CN107222562A - A kind of user's intelligent recommendation system based on Internet user's feature - Google Patents
A kind of user's intelligent recommendation system based on Internet user's feature Download PDFInfo
- Publication number
- CN107222562A CN107222562A CN201710535129.6A CN201710535129A CN107222562A CN 107222562 A CN107222562 A CN 107222562A CN 201710535129 A CN201710535129 A CN 201710535129A CN 107222562 A CN107222562 A CN 107222562A
- Authority
- CN
- China
- Prior art keywords
- user
- stage
- information
- feature
- users
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Stage, Users'Data Analysis stage and user's screening recommendation stage are extracted the invention discloses a kind of user's intelligent recommendation system based on Internet user's feature, including user information collection;The user information collection extraction stage, which will collect user's characteristic information and collect user preference information, is sent to the Users'Data Analysis stage, the Users'Data Analysis stage is according to user characteristics weight height, analysis result is sent to user's screening recommendation stage, user filters out qualified user and recommend party A-subscriber in the screening recommendation stage;By using Internet technology means, the information such as feature and preference according to user, it accurate in real time can recommend to meet the object of its regard to user, user is helped more rapidly to find oneself suitable object, promote between user and user, the degree of coupling between user and platform, so as to strengthen the viscosity between user and product, a kind of benign cycle is reached.
Description
Technical field
The present invention relates to Internet technical field, specially a kind of user's intelligent recommendation system based on Internet user's feature
System.
Background technology
In recent years, how the very growth that the social platform of internet has developed, allow user to be quickly found out and meet oneself
The object admired, is the problem of emphasis will be solved.Particularly with the service of marriage and making friend's class, how according to user characteristics and individual
Preference information becomes particularly important to user " intelligent recommendation " good friend.
The current existing way of recommendation is real-time, it is therefore desirable to analyze user characteristics and a large amount of targeted customer's numbers in real time
According to, so that the object of user preference is filtered out, and this process needs Continuous optimization than relatively time-consuming in subsequent process.
The content of the invention
, being capable of basis it is an object of the invention to provide a kind of user's intelligent recommendation system based on Internet user's feature
The information such as the feature and preference of user, recommend suitable object to user, so as to strengthen the viscosity between user and product, reach
Circulated benignly to one kind, to solve the problems mentioned in the above background technology.
To achieve the above object, the present invention provides following technical scheme:A kind of user's intelligence based on Internet user's feature
Energy commending system, including user information collection extract stage, Users'Data Analysis stage and user's screening recommendation stage;It is described to use
Family information extracts the stage including collecting user's characteristic information and collecting user preference information;The user information collection is extracted
Stage, which will collect user's characteristic information and collect user preference information, is sent to the Users'Data Analysis stage;The user data point
The analysis stage includes analysis user profile, according to user characteristics weight height, calculates weighted value of each user relative to party A-subscriber,
And analysis result is sent to user's screening recommendation stage;User's screening recommendation stage arranges according to the weighted value flashback of calculating
Row, filter out qualified user and recommend party A-subscriber.
It is preferred that, it is equal that the user information collection extracts stage, Users'Data Analysis stage and user's screening recommendation stage
Come and go and carry out between background server and client.
It is preferred that, it is described to collect sex of the user's characteristic information including user, age, appearance, height, city, family's back of the body
Scape.
It is preferred that, the collection user preference information includes age of user scope, place industry, hobby.
It is preferred that, the user information collection extracts the stage and the Users'Data Analysis stage updates weekly once.
It is preferred that, buffer memory capacity built in the commending system is analyzed according to user profile and the real-time amount of calculation of weight
Size, is periodically extended.
It is preferred that, message mechanism built in the commending system, when user profile changes, passes through message mechanism asynchronous refresh
Recommend caching.
