characteristic mean into each binary classifier；When any one binary classifier
Output result be true value when, the corresponding commodity class of this binary classifier is recommended in the corresponding user class of this feature mean value
Each user, when this allows for carrying out real-time recommendation during user's use, the operand that system end needs is only
The operation of binary classifier, and operand of the binary classifier after formation be it is very small, compare point in the prior art
To the mode recommended, advisory speed can be greatly improved.
Embodiment 2
On the basis of embodiment 1, binary classifier described in step S2 uses linear binary classifier to the present embodiment.
When the present embodiment is implemented, in order to further increase recommendation efficiency, using linear binary classifier.
Embodiment 3
The present embodiment is on the basis of embodiment 1, further comprising the steps of：S7：When platform is added in new user, from big number
Characteristic value according to the middle browsing and transaction record for extracting the user as new user；According to new user characteristics be worth new user and
The distance between all user class, and new user is added and the shortest user class of new user distance.
When the present embodiment is implemented, in order to quickly be matched to the preference newly into user, using direct and existing use
The mode that family class is compared will be distributed newly into user into carrying out commercial product recommending in existing class, without will newly into user with
Up to ten million kinds of commodity carry out matching comparison again, effectively increase recommendation efficiency, reduce operand.Distance described in step S7
For COS distance.
Embodiment 4
On the basis of embodiment 1, step S5 includes the following steps the present embodiment：S51：It is used according in the same user class
The characteristic value at family obtains the central point of the user class；S52：Inverse using user to user class central point distance is weight to user
Characteristic value be weighted and averaged to obtain the characteristic mean of user class.
When the present embodiment is implemented, in order to further simplify to calculating process, since cluster has been carried out in user
Analysis forms user class, so inventor obtains the weight of user using the operation mode of central point distance, improves recommendation effect
Rate reduces operand, effectively improves the experience of user.Distance described in step S52 is COS distance.
Above-described specific embodiment has carried out further the purpose of the present invention, technical scheme and beneficial effects
It is described in detail, it should be understood that being not intended to limit the present invention the foregoing is merely a specific embodiment of the invention
Protection scope, all within the spirits and principles of the present invention, any modification, equivalent substitution, improvement and etc. done should all include
Within protection scope of the present invention.
Claims (6)
1. the Method of Commodity Recommendation based on big data, which is characterized in that include the following steps：
S1：All commodity are divided into multiple commodity classes according to the type of merchandise；
S2：The feature for extracting commodity in the same commodity class carries out SVM machine learning and generates the binary classifier of the commodity class；
The quantity of the binary classifier is identical as the quantity of commodity class, and binary classifier and commodity class correspond；
S3：From extracting browsing and transaction record characteristic value as user of all users on platform in big data；
S4：Clustering is carried out to all users with the characteristic value of user, generates multiple user class；
S5：Extract the characteristic value of user in the same user class and be weighted and averaged to obtain each user class feature it is equal
Value；
S6：Bring characteristic mean into each binary classifier；It, will when the output result of any one binary classifier is true value
The corresponding commodity class of this binary classifier recommends each of the corresponding user class of this feature mean value user.
2. the Method of Commodity Recommendation according to claim 1 based on big data, which is characterized in that binary described in step S2
Classifier uses linear binary classifier.
3. the Method of Commodity Recommendation according to claim 1 based on big data, which is characterized in that further comprising the steps of：
S7：When platform is added in new user, the spy of the browsing and transaction record of the user as new user is extracted from big data
Value indicative；It is worth the distance between new user and all user class according to new user characteristics, and new user is added and new user
Apart from shortest user class.
4. the Method of Commodity Recommendation according to claim 3 based on big data, which is characterized in that distance described in step S7
For COS distance.
5. the Method of Commodity Recommendation according to claim 1 based on big data, which is characterized in that step S5 includes following step
Suddenly：
S51：The central point of the user class is obtained according to the characteristic value of user in the same user class；
S52：It is weighted and averaged and is used as characteristic value of the weight to user using the inverse of user to user class central point distance
The characteristic mean of family class.