It is preferred that, the workflow of commending system is as follows:
S1:User fills in personal essential information, Working Life information, conditional information of choosing spouse;
S2:User A sends recommendation request to server;
S3:Feature, choose spouse information of the server according to user A, calculate party A-subscriber's weighted value corresponding with other users;
S4:Server is arranged according to weighted value descending, then does further screening to the data after sequence;
S5:Recommendation results are put into caching, and caching is updated using rational cache policy;
S6:Final result is returned to client by server, shows user, is sorted from high to low according to matching degree, complete
Into a recommendation service.
Compared with prior art, the beneficial effects of the invention are as follows:This user's intelligent recommendation based on Internet user's feature
System, using Internet technology means, according to information such as the features and preference of user, accurate in real time can recommend to accord with to user
Close the object of its regard, help user more rapidly to find oneself suitable object, promote between user and user, user and platform
Between the degree of coupling, so as to strengthen the viscosity between user and product, reach a kind of benign cycle.
Brief description of the drawings
Fig. 1 is overall flow figure of the invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
In the embodiment of the present invention:A kind of user's intelligent recommendation system based on Internet user's feature, including user profile
Extraction stage, Users'Data Analysis stage and user's screening recommendation stage are collected, user information collection extracts stage, user data
Analysis phase and user screen the recommendation stage and come and go and carry out between background server and client, promote user and user it
Between, the degree of coupling between user and platform, help user to find object;It is special including collecting user that user information collection extracts the stage
Reference ceases and collected user preference information, collect the sex of user's characteristic information including user, the age, appearance, height, city,
Family background etc., collecting user preference information includes age of user scope, place industry, hobby etc.;Then, user profile
The collection extraction stage, which will collect user's characteristic information and collect user preference information, is sent to Users'Data Analysis stage, Yong Huxin
Breath collects the extraction stage and the Users'Data Analysis stage updates weekly once, it is ensured that the real-time of user profile;User data point
The analysis stage includes analysis user profile, according to user characteristics weight height, calculates weighted value of each user relative to party A-subscriber,
Because the operation such as calculating in real time of user profile analysis and weight is relatively time-consuming, it is therefore desirable to appropriate using caching, and because of information
Changing can make some difference to the accuracy of the recommended user in caching, therefore, it is recommended that the buffer memory capacity built in system is according to user
Information analysis and the size of the real-time amount of calculation of weight, are periodically extended;Then, the Users'Data Analysis stage again ties analysis
Fruit is sent to user's screening recommendation stage, and user screens the recommendation stage according to the weighted value flashback of calculating arrangement, filters out and meet
The user of condition recommends party A-subscriber, and message mechanism built in commending system is asynchronous by message mechanism when user profile changes
Update and recommend caching, it is ensured that accuracy of information.
Specific embodiment one:
Referring to Fig. 1, a kind of user's intelligent recommendation system based on Internet user's feature, its workflow is as follows:
The first step:User fills in the information such as personal essential information, Working Life information, condition of choosing spouse in order to accurate to its
Recommended;
Second step:User A sends recommendation request to server;
3rd step:Server calculates party A-subscriber's weighted value corresponding with other users according to A feature, the information such as choose spouse,
Weighted value is higher, more meets user A requirement;
4th step:Server is arranged according to weighted value descending, then does further screening to the data after sequence;
5th step:Recommendation results are put into caching, and caching is updated using rational cache policy, it is ensured that recommending data
Accuracy;
6th step:Server returns result to client, shows user, is sorted from high to low according to matching degree, extremely
This, a recommendation service is completed.
In summary:This user's intelligent recommendation system based on Internet user's feature, using Internet technology means, root
The information such as feature and preference according to user, accurate in real time can recommend to meet the object of its regard to user, help user more
It is quickly found out oneself suitable object, promotes between user and user, the degree of coupling between user and platform, so as to strengthens user
Viscosity between product, reaches a kind of benign cycle.
The foregoing is only a preferred embodiment of the present invention, but protection scope of the present invention be not limited thereto,
Any one skilled in the art the invention discloses technical scope in, technique according to the invention scheme and its
Inventive concept is subject to equivalent substitution or change, should all be included within the scope of the present invention.