6. the Method of Commodity Recommendation according to claim 5 based on big data, which is characterized in that described in step S52 away from
From for COS distance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810779565.2A CN108921673B (en) | 2018-07-16 | 2018-07-16 | Commodity recommendation method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810779565.2A CN108921673B (en) | 2018-07-16 | 2018-07-16 | Commodity recommendation method based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108921673A true CN108921673A (en) | 2018-11-30 |
| CN108921673B CN108921673B (en) | 2021-06-01 |
Family
ID=64411929
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810779565.2A Active CN108921673B (en) | 2018-07-16 | 2018-07-16 | Commodity recommendation method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108921673B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111612557A (en) * | 2019-02-25 | 2020-09-01 | 阿里巴巴集团控股有限公司 | Method and device for providing commodity object information and electronic equipment |
| CN111709812A (en) * | 2020-06-19 | 2020-09-25 | 山东财经大学 | E-commerce platform commodity recommendation method and system based on user dynamic classification |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103399891A (en) * | 2013-07-22 | 2013-11-20 | 百度在线网络技术（北京）有限公司 | Method, device and system for automatic recommendation of network content |
| CN104616178A (en) * | 2015-03-06 | 2015-05-13 | 浪潮集团有限公司 | Recommendation method of E-commerce goods based on big-data multi-label classification method |
| CN105357583A (en) * | 2015-10-16 | 2016-02-24 | Tcl集团股份有限公司 | Method and device for discovering interest and preferences of intelligent television user |
| CN105389713A (en) * | 2015-10-15 | 2016-03-09 | 南京大学 | Mobile data traffic package recommendation algorithm based on user historical data |
| CN105787770A (en) * | 2016-04-27 | 2016-07-20 | 上海遥薇(集团)有限公司 | Non-negative matrix factorization (NMF) algorithm-based big data commodity and service recommending method and system |
| CN106127525A (en) * | 2016-06-27 | 2016-11-16 | 浙江大学 | A kind of TV shopping Method of Commodity Recommendation based on sorting algorithm |
| CN106157114A (en) * | 2016-07-06 | 2016-11-23 | 商宴通（上海）网络科技有限公司 | Have dinner based on user the homepage proposed algorithm of behavior modeling |
| CN106294783A (en) * | 2016-08-12 | 2017-01-04 | 乐视控股（北京）有限公司 | A kind of video recommendation method and device |
| CN106407379A (en) * | 2016-09-13 | 2017-02-15 | 天津大学 | Hadoop platform based movie recommendation method |
| CN107360222A (en) * | 2017-06-30 | 2017-11-17 | 广东欧珀移动通信有限公司 | Merchandise news method for pushing, device, storage medium and server |
| CN107424043A (en) * | 2017-06-15 | 2017-12-01 | 北京三快在线科技有限公司 | A kind of Products Show method and device, electronic equipment |
| CN107480719A (en) * | 2017-08-17 | 2017-12-15 | 广东工业大学 | A kind of recommendation method and system of the skin-protection product based on skin properties evaluation |
| CN107578332A (en) * | 2017-09-22 | 2018-01-12 | 深圳乐信软件技术有限公司 | A kind of method, apparatus, equipment and storage medium for recommending cash commodity |
| CN107633430A (en) * | 2017-09-20 | 2018-01-26 | 哈尔滨工业大学 | A kind of Method of Commodity Recommendation based on community of colony |
| CN107704485A (en) * | 2017-07-31 | 2018-02-16 | 北京拉勾科技有限公司 | A kind of position recommends method and computing device |
| CN107888793A (en) * | 2017-11-15 | 2018-04-06 | 中国联合网络通信集团有限公司 | Package recommendation method, apparatus and system |
-
2018
- 2018-07-16 CN CN201810779565.2A patent/CN108921673B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103399891A (en) * | 2013-07-22 | 2013-11-20 | 百度在线网络技术（北京）有限公司 | Method, device and system for automatic recommendation of network content |
| CN104616178A (en) * | 2015-03-06 | 2015-05-13 | 浪潮集团有限公司 | Recommendation method of E-commerce goods based on big-data multi-label classification method |
| CN105389713A (en) * | 2015-10-15 | 2016-03-09 | 南京大学 | Mobile data traffic package recommendation algorithm based on user historical data |
| CN105357583A (en) * | 2015-10-16 | 2016-02-24 | Tcl集团股份有限公司 | Method and device for discovering interest and preferences of intelligent television user |
| CN105787770A (en) * | 2016-04-27 | 2016-07-20 | 上海遥薇(集团)有限公司 | Non-negative matrix factorization (NMF) algorithm-based big data commodity and service recommending method and system |
| CN106127525A (en) * | 2016-06-27 | 2016-11-16 | 浙江大学 | A kind of TV shopping Method of Commodity Recommendation based on sorting algorithm |
| CN106157114A (en) * | 2016-07-06 | 2016-11-23 | 商宴通（上海）网络科技有限公司 | Have dinner based on user the homepage proposed algorithm of behavior modeling |