Claims (8)
1. a kind of user's intelligent recommendation system based on Internet user's feature, it is characterised in that carried including user information collection
Take stage, Users'Data Analysis stage and user's screening recommendation stage;The user information collection is extracted the stage and used including collecting
Family characteristic information and collection user preference information;The user information collection extracts the stage will collection user's characteristic information and collection
User preference information is sent to the Users'Data Analysis stage;The Users'Data Analysis stage includes analysis user profile, according to
User characteristics weight height, calculates the weighted value of each user relative to party A-subscriber, and analysis result is sent into user's screening and push away
Recommend the stage;User's screening recommendation stage arranges according to the weighted value flashback of calculating, filters out qualified user and recommends
To party A-subscriber.
2. a kind of user's intelligent recommendation system based on Internet user's feature according to claim 1, it is characterised in that
The user information collection extracts stage, Users'Data Analysis stage and user and screens the recommendation stage in background server and visitor
Come and go and carry out between the end of family.
3. a kind of user's intelligent recommendation system based on Internet user's feature according to claim 1, it is characterised in that
The collection user's characteristic information includes sex, age, appearance, height, city, the family background of user.
4. a kind of user's intelligent recommendation system based on Internet user's feature according to claim 1, it is characterised in that
The collection user preference information includes age of user scope, place industry, hobby.
5. a kind of user's intelligent recommendation system based on Internet user's feature according to claim 1, it is characterised in that
The user information collection extracts the stage and the Users'Data Analysis stage updates weekly once.
6. a kind of user's intelligent recommendation system based on Internet user's feature according to claim 1, it is characterised in that
Buffer memory capacity built in the commending system is periodically expanded according to user profile analysis and the size of the real-time amount of calculation of weight
Exhibition.
7. a kind of user's intelligent recommendation system based on Internet user's feature according to claim 1, it is characterised in that
Message mechanism built in the commending system, when user profile changes, recommends to cache by message mechanism asynchronous refresh.
8. user intelligent recommendation system of any one according to claim 1-7 based on Internet user's feature, it is special
Levy and be, the workflow of commending system is as follows:
S1:User fills in personal essential information, Working Life information, conditional information of choosing spouse;
S2:User A sends recommendation request to server;
S3:Feature, choose spouse information of the server according to user A, calculate party A-subscriber's weighted value corresponding with other users;
S4:Server is arranged according to weighted value descending, then does further screening to the data after sequence;
S5:Recommendation results are put into caching, and caching is updated using rational cache policy;
S6:Final result is returned to client by server, shows user, is sorted from high to low according to matching degree, completes one
Secondary recommendation service.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710535129.6A CN107222562A (en) | 2017-07-03 | 2017-07-03 | A kind of user's intelligent recommendation system based on Internet user's feature |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710535129.6A CN107222562A (en) | 2017-07-03 | 2017-07-03 | A kind of user's intelligent recommendation system based on Internet user's feature |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107222562A true CN107222562A (en) | 2017-09-29 |
Family
ID=59951599
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710535129.6A Pending CN107222562A (en) | 2017-07-03 | 2017-07-03 | A kind of user's intelligent recommendation system based on Internet user's feature |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107222562A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109981787A (en) * | 2019-04-03 | 2019-07-05 | 北京字节跳动网络技术有限公司 | Method and apparatus for showing information |
CN110110203A (en) * | 2018-01-11 | 2019-08-09 | 腾讯科技(深圳)有限公司 | Resource information method for pushing and server, resource information methods of exhibiting and terminal |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101320447A (en) * | 2008-06-27 | 2008-12-10 | 广州市盈海文化传播有限公司 | Method for recommending dormant matching mate based on psychological traits |
CN102662975A (en) * | 2012-03-12 | 2012-09-12 | 浙江大学 | Bidirectional and clustering mixed friend recommendation method |
CN103678394A (en) * | 2012-09-21 | 2014-03-26 | 孟露芳 | Image matching degree based marriage dating recommendation method and system |
CN103927682A (en) * | 2013-01-14 | 2014-07-16 | 上海爱相随信息科技有限公司 | Mechanism used for ranking member information of mobile dating platform and integrating time and space dimensions |
CN106372970A (en) * | 2016-09-07 | 2017-02-01 | 上海斐讯数据通信技术有限公司 | Private tour guide automatic recommendation method and system |
-
2017
- 2017-07-03 CN CN201710535129.6A patent/CN107222562A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101320447A (en) * | 2008-06-27 | 2008-12-10 | 广州市盈海文化传播有限公司 | Method for recommending dormant matching mate based on psychological traits |
CN102662975A (en) * | 2012-03-12 | 2012-09-12 | 浙江大学 | Bidirectional and clustering mixed friend recommendation method |
CN103678394A (en) * | 2012-09-21 | 2014-03-26 | 孟露芳 | Image matching degree based marriage dating recommendation method and system |
CN103927682A (en) * | 2013-01-14 | 2014-07-16 | 上海爱相随信息科技有限公司 | Mechanism used for ranking member information of mobile dating platform and integrating time and space dimensions |
CN106372970A (en) * | 2016-09-07 | 2017-02-01 | 上海斐讯数据通信技术有限公司 | Private tour guide automatic recommendation method and system |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110110203A (en) * | 2018-01-11 | 2019-08-09 | 腾讯科技(深圳)有限公司 | Resource information method for pushing and server, resource information methods of exhibiting and terminal |
CN110110203B (en) * | 2018-01-11 | 2023-04-28 | 腾讯科技(深圳)有限公司 | Resource information pushing method, server, resource information display method and terminal |
CN109981787A (en) * | 2019-04-03 | 2019-07-05 | 北京字节跳动网络技术有限公司 | Method and apparatus for showing information |
CN109981787B (en) * | 2019-04-03 | 2022-03-29 | 北京字节跳动网络技术有限公司 | Method and device for displaying information |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Payus et al. | Impact of extreme drought climate on water security in North Borneo: Case study of Sabah | |
CN107909433A (en) | A kind of Method of Commodity Recommendation based on big data mobile e-business | |
CN104424235B (en) | The method and apparatus for realizing user profile cluster | |
CN103714135B (en) | MapReduce recommendation method and system of second-degree interpersonal relationships of massive users | |
Ortega et al. | Institutional and country collaboration in an online service of scientific profiles: Google Scholar Citations | |
CN103425763B (en) | User based on SNS recommends method and device | |
CN103475717B (en) | A kind of friend recommendation method and system based on social networks | |
CN107895038A (en) | A kind of link prediction relation recommends method and device | |
CN106203473B (en) | A kind of mobile subscriber's gender prediction's method based on installation the package list | |
CN112036445B (en) | User identity recognition method across social networks based on neural tensor network | |
CN104598450A (en) | Popularity analysis method and system of network public opinion event | |
CN107391670A (en) | A kind of mixing recommendation method for merging collaborative filtering and user property filtering | |
CN106776930A (en) | A kind of location recommendation method for incorporating time and geographical location information | |
CN105760649A (en) | Big-data-oriented creditability measuring method | |
CN107222562A (en) | A kind of user's intelligent recommendation system based on Internet user's feature | |
CN109840702A (en) | A kind of new projects' collaborative recommendation method based on multi-core integration | |
CN110347897A (en) | Micro blog network emotion community detection method based on event detection | |
CN106777946A (en) | Personalized health service recommendation method based on hierarchal model | |
CN110168316B (en) | Foot step counting method, device and equipment based on step frequency | |
CN109885776A (en) | Recommended models can be explained in open source community PR reviewer | |
CN106503431A (en) | The processing method of exercise data | |
CN103457799A (en) | Microblog zombie user detection method based on relational graph | |
CN109460299B (en) | Distributed parallel multi-source social network data acquisition system and method | |
CN106354886B (en) | The method of potential neighbor relational graph screening nearest-neighbors is utilized in recommender system | |
CN105574139B (en) | It is a kind of that method and system are recommended based on strange make friends of social networks that double Attraction Degrees are calculated |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170929 |
|
RJ01 | Rejection of invention patent application after publication |