| CN106294783A (en) * | 2016-08-12 | 2017-01-04 | 乐视控股（北京）有限公司 | A kind of video recommendation method and device |
| CN106407379A (en) * | 2016-09-13 | 2017-02-15 | 天津大学 | Hadoop platform based movie recommendation method |
| CN107424043A (en) * | 2017-06-15 | 2017-12-01 | 北京三快在线科技有限公司 | A kind of Products Show method and device, electronic equipment |
| CN107360222A (en) * | 2017-06-30 | 2017-11-17 | 广东欧珀移动通信有限公司 | Merchandise news method for pushing, device, storage medium and server |
| CN107704485A (en) * | 2017-07-31 | 2018-02-16 | 北京拉勾科技有限公司 | A kind of position recommends method and computing device |
| CN107480719A (en) * | 2017-08-17 | 2017-12-15 | 广东工业大学 | A kind of recommendation method and system of the skin-protection product based on skin properties evaluation |
| CN107633430A (en) * | 2017-09-20 | 2018-01-26 | 哈尔滨工业大学 | A kind of Method of Commodity Recommendation based on community of colony |
| CN107578332A (en) * | 2017-09-22 | 2018-01-12 | 深圳乐信软件技术有限公司 | A kind of method, apparatus, equipment and storage medium for recommending cash commodity |
| CN107888793A (en) * | 2017-11-15 | 2018-04-06 | 中国联合网络通信集团有限公司 | Package recommendation method, apparatus and system |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111612557A (en) * | 2019-02-25 | 2020-09-01 | 阿里巴巴集团控股有限公司 | Method and device for providing commodity object information and electronic equipment |
| CN111612557B (en) * | 2019-02-25 | 2023-06-30 | 阿里巴巴集团控股有限公司 | Method and device for providing commodity object information and electronic equipment |
| CN111709812A (en) * | 2020-06-19 | 2020-09-25 | 山东财经大学 | E-commerce platform commodity recommendation method and system based on user dynamic classification |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108921673B (en) | 2021-06-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102193936B (en) | Data classification method and device | |
| WO2021068610A1 (en) | Resource recommendation method and apparatus, electronic device and storage medium | |
| CN108984675B (en) | Data query method and apparatus based on evaluation | |
| CN109492180A (en) | Resource recommendation method, device, computer equipment and computer readable storage medium | |
| CN103246980B (en) | Information output method and server | |
| CN108320213A (en) | Electric business Method of Commodity Recommendation and electric business Platform Server | |
| US9128982B2 (en) | Search system and search method for recommending reduced query | |
| CN108153792B (en) | Data processing method and related device | |
| CN106296368A (en) | A kind of vehicle commending system and method | |
| KR102142126B1 (en) | Hierarchical Category Cluster Based Shopping Basket Associated Recommendation Method | |
| CN110503497A (en) | A kind of electric business management platform Method of Commodity Recommendation of the consumption habit based on client | |
| CN103886486A (en) | Electronic commerce recommending method based on support vector machine (SVM) | |
| CN108197851A (en) | A kind of e-commerce mostly single flow distribution method with address | |
| CN107832444A (en) | Event based on search daily record finds method and device | |
| CN111858922A (en) | Service side information query method and device, electronic equipment and storage medium | |
| CN108921673A (en) | Method of Commodity Recommendation based on big data | |
| CN105931082B (en) | Commodity category keyword extraction method and device | |
| KR20200141251A (en) | Method of advertising personalized fashion item and server performing the same | |
| CN110619559A (en) | Method for accurately recommending commodities in electronic commerce based on big data information | |
| CN103426089B (en) | Commodity purchase guiding system and method | |
| CN104331395A (en) | Method and device for identifying Chinese product name from text | |
| CN106469184B (en) | Data object label processing and displaying method, server and client | |
| US20150206220A1 (en) | Recommendation Strategy Portfolios | |
| CN105550892A (en) | On-line member gender recognition method and system, and information recommendation system | |
| CN110717095B (en) | Service item pushing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200806 Address after: 510000 room 711, floor 7, No. 733 (1), Dongfeng East Road, Yuexiu District, Guangzhou City, Guangdong Province (only for office use) Applicant after: GUANGZHOU TENTCOO SOFTWARE TECHNOLOGY Co.,Ltd. Address before: 510000 Guangdong Guangzhou Haizhuqu District Xingang East Road 1000 1103, 1104, 1105, 1106 rooms Applicant before: GUANGZHOU YOUMI TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